SlideShare una empresa de Scribd logo
1 de 57
Comparison of Segmentation Algorithms and
Estimation of Optimal Segmentation
Parameters for Very High Resolution
Satellite Imagery
P. R. Sarkar1 P. Srinivas2 J .Srinivasulu3 D. Sita4
1Department of Avionics
Indian Institute of Space Science and Technology
2Head,GRD
3Scientist- ‘F’
4Scientist - ’E’
Advanced Data Processing Research Institute
Outline
New paradigm in remote sensing, GEOBIA
Image Segmentation, the first and critical step
Segmentation algorithms
Objective of this Study
Preparatory work
Study area & Quality assessment technique
Methodologies
Selection of optimal segmentation parameters
Estimation of segmentation parameters
Existing methods
Proposed approach
Results
Evaluation of segmentation algorithms
Evaluation of Automatic Estimation of Segmentation Parameter Technique
Conclusions
Why GEOBIA?
Geographic Object Based Image Analysis
1. The latest breed of very high resolution (VHR) commercial satellite imagery
(<2.0m) imagery, which has dramatically increased new possibilities in
remote sensing and cartographic applications.
2. Pixel based analysis neglects the spatial information of very high resolution
images.
3. Several study demonstrated that geographic object based classifier is a
significantly better approach than the classical pixel classifier.
4. A dramatic increase in availability of affordable powerful
computing systems.
5. Need of the multi-scale approaches in the monitoring, modelling and
management of the environment. GEOBIA is the best choice for this.
Image Segmentation
Segmentation is a process of completely partitioning an image into
non-overlapping regions based on homogeneity parameters or on
differentiation of heterogeneity parameters.
Mathematically, it can be defined as follows: if F is the set of all pixels
and P( ) is a homogeneity defined on group of connected pixels, then
segmentation is a partitioning of the set F into a set of connected
regions (S1, S2, ..., Sn) such that:
Why Segmentation?
1. In GEOBIA, we treat a remotely sensed image as union of meaningful
image objects. To extract each image objects, we need to use
segmentation techniques.
2. As discussed in slide: 3, considering an image as objects gives better
classification accuracy and also opportunity to use spatial information.
Segmentation Algorithms
1. Mean-shift Segmentation
2. Multi-resolution Segmentation
3. k-means Segmentation
4. Watershed Segmentation
Mean-shift segmentation
Mean-shift algorithm was introduced by Fukunaga and Hostetler in
1975. It is a versatile, non-parametric density gradient estimation for
mode finding or clustering procedure.
Idea: For each data point, mean shift defines a window around it and
computes the mean of the data point. Then it shifts the center of the
window to the mean and repeats the algorithm till it converges. After
each iteration, we can consider that the window shifts to a more
denser region of the dataset.
Mean-shift segmentation
At the high level, we can specify Mean Shift as follows:
1. Fix a window around each data point.
2. Compute the mean of data within the window.
3. Shift the window to the mean and repeat till convergence
Mean-shift segmentation
Mean-shift segmentation
Multi-resolution segmentation
1. It is a bottom-up region merging technique, which starts from one-pixel
object.
2. Throughout this clustering process, the underlying optimisation
procedure minimizes the weighted heterogeneity nh in the image objects
where,
n is the number of the pixels of image segment
h is the definition of heterogeneity measure.
3. The increment of heterogeneity (f) is calculated before the
merging of two adjacent object happens.
4. No further fusion takes place when the increment in
heterogeneity exceeds a threshold or scale.
Multi-resolution segmentation
k-means segmentation
This algorithm has been the most popular unsupervised learning
algorithm which is widely used for image segmentation.
The k-means clustering algorithm is as follows:
1. Initialize the cluster centroids µ1, µ2, ..., µk randomly.
2. Repeat till convergence
Watershed segmentation
1. The watershed transform is a region based segmentation approach.
2. Imagine the landscape is being immersed in a lake, with holes
pierced in topical minima. The process of filling water is stopped
when water reaches the highest peak in the landscape. This process
finally gives a portioned region or basins separated by dams also
called watershed lines.
3. Flow diagram of this algorithm is given in the next slide.
Watershed segmentation
Objective of this Study
Objective of this study
1. Study of various segmentation algorithms and deciding which
algorithm works better than the existing techniques for different
h-resolution terrain surfaces.
2. Comparing the quality of the segmentation algorithms for very high
spatial multi-spectral remotely sensed satellite imagery.
3. Automatic estimation of optimal parameter for segmentation
algorithms
Study Area & Quality Assessment Technique
Study area
The study area analysed for this research downloaded from Digitalglobe website.
Figure: Main
study area with
16384 × 16384
resolution
Regions of study
Rural area
Urban area Forest area
Residential area
Quality assessment technique
1. Visual assessment is taken into account for quality checking of
segmentation techniques.
2. In this paper, we decided upon visual assessment on the human eye
is considered as strong and experienced source for evaluation of
segmentation techniques
Selection of the Optimal Segmentation Parameters
Segmentation algorithms and parameters in ORFEO
Mean-shift environment Watershed environment
Segmentation algorithm and parameters in eCogniton
Parameters in eCognition
Segmentation algorithms and parameters in Matlab
1. Mean-shift algorithm has only one bandwidth parameter.
2. k-means has only class parameter.
3. Watershed algorithm does not have any parameter.
Parameter selection for mean-shift segmentation
We used spatial profile to select optimal parameters
Spatial profile in horizontal axis
