SlideShare a Scribd company logo
CNN & LSTM based Land use and Land cover
Change Detection in Remote Sensing Images
Presented by
Siba Jasmine S (Reg no)
II Year ME (Communication Systems)
9131 - Velammal College of Engineering & Technology
Guided by
Dr. S. Gandhimathi @ Usha
Associate Professor , ECE
9131-Velammal College of Engineering & Technology
Introduction
• Remote sensing is the process of detecting and monitoring an object or
phenomenon without making physical contact with the object.
• Remote sensing images are used to detect and classify the objects on
the Earth surfaces.
• Change detection is to detect significant changes from sequential
images acquired at different points in time.
• Urban change detection is used for monitoring land use/land cover
changes in urban areas over the specified interval.
Title Year Author Methodology Advantages Disadvantages
Buildings change
detection based on
shape matching
for
multi-resolution
remote sensing
imagery
2017 Abdessetar
and Zhong
Shape matching Algorithm It is very fast both
to build and to
match.
The bits cannot be
processed
independently
in BRIEF.
Literature Survey
Title Year Author Methodology Advantages Disadvantages
A theoretical
framework for
unsupervised
change detection
based on change
vector analysis in
the polar domain
2018 F. Bovolo and
L. Bruzzone,
Change Vector Analysis
(CVA) technique
A proper Polar
framework for the
representation and
the analysis of
multi-temporal
data in the context
of the CVA
technique.
The Spatial
autocorrelation
function of the
images is not
impulsive.
Title Year Author Methodology Advantages Disadvantages
Unsupervised
change detection
in satellite images
using PCA
and k-means
clustering
2019 T. Celik PCA and k-means clustering Unsupervised
change-detection
method is
exploited for both
the noise-free and
the noisy images
Difference image
lies in the lack of
efficient automatic
techniques for
discriminating
between changed
and unchanged
pixels in the
difference image.
Title Year Author Methodology Advantages Disadvantages
Change detection
in Springer
Handbook of
Geographic
Information
2020 J. Théau Image differencing, principal
component analysis, post-
classification comparison,
Change Detection technology.
change detection
algorithms have
their own merits
and no single
approach is
optimal and
applicable to all
cases.
The data selection
is a critical step in
change detection.
Title Year Author Methodology Advantages Disadvantages
Automatic
analysis of the
difference image
for unsupervised
change detection
2021 L. Bruzzone
and D. Prieto
Bayesian decision theory, an
iterative technique (based on
the EM
algorithm)
it allows the
automatic
selection of the
decision-threshold
value that
minimizes the
overall change-
detection error
probability.
the estimation
process cannot be
performed on the
basis of a
training set.
• To use Remote Sensing techniques to study Land Use changes.
• To perform Classification using CNN and LSTM.
• To compare the performance of proposed method with existing method.
Objective
• Shape matching algorithm.
• Change vector analysis technique.
• PCA and k-means clustering.
• EM(Expectation - Maximization) method.
Existing Methodology
Preprocessing
Feature Extraction
Classification
Performance Measure
Segmentation
Binary descriptors and
hamming distance
Input Image
Morphological
• Gabor
• Zernike Moment
• Local Features
CNN
• Accuracy
• Sensitivity
• Precision
• Specificity
Proposed Methodology
• Two QuickBird Satellite images are segmented using:
1. Binary descriptors and Hamming distance method
2. Morphological operation.
• The following features are extracted from the segmented images :
1. Gabor features
2. Zernike Moment features
3. Local Features
• After feature extraction, classification is done by CNN (Convolutional Neural Network)
Algorithm.
Preprocessing
• Preprocessing helps to improve the quality of the image so that the
data can inspect in a better way.
• The images are resized into an exact 256 x 256 pixels.
• These are resized according to the requirements either by Upscaling
or Downscaling method.
• Two QuickBird satellite images are segmented using:
1. Binary Descriptors – Converts images into binary data
2. Hamming distance method – identify the difference between the
binary data
3. Morphological operation – Extracts the different binary data
Segmentation
• Gabor Feature – Extracts Texture, Pattern
• Zernike moment feature – Extracts Shapes
• Local feature – Extracts Intensity
Feature Extraction
• The changes in the QuickBird Satellite images is classified CNN algorithm.
• CNN(Convolutional Neural Networks) is a deep learning algorithm. It is used in
image classification and recognition because of its high accuracy.
• The difference is denoted in yellow as crowded building, Forest to land.
Classification
Input Image 1
Place and year : Russia, 2005
Pixel size : 1130 x 1129
The above figure shows the QuickBird Satellite image of Russia, 2005 with the pixel size of 1130 X
1129 as a first input image.
Input Image 2
Place and year : Russia, 2010
Pixel size : 1130 x 1129
The above figure shows the QuickBird Satellite image of Russia, 2010 with the pixel size of 1130 X
1129 as a second input image.
Resized Images
Resized to 256 X 256 pixels
Segmented Image
The above figure shows segmented image in which the difference between the binary data
(identified by hamming distance method) is extracted (Morphological operation)
and marked in the colour of white and remaining data in the colour of black.
Zernike feature extraction
The above figure shows the Zernike moment features to extract the shapes by
keeping the value of threshold and pixel intensity constant and rotating the images
by horizontal oval, -45-degree oval, vertical oval, horizontal shape and vertical
shape.
The above figure shows the graph of pixel intensity vs threshold in which x-axis is
the pixel intensity and y-axis are the threshold.
Classification
- Change as Crowded building
The above figure shows the classification of the satellite image changes and marked
in the colour of yellow
Identification
The above figure shows the identification of the change such as Crowded
building, Before fire & After fire and Forest to land.
Performance Measures
The following 4 metrics are determined in order to find the performance measures.
The table shows the Accuracy, Sensitivity, Specificity and Precision of different
Datsets.
Parameter Dataset 1 Dataset 2
Accuracy 96 95.95
Sensitivity 95.9596 95.9132
Specificity 99.9592 99.9510
Precision 95.9596 95.9132
The Performance measure values for the given input dataset is shown in
above graph.
Conclusion
• In this method the capability of a simple technique (image difference) to display
change were tested using QuickBird Satellite data for the city of Russia to monitor
urban change in two years 2005 and 2010.
• In the result of classified image the changes in the urban area are marked in the
colour of yellow and is identified as crowded building.
• The results from sub-scenes exposed that image difference technique effectively
emphasizes temporal changes in the study area and provides an excellent and easy to
interpret first position suggestion of change in urban areas
[1] P. P. Singh and R. Garg, “Automatic road extraction from high resolution satellite image using adaptive
global thresholding and morphological operations,” J. Indian Soc. Remote Sens., vol. 41, no. 3, pp. 631–640,
2013.
[2] J. H. Kim et al., “Objects segmentation from high-resolution aerial images using U-Net with pyramid
pooling layers,” IEEE Geosci. Remote Sens. Lett., vol. 16, no. 1, pp. 115–119, Jan. 2019.
[3] Y. Hua, L.Mou, and X. X. Zhu, “Recurrently exploring class-wise attention in a hybrid convolutional and
bidirectional LSTM network for multi-label aerial image classification,” ISPRS J. Photogrammetry Remote
Sens., vol. 149, pp. 188–199, 2019.
References
[4] Y. Na, J. H. Kim, K. Lee, J. Park, J. Y. Hwang, and J. P. Choi, “Domain adaptive transfer attack-based
segmentation networks for building extraction from aerial images,” IEEE Trans. Geosci. Remote Sens., to be
published, doi: 10.1109/TGRS.2020.3010055.
[5] S. Liu, Q. Shi, and L. Zhang, “Few-shot hyperspectral image classification with unknown classes using
multitask deep learning,” IEEE Trans. Geosci. Remote Sens., to be published, doi:
10.1109/TGRS.2020.3018879.
[6] Q. Shi et al., “Domain adaption for fine-grained urban village extraction from satellite images,” IEEE
Geosci. Remote Sens. Lett., vol. 17, no. 8, pp. 1430–1434, Aug. 2020
Annexure
This paper was published at 10th International Conference on
Contemporary Engineering and Technology (ICCET) , May 21st – 22nd
2022 Organized by Organization of Science and Innovative Engineering
and Technology (OSIET), Chennai, India.
ICCET - 2022
Thank You…

