Improving the calibration of the MOLAND urban growth model with land-use info...Beniamino Murgante
Improving the calibration of the MOLAND urban growth model with land-use information derived from a time-series of medium resolution remote sensing data - Tim Van de Voorde, Johannes van der Kwast, Inge Uljee
Guy Engelen, Frank Canters
Airport Runway Detection Based On ANN AlgorithmIJTET Journal
Automatic detection of airports is especially essential, attributable to the strategic importance of those targets. during this paper, a detection methodology is planned for flying field runways. This methodology, that operates on massive optical satellite pictures, consists of a segmentation methodsupported textural properties, and a runway form detection stage. within the segmentation method, manynative textural optionsarea unit extracted. Since the most effective discriminative options for flying field runways cannot be trivially foreseen, the ANN algorithmic ruleis utilized as a feature selector over an oversized set of options. Moreover, the chosenoptions with corresponding weights willgivedata on the hidden characteristics of runways. The plannedalgorithmic rule is examined with experimental work employing a comprehensive knowledge set consisting of enormous and high resolution satellite pictures and thriving results area unit achieved.
Today very high resolution DEM from satellite image data with resolution of about one meter allows to depict very detailed surface changes.
High resolution DEM increase accurate satellite image geometry and adding DGPS ground control points increases x.y.z accuracy.
Wrong positioning of objects or bad parameters calculation often result in bad image geometry.
From along track stereo pairs of VHR satellite optical data it’s possible to generate an automatic DEM.
Applications :
Ortho-rectification of satellite images, 3D display.
Creation of accurate topographic reference, relief maps.
Topographic profiles and contour generation.
Surface analysis.
Calculations of slope, orientation and shading.
Calculations of volume and elevation
Extraction of terrain and morphometric parameters.
Geomorphology and structural analysis.
Geological quantifications (dips, lithological thicknesses, faults and folds of geometry, etc.).
3D Reference map of resources extraction zones (quarries, open-pits).
Calculation of hydrographic networks and watershed basin.
Determination of hypsometric curves, knickpoints, etc.
Characterization of eroded areas.
Floods simulation, risks evaluation.
Volume calculation for restraints of dams.
Improving the calibration of the MOLAND urban growth model with land-use info...Beniamino Murgante
Improving the calibration of the MOLAND urban growth model with land-use information derived from a time-series of medium resolution remote sensing data - Tim Van de Voorde, Johannes van der Kwast, Inge Uljee
Guy Engelen, Frank Canters
Airport Runway Detection Based On ANN AlgorithmIJTET Journal
Automatic detection of airports is especially essential, attributable to the strategic importance of those targets. during this paper, a detection methodology is planned for flying field runways. This methodology, that operates on massive optical satellite pictures, consists of a segmentation methodsupported textural properties, and a runway form detection stage. within the segmentation method, manynative textural optionsarea unit extracted. Since the most effective discriminative options for flying field runways cannot be trivially foreseen, the ANN algorithmic ruleis utilized as a feature selector over an oversized set of options. Moreover, the chosenoptions with corresponding weights willgivedata on the hidden characteristics of runways. The plannedalgorithmic rule is examined with experimental work employing a comprehensive knowledge set consisting of enormous and high resolution satellite pictures and thriving results area unit achieved.
Today very high resolution DEM from satellite image data with resolution of about one meter allows to depict very detailed surface changes.
High resolution DEM increase accurate satellite image geometry and adding DGPS ground control points increases x.y.z accuracy.
Wrong positioning of objects or bad parameters calculation often result in bad image geometry.
From along track stereo pairs of VHR satellite optical data it’s possible to generate an automatic DEM.
Applications :
Ortho-rectification of satellite images, 3D display.
Creation of accurate topographic reference, relief maps.
Topographic profiles and contour generation.
Surface analysis.
Calculations of slope, orientation and shading.
Calculations of volume and elevation
Extraction of terrain and morphometric parameters.
Geomorphology and structural analysis.
Geological quantifications (dips, lithological thicknesses, faults and folds of geometry, etc.).
3D Reference map of resources extraction zones (quarries, open-pits).
Calculation of hydrographic networks and watershed basin.
Determination of hypsometric curves, knickpoints, etc.
Characterization of eroded areas.
Floods simulation, risks evaluation.
Volume calculation for restraints of dams.
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...Bayes Ahmed
This is my final Mater thesis presentation. The thesis defense was held on March' 07, 2011 at 15:30 in the seminar room of Universitat Jaume I (UJI), Castellón, Spain.
Surveying for Civil engineering is a
particular type of surveying known as "land surveying", it is the
detailed study or inspection, as by gathering information through
observations, measurements in the field, questionnaires, or
research of legal instruments, and data analysis in the support of
planning, designing, and establishing of property boundaries.
Land surveying can include associated services such as mapping
and related data accumulation, construction layout surveys,
precision measurements of length, angle, elevation, area, and
volume, as well as horizontal and vertical control surveys, and
the analysis and utilization of land survey data. Surveyors use
various tools to do their work successfully and accurately, such
as total stations, robotic total stations, GPS receivers, prisms, 3D
scanners, radio communicators, handheld tablets, digital levels,
and surveying software.
Survey data can be directly entered into a GIS from digital
data collection systems on survey instruments. When data is
captured, the user should consider if the data should be captured
with either a relative accuracy or absolute accuracy, since this
could not only influence how information will be interpreted but
also the cost of data captured.
In this paper GIS maps were developed depending on the
field surveying data made for a two traverses. First one has ribs
less than 50m length and the other larger than 50m. Each
traverse is holding five times using five equipments and
instruments: Tape, Level, Digital level, Digital theodolite and
Laser tape. Also those maps were drawn by using both of ACAD
and ArcView softwares. Then a detail surveying map was
produced. The precision was computed for both traverses in each
method. Its value is range from 1/140 to 1/10000.
Radiometric corrections include correcting the data for sensor irregularities and unwanted sensor or atmospheric noise, and converting the data so they accurately represent the reflected or emitted radiation measured by the sensor.
Mapping the anthropic backfill of the historical center of Rome (Italy) by us...Beniamino Murgante
Mapping the anthropic backfill of the historical center of Rome (Italy) by using Intrinsic Random Functions of order k (IRF-k)
Ciotoli Giancarlo, Francesco Stigliano, Fabrizio Marconi, Massimiliano Moscatelli, Marco Mancini, Gian Paolo Cavinato - Institute of Environmental Geology and Geo-engineering (I.G.A.G.), National Research Council, Italy
International Journal of Modern Engineering Research (IJMER) is Peer reviewed, online Journal. It serves as an international archival forum of scholarly research related to engineering and science education.
International Journal of Modern Engineering Research (IJMER) covers all the fields of engineering and science: Electrical Engineering, Mechanical Engineering, Civil Engineering, Chemical Engineering, Computer Engineering, Agricultural Engineering, Aerospace Engineering, Thermodynamics, Structural Engineering, Control Engineering, Robotics, Mechatronics, Fluid Mechanics, Nanotechnology, Simulators, Web-based Learning, Remote Laboratories, Engineering Design Methods, Education Research, Students' Satisfaction and Motivation, Global Projects, and Assessment…. And many more.
Feature Extraction for High Resolution Remote Sensing Image Classification us...Simone Rossi
The thesis explores the application of a advanced feature extraction technique, called "histogram of oriented gradients" (HOG), applied to multispectral VHR images. The algorithm, widely used in the human detection area, but new in this context of remote sensing, has been thoroughly analyzed in each phase, highlighting the correspondance between different parameter sets and different accuracy variations.