Spatial profile in vertical axis
1. From these spatial profiles we can notice peaks in all bands which
indicates transition between two different classes. The range
between the pixel positions at left side maximum value and right
side maximum value, is taken as range radius.
2. Spatial radius is taken by a trial-and-error method.
3. The other three parameters are taken as constants for all
the images under consideration.
4. The optimal parameters are chosen based on visual assessments.
The windowing method is described in the next slide.
Parameter selection at different window size
Optimal output of mean-shift
Parameter selection at 761 X 577 Parameter selection at 780 x 577
Optimal output of multi-resolution
WinSize =
128 X 128
WinSize =
352 X 352
WinSize =
468 X 468
WinSize =
212 X 212
Parameter selection for k-means and watershed segmentation
k-means:
1. The only parameter here is class. Selection of proper class is not difficult
when the test image is small, but it produce slots of ambiguity when it
comes for big remote images.
2. One approach to learn the class is to use Elbows method.
Watershed segmentation:
The two parameters for watershed segmentation are chosen based on
visual inspection.
Estimation of the Optimal Segmentation Parameters
Existing methods
Post-estimation of segmentation parameters:
1. Kim et. al has used the concept of local variance to determine optimal
segmentation parameters of alliance-level forest classification.
2. Dragut et. al used local variance in image object level and extended it into multi-
scale analysis based on single layer and later in multiple layers.
3. Zhao et. al has used the rate of change of local variance which is similar to the ESP
tool, to estimate the optimal parameter.
4. Emary et. al used a similarity measure between two image objects in set of
successive scales.
5. Karl and Maurer et. Al have used semi-variogram based spatial dependency
prediction.
Pre-estimation of segmentation parameters:
Ming et. al applies spatial statistics to select optimal parameters for mean-
shift segmentation algorithm.
Proposed Approach
Input features extraction
Calculation of spatial statistics before feeding in BPNN
Training of the BPNN
Training BPNN for estimating parameters
Results
Evaluation of Segmentation Algorithms
Rural area Multi-resolution in eCognition Mean-shift in ORFEO
Mean-shift in Matlab K-means in Matlab Watershed in Matlab
Multi-resolution
parameters
Mean-shift
parameters
Residential area Multi-resolution in eCognition Mean-shift in ORFEO
Mean-shift in Matlab K-means in Matlab Watershed in Matlab
Multi-resolution
parameters
Mean-shift
parameters
Urban area Multi-resolution in eCognition Mean-shift in ORFEO
Mean-shift in Matlab K-means in Matlab Watershed in Matlab
Multi-resolution
parameters
Mean-shift
parameters
Forest area Multi-resolution in eCognition Mean-shift in ORFEO
Mean-shift in Matlab K-means in Matlab Watershed in Matlab
Multi-resolution
parameters
Mean-shift
parameters
Evaluation of Automatic Estimation of Segmentation
Parameter Technique
Mean Square Error plot for the Trained Network
Average local variance v/s band for four regions of study
Test Images
Rural area Residential area
Urban area Forest area
Estimation of Segmentation Parameters of Multi-resolution
Rural area Residential area
Urban area Forest area
Estimation of Segmentation Parameters of Multi-resolution
Rural area Residential area
Urban area Forest area
Conclusions
Assessment of Segmentation Algorithm
• we see that the watershed algorithm is poor.
• k-means gives a good segmentation solution though it is affected by
salt and paper noise due to within-field variability.
• Multi-resolution segmentation is now becoming very famous due to
its robust nature and fast processing using multi-threading. From the
outcomes, we see that it gives very good segmentation in object level.
• Mean-shift segmentation is also a multi-scale segmentation like multi-
resolution, but it take a huge amount of time to process in both
ORFEO and Matlab.
Comparison between multi-resolution and mean-shift
segmentation
Automatic Estimation of the Optimal Segmentation Parameters
Advantages
• The proposed method is a pre-estimation method while other studies are
related to post-estimation. Only one approach is there which does pre-
estimation, but it only limits its scale selection to certain segmentation
algorithm.
• This proposed approach is not limited to any particular segmentation
algorithm. It can estimate any number of parameters for any segmentation
algorithm.
• Different remote sensing analysis vendors provide different implementation
of segmentation algorithms. This approach tries to map between any VHR
landcover and optimal segmentation parameter.
• Geo-statistics of every band is being considered which makes it more robust
to any multi-spectral data.
Limitations
• Training the BPNN network is a difficult task. Discussion about BPNN
network is beyond of the scope of this project.
• Calculation of local variance in multiple scale takes a long time. Due
to the advancement of high performance computing this limitation
can be overcome.
• The most important disadvantage is to make a training set for
learning the network. Initial human effort is needed but once the
network is learnt, the automation process is done
Thank you!
Any questions?

Más contenido relacionado

La actualidad más candente

COLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATION
COLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATIONCOLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATION
COLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATION
IAEME Publication
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation ppt
Gichelle Amon
 
IMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSINGIMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSING
garima0690
 

La actualidad más candente (20)

Image segmentation using wvlt trnsfrmtn and fuzzy logic. ppt
Image segmentation using wvlt trnsfrmtn and fuzzy logic. pptImage segmