In the present growth of sensor technology is to improve the new chance and applications in GIS. This enhances the technology law a new method that should not focus on real time available products, but it must automatically lead to new ones. The aim of the paper is to make a maximum use of remote sensing data and GIS techniques to access land use and land cover classification in the Kiliyar sub basin sector in palar river of northen part of Tamil Nadu.IRS P6 LISS III is merged data to perform the classification using ERDAS Imaging. The RGB and L base supervised classification was based up on a Multispectral analysis, land use and land cover information‟s (maps and existing reports), which involves advanced technology and complex data processing to find detailed imagery in the study region. Ground surface reflects more radar energy emitted by the sensor from the study region, which makes it easy to distinguish between the water body, hilly, agriculture, settlement and wetland.
A novel approach for georeferenced data analysis using hard clustering algorithmeSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
Remote sensing and GIS can be applied in civil engineering for spatial analysis and to answer geographic queries. Spatial analysis examines how the locations of objects impact analysis results and can reveal patterns. GIS uses methods like overlay, proximity, density, and network analysis to study spatial relationships. Common analyses include measuring distances, areas and shapes, transforming datasets, descriptive summaries of data, and optimizing locations.
Classification of Satellite broadcasting Image and Validation Exhausting Geom...IJSRD
Classification of Land Use/Land Cover (LULC) data from satellite images is extremely remarkable to design the thematic maps for analysis of natural resources like Forest, Agriculture, Water bodies, urban areas etc. The process of Satellite Image Classification involves grouping the pixel values into significant categories and estimating areas by counting each category pixels. Manual classification by visual interpretation technique is accurate but time consuming and requires field experts. To overcome these difficulties, the present research work investigated efficient and effective automation of satellite image classification. Automated classification approaches are broadly classified in to i) Supervised Classification ii) Unsupervised Classification iii) Object Based Classification. This paper presents classification capabilities of K-Means, Parallel Pipe and Maximum Likelihood classifiers to classify multispectral spatial data (LISS-4). Using statistical inference, classified results are validated with reference data collected from field experts. Among three, Maximum Likelihood classifier (MLC) gained a significant credit in terms of getting maximum Overall accuracy and Kappa Factor.
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...IOSR Journals
Abstract: We investigated the Classification of satellite images and multispectral remote sensing data .we
focused on uncertainty analysis in the produced land-cover maps .we proposed an efficient technique for
classifying the multispectral satellite images using Support Vector Machine (SVM) into road area, building area
and green area. We carried out classification in three modules namely (a) Preprocessing using Gaussian
filtering and conversion from conversion of RGB to Lab color space image (b) object segmentation using
proposed Cluster repulsion based kernel Fuzzy C- Means (FCM) and (c) classification using one-to-many SVM
classifier. The goal of this research is to provide the efficiency in classification of satellite images using the
object-based image analysis. The proposed work is evaluated using the satellite images and the accuracy of the
proposed work is compared to FCM based classification. The results showed that the proposed technique has
achieved better results reaching an accuracy of 79%, 84%, 81% and 97.9% for road, tree, building and vehicle
classification respectively.
Keywords:-Satellite image, FCM Clustering, Classification, SVM classifier.
Soil Classification Using Image Processing and Modified SVM Classifierijtsrd
Recently the use of soil classification has gained more and more importance and recent direction in research works indicates that image classification of images for soil information is the preferred choice. Various methods for image classification have been developed based on different theories or models. In this study, three of these methods Maximum Likelihood classification MLC , Sub pixel classification SP and Support Vector machine SVM are used to classify a soil image into seven soil classes and the results compared. MLC and SVM are hard classification methods but SP is a soft classification. Hardening of soft classifications for accuracy determination leads to loss of information and the accuracy may not necessary represent the strength of class membership. Therefore, in the comparison of the methods, the top 20 compositions per soil class of the SP were used instead. Results from the classification, indicated that output from SP was generally poor although it performs well with soils such as forest that are homogeneous in character. Of the two hard classifiers, SVM gave a better output than MLC. Priyanka Dewangan | Vaibhav Dedhe "Soil Classification Using Image Processing and Modified SVM Classifier" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-6 , October 2018, URL: http://www.ijtsrd.com/papers/ijtsrd18489.pdf
Multiple Crop Classification Using Various Support Vector Machine Kernel Func...IJERA Editor
This study was carried out with techniques of Remote Sensing (RS) based crop discrimination and area estimation with single date approach. Several kernel functions are employed and compared in this study for mapping the input space with including linear, sigmoid, and polynomial and Radial Basis Function (RBF). The present study highlights the advantages of Remote Sensing (RS) and Geographic Information System (GIS) techniques for analyzing the land use/land cover mapping for Aurangabad region of Maharashtra, India. Single date, cloud free IRS-Resourcesat-1 LISS-III data was used for further classification on training set for supervised classification. ENVI 4.4 is used for image analysis and interpretation. The experimental tests show that system is achieved 94.82% using SVM with kernel functions including Polynomial kernel function compared with Radial Basis Function, Sigmoid and linear kernel. The Overall Accuracy (OA) to up to 5.17% in comparison to using sigmoid kernel function, and up to 3.45% in comparison to a 3rd degree polynomial kernel function and RBF with 200 as a penalty parameter.
IRJET- Land Cover Index Classification using Satellite Images with Different ...IRJET Journal
This document presents a study on land cover index classification of satellite images of the Ayeyarwaddy Delta region of Myanmar. The study uses Google Earth satellite images from 2004-2014. The images are classified into three indices: buildings, vegetation, and roads. Three image enhancement methods are applied prior to classification - V-channel enhancement, histogram equalization, and adaptive histogram equalization. K-means clustering is then used to classify the enhanced images into the three indices in CIE L*a*b* color space. The classification results of each enhancement method are evaluated and compared using mean squared error and peak signal-to-noise ratio. According to the results, V-channel enhancement provides the best classification results compared to
A novel approach for georeferenced data analysis using hard clustering algorithmeSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
Remote sensing and GIS can be applied in civil engineering for spatial analysis and to answer geographic queries. Spatial analysis examines how the locations of objects impact analysis results and can reveal patterns. GIS uses methods like overlay, proximity, density, and network analysis to study spatial relationships. Common analyses include measuring distances, areas and shapes, transforming datasets, descriptive summaries of data, and optimizing locations.
Classification of Satellite broadcasting Image and Validation Exhausting Geom...IJSRD
Classification of Land Use/Land Cover (LULC) data from satellite images is extremely remarkable to design the thematic maps for analysis of natural resources like Forest, Agriculture, Water bodies, urban areas etc. The process of Satellite Image Classification involves grouping the pixel values into significant categories and estimating areas by counting each category pixels. Manual classification by visual interpretation technique is accurate but time consuming and requires field experts. To overcome these difficulties, the present research work investigated efficient and effective automation of satellite image classification. Automated classification approaches are broadly classified in to i) Supervised Classification ii) Unsupervised Classification iii) Object Based Classification. This paper presents classification capabilities of K-Means, Parallel Pipe and Maximum Likelihood classifiers to classify multispectral spatial data (LISS-4). Using statistical inference, classified results are validated with reference data collected from field experts. Among three, Maximum Likelihood classifier (MLC) gained a significant credit in terms of getting maximum Overall accuracy and Kappa Factor.
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...IOSR Journals
Abstract: We investigated the Classification of satellite images and multispectral remote sensing data .we
focused on uncertainty analysis in the produced land-cover maps .we proposed an efficient technique for
classifying the multispectral satellite images using Support Vector Machine (SVM) into road area, building area
and green area. We carried out classification in three modules namely (a) Preprocessing using Gaussian
filtering and conversion from conversion of RGB to Lab color space image (b) object segmentation using
proposed Cluster repulsion based kernel Fuzzy C- Means (FCM) and (c) classification using one-to-many SVM
classifier. The goal of this research is to provide the efficiency in classification of satellite images using the
object-based image analysis. The proposed work is evaluated using the satellite images and the accuracy of the
proposed work is compared to FCM based classification. The results showed that the proposed technique has
achieved better results reaching an accuracy of 79%, 84%, 81% and 97.9% for road, tree, building and vehicle
classification respectively.
Keywords:-Satellite image, FCM Clustering, Classification, SVM classifier.
Soil Classification Using Image Processing and Modified SVM Classifierijtsrd
Recently the use of soil classification has gained more and more importance and recent direction in research works indicates that image classification of images for soil information is the preferred choice. Various methods for image classification have been developed based on different theories or models. In this study, three of these methods Maximum Likelihood classification MLC , Sub pixel classification SP and Support Vector machine SVM are used to classify a soil image into seven soil classes and the results compared. MLC and SVM are hard classification methods but SP is a soft classification. Hardening of soft classifications for accuracy determination leads to loss of information and the accuracy may not necessary represent the strength of class membership. Therefore, in the comparison of the methods, the top 20 compositions per soil class of the SP were used instead. Results from the classification, indicated that output from SP was generally poor although it performs well with soils such as forest that are homogeneous in character. Of the two hard classifiers, SVM gave a better output than MLC. Priyanka Dewangan | Vaibhav Dedhe "Soil Classification Using Image Processing and Modified SVM Classifier" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-6 , October 2018, URL: http://www.ijtsrd.com/papers/ijtsrd18489.pdf
Multiple Crop Classification Using Various Support Vector Machine Kernel Func...IJERA Editor
This study was carried out with techniques of Remote Sensing (RS) based crop discrimination and area estimation with single date approach. Several kernel functions are employed and compared in this study for mapping the input space with including linear, sigmoid, and polynomial and Radial Basis Function (RBF). The present study highlights the advantages of Remote Sensing (RS) and Geographic Information System (GIS) techniques for analyzing the land use/land cover mapping for Aurangabad region of Maharashtra, India. Single date, cloud free IRS-Resourcesat-1 LISS-III data was used for further classification on training set for supervised classification. ENVI 4.4 is used for image analysis and interpretation. The experimental tests show that system is achieved 94.82% using SVM with kernel functions including Polynomial kernel function compared with Radial Basis Function, Sigmoid and linear kernel. The Overall Accuracy (OA) to up to 5.17% in comparison to using sigmoid kernel function, and up to 3.45% in comparison to a 3rd degree polynomial kernel function and RBF with 200 as a penalty parameter.
IRJET- Land Cover Index Classification using Satellite Images with Different ...IRJET Journal
This document presents a study on land cover index classification of satellite images of the Ayeyarwaddy Delta region of Myanmar. The study uses Google Earth satellite images from 2004-2014. The images are classified into three indices: buildings, vegetation, and roads. Three image enhancement methods are applied prior to classification - V-channel enhancement, histogram equalization, and adaptive histogram equalization. K-means clustering is then used to classify the enhanced images into the three indices in CIE L*a*b* color space. The classification results of each enhancement method are evaluated and compared using mean squared error and peak signal-to-noise ratio. According to the results, V-channel enhancement provides the best classification results compared to
it is highly useful for geography students in the field of remote sensing and it is in very simple and explanatory for the purpose of simplification with relevant images in this ppt.
Data models are a set of rules and/or constructs used to describe and represent aspects of the real world in a computer. GIS can handle four data models for various applications. This module explains those four.
Supervised and unsupervised classification techniques for satellite imagery i...gaup_geo
This document compares supervised and unsupervised classification techniques for satellite imagery analysis of land cover in the Porto Alegre region of Brazil. Supervised classification involved collecting over 500 training sites to create signatures for 8 land cover classes. Unsupervised classification used ISOcluster to generate 36 spectral classes which were grouped into the 8 informational classes. Both classifications underwent post-processing including majority filtering and polygon elimination to produce final 1-hectare minimum mapping unit vector maps. Accuracy assessments found the supervised classification to be more accurate at 76% compared to 48% for the unsupervised method.
This document provides an overview of remote sensing and image interpretation. It discusses key topics such as the use of maps as models to represent features on Earth, different types of map scales and spatial referencing systems, and how computers are used in map production. It also outlines the process of image interpretation, including levels of interpretation keys and basic elements to examine like size, shape, shadow, tone, color, and texture. Software programs used in map production like ArcGIS and types of data products from remote sensing are also reviewed.
The document summarizes seven categories of change detection techniques:
1. Algebra based approaches include image differencing, regression, ratioing, and change vector analysis. These methods are simple to implement but cannot provide complete change matrices.
2. Transformation techniques apply transformations like PCA and tasseled cap to images before change detection.
3. Classification based techniques perform post-classification comparison or combine classification with other algorithms.
4. Advanced models use techniques like spectral mixture analysis and biophysical parameters.
5. GIS and remote sensing are integrated in some methods.
6. Visual analysis relies on human interpretation of image differences.
7. Other techniques include measures of spatial dependence,
An Efficient K-Nearest Neighbors Based Approach for Classifying Land Cover Re...IDES Editor
In recent times, researchers in the remote
sensing community have been greatly interested in
utilizing hyperspectral data for in-depth analysis of
Earth’s surface. In general, hyperspectral imaging comes
with high dimensional data, which necessitates a pressing
need for efficient approaches that can effectively process
on these high dimensional data. In this paper, we present
an efficient approach for the analysis of hyperspectral
data by incorporating the concepts of Non-linear manifold
learning and k-nearest neighbor (k-NN). Instead of
dealing with the high dimensional feature space directly,
the proposed approach employs Non-linear manifold
learning that determines a low-dimensional embedding of
the original high dimensional data by computing the
geometric distances between the samples. Initially, the
dimensionality of the hyperspectral data is reduced to a
pairwise distance matrix by making use of the Johnson's
shortest path algorithm and Multidimensional scaling
(MDS). Subsequently, based on the k-nearest neighbors,
the classification of the land cover regions in the
hyperspectral data is achieved. The proposed k-NN based
approach is evaluated using the hyperspectral data
collected by the NASA’s (National Aeronautics and Space
Administration) AVIRIS (Airborne Visible/Infrared
Imaging Spectrometer) from Kennedy Space Center,
Florida. The classification accuracies of the proposed k-
NN based approach demonstrate its effectiveness in land
cover classification of hyperspectral data.
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...Fatwa Ramdani
This remote sensing e-course will focus on comparing the Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper algorithms for semi-automatic classification of Landsat 8 OLI imagery in QGIS. The course will explain the concepts, demonstrate the algorithms in QGIS, and have students complete exercises to classify land cover and assess accuracy. Minimum Distance classifies pixels based on distance to class means, Maximum Likelihood uses probability, and Spectral Angle Mapper compares spectral angles insensitive to illumination.
Object-Oriented Image Processing Of An High Resolution Satellite Imagery With...CSCJournals
This document presents an object-oriented image analysis of high resolution satellite imagery to derive spatial information for urban planning in Vijayawada, India. It uses IRS P-6 LISS-III imagery and performs unsupervised classification, supervised classification, and object-oriented image segmentation and classification using eCognition. Accuracy assessment shows the object-oriented method achieved an overall accuracy of 94.2% and Kappa coefficient of 0.91. The classified image indicates urban areas cover 34.6 sq km of the 58 sq km study area. Recommendations are provided for more balanced land use planning over the next 20 years as the city grows.
High Performance Computing for Satellite Image Processing and Analyzing – A ...Editor IJCATR
High Performance Computing (HPC) is the recently developed technology in the field of computer science, which evolved
due to meet increasing demands for processing speed and analysing/processing huge size of data sets. HPC brings together several
technologies such as computer architecture, algorithm, programs and system software under one canopy to solve/handle advanced
complex problems quickly and effectively. It is a crucial element today to gather and process large amount of satellite (remote sensing)
data which is the need of an hour. In this paper, we review recent development in HPC technology (Parallel, Distributed and Cluster
Computing) for satellite data processing and analysing. We attempt to discuss the fundamentals of High Performance Computing
(HPC) for satellite data processing and analysing, in a way which is easy to understand without much previous background. We sketch
the various HPC approach such as Parallel, Distributed & Cluster Computing and subsequent satellite data processing & analysing
methods like geo-referencing, image mosaicking, image classification, image fusion and Morphological/neural approach for hyperspectral satellite data. Collective, these works deliver a snapshot, tables and algorithms of the recent developments in those sectors and
offer a thoughtful perspective of the potential and promising challenges of satellite data processing and analysing using HPC
paradigms.
16 9252 eeem gis based satellite image denoising (edit ari)IAESIJEECS
This document discusses a method for denoising satellite images using curvelet transform and k-means clustering. Curvelet transform is used to denoise the images by taking advantage of its ability to represent lines and edges. K-means clustering is then used to segment the image into background and water regions. Bridges are then extracted based on pixel intensity differences. The methodology is tested on satellite images and the denoised images are found to have higher PSNR values compared to the noisy input images, indicating the method is effective at reducing noise from satellite images.
Object-Oriented Approach of Information Extraction from High Resolution Satel...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
This document summarizes a study that used satellite images and supervised classification to monitor forest land cover in Gisoom forest park in Iran. Land samples were taken using GPS and classified using ENVI software. Maximum likelihood classification of satellite images from 2007 achieved a total accuracy of 75.98% and kappa coefficient of 74.73%, indicating good classification. The study found that residential development, construction of recreational structures, roads, and tourism led to decreases in forest areas over time.
Google Earth Web Service as a Support for GIS Mapping in Geospatial Research ...Universität Salzburg
The geospatial work has been performed using combination of the Google Earth imagery, Landsat TM images and Erdas Imagine GIS software. The advantage of utilizing Google Earth scenes with Landsat TM satellite imagery, along with GIS techniques and methods, for inventorying land cover types has been demonstrated for landscape studies. Combination of land cover type characteristics and landscape changes enabled to analyse landscape dynamics, as well as applicability of Google Earth service for thematic mapping. The used data included Landsat TM and ETM+ multi-band imagery covering area in Izmir, western Turkey. The image processing was per- formed using supervised classification in Erdas Imagine software. The Google Earth web service technologies were applied to test the accuracy of mapping via the available module of Erdas Imagine «Linking with Google Earth».
Topics:
1. Introduction to GIS
2. Components of GIS
3. Types of Data
4. Spatial Data
5. Non-Spatial Data
6. GIS Operations
7. Coordinate Systems
8. Datum
9. Map Projections
10. Raster Data Compression Techniques
11. GIS Software
12. Free GIS Data Resources
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This paper presents to building identification from satellite images. Because of monitoring illegal land usage. Nowadays rapid urbanization leads to
increase the land usage, in this case of monitoring illegal land usage is very important. This project implemented to building identification from
satellite images, images are provided from Bing maps. Adaptive Neuro Fuzzy Inference System used to check data base information. In this proposed
system, I can identify only building images from the satellite images, To improving the image details effectively.
This document describes a practical demonstration on using GIS for land suitability mapping for precision farming. The goals of the demonstration are to identify areas suitable, moderately suitable, and highly suitable for crop production based on soil characteristics. The demonstration will use ArcGIS to interpolate soil property rasters from sample data, reclassify the rasters into classes, overlay the reclassified rasters to combine criteria, and label the final overlay classes as the soil suitability map.
Freshness is an important quality for many food products. Keeping foods fresh helps ensure they are safe to eat and taste good. Proper storage and handling can help maintain the freshness of foods.
This document lists numerous important historical and cultural sites located throughout Turkey, including many mosques, palaces, and other landmarks in major cities like Istanbul, Izmir, and Konya. Some of the notable sites mentioned are the Hagia Sophia and Blue Mosque in Istanbul, Ephesus in Izmir, and the Mausoleum of Mustafa Kemal Atatürk in Ankara. The list highlights Turkey's rich cultural heritage spanning various empires and civilizations over millennia.
Design and Optimisation of Sae Mini Baja ChassisIJERA Editor
The objective is to design and develop the roll cage for All - Terrain Vehicle accordance with the rulebook of BAJA 2014 given by SAE. The frame of the SAE Baja vehicle needs to be lightweight and structurally sound to be competitive but still protect the driver. The vehicle needs to traverse all types of off-road conditions including large rocks, downed logs, mud holes, steep inclines, jumps and off camber turns. During the competition events there is significant risk of rollovers, falling from steep ledges, collisions with stationary objects, or impacts from other vehicles. Material for the roll cage is selected based on strength and availability. A software model is prepared in Pro-engineer. Later the design is tested against all modes of failure by conducting various simulations and stress analysis with the aid of ANSYS 13. Based on the result obtained from these tests the design is modified accordingly. A target of 2 is set for Yield Factor of Safety.
Parallel Processing Technique for Time Efficient Matrix MultiplicationIJERA Editor
The document proposes a parallel-parallel input single output (PPI-SO) design for matrix multiplication that reduces hardware resources compared to existing designs. It uses fewer multipliers and registers than existing designs, trading off increased completion time. Simulation results show the PPI-SO design uses 30% less energy and involves 70% less area-delay product than other designs.
it is highly useful for geography students in the field of remote sensing and it is in very simple and explanatory for the purpose of simplification with relevant images in this ppt.
Data models are a set of rules and/or constructs used to describe and represent aspects of the real world in a computer. GIS can handle four data models for various applications. This module explains those four.
Supervised and unsupervised classification techniques for satellite imagery i...gaup_geo
This document compares supervised and unsupervised classification techniques for satellite imagery analysis of land cover in the Porto Alegre region of Brazil. Supervised classification involved collecting over 500 training sites to create signatures for 8 land cover classes. Unsupervised classification used ISOcluster to generate 36 spectral classes which were grouped into the 8 informational classes. Both classifications underwent post-processing including majority filtering and polygon elimination to produce final 1-hectare minimum mapping unit vector maps. Accuracy assessments found the supervised classification to be more accurate at 76% compared to 48% for the unsupervised method.
This document provides an overview of remote sensing and image interpretation. It discusses key topics such as the use of maps as models to represent features on Earth, different types of map scales and spatial referencing systems, and how computers are used in map production. It also outlines the process of image interpretation, including levels of interpretation keys and basic elements to examine like size, shape, shadow, tone, color, and texture. Software programs used in map production like ArcGIS and types of data products from remote sensing are also reviewed.
The document summarizes seven categories of change detection techniques:
1. Algebra based approaches include image differencing, regression, ratioing, and change vector analysis. These methods are simple to implement but cannot provide complete change matrices.
2. Transformation techniques apply transformations like PCA and tasseled cap to images before change detection.
3. Classification based techniques perform post-classification comparison or combine classification with other algorithms.
4. Advanced models use techniques like spectral mixture analysis and biophysical parameters.
5. GIS and remote sensing are integrated in some methods.
6. Visual analysis relies on human interpretation of image differences.
7. Other techniques include measures of spatial dependence,
An Efficient K-Nearest Neighbors Based Approach for Classifying Land Cover Re...IDES Editor
In recent times, researchers in the remote
sensing community have been greatly interested in
utilizing hyperspectral data for in-depth analysis of
Earth’s surface. In general, hyperspectral imaging comes
with high dimensional data, which necessitates a pressing
need for efficient approaches that can effectively process
on these high dimensional data. In this paper, we present
an efficient approach for the analysis of hyperspectral
data by incorporating the concepts of Non-linear manifold
learning and k-nearest neighbor (k-NN). Instead of
dealing with the high dimensional feature space directly,
the proposed approach employs Non-linear manifold
learning that determines a low-dimensional embedding of
the original high dimensional data by computing the
geometric distances between the samples. Initially, the
dimensionality of the hyperspectral data is reduced to a
pairwise distance matrix by making use of the Johnson's
shortest path algorithm and Multidimensional scaling
(MDS). Subsequently, based on the k-nearest neighbors,
the classification of the land cover regions in the
hyperspectral data is achieved. The proposed k-NN based
approach is evaluated using the hyperspectral data
collected by the NASA’s (National Aeronautics and Space
Administration) AVIRIS (Airborne Visible/Infrared
Imaging Spectrometer) from Kennedy Space Center,
Florida. The classification accuracies of the proposed k-
NN based approach demonstrate its effectiveness in land
cover classification of hyperspectral data.
Semi-Automatic Classification Algorithm: The differences between Minimum Dist...Fatwa Ramdani
This remote sensing e-course will focus on comparing the Minimum Distance, Maximum Likelihood, and Spectral Angle Mapper algorithms for semi-automatic classification of Landsat 8 OLI imagery in QGIS. The course will explain the concepts, demonstrate the algorithms in QGIS, and have students complete exercises to classify land cover and assess accuracy. Minimum Distance classifies pixels based on distance to class means, Maximum Likelihood uses probability, and Spectral Angle Mapper compares spectral angles insensitive to illumination.
Object-Oriented Image Processing Of An High Resolution Satellite Imagery With...CSCJournals
This document presents an object-oriented image analysis of high resolution satellite imagery to derive spatial information for urban planning in Vijayawada, India. It uses IRS P-6 LISS-III imagery and performs unsupervised classification, supervised classification, and object-oriented image segmentation and classification using eCognition. Accuracy assessment shows the object-oriented method achieved an overall accuracy of 94.2% and Kappa coefficient of 0.91. The classified image indicates urban areas cover 34.6 sq km of the 58 sq km study area. Recommendations are provided for more balanced land use planning over the next 20 years as the city grows.
High Performance Computing for Satellite Image Processing and Analyzing – A ...Editor IJCATR
High Performance Computing (HPC) is the recently developed technology in the field of computer science, which evolved
due to meet increasing demands for processing speed and analysing/processing huge size of data sets. HPC brings together several
technologies such as computer architecture, algorithm, programs and system software under one canopy to solve/handle advanced
complex problems quickly and effectively. It is a crucial element today to gather and process large amount of satellite (remote sensing)
data which is the need of an hour. In this paper, we review recent development in HPC technology (Parallel, Distributed and Cluster
Computing) for satellite data processing and analysing. We attempt to discuss the fundamentals of High Performance Computing
(HPC) for satellite data processing and analysing, in a way which is easy to understand without much previous background. We sketch
the various HPC approach such as Parallel, Distributed & Cluster Computing and subsequent satellite data processing & analysing
methods like geo-referencing, image mosaicking, image classification, image fusion and Morphological/neural approach for hyperspectral satellite data. Collective, these works deliver a snapshot, tables and algorithms of the recent developments in those sectors and
offer a thoughtful perspective of the potential and promising challenges of satellite data processing and analysing using HPC
paradigms.
16 9252 eeem gis based satellite image denoising (edit ari)IAESIJEECS
This document discusses a method for denoising satellite images using curvelet transform and k-means clustering. Curvelet transform is used to denoise the images by taking advantage of its ability to represent lines and edges. K-means clustering is then used to segment the image into background and water regions. Bridges are then extracted based on pixel intensity differences. The methodology is tested on satellite images and the denoised images are found to have higher PSNR values compared to the noisy input images, indicating the method is effective at reducing noise from satellite images.
Object-Oriented Approach of Information Extraction from High Resolution Satel...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
This document summarizes a study that used satellite images and supervised classification to monitor forest land cover in Gisoom forest park in Iran. Land samples were taken using GPS and classified using ENVI software. Maximum likelihood classification of satellite images from 2007 achieved a total accuracy of 75.98% and kappa coefficient of 74.73%, indicating good classification. The study found that residential development, construction of recreational structures, roads, and tourism led to decreases in forest areas over time.