Urban Land Cover Change Detection Analysis and Modelling Spatio-Temporal Grow...Bayes Ahmed
This is my final Mater thesis presentation. The thesis defense was held on March' 07, 2011 at 15:30 in the seminar room of Universitat Jaume I (UJI), Castellón, Spain.
Surveying for Civil engineering is a
particular type of surveying known as "land surveying", it is the
detailed study or inspection, as by gathering information through
observations, measurements in the field, questionnaires, or
research of legal instruments, and data analysis in the support of
planning, designing, and establishing of property boundaries.
Land surveying can include associated services such as mapping
and related data accumulation, construction layout surveys,
precision measurements of length, angle, elevation, area, and
volume, as well as horizontal and vertical control surveys, and
the analysis and utilization of land survey data. Surveyors use
various tools to do their work successfully and accurately, such
as total stations, robotic total stations, GPS receivers, prisms, 3D
scanners, radio communicators, handheld tablets, digital levels,
and surveying software.
Survey data can be directly entered into a GIS from digital
data collection systems on survey instruments. When data is
captured, the user should consider if the data should be captured
with either a relative accuracy or absolute accuracy, since this
could not only influence how information will be interpreted but
also the cost of data captured.
In this paper GIS maps were developed depending on the
field surveying data made for a two traverses. First one has ribs
less than 50m length and the other larger than 50m. Each
traverse is holding five times using five equipments and
instruments: Tape, Level, Digital level, Digital theodolite and
Laser tape. Also those maps were drawn by using both of ACAD
and ArcView softwares. Then a detail surveying map was
produced. The precision was computed for both traverses in each
method. Its value is range from 1/140 to 1/10000.
Radiometric corrections include correcting the data for sensor irregularities and unwanted sensor or atmospheric noise, and converting the data so they accurately represent the reflected or emitted radiation measured by the sensor.
Mapping the anthropic backfill of the historical center of Rome (Italy) by us...Beniamino Murgante
Mapping the anthropic backfill of the historical center of Rome (Italy) by using Intrinsic Random Functions of order k (IRF-k)
Ciotoli Giancarlo, Francesco Stigliano, Fabrizio Marconi, Massimiliano Moscatelli, Marco Mancini, Gian Paolo Cavinato - Institute of Environmental Geology and Geo-engineering (I.G.A.G.), National Research Council, Italy
International Journal of Modern Engineering Research (IJMER) is Peer reviewed, online Journal. It serves as an international archival forum of scholarly research related to engineering and science education.
International Journal of Modern Engineering Research (IJMER) covers all the fields of engineering and science: Electrical Engineering, Mechanical Engineering, Civil Engineering, Chemical Engineering, Computer Engineering, Agricultural Engineering, Aerospace Engineering, Thermodynamics, Structural Engineering, Control Engineering, Robotics, Mechatronics, Fluid Mechanics, Nanotechnology, Simulators, Web-based Learning, Remote Laboratories, Engineering Design Methods, Education Research, Students' Satisfaction and Motivation, Global Projects, and Assessment…. And many more.
Feature Extraction for High Resolution Remote Sensing Image Classification us...Simone Rossi
The thesis explores the application of a advanced feature extraction technique, called "histogram of oriented gradients" (HOG), applied to multispectral VHR images. The algorithm, widely used in the human detection area, but new in this context of remote sensing, has been thoroughly analyzed in each phase, highlighting the correspondance between different parameter sets and different accuracy variations.
Unsupervised Building Extraction from High Resolution Satellite Images Irresp...CSCJournals
Extraction of geospatial data from the photogrammetric sensing images becomes more and more important with the advances in the technology. Today Geographic Information Systems are used in a large variety of applications in engineering, city planning and social sciences. Geospatial data like roads, buildings and rivers are the most critical feeds of a GIS database. However, extracting buildings is one of the most complex and challenging tasks as there exist a lot of inhomogeneity due to varying hierarchy. The variety of the type of buildings and also the shapes of rooftops are very inconstant. Also in some areas, the buildings are placed irregularly or too close to each other. For these reasons, even by using high resolution IKONOS and QuickBird satellite imagery the quality percentage of building extraction is very less. This paper proposes a solution to the problem of automatic and unsupervised extraction of building features irrespective of rooftop structures in multispectral satellite images. The algorithm instead of detecting the region of interest, eliminates areas other than the region of interest which extract the rooftops completely irrespective of their shapes. Extensive tests indicate that the methodology performs well to extract buildings in complex environments.