More Related Content

Similar to sheeba 1.pptx

Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Pinaki Ranjan Sarkar
 
Application of Image Retrieval Techniques to Understand Evolving Weather
Application of Image Retrieval Techniques to Understand Evolving WeatherApplication of Image Retrieval Techniques to Understand Evolving Weather
Application of Image Retrieval Techniques to Understand Evolving Weather
ijsrd.com
 
V.KARTHIKEYAN PUBLISHED ARTICLE 1
V.KARTHIKEYAN PUBLISHED ARTICLE 1V.KARTHIKEYAN PUBLISHED ARTICLE 1
V.KARTHIKEYAN PUBLISHED ARTICLE 1
KARTHIKEYAN V
 
Automated features extraction from satellite images.
Automated features extraction from satellite images.Automated features extraction from satellite images.
Automated features extraction from satellite images.
HimanshuGupta1081
 
Cnn acuracia remotesensing-08-00329
Cnn acuracia remotesensing-08-00329Cnn acuracia remotesensing-08-00329
Cnn acuracia remotesensing-08-00329
Universidade Fumec
 
Orientation Spectral Resolution Coding for Pattern Recognition
Orientation Spectral Resolution Coding for Pattern RecognitionOrientation Spectral Resolution Coding for Pattern Recognition
Orientation Spectral Resolution Coding for Pattern Recognition
IOSRjournaljce
 
Feature extraction based retrieval of
Feature extraction based retrieval ofFeature extraction based retrieval of
Feature extraction based retrieval of
ijcsity
 
Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...
CSCJournals
 
Comparison of various Image Registration Techniques with the Proposed Hybrid ...
Comparison of various Image Registration Techniques with the Proposed Hybrid ...Comparison of various Image Registration Techniques with the Proposed Hybrid ...
Comparison of various Image Registration Techniques with the Proposed Hybrid ...
idescitation
 
Effect of sub classes on the accuracy of the classified image
Effect of sub classes on the accuracy of the classified imageEffect of sub classes on the accuracy of the classified image
Effect of sub classes on the accuracy of the classified imageiaemedu
 
An Unsupervised Change Detection in Satellite IMAGES Using MRFFCM Clustering
An Unsupervised Change Detection in Satellite IMAGES Using MRFFCM ClusteringAn Unsupervised Change Detection in Satellite IMAGES Using MRFFCM Clustering
An Unsupervised Change Detection in Satellite IMAGES Using MRFFCM Clustering
Editor IJCATR
 
Wujanz_Error_Projection_2011
Wujanz_Error_Projection_2011Wujanz_Error_Projection_2011
Wujanz_Error_Projection_2011Jacob Collstrup
 
Building Extraction from Satellite Images
Building Extraction from Satellite ImagesBuilding Extraction from Satellite Images
Building Extraction from Satellite Images
IOSR Journals
 
A Review on Deformation Measurement from Speckle Patterns using Digital Image...
A Review on Deformation Measurement from Speckle Patterns using Digital Image...A Review on Deformation Measurement from Speckle Patterns using Digital Image...
A Review on Deformation Measurement from Speckle Patterns using Digital Image...
IRJET Journal
 
Object extraction using edge, motion and saliency information from videos
Object extraction using edge, motion and saliency information from videosObject extraction using edge, motion and saliency information from videos
Object extraction using edge, motion and saliency information from videos
eSAT Journals
 
Importance of Mean Shift in Remote Sensing Segmentation
Importance of Mean Shift in Remote Sensing SegmentationImportance of Mean Shift in Remote Sensing Segmentation
Importance of Mean Shift in Remote Sensing Segmentation
IOSR Journals
 

Similar to sheeba 1.pptx (20)

Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation ...
 
Application of Image Retrieval Techniques to Understand Evolving Weather
Application of Image Retrieval Techniques to Understand Evolving WeatherApplication of Image Retrieval Techniques to Understand Evolving Weather
Application of Image Retrieval Techniques to Understand Evolving Weather
 
V.KARTHIKEYAN PUBLISHED ARTICLE 1
V.KARTHIKEYAN PUBLISHED ARTICLE 1V.KARTHIKEYAN PUBLISHED ARTICLE 1
V.KARTHIKEYAN PUBLISHED ARTICLE 1
 
Automated features extraction from satellite images.
Automated features extraction from satellite images.Automated features extraction from satellite images.
Automated features extraction from satellite images.
 
Cnn acuracia remotesensing-08-00329
Cnn acuracia remotesensing-08-00329Cnn acuracia remotesensing-08-00329
Cnn acuracia remotesensing-08-00329
 
Orientation Spectral Resolution Coding for Pattern Recognition
Orientation Spectral Resolution Coding for Pattern RecognitionOrientation Spectral Resolution Coding for Pattern Recognition
Orientation Spectral Resolution Coding for Pattern Recognition
 
Feature extraction based retrieval of
Feature extraction based retrieval ofFeature extraction based retrieval of
Feature extraction based retrieval of
 
Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...
 
J25043046
J25043046J25043046
J25043046
 
J25043046
J25043046J25043046
J25043046
 
Comparison of various Image Registration Techniques with the Proposed Hybrid ...
Comparison of various Image Registration Techniques with the Proposed Hybrid ...Comparison of various Image Registration Techniques with the Proposed Hybrid ...
Comparison of various Image Registration Techniques with the Proposed Hybrid ...
 
Effect of sub classes on the accuracy of the classified image
Effect of sub classes on the accuracy of the classified imageEffect of sub classes on the accuracy of the classified image
Effect of sub classes on the accuracy of the classified image
 
An Unsupervised Change Detection in Satellite IMAGES Using MRFFCM Clustering
An Unsupervised Change Detection in Satellite IMAGES Using MRFFCM ClusteringAn Unsupervised Change Detection in Satellite IMAGES Using MRFFCM Clustering
An Unsupervised Change Detection in Satellite IMAGES Using MRFFCM Clustering
 
Wujanz_Error_Projection_2011
Wujanz_Error_Projection_2011Wujanz_Error_Projection_2011
Wujanz_Error_Projection_2011
 
ei2106-submit-opt-415
ei2106-submit-opt-415ei2106-submit-opt-415
ei2106-submit-opt-415
 
Building Extraction from Satellite Images
Building Extraction from Satellite ImagesBuilding Extraction from Satellite Images
Building Extraction from Satellite Images
 
A Review on Deformation Measurement from Speckle Patterns using Digital Image...
A Review on Deformation Measurement from Speckle Patterns using Digital Image...A Review on Deformation Measurement from Speckle Patterns using Digital Image...
A Review on Deformation Measurement from Speckle Patterns using Digital Image...
 
Object extraction using edge, motion and saliency information from videos
Object extraction using edge, motion and saliency information from videosObject extraction using edge, motion and saliency information from videos
Object extraction using edge, motion and saliency information from videos
 
Importance of Mean Shift in Remote Sensing Segmentation
Importance of Mean Shift in Remote Sensing SegmentationImportance of Mean Shift in Remote Sensing Segmentation
Importance of Mean Shift in Remote Sensing Segmentation
 
sibgrapi2015
sibgrapi2015sibgrapi2015
sibgrapi2015
 

Recently uploaded

一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
zwunae
 
Self-Control of Emotions by Slidesgo.pptx
Self-Control of Emotions by Slidesgo.pptxSelf-Control of Emotions by Slidesgo.pptx
Self-Control of Emotions by Slidesgo.pptx
iemerc2024
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
Rahul
 
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
obonagu
 
Unbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptxUnbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptx
ChristineTorrepenida1
 
Fundamentals of Electric Drives and its applications.pptx
Fundamentals of Electric Drives and its applications.pptxFundamentals of Electric Drives and its applications.pptx
Fundamentals of Electric Drives and its applications.pptx
manasideore6
 
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
dxobcob
 
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTSHeap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Soumen Santra
 
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
ydteq
 
Literature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptxLiterature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptx
Dr Ramhari Poudyal
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
gestioneergodomus
 
Hierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power SystemHierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power System
Kerry Sado
 
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.pptPROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
bhadouriyakaku
 
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdfBPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
MIGUELANGEL966976
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Christina Lin
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
Aditya Rajan Patra
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
insn4465
 
Water billing management system project report.pdf
Water billing management system project report.pdfWater billing management system project report.pdf
Water billing management system project report.pdf
Kamal Acharya
 
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdfTutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
aqil azizi
 
sieving analysis and results interpretation
sieving analysis and results interpretationsieving analysis and results interpretation
sieving analysis and results interpretation
ssuser36d3051
 

Recently uploaded (20)

一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
 
Self-Control of Emotions by Slidesgo.pptx
Self-Control of Emotions by Slidesgo.pptxSelf-Control of Emotions by Slidesgo.pptx
Self-Control of Emotions by Slidesgo.pptx
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
 
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
 
Unbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptxUnbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptx
 
Fundamentals of Electric Drives and its applications.pptx
Fundamentals of Electric Drives and its applications.pptxFundamentals of Electric Drives and its applications.pptx
Fundamentals of Electric Drives and its applications.pptx
 
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
 
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTSHeap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
 
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
 
Literature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptxLiterature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptx
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
 
Hierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power SystemHierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power System
 
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.pptPROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
 
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdfBPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
 
Water billing management system project report.pdf
Water billing management system project report.pdfWater billing management system project report.pdf
Water billing management system project report.pdf
 
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdfTutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
 
sieving analysis and results interpretation
sieving analysis and results interpretationsieving analysis and results interpretation
sieving analysis and results interpretation
 

sheeba 1.pptx

  • 1. CNN & LSTM based Land use and Land cover Change Detection in Remote Sensing Images Presented by Siba Jasmine S (Reg no) II Year ME (Communication Systems) 9131 - Velammal College of Engineering & Technology Guided by Dr. S. Gandhimathi @ Usha Associate Professor , ECE 9131-Velammal College of Engineering & Technology
  • 2. Introduction • Remote sensing is the process of detecting and monitoring an object or phenomenon without making physical contact with the object. • Remote sensing images are used to detect and classify the objects on the Earth surfaces. • Change detection is to detect significant changes from sequential images acquired at different points in time. • Urban change detection is used for monitoring land use/land cover changes in urban areas over the specified interval.
  • 3. Title Year Author Methodology Advantages Disadvantages Buildings change detection based on shape matching for multi-resolution remote sensing imagery 2017 Abdessetar and Zhong Shape matching Algorithm It is very fast both to build and to match. The bits cannot be processed independently in BRIEF. Literature Survey
  • 4. Title Year Author Methodology Advantages Disadvantages A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain 2018 F. Bovolo and L. Bruzzone, Change Vector Analysis (CVA) technique A proper Polar framework for the representation and the analysis of multi-temporal data in the context of the CVA technique. The Spatial autocorrelation function of the images is not impulsive.
  • 5. Title Year Author Methodology Advantages Disadvantages Unsupervised change detection in satellite images using PCA and k-means clustering 2019 T. Celik PCA and k-means clustering Unsupervised change-detection method is exploited for both the noise-free and the noisy images Difference image lies in the lack of efficient automatic techniques for discriminating between changed and unchanged pixels in the difference image.
  • 6. Title Year Author Methodology Advantages Disadvantages Change detection in Springer Handbook of Geographic Information 2020 J. Théau Image differencing, principal component analysis, post- classification comparison, Change Detection technology. change detection algorithms have their own merits and no single approach is optimal and applicable to all cases. The data selection is a critical step in change detection.
  • 7. Title Year Author Methodology Advantages Disadvantages Automatic analysis of the difference image for unsupervised change detection 2021 L. Bruzzone and D. Prieto Bayesian decision theory, an iterative technique (based on the EM algorithm) it allows the automatic selection of the decision-threshold value that minimizes the overall change- detection error probability. the estimation process cannot be performed on the basis of a training set.
  • 8. • To use Remote Sensing techniques to study Land Use changes. • To perform Classification using CNN and LSTM. • To compare the performance of proposed method with existing method. Objective
  • 9. • Shape matching algorithm. • Change vector analysis technique. • PCA and k-means clustering. • EM(Expectation - Maximization) method. Existing Methodology
  • 10. Preprocessing Feature Extraction Classification Performance Measure Segmentation Binary descriptors and hamming distance Input Image Morphological • Gabor • Zernike Moment • Local Features CNN • Accuracy • Sensitivity • Precision • Specificity Proposed Methodology
  • 11. • Two QuickBird Satellite images are segmented using: 1. Binary descriptors and Hamming distance method 2. Morphological operation. • The following features are extracted from the segmented images : 1. Gabor features 2. Zernike Moment features 3. Local Features • After feature extraction, classification is done by CNN (Convolutional Neural Network) Algorithm.