Google Earth Web Service as a Support for GIS Mapping in Geospatial Research ...Universität Salzburg
The geospatial work has been performed using combination of the Google Earth imagery, Landsat TM images and Erdas Imagine GIS software. The advantage of utilizing Google Earth scenes with Landsat TM satellite imagery, along with GIS techniques and methods, for inventorying land cover types has been demonstrated for landscape studies. Combination of land cover type characteristics and landscape changes enabled to analyse landscape dynamics, as well as applicability of Google Earth service for thematic mapping. The used data included Landsat TM and ETM+ multi-band imagery covering area in Izmir, western Turkey. The image processing was per- formed using supervised classification in Erdas Imagine software. The Google Earth web service technologies were applied to test the accuracy of mapping via the available module of Erdas Imagine «Linking with Google Earth».
Topics:
1. Introduction to GIS
2. Components of GIS
3. Types of Data
4. Spatial Data
5. Non-Spatial Data
6. GIS Operations
7. Coordinate Systems
8. Datum
9. Map Projections
10. Raster Data Compression Techniques
11. GIS Software
12. Free GIS Data Resources
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This paper presents to building identification from satellite images. Because of monitoring illegal land usage. Nowadays rapid urbanization leads to
increase the land usage, in this case of monitoring illegal land usage is very important. This project implemented to building identification from
satellite images, images are provided from Bing maps. Adaptive Neuro Fuzzy Inference System used to check data base information. In this proposed
system, I can identify only building images from the satellite images, To improving the image details effectively.
This document describes a practical demonstration on using GIS for land suitability mapping for precision farming. The goals of the demonstration are to identify areas suitable, moderately suitable, and highly suitable for crop production based on soil characteristics. The demonstration will use ArcGIS to interpolate soil property rasters from sample data, reclassify the rasters into classes, overlay the reclassified rasters to combine criteria, and label the final overlay classes as the soil suitability map.
Freshness is an important quality for many food products. Keeping foods fresh helps ensure they are safe to eat and taste good. Proper storage and handling can help maintain the freshness of foods.
This document lists numerous important historical and cultural sites located throughout Turkey, including many mosques, palaces, and other landmarks in major cities like Istanbul, Izmir, and Konya. Some of the notable sites mentioned are the Hagia Sophia and Blue Mosque in Istanbul, Ephesus in Izmir, and the Mausoleum of Mustafa Kemal Atatürk in Ankara. The list highlights Turkey's rich cultural heritage spanning various empires and civilizations over millennia.
Design and Optimisation of Sae Mini Baja ChassisIJERA Editor
The objective is to design and develop the roll cage for All - Terrain Vehicle accordance with the rulebook of BAJA 2014 given by SAE. The frame of the SAE Baja vehicle needs to be lightweight and structurally sound to be competitive but still protect the driver. The vehicle needs to traverse all types of off-road conditions including large rocks, downed logs, mud holes, steep inclines, jumps and off camber turns. During the competition events there is significant risk of rollovers, falling from steep ledges, collisions with stationary objects, or impacts from other vehicles. Material for the roll cage is selected based on strength and availability. A software model is prepared in Pro-engineer. Later the design is tested against all modes of failure by conducting various simulations and stress analysis with the aid of ANSYS 13. Based on the result obtained from these tests the design is modified accordingly. A target of 2 is set for Yield Factor of Safety.
Parallel Processing Technique for Time Efficient Matrix MultiplicationIJERA Editor
The document proposes a parallel-parallel input single output (PPI-SO) design for matrix multiplication that reduces hardware resources compared to existing designs. It uses fewer multipliers and registers than existing designs, trading off increased completion time. Simulation results show the PPI-SO design uses 30% less energy and involves 70% less area-delay product than other designs.
Improving Data Storage Security in Cloud using HadoopIJERA Editor
The rising abuse of information stored on large data centres in cloud emphasizes the need to safe guard the data. Despite adopting strict authentication policies for cloud users data while transferred over to secure channel when reaches data centres is vulnerable to numerous attacks .The most widely adoptable methodology is safeguarding the cloud data is through encryption algorithm. Encryption of large data deployed in cloud is actually a time consuming process. For the secure transmission of information AES encryption has been used which provides most secure way to transfer the sensitive information from sender to the intended receiver. The main purpose of using this technique is to make sensitive information unreadable to all other except the receiver. The data thus compressed enables utilization of storage space in cloud environment. It has been augmented with Hadoop‟s map-reduce paradigm which works in a parallel mode. The experimental results clearly reflect the effectiveness of the methodology to improve the security of data in cloud environment.
Este documento discute la importancia de la educación artística como factor vinculante entre la cultura, la educación y el arte. En primer lugar, señala que la educación artística garantiza el desarrollo de habilidades sensoriales, imaginativas y emocionales. En segundo lugar, destaca que los retos de la política cultural y educativa incluyen preservar la diversidad cultural y promover el acceso equitativo a bienes culturales y educativos. Por último, argumenta que la educación artística debe ser un hábito y no una excepci
A União Europeia está considerando novas regras para veículos autônomos. As regras propostas exigiriam que os fabricantes de veículos autônomos assumam mais responsabilidade por acidentes e garantam que os sistemas de direção sejam projetados para proteger os pedestres e ciclistas. A UE também está discutindo como regular o uso compartilhado de veículos autônomos.
O documento discute o batismo no Espírito Santo, afirmando que todo crente em Jesus Cristo já foi batizado com o Espírito Santo. Ele explora como o Espírito Santo age no Velho e Novo Testamento, e como Ele habita em todo crente após a ressurreição de Cristo. O documento conclui que os crentes devem desenvolver sua salvação por meio do Espírito Santo que habita neles.
Make them Fall in Love All Over Again: Nurturing the Inbound WayKirsten Knipp
Learn how creating marketing that people LOVE and engaging with them over time via personalization can result in improved conversion and customer retention over time.
Review of theModern developments in Suction processes of IC EnginesIJERA Editor
This review paper deals with the evolution of the general processes employed in the suction process of IC
Engines. The suction process has evolved from the traditional use of carburettors to much more sophisticated
systems like CRDi, MPFi, etc. used in modern days. In doing so, various parameters such as the volumetric
efficiency and the turbulence, etc. inside the engine have to be considered. Additional processes such as
supercharging and turbocharging are employed to improve these parameters. It is also highly desirable to vary
the Air-Fuel ratio effectively according to the speed of the engine for better power output and mileage. Thus
researchers have developed several ways over the years to achieve it. Recent research work being carried out in
this field is in the areas of Pressure Wave Superchargers, Variable Geometry Turbochargers, Multiple Intake
valves, Shrouded Intake Valves, Camless Engines etc. Many of these technologies have been employed in the
industry such as the DTS-Si, TDi&i-vtec Engines. Thus, the Automobile Industry has come a long way in
evolving the intake processes and further developments will always be on the way.
This document summarizes a proposed 10 MWp solar PV farm project in Romania. Key details include:
- The project will be developed on 64 hectares of leased land and include PV panels, infrastructure like access roads and a substation.
- Construction is planned to start in late 2014 and be completed in late 2016, with the PV farm operational by mid-2017.
- Once built, the PV farm will require some administrative staff but operate automatically, generating an estimated 11.13 GWh annually.
Hack Recognition In Wireless Sensor NetworkIJERA Editor
A wireless sensor network can get separated into multiple connected components due to the failure of some of its nodes, which is called a ―cut‖. In this article we consider the problem of detecting cuts by the remaining nodes of a wireless sensor network. We propose an algorithm that allows like every node to detect when the connectivity to a specially designated node has been lost, and one or more nodes (that are connected to the special node after the cut) to detect the occurrence of the cut. The algorithm is distributed and asynchronous: every node needs to communicate with only those nodes that are within its communication range. The algorithm is based on the iterative computation of a fictitious ―electrical potential‖ of the nodes. The convergence rate of the underlying iterative scheme is independent of the size and structure of the network.
An On-Chip Bus Tracer Analyzer With Amba AHB For Real Time Tracing With Lossl...IJERA Editor
The Advanced Microcontroller Bus Architecture (AMBA) widely used as the on-chip bus in System-on-a-chip (SoC) designs. The important aspect of a SoC is not only which components or blocks it houses, but also how they are interconnected. AMBA is a solution for the blocks to interface with each other. The biggest challenge in SoC design is in validating and testing the system. AHB Bus Tracer is a significant infrastructure that is needed to monitor the on chip-bus signals, which is vital for debugging and performance analysis and also optimizing the SOC. Basically on chip signals are difficult to observe since they are deeply embedded in a SoC and no sufficient I/O pins are required to access those signals. Therefore, we embed a bus tracer in SoC to capture the bus signals and store them. The AMBA AHB should be used to which are high bandwidth and require the high performance of a pipelined bus interface. Performance can be improved at high-frequency operation. Performance is independent of the mark-space ratio of the clock. No special considerations are required for automatic test insertion. Our aim in this project is to Design the AHB- protocol with bus tracer. For real-time tracing, we should reduce the trace size as much as possible without reducing the original data.SYS-HMRBT supports tracing after/before an event triggering, named post-triggering trace/pre-triggering trace, respectively. SYS-HMRBT runs at 500 MHz and costs 42 K gates in TSMC 0.13- m technology, indicating that it is capable of real time tracing and is very small in modern SoCs.The experimental results show that trace compression ratio reduced by 96.32%. Finally this approach was designed successfully along with MODEL SIM and synthesis using Xilinx ISE. The SoC can be verified in field-programmable gate array.
A União Europeia está considerando novas regras para veículos autônomos. As regras propostas exigiriam que os fabricantes provassem que seus veículos são seguros e cumprem as leis de trânsito antes de serem autorizados a operar sem um motorista. A UE também estabeleceria padrões mínimos de segurança e responsabilidade para proteger os passageiros e pedestres.
Empirical Determination of Locations of Unstable and Blank Gsm Signal Network...IJERA Editor
In a GSM network coverage area there exist locations where network signal reception is always either unsteady or blank. These problems are the cause of intermittent call receptions or no network reception at some locations in cell sites. This paper discusses a practical work carried out in a cell site located in a remote area in Eastern Nigeria to determine such locations. To do that, received signal field strength measurements were initially conducted at 3m interval starting from 100m away from the base Station to determine the suspected locations of unsteady and blank network receptions in the field. Further extensive measurements were then taken at each of the suspect locations. Analyses of the data obtained shows that a lot of such phenomenon may exist in cell sites.
This study examined the effect of manganese citrate and manganese sulfate on the growth of the medicinal mushroom Trametes versicolor. It found that manganese citrate significantly increased the biomass of T. versicolor compared to manganese sulfate when added to a GPY medium. However, when added to a synthetic GAsn medium, manganese citrate and manganese sulfate had an equally low effect on biomass growth. Notably, manganese citrate resulted in lower glucose consumption from the GAsn medium compared to manganese sulfate. This demonstrates that manganese citrate and sulfate have different impacts on the fungus's ability to absorb nutrients from culture media depending on the medium composition.
Enhancing Data Integrity in Multi Cloud StorageIJERA Editor
Cloud computing is a way to increase the capacity or add capabilities dynamically without investing in new infrastructure, training new personnel, or licensing new software. Cloud is surrounded by many security issues like securing data and examining the utilization of cloud by the cloud computing vendors. Security is one of the major issues which reduce the growth of cloud computing. A large number of clients or data owners store their data on servers in the cloud and it is provided back to them whenever needed. The data provided should not be jeopardized. Data integrity should be taken into account so that the data is correct, consistent and accessible. For ensuring the integrity in cloud computing environment, cloud storage providers should be trusted. Dealing with single cloud providers is predicted to become less secure with customers due to risks of service availability, failure and the possibility of malicious insiders in the single cloud. This paper deals with multi cloud environments to resolve these issues. The integrity of the data in multi cloud storage has been provided with the help of trusted third party using cryptographic algorithm.
El documento critica la hipocresía de Europa al tratar de evitar la llegada de inmigrantes africanos, cuando Europa se enriqueció a costa de saquear y explotar a África durante siglos de colonialismo. Compara a Europa con el príncipe en "La máscara de la muerte roja" de Poe, que intentó encerrarse de la peste pero la muerte entró de todos modos. Afirma que los africanos tienen derecho a compartir la riqueza que Europa se llevó de África, y que Europa debería rec
Winrar es un programa gratuito para comprimir y descomprimir archivos. Se puede descargar la versión crackeada de Winrar desde un enlace proporcionado. Una vez descargado, se instala haciendo doble clic en el archivo de instalación. Winrar permite comprimir archivos de forma rápida haciendo clic derecho y seleccionando "Añadir a archivo..." o "Añadir a *.rar", y descomprimir archivos seleccionando "Extraer archivos...".
This document compares three methods for mapping land cover of Vaderahalli Village, India: analysis of satellite imagery using GIS software MapInfo, analysis of Google Earth images using Google Pro software, and analysis of Google Earth images using MATLAB software. Land cover features mapped included green cover, water bodies, open spaces, paved surfaces and built-up areas. Results from each method were verified on-site using GPS. Analysis with MapInfo using satellite imagery provided the most accurate results but was more expensive and complex. Google Pro analysis was less accurate but simpler and cheaper. MATLAB analysis was least accurate and most complex and time-consuming. Overall, remote sensing with GIS provided the most effective land cover mapping approach.
A Review Of Different Approaches Of Land Cover MappingJose Katab
This document reviews different approaches for land cover mapping, including artificial neural networks (ANNs), fuzzy logic, supervised/unsupervised classification, and maximum likelihood. It discusses how each approach has been applied in previous studies for land cover classification using remote sensing data. The document also examines common problems in remote sensing image classification, such as mixed pixels, and different methods that have been proposed and used to address these issues, such as maximum likelihood classification and fuzzy classifiers. Overall, the review analyzes and compares algorithms for land cover classification and evaluates methods for overcoming problems encountered during the classification process.
IRJET- Impact Assessment of Mining Activities through Change Detection AnalysisIRJET Journal
1) The document discusses a study assessing the impact of mining activities in Ariyalur district, Tamil Nadu, India through change detection analysis from 1979 to 2019.
2) Landsat images from three different years were analyzed using techniques like image rectification, classification, and GIS integration to map land use/land cover changes and the expansion of mining areas over time.
3) Preliminary results found mining has caused rapid changes to the local environment, including increased pollution and deforestation. Further analysis of the satellite images aims to better understand these impacts and provide recommendations to control ecological disturbance from mining.
IRJET- Land Use & Land Cover Change Detection using G.I.S. & Remote SensingIRJET Journal
This document discusses land use and land cover change detection in Vadodara, India between 1998 and 2008 using remote sensing and GIS techniques. Specifically, it analyzed Landsat satellite images from those two decades to map and classify land use, including built up area, vegetation, vacant land, and water bodies. The methodology involved image preprocessing like geometric correction and radiometric normalization. Images were then enhanced and classified using both supervised and unsupervised classification. Comparing the classified maps from 1998 and 2008 allowed analyzing changes in land use over that 10-year period and calculating the rate of land consumption. The study aimed to provide information to urban planners for predicting future growth and avoiding problems associated with rapid urbanization.
This document reviews research on classifying crops from remotely sensed images. It discusses how multispectral and hyperspectral imagery have been used with both supervised and unsupervised classification techniques. Multispectral imagery provides good information for overall vegetation mapping but has limitations differentiating similar crops. Hyperspectral imagery can help overcome these limitations by identifying fine spectral differences. The document also discusses how microwave remote sensing, which is unaffected by clouds, can complement optical imagery by improving classification accuracy when data is fused. Overall, the review finds that remote sensing is useful for crop monitoring but challenges remain in identifying multiple crop types and differentiating similar crops.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Classification of aurangabad city using high resolution remote sensing dataeSAT Journals
Abstract
The current study highlights the advantages of remote sensing and Geographic Information System (GIS) in the field urban planning and management. IRS-P6 Resourcesat-1 LISS-IV high spatial resolution (5.8m) data with three spectral bands were used for urban classification. The study area Aurangabad is the capital metro city of Maharashtra State, India. ENVI 4.4 image processing tool was used for classification of satellite data on the basis of supervised approach. Two statistical algorithms were used for urban classification such as Minimum distance and Mahalanobis distance classifier. Lastly the accuracy of the classification was performed through ground truth. The result indicates that the Minimum distance classifier gives the better results than Mahalanobis classifier which are 80.2817% and 70.4225% respectively. Hence it is identified minimum distance is best for urban classification.
Keywords: Supervised classification, Multispectral, Confusion matrix, Producer’s accuracy, Users accuracy.
Detection of urban tree canopy from very high resolution imagery using an ob...IJECEIAES
Tree that grows within a town, city and suburban areas, collection of these trees makes the urban forest. These urban forest and urban trees have impact on urban water, pollution and heat. Nowadays we are experiencing drastic climatic changes because of cutting of trees for our growth and increasing population which leads to expansion of roads, towers, and airports. Individual tree crown detection is necessary to map the forest along with feasible planning for urban areas. In this study, using WorldView-2imagery, trees in specific area are detected with object-based image analysis (OBAI) approach. Therefore with improvement in spatial and spectral resolution of an image, extracted from WorldView-2 carried out urban features with better accuracy. The aim of this research is to illustrate how object-based method can be applied to the available data to accurately find out vegetation, which can be further sub-classified to obtain area under tree canopy. The result thus obtained gives area under tree canopy with an accuracy of 92.43 % and a Kappa coefficient of 0.80.
Unsupervised Building Extraction from High Resolution Satellite Images Irresp...CSCJournals
The document discusses an unsupervised method for extracting buildings from high resolution satellite images regardless of rooftop structures. The method first calculates NDVI and chromaticity ratios to segment vegetation and shadows. Rooftops and roads are then detected and eliminated. Principal component analysis and area analysis are performed to accurately extract buildings. The algorithm aims to eliminate inhomogeneities caused by varying building hierarchies by focusing on eliminating non-building regions rather than detecting building regions of interest. The methodology is tested on Quickbird satellite imagery and results indicate it can extract buildings in complex environments irrespective of rooftop shape.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This document summarizes a research paper that classified multi-date remote sensing images using NDVI values. It discusses how NDVI values were calculated from Terra satellite imagery using red and infrared band values. A similarity measure formula was proposed to classify images based on comparing NDVI values of unknown images to reference images. The formula measured similarity between image windows using sum of absolute differences of NDVI values. Five Terra images from different dates were classified into 20 reference classes using this approach.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document summarizes research comparing three machine learning classification methods - Decision Tree, Support Vector Machine (SVM), and k-Nearest Neighbors (k-NN) - for classifying land use from high and low resolution satellite imagery. The researchers applied each method to classify Pleiades satellite images of Taiwan and Colorado. SVM achieved the highest overall accuracy of 78.6% for high resolution imagery and 83.3% for low resolution imagery. Decision Trees and k-NN were less accurate. The document outlines the methodology, including image preprocessing, parameter selection, accuracy assessment, and findings.
Automatic traffic light controller for emergency vehicle using peripheral int...IJECEIAES
Traffic lights play such important role in traffic management to control the traffic on the road. Situation at traffic light area is getting worse especially in the event of emergency cases. During traffic congestion, it is difficult for emergency vehicle to cross the road which involves many junctions. This situation leads to unsafe conditions which may cause accident. An Automatic Traffic Light Controller for Emergency Vehicle is designed and developed to help emergency vehicle crossing the road at traffic light junction during emergency situation. This project used Peripheral Interface Controller (PIC) to program a priority-based traffic light controller for emergency vehicle. During emergency cases, emergency vehicle like ambulance can trigger the traffic light signal to change from red to green in order to make clearance for its path automatically. Using Radio Frequency (RF) the traffic light operation will turn back to normal when the ambulance finishes crossing the road. Result showed the design is capable to response within the range of 55 meters. This project was successfully designed, implemented and tested.
study and analysis of hy si data in 400 to 500IJAEMSJORNAL
This document summarizes a research paper that analyzed hyperspectral data in the 400-500nm visible and near infrared (VNIR) spectrum for precision agriculture applications. Specifically:
1) Hyperspectral imagery of the Amravati region of India was classified using maximum likelihood classification to determine soil, water, and vegetation indices. Spectral graphs showed reflectance curves for each.
2) The analysis aims to extract information about the terrain from hyperspectral data in a way that is easily understood. Such data provides more accurate information than multispectral data due to the large number of narrow bands.
3) Supervised classification with maximum likelihood was used to categorize pixels into classes for producing the
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
IRJET-Mapping of Mineral Zones using the Spectral Feature Fitting Method in J...IRJET Journal
This document summarizes a study that used the Spectral Feature Fitting (SFF) algorithm to map mineral zones in the Jahazpur belt area of Rajasthan, India using Airborne Visible/Infrared Imaging Spectrometer Next Generation (AVIRIS-NG) hyperspectral imagery. The SFF algorithm was applied to process the AVIRIS-NG imagery to identify and enhance mineral mapping with better accuracy. Preprocessing steps including noise removal and dimensionality reduction using Minimum Noise Fraction transformation were applied. Pixel Purity Index and n-Dimensional visualization were used to extract pure pixel endmembers. The SFF method then helped classify the imagery and produce a mineral distribution map of the study area with high efficiency.
Accuracy Assessment of Land Use/Land Cover Classification using multi tempora...IRJET Journal
This document analyzes land use/land cover (LULC) changes in Varanasi city, India over a 20 year period from 2000 to 2020 using multi-temporal satellite imagery. Landsat images from 2000, 2010, and 2020 were classified into six LULC classes - water bodies, sandbars, fallow land, built up area, vegetation, and crop land. The results show significant increases in built up area and fallow land, with corresponding decreases in vegetation and crop land. Accuracy assessment using confusion matrices found overall classification accuracies of 93.94%, 91.66%, and 89.47% for the 2000, 2010, and 2020 images respectively. The study demonstrates the use of GIS and remote sensing
IRJET- Accuracy Assessment of Land use Land Cover Classifiaction using Erda’s...IRJET Journal
This document discusses using ERDA's software to classify land use and land cover from satellite imagery and assess the accuracy of the classification. It performed supervised classification on imagery of a study area in India using non-parametric rules, classifying pixels into agriculture, water bodies, built-up areas, forests, shrubs, and barren land. An accuracy assessment found an overall classification accuracy of 81.7% and kappa coefficient of 0.722, indicating substantial agreement between predicted and actual land cover classifications. The study demonstrates how ERDA's software can accurately classify land use/cover maps from remote sensing data.
Similar to Performance of RGB and L Base Supervised Classification Technique Using Multispectral Satellite Imagery (20)
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsVictor Morales
K8sGPT is a tool that analyzes and diagnoses Kubernetes clusters. This presentation was used to share the requirements and dependencies to deploy K8sGPT in a local environment.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Batteries -Introduction – Types of Batteries – discharging and charging of battery - characteristics of battery –battery rating- various tests on battery- – Primary battery: silver button cell- Secondary battery :Ni-Cd battery-modern battery: lithium ion battery-maintenance of batteries-choices of batteries for electric vehicle applications.
Fuel Cells: Introduction- importance and classification of fuel cells - description, principle, components, applications of fuel cells: H2-O2 fuel cell, alkaline fuel cell, molten carbonate fuel cell and direct methanol fuel cells.
TIME DIVISION MULTIPLEXING TECHNIQUE FOR COMMUNICATION SYSTEMHODECEDSIET
Time Division Multiplexing (TDM) is a method of transmitting multiple signals over a single communication channel by dividing the signal into many segments, each having a very short duration of time. These time slots are then allocated to different data streams, allowing multiple signals to share the same transmission medium efficiently. TDM is widely used in telecommunications and data communication systems.
### How TDM Works
1. **Time Slots Allocation**: The core principle of TDM is to assign distinct time slots to each signal. During each time slot, the respective signal is transmitted, and then the process repeats cyclically. For example, if there are four signals to be transmitted, the TDM cycle will divide time into four slots, each assigned to one signal.
2. **Synchronization**: Synchronization is crucial in TDM systems to ensure that the signals are correctly aligned with their respective time slots. Both the transmitter and receiver must be synchronized to avoid any overlap or loss of data. This synchronization is typically maintained by a clock signal that ensures time slots are accurately aligned.
3. **Frame Structure**: TDM data is organized into frames, where each frame consists of a set of time slots. Each frame is repeated at regular intervals, ensuring continuous transmission of data streams. The frame structure helps in managing the data streams and maintaining the synchronization between the transmitter and receiver.
4. **Multiplexer and Demultiplexer**: At the transmitting end, a multiplexer combines multiple input signals into a single composite signal by assigning each signal to a specific time slot. At the receiving end, a demultiplexer separates the composite signal back into individual signals based on their respective time slots.
### Types of TDM
1. **Synchronous TDM**: In synchronous TDM, time slots are pre-assigned to each signal, regardless of whether the signal has data to transmit or not. This can lead to inefficiencies if some time slots remain empty due to the absence of data.
2. **Asynchronous TDM (or Statistical TDM)**: Asynchronous TDM addresses the inefficiencies of synchronous TDM by allocating time slots dynamically based on the presence of data. Time slots are assigned only when there is data to transmit, which optimizes the use of the communication channel.
### Applications of TDM
- **Telecommunications**: TDM is extensively used in telecommunication systems, such as in T1 and E1 lines, where multiple telephone calls are transmitted over a single line by assigning each call to a specific time slot.
- **Digital Audio and Video Broadcasting**: TDM is used in broadcasting systems to transmit multiple audio or video streams over a single channel, ensuring efficient use of bandwidth.
- **Computer Networks**: TDM is used in network protocols and systems to manage the transmission of data from multiple sources over a single network medium.
### Advantages of TDM
- **Efficient Use of Bandwidth**: TDM all
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesChristina Lin
Traditionally, dealing with real-time data pipelines has involved significant overhead, even for straightforward tasks like data transformation or masking. However, in this talk, we’ll venture into the dynamic realm of WebAssembly (WASM) and discover how it can revolutionize the creation of stateless streaming pipelines within a Kafka (Redpanda) broker. These pipelines are adept at managing low-latency, high-data-volume scenarios.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
Advanced control scheme of doubly fed induction generator for wind turbine us...
Performance of RGB and L Base Supervised Classification Technique Using Multispectral Satellite Imagery
1. Mr. S Thirunavkkarsu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 9( Version 6), September 2014, pp.44-49
www.ijera.com 44 | P a g e
Performance of RGB and L Base Supervised Classification Technique Using Multispectral Satellite Imagery Mr. S Thirunavkkarsu*, Capt. Dr. S Santhosh Baboo** *Research Schollar, P.G. and Research Department of Computer Science, Dwaraka Doss Goverdhan Doss Vaishnav College, Chennai – 600 106. ** Associate Professor, P.G. and Research Department of Computer Science, Dwaraka Doss Goverdhan Doss Vaishnav College, Chennai – 600 106.
ABSTRACT In the present growth of sensor technology is to improve the new chance and applications in GIS. This enhances the technology law a new method that should not focus on real time available products, but it must automatically lead to new ones. The aim of the paper is to make a maximum use of remote sensing data and GIS techniques to access land use and land cover classification in the Kiliyar sub basin sector in palar river of northen part of Tamil Nadu.IRS P6 LISS III is merged data to perform the classification using ERDAS Imaging. The RGB and L base supervised classification was based up on a Multispectral analysis, land use and land cover information‟s (maps and existing reports), which involves advanced technology and complex data processing to find detailed imagery in the study region. Ground surface reflects more radar energy emitted by the sensor from the study region, which makes it easy to distinguish between the water body, hilly, agriculture, settlement and wetland.
Keywords - Multispectral, Classification, RGB&L, SAM, SCM,
I. INTRODUCTION
A procedure that use the satellite imagery data to produce maps and/or tables shows the study region and point of different selected land cover types or ground characteristic is called image classification[2]. This is the next step of the imagery enhancement or post processing. This is the most common ways to use remotely sensed data for generate land cover maps. This technique requires minimal prior knowledge of the area where a map is needed and easily incorporates ancillary data. Remote sensing image classification can be viewed as a joint venture of both image processing and classification techniques. Generally, image classification, in the field of remote sensing is the process of assigning pixels or the basic units of an image to classes. It is likely to assemble groups of identical pixels found in remotely sensed data into classes that match the informational categories of user interest by comparing pixels to one another and to those of known identity. Several technique of image classification exists.
Image classification is an important part of the remote sensing, image analysis and pattern recognition. In some instances, the classification itself may be the object of the analysis. For example, classification of land use from remotely sensed data produces a map like imagery as the final product of the analysis [6]. In other cases, the classification can serve only as an intermediate step in more intricate analyses, such as land degradation studies, process studies, landscape modeling, coastal zone management, resource management and other environment monitoring applications. The image classification therefore forms an important tool for examination of the digital images. Using this classification tool, we can extract our own representation of land use/land cover information. As a result, image classification has emerged as a significant tool for investigating digital images. Moreover, the selection of the appropriate classification technique to be employed can have a considerable upshot on the results of whether the classification is used as an ultimate product or as one of numerous analytical procedures applied for deriving information from an imagery for additional analyses[5].
Multispectral imagery is used for imagery classification based on unsupervised and supervised classification algorithm. In the preprocessing stage, RGB and L based spectral sharpening method is applied to sharpen and resample for achieving pixel size based on high resolution. The performance evaluation metrics proved that spectral sharpening performs better than sharpening the RGB and L between the boundaries. The minimum distance to mean classifier, the maximum likelihood classifier and the box classification were used. According to the
RESEARCH ARTICLE OPEN ACCESS
2. Mr. S Thirunavkkarsu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 9( Version 6), September 2014, pp.44-49
www.ijera.com 45 | P a g e
land cover reflectance characteristics of the surface material, the land use and land cover classification indicated 5 classes that belong to 30 classes. The land use and land cover map contains 5 classes. It has been shown, within the limitation, threshold parameters and classification algorithms containing significant influence on the classification results and should be selected carefully based on the study region.
II. STUDY AREA
Palar is a southern India river, originated from Nandidurg hills of Karnataka state and flows through Karnataka, Andhra Pradesh, Tamil Nadu and finally convergence into the Bay of Bengal at Vayalur, Tamilnadu.
Fig. 1. Study Area
Palar River Basin is one of the 17 major rivers of Tamil Nadu. This basin is divided in to 8 sub basins. Kiliyar is one of the sub basins, which mostly covers Thiruvannamalai and Kanchipuram districts about 914.45 sq. km total geographical area.
III. METHODOLOGY
Fig. 2. Methodology Diagram for Image Classification
This methodology involves both the primary and the secondary information. This research focuses land use and/or land cover classification in Kiliyar sub basin in Northern Tamilnadu. Land use types of 2008 have been categorized on the basis of land use category classified by district resource map, agriculture, forest, built-up area, water bodies and barren land. Similarly, for land use data of 2008 toposheets (scale 1:50000 to topographic map) generated by Survey of India. Different land use categories have taken and classified by department of survey during preparation of topographic map viz agriculture, forest, settlement, water bodies, landslide. All the necessary data set for the research work such land use map 2008, land cover map 1972 to 1976, roads, rivers, settlements contours have been converted into 'digital' form through using ERDAS Imaging. The study region satellite imagery is shown in following fig. 3.
Fig. 3. Unclassified Satellite Imagery for Study Area
To obtain the study area map during the year 1972- 1976 (scale 1:50000), geology map (scale 1:50000) prepared District resource map of geological survey of india in 2008 and Resource map bhoovan sample data, NRSC website during the year 1990 to 2010.
IV. IMAGE TRAINING PROCESS
The overall goal of this step is to group a set of raw data that describe the natural result pattern for each land use land cover types to be classified in an imagery of the study area. Locate and classify using RGB & L based, to several relatively blocks of imagery, dispersed over the entire study site, each containing as a segregate of land cover type of interest. These are known as candidate training sets. The training set is to create and analyze the image pixels we must describe the each class or category that are to be mapped in the imagery; and we should identify the pixel values by which the category is to be recognized and identified, differentiate varying pixel values for each category as a result we can get most appropriate and accurate results.
We define the brightness level or the density of color intensity of the classing color; we must also describe the tolerance level of each channel or of the composite color by which the comparison can make an adjustment while examination at each pixel. Clusters in the feature space were used to determine the spectral classes in to which the imagery is resolved, and to perform representative subset of raw data by sampling method to acquire sets of ground truth that can be used to establish decision system for
Display the Result
Identifying the Classes
Classification Technique Selection
Color based pixels Identified
Imagery is to be processed
Satellite Imagery
3. Mr. S Thirunavkkarsu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 9( Version 6), September 2014, pp.44-49
www.ijera.com 46 | P a g e
the classification of every pixel in the satellite imagery data set. Training data set is called signature file creation is shown in the following fig.4.
Fig. 4. Image Pixel Identification for Signature File Creation
In the fig. 4, various category of classes like Hills, Water body, Agriculture Land, Wetland, Settlement were chosen as training area. In this process the block pixels are trained as water body or tank, the dark gray pixels selected as Hills, the ash green pixels are trained as barren land and the red pixels are trained as cropland, continue in this process according to our classification method. Thus under the hole system we will require to provide the following data as training data set.
Name or label of the group
RGB channel values of the color for the group
Tolerance of the color from the described color
4.1. Input the Imagery to Process
Imagery for analysis must be specified as RGB and L base techniques deal with the pixel values, regardless of the type of the imagery or any imagery can be analyzed. In this satellite imagery, details are given below Table 1. Table1: Satellite Imagery Details
Image Type
Pan and Liss III Merged Data
File Format
Geo TIFF
Projection Type
UTM
Spheroid Name
WGS 84
Datum Name
WGS84
UTM Zone
1
North or South
North
4.2. Color Based Pixel Identification
From the top left corner of the input imagery, the pixels are grip and are used for assessment. While grievance the pixel values, we transform the pixels color values into the separate channel values and the brightness level or identify its density level.
4.3. Proposed Classification Method
The remote sensing presents with a number of supervised and unsupervised technique, that have been developed to undertake the multispectral data classification problem. In this paper RGB & L base supervised technique is used. The statistical method in use for the previous studies of land use land cover classification is the maximum likelihood classifier. Nowadays, various studies have applied artificial intelligence techniques as substitutes to remotely sensed image classification applications. In addition, diverse ensemble classification method has been proposed to significantly improve classification accuracy. Scientists and practitioners have made great efforts in developing efficient classification approaches and techniques for improving classification accuracy. The image quality of a supervised classification [3] depends on the quality of the training sites. All the supervised classifications usually have a sequence of operations that must be followed.
Defining of the Training Sites.
Extraction of Signatures.
Classification of the Imagery
The training sites are done with digitized features. Usually two or three training sites are selected. The more training site is selected, the better results can be gained. This procedure assures both the accuracy of classification and the true interpretation of the results. After the training site areas are digitized then the statistical characterizations of the information are created. These are called Signatures. Finally the classification methods are applied. At present, there are different image classifications procedures are used for different purposes by various researchers. These techniques are distinguished in two main ways as supervised and unsupervised classifications. Additionally, supervised classification has different sub classification methods, which are named as parallelepiped, maximum likelihood and minimum distances. These methods are named as Hard Classifier. In this work RGB& L Base method is used for supervised classification methods. Its result and performance given below.
4.4. Identifying the Classes Categories
After picking up pixel and splitting up channels, each channel must be compared with the channels of each groups training data. On examining that the pixel value contains the value of training data, we consider the following constraints.
Hills
Water Body
Settlement
Wetland
4. Mr. S Thirunavkkarsu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 9( Version 6), September 2014, pp.44-49
www.ijera.com 47 | P a g e
If each channel has the accurate values as the
training data, then it must signature file.
If each channel or any of them fails to prove, to
be the exact values in the signature value then
the pixel‟s values must be compared with the
abide color values form the color of the group.
If in, the pixel a value does not matches any of
the above conditions then the pixel is labeled
to be an “unknown” pixel and must start
comparing again with next class.
Assessment of a pixel must run until a category is
found for a pixel or all the class found unmatched for
the pixel.
4.5. Display the Result
After all the pixels were examined, we can display
the result. With the result, we can easily plot
classified map imagery, according to the supervised
classes. All the unknown pixels from this plotting will
be the borders of the category specified in any way
and we can easily draw the borders of each group
without any fail.
V. RESULT AND DISCUSSION
The main aim of the study is to evaluate the
performance of the different classification algorithms
using the multispectral data. This is implemented with
ERDAS Imaging 2014 [14]. In a similar way, the
classification algorithms can be applied for the
multispectral data [15].
There are three existing classification method
classified and tested in unclassified satellite Imagery.
Beginning of the classification, Analysts could not
locate which is water body, hills, crop, fallow and
other classes. The satellite unclassified imagery
shown in above fig.3.
5.1. Proposed Classification Algorithm
Fig. 5. Classified imagery for RGB & L Based Method
5.2. Maximum Likelihood Classification
Algorithm
First the unclassified satellite imagery was tested
with maximum likelihood classification technique.
This Classification uses the training data by means of
estimating means and variances of the classes, which
are used to estimate probabilities and also consider the
variability of brightness values in each class.
Fig. 6. Classified imagery for Maximum Likelihood Method
This classifier is based on Bayesian probability
theory. It is the most powerful classification methods
when accurate training data is provided and one of the
most widely used algorithm. The classified imagery is
shown in above figure 6.
The Maximum Likelihood classification is
calculated as:
ln ( 1) 1
i
t
i i v
y y
d x v
Where di denote as distance between feature vector
(x) and a class mean (mi) based on probabilities, vi
denote as the n x n variance-covariance matrix of
class i, where n is the number of input bands, y denote
as x - mi; is the difference vector between feature
vector x and class mean vector mi and yt denote as the
transposed of y.
5.3. Minimum Distance Classification
Algorithm
Second the unclassified satellite imagery was tested
with minimum Distance classification technique. It is
based on the minimum distance decision rule that
calculates the spectral distance between the
measurement vector for the imagery pixel and the
mean vector for each sample. Then it assigns the
candidate pixel to the class having the minimum
spectral distance. The classified imagery is shown in
figure 7.
Fig. 7. Classified imagery for Minimum Distance Method
For each feature vector, the distances towards
class means are calculated.
The shortest Euclidian distance to a class
mean is found.
If this shortest distance to a class mean is
smaller than the user-defined threshold, then
this class name is assigned to the output pixel.
Else the undefined value is assigned.
5. Mr. S Thirunavkkarsu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 9( Version 6), September 2014, pp.44-49
www.ijera.com 48 | P a g e
5.4. Parallelepiped Classification Algorithm
Finally the unclassified satellite imagery was tested
with parallel piped classification technique. This is a
widely used decision rule based on simple Boolean
“and/or” logic. Training data in „n‟ spectral bands are
used in performing the classifications. Brightness
values from each pixel of the multispectral imagery
are used to produce an n-dimensional mean vector,
Mc = (μck , μc2 , μ c3 , ... μcn ) with μck being the mean
value of the training data obtained for class c in band
k out of possible classes, as previously defined. Sck is
the standard deviation of the training data class c of
band k out of m possible classes.
The parallelepiped algorithm is a computationally
efficient method for classifying remote sensor data.
Unfortunately, because some parallelepiped overlap,
it is possible that an unknown candidate pixel might
satisfy the criteria of more than one class. In such
cases it is usually assigned to the first class for which
it meets all criteria. A more elegant solution is to take
this pixel and can be assigned to more than one class
and use a minimum distance by means of decision
rule to assign it to just one class. The parallelepiped
classifier uses the class limits and stored in each class
signature to determine, if a given pixel falls within the
class or not. The class limits specify the dimensions of
each side of a parallelepiped surrounding the mean of
the class in feature space. If the pixel falls inside the
parallelepiped, it is assigned to the class. However, if
the pixel falls within more than one class, it is put in
the overlap class. If the pixel does not fall inside any
class, it is assigned to the null class. The classified
imagery is shown in figure 8.
Fig. 8. Classified imagery for Parallel Piped Method
5.5. Mahalanobis distance Classification
Algorithm
Mahalanobis distance classification is similar to
minimum distance classification except that the
covariance matrix is used. The Mahalanobis distance
classification algorithm assumes that the histograms
of the bands have normal distributions. The classified
imagery is shown the figure 9.
The Mahalanobis distance is calculated as:
( 2) 1
i
t
i v
y y
d x
Clarification of the limits as follow
For each feature vector x, the shortest
Mahalanobis distance to a class mean is
found.
If this shortest distance to a class mean is
smaller than the user-defined threshold, then
this class name is assigned to the output pixel.
Else the undefined value is assigned.
Fig. 9. Classified imagery for Mahalanobis distance Method
5.6. Spectral Angle Mapper Classification
Algorithm
The Spectral Angle Mapper (SAM) method is an
automated method for directly comparing imagery
spectra to known spectra. This method cares for both
spectra as vectors and compute the spectral point of
view between them. This method is insensitive to
illumination since the SAM algorithm uses only the
vector direction and not the vector length. The result
of the SAM classification is an imagery show in
figure 10.
Fig. 10. Classified imagery for Spectral Angle Mapper Method
SAM Presents the following formula
cos (3) 2 2
1
x y
xy
denote as Angle formed between reference
spectrum and image spectrum, x denote as image
spectrum, y denote as reference spectrum.
5.7. Spectral Correlation Mapper
Classification Algorithm
The Spectral Correlation Mapper (SCM) method is
a derivative of Pearsonian Correlation Coefficient that
eliminates negative correlation and maintains the
SAM characteristic of minimizing the shading
consequence resulting in improved result shown
figure 11.
The SCM algorithm method, similar to SAM, uses
the reference spectrum defined by the researcher, in
agreement with the imagery user wants to classify.
SCM presents the following formula
6. Mr. S Thirunavkkarsu Int. Journal of Engineering Research and Applications www.ijera.com
ISSN : 2248-9622, Vol. 4, Issue 9( Version 6), September 2014, pp.44-49
www.ijera.com 49 | P a g e
(4)
2
1
2 2 2
1
2 2
N x x N y y
N xy x y
R
The function cos (SAM) is similar to the
Pearsonian Correlation Coefficient above equation.
The big difference is that Pearsonian Correlation
Coefficient standardizes the data, centralizing itself in
the mean of x and y.
Fig. 11. Classified imagery for Spectral Correlation Mapper
Method
VI. CONCLUSION
The proposed supervised classification method
gave better accuracy than the other classification
methods. It is observed that the spectral means of the
classes in all bands was improved. The proposed
method compares with existing method namely
Parallelepiped, Maximum Likelihood, Minimum
Distance, Mahalanobis distance, SAM and SCM. If
the result is better, it indicates that the training
samples were spectrally separable and the
classification works well in the study region. This aids
in the training set refinement process, but indicates
little about classifier performance elsewhere in the
scene.
REFERENCES
[1] Ozesmi, Stacy L., and Marvin E. Bauer. "Satellite
remote sensing of wetlands."Wetlands ecology
and management 10.5 (2002): 381-402.
[2] Fukue, Kiyonari, et al. "Evaluations of
unsupervised methods for land‐cover/use
classifications of landsat TM data." Geocarto
International 3.2 (1988): 37-44.
[3] Lu, D., M. Batistella, and E. Moran. "Land‐cover
classification in the Brazilian Amazon with the
integration of Landsat ETM+ and Radarsat
data." International Journal of Remote
Sensing 28.24 (2007): 5447-5459.
[4] Akgün, Aykut, A. Hüsnü Eronat, and Necdet
Turk. "Comparing Different Satellite Image
Classification Methods: An Application In
Ayvalýk District, Western Turkey." XXth
International Congress for Photogrammetry and
Remote Sensing, Istanbul, Turkey. 2004.
[5] Lillesand, Thomas M., Ralph W. Kiefer, and
Jonathan W. Chipman. Remote sensing and
image interpretation. No. Ed. 5. John Wiley &
Sons Ltd, 2004.
[6] Lu, Dengsheng, and Qihao Weng. "A survey of
image classification methods and techniques for
improving classification
performance." International journal of Remote
sensing 28.5 (2007): 823-870.
[7] Story, Michael, and Russell G. Congalton.
"Accuracy assessment-A user's
perspective." Photogrammetric Engineering and
remote sensing 52.3 (1986): 397-399.
[8] Dean, A. M., and G. M. Smith. "An evaluation of
per-parcel land cover mapping using maximum
likelihood class probabilities." International
Journal of Remote Sensing 24.14 (2003): 2905-
2920.
[9] Jasinski, Michael F. "Estimation of subpixel
vegetation density of natural regions using
satellite multispectral imagery." Geoscience and
Remote Sensing, IEEE Transactions on 34.3
(1996): 804-813.
[10] Palaniswami, C., A. K. Upadhyay, and H. P.
Maheswarappa. "Spectral mixture analysis for
subpixel classification of coconut." CURRENT
SCIENCE-BANGALORE- 91.12 (2006): 1706.
[11] Lu, Dengsheng, and Qihao Weng. "A survey of
image classification methods and techniques for
improving classification
performance." International journal of Remote
sensing 28.5 (2007): 823-870.
[12] Landgrebe, David. "On information extraction
principles for hyperspectral data."Purdue
University, West Lafayette, IN, USA (1997): 34.
[13] Govender, M., et al. "A comparison of satellite
hyperspectral and multispectral remote sensing
imagery for improved classification and mapping
of vegetation."Water SA 34.2 (2008): 147-154.
[14] Richason Jr, Benjamin F. "Introduction to remote
sensing of the environment."Introduction to
remote sensing of the environment. (1978).
[15] Richards, John A., and J. A. Richards. Remote
sensing digital image analysis. Vol. 3. Berlin et
al.: Springer, 1999.
[16] Landgrebe, David. "Hyperspectral image data
analysis." Signal Processing Magazine,
IEEE 19.1 (2002): 17-28.