Extended hybrid region growing segmentation of point clouds with different re...csandit
In the recent years, 3D city reconstruction is one of the active researches in the field of
photogrammetry. The goal of this work is to improve and extend region growing based
segmentation in the X-Y-Z image in the form of 3D structured data with combination of spectral
information of RGB and grayscale image to extract building roofs, streets and vegetation. In
order to process 3D point clouds, hybrid segmentation is carried out in both object space and
image space. Our experiments on two case studies verify that updating plane parameters and
robust least squares plane fitting improves the results of building extraction especially in case
of low accurate point clouds. In addition, region growing in image space has been derived to
the fact that grayscale image is more flexible than RGB image and results in more realistic
building roofs.
EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RE...cscpconf
In the recent years, 3D city reconstruction is one of the active researches in the field of photogrammetry. The goal of this work is to improve and extend region growing based
segmentation in the X-Y-Z image in the form of 3D structured data with combination of spectral information of RGB and grayscale image to extract building roofs, streets and vegetation. In order to process 3D point clouds, hybrid segmentation is carried out in both object space and
image space. Our experiments on two case studies verify that updating plane parameters and robust least squares plane fitting improves the results of building extraction especially in case of low accurate point clouds. In addition, region growing in image space has been derived to the fact that grayscale image is more flexible than RGB image and results in more realistic
building roofs.
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...Pinaki Ranjan Sarkar
Recent advancement in sensor technology allows very high spatial resolution along with multiple spectral bands. There are many studies, which highlight that Object Based Image Analysis(OBIA) is more accurate than pixel-based classification for high resolution(< 2m) imagery. Image segmentation is a crucial step for OBIA and it is a very formidable task to estimate optimal parameters for segmentation as it does not have any unique solution. In this paper, we have studied different segmentation algorithms (both mono-scale and multi-scale) for different terrain categories and showed how the segmented output depends on upon various parameters. Later, we have introduced a novel method to estimate optimal segmentation parameters. The main objectives of this study are to highlight the effectiveness of presently available segmentation techniques on very high-resolution satellite data and to automate segmentation process. Pre-estimation of segmentation parameter is more practical and efficient in OBIA. Assessment of segmentation algorithms and estimation of segmentation parameters are examined based on the very high-resolution multi-spectral WorldView-3(0.3m, PAN sharpened) data.
Digital Elevation Model (DEM) is the digital representation of the land surface elevation with respect to any reference datum. DEM is frequently used to refer to any digital representation of a topographic surface. DEM is the simplest form of digital representation of topography. GIS applications depend mainly on DEMs, today.
An in depth examination of airborne lidar density measurement and reporting. This will review issues with existing methodologies and comparisons to a proposed replacement.
1. University of Genoa
Classification of Remote Sensing Images of Large Urban
Zones using Mathematical Morphology
Eridon Brahimllari
Supervisor: Co-supervisor:
Gabriele Moser Vladimir Krylov
Academic Year 2014-2015
Master Thesis
2. Outline
• Remote Sensing and its Applications
• Land cover classification in urban areas
• Mathematical Morphology
• Differential Morphological Profiles
• Support Vector Machines
• Data sets for the experiments
• Experimental results
• Conclusion
3. Remote Sensing and its Applications
• RS is the science of obtaining information about objects or areas using measurements
acquired from a distance without contact with the investigated objects or areas
• In the case of Earth observation, sensors are usually onboard satellite systems or
aerial platforms.
• RS provides important technologies to support environmental applications such as
1. Urban planning
2. Land-use and land cover mapping
3. Risk assessment and mitigation
• High resolution (HR) optical images play an important role in applications to urban
planning because of the spatial information and geometrical detail they provide.
4. Land cover classification in urban areas
• High resolution image classification provides a collection of methodological tools to
support urban planning.
• Land cover mapping in urban areas is a challenging classification problem due to the
need to define accurate models for the spatial-geometrical information associated
with the imaged urban areas.
• Objective of the thesis: exploring experimentally the approach based on Differential
Morphological Profiles (DMP) to feature extraction, within the application to the
classification of large urban zones.
5. Mathematical Morphology
• An important family of techniques, based on set theory, for the processing of images including
geometrical structures
• Erosion and dilation, with respect to a predefined structuring elements (SE), are the basic
operators leading to several morphological transformations such as
1. Reconstruction by dilation, 𝜌 𝐼
𝐽 = ∨ 𝑛>1 𝛿 𝑛
𝐼
𝐽 𝑠𝑢𝑐ℎ 𝑡ℎ𝑎𝑡 𝛿(𝑛)
𝐼
=𝛿(𝑛+1)
𝐼
2. Reconstruction by erosion, 𝜌∗ 𝐼
𝐽 = ∧ 𝑛>1 𝜀 𝑛
𝐼
𝐽 𝑠𝑢𝑐ℎ 𝑡ℎ𝑎𝑡 𝜀(𝑛)
𝐼
= 𝜀(𝑛+1)
𝐼
• The usefulness of such operators is strictly related to the extraction of spatial and geometrical
information from the input image.
6. Differential Morphological Profile
• DMP is a feature extraction method constructed by using morphological profiles (MPs) and applied
to urban area images in order to model spatial information related to geometrical objects.
△ 𝛾 𝑥 = Δ𝛾 𝜆: Δ𝛾 𝜆 = Π 𝛾 𝜆
− Π 𝛾 𝜆−1
, ∀ 𝜆 𝜖 1, ⋯ , 𝑛
• The MP is composed of results of opening and closing by reconstruction obtained using various
sizes of the SE.
• Opening by reconstruction is obtained from erosion and reconstruction by dilation which have the
property to remove objects smaller than the SE.
• By iteratively varying the size of the SE, it is possible to extract multiscale spatial features that are
useful to the classification of urban areas.
7. Support Vector Machines
• A Support Vector Machine (SVM) is used to classify in the feature space of the spectral
channels of the input image and of the extracted DMPs.
• The main ideas of SVM are to separate feature vectors with a linear decision boundary in a
nonlinearly transformed space, and to maximize the margin between the different classes.
Maximize 𝐿 𝐷= 𝑖 𝛼𝑖 -
1
2 𝑖,𝑗 𝛼𝑖 𝛼𝑗 𝑦𝑖 𝑦𝑗 𝐾(𝑥𝑖, 𝑥𝑗)
subject to 𝑖 𝛼𝑖 𝑦𝑖= 0 , 0 ≤ 𝛼𝑖 ≤ 𝐶 ∀𝑖
𝑓 𝑥 = 𝑖 𝛼𝑖 𝑦𝑖 𝐾(𝑥, 𝑥𝑗) − 𝑏
• SVM is applicable to overlapping and non-linearly separable classes by using kernel functions.
• It has been demonstrated effective in dealing with high dimensional data with little need for
possible feature reduction.
8. Data sets for the experiments
Training map (Osnabruck)
Aerial RGB image acquired over Osnabruck, Germany,
1-m spatial resolution
Buildings
Trees
Low vegetation
Vegetated arable
land
Roads & Pavements
Bare soil
Land cover Types.
Buildings
Trees
Low vegetation
Vegetated arable
land
Roads & Pavements
Bare soil
Water
Land cover Types
Training map (Amiens)
Satellite NIR-R-G image acquired by SPOT5
over Amiens, France, 5-m spatial resolution
9. Experimental Results
Case Study of Amiens
• OA - Overall Accuracy
• AA - Average Accuracy
• PA - Producer Accuracy
Test
Accuracies
With
DMP
Without
DMP
PA -Buildings 68 % 63 %
PA -Bare Soil 73 % 73 %
PA -Roads &
Pavements
52 % 54 %
PA - Low
Vegetation
63 % 61 %
PA - Trees 94 % 94 %
PA - Arable
land
95 % 91 %
PA - Water 78 % 78 %
OA 80 % 79 %
AA 74 % 73 %
Quantitative accuracy analysis
using test samples
Buildings
Trees
Low vegetation
Vegetated arable
land
Roads & Pavements
Bare soil
Water
Land cover Types.
A region from the original image, Amiens.
Classification map using DMP.
Classification map without using DMP.
10. Experimental Results
Case Study of Amiens
Classification map using DMP
Classification map without using DMP
A region from the original image acquired over Amiens.
• Visually quite similar classification maps
• However, improvements in areas including
geometrical structures can be noted.
11. Experimental Results
Case Study of Osnabruck
Classification maps for a given region of the original image. (a) original image,
(b) classification map without using DMP and (c) classification map using DMP.
(a) (b) (c)
Buildings
Trees
Low vegetation
Vegetated arable land
Roads & Pavements
Bare soil
Land cover Types
• Better visual discrimination of the classes
that exhibit geometrical structures.
• In the classification map obtained using
DMP:
1. Buildings are more accurately detected.
2. Roads & Pavements are more correctly
discriminated.
12. Experimental Results
Case Study of Osnabruck
Test
Accuracies
With
DMP
Without
DMP
PA - Buildings 90 % 89 %
PA - Bare Soil 95 % 53 %
PA - Roads &
Pavements
89 % 84 %
PA - Low
Vegetation
75 % 82 %
PA - Trees 77 % 98 %
PA - Arable
land
68 % 76 %
OA 80 % 83 %
AA 82 % 80 %
• OA - Overall Accuracy
• AA - Average Accuracy
• PA - Producer Accuracy
An imaged area describing mainly a field of bare soil.
The related classification map exhibits artefacts.
Quantitative accuracy analysis
using test samples.
13. Conclusion
• Quite high accuracies on challenging high-resolution data sets suggest the possible effectiveness of
DMP as a feature extraction tool for urban applications.
• The qualitative visual analysis of the resulting classification maps shows a better discrimination of
classes with geometrical structures when DMP features are used.
• The DMP approach also suffers from some limitations:
1. DMP is less useful to the discrimination of classes characterized by non-geometrical textures.
2. Computational complexity increases linearly with the number of multiscale levels in the profile.
3. Artefacts could arise due to the moving window approach taken by DMP.
• In order to overcome these limitations, future work might consider the application of the so-called
Attribute Profile (AP) features.
14. References
• M. Pesaresi and J. A. Benediktsson, “A new approach for the morphological segmentation of
high-resolution satellite imagery,” IEEE Trans.Geosci. Remote Sensing, vol. 39, pp. 309–320
Feb. 2001.
• Gabriele Moser, Sebastiano B. Serpico, and Jo´n Atli Benediktsson,“Land-Cover Mapping by
Markov Modeling of Spatial–Contextual Information in Very-High-Resolution Remote Sensing
Images”, Proceedings of the IEEE vol 101,No.3,March 2013.
• P. Soille, Morphological Image Analysis: Principles and Applications.
Berlin, Germany: Springer-Verlag, 1999.
• Vapnik V, “The nature of statistical learning theory”, Springer-Verlag, 1995.
• John A. Richards and Xiuping Jia,“Remote Sensing Digital Image Analysis” ,4th Edition,
Springer,2006.