  • 12. Preprocessing • Preprocessing helps to improve the quality of the image so that the data can inspect in a better way. • The images are resized into an exact 256 x 256 pixels. • These are resized according to the requirements either by Upscaling or Downscaling method.
  • 13. • Two QuickBird satellite images are segmented using: 1. Binary Descriptors – Converts images into binary data 2. Hamming distance method – identify the difference between the binary data 3. Morphological operation – Extracts the different binary data Segmentation
  • 14. • Gabor Feature – Extracts Texture, Pattern • Zernike moment feature – Extracts Shapes • Local feature – Extracts Intensity Feature Extraction
  • 15. • The changes in the QuickBird Satellite images is classified CNN algorithm. • CNN(Convolutional Neural Networks) is a deep learning algorithm. It is used in image classification and recognition because of its high accuracy. • The difference is denoted in yellow as crowded building, Forest to land. Classification
  • 16. Input Image 1 Place and year : Russia, 2005 Pixel size : 1130 x 1129 The above figure shows the QuickBird Satellite image of Russia, 2005 with the pixel size of 1130 X 1129 as a first input image.
  • 17. Input Image 2 Place and year : Russia, 2010 Pixel size : 1130 x 1129 The above figure shows the QuickBird Satellite image of Russia, 2010 with the pixel size of 1130 X 1129 as a second input image.
  • 18. Resized Images Resized to 256 X 256 pixels
  • 19. Segmented Image The above figure shows segmented image in which the difference between the binary data (identified by hamming distance method) is extracted (Morphological operation) and marked in the colour of white and remaining data in the colour of black.
  • 21. The above figure shows the Zernike moment features to extract the shapes by keeping the value of threshold and pixel intensity constant and rotating the images by horizontal oval, -45-degree oval, vertical oval, horizontal shape and vertical shape. The above figure shows the graph of pixel intensity vs threshold in which x-axis is the pixel intensity and y-axis are the threshold.
  • 22. Classification - Change as Crowded building The above figure shows the classification of the satellite image changes and marked in the colour of yellow
  • 23. Identification The above figure shows the identification of the change such as Crowded building, Before fire & After fire and Forest to land.
  • 24. Performance Measures The following 4 metrics are determined in order to find the performance measures. The table shows the Accuracy, Sensitivity, Specificity and Precision of different Datsets. Parameter Dataset 1 Dataset 2 Accuracy 96 95.95 Sensitivity 95.9596 95.9132 Specificity 99.9592 99.9510 Precision 95.9596 95.9132
  • 25. The Performance measure values for the given input dataset is shown in above graph.
  • 26. Conclusion • In this method the capability of a simple technique (image difference) to display change were tested using QuickBird Satellite data for the city of Russia to monitor urban change in two years 2005 and 2010. • In the result of classified image the changes in the urban area are marked in the colour of yellow and is identified as crowded building. • The results from sub-scenes exposed that image difference technique effectively emphasizes temporal changes in the study area and provides an excellent and easy to interpret first position suggestion of change in urban areas
  • 27. [1] P. P. Singh and R. Garg, “Automatic road extraction from high resolution satellite image using adaptive global thresholding and morphological operations,” J. Indian Soc. Remote Sens., vol. 41, no. 3, pp. 631–640, 2013. [2] J. H. Kim et al., “Objects segmentation from high-resolution aerial images using U-Net with pyramid pooling layers,” IEEE Geosci. Remote Sens. Lett., vol. 16, no. 1, pp. 115–119, Jan. 2019. [3] Y. Hua, L.Mou, and X. X. Zhu, “Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification,” ISPRS J. Photogrammetry Remote Sens., vol. 149, pp. 188–199, 2019. References
  • 28. [4] Y. Na, J. H. Kim, K. Lee, J. Park, J. Y. Hwang, and J. P. Choi, “Domain adaptive transfer attack-based segmentation networks for building extraction from aerial images,” IEEE Trans. Geosci. Remote Sens., to be published, doi: 10.1109/TGRS.2020.3010055. [5] S. Liu, Q. Shi, and L. Zhang, “Few-shot hyperspectral image classification with unknown classes using multitask deep learning,” IEEE Trans. Geosci. Remote Sens., to be published, doi: 10.1109/TGRS.2020.3018879. [6] Q. Shi et al., “Domain adaption for fine-grained urban village extraction from satellite images,” IEEE Geosci. Remote Sens. Lett., vol. 17, no. 8, pp. 1430–1434, Aug. 2020
  • 29. Annexure This paper was published at 10th International Conference on Contemporary Engineering and Technology (ICCET) , May 21st – 22nd 2022 Organized by Organization of Science and Innovative Engineering and Technology (OSIET), Chennai, India.
  • 30.
  • 32.
  • 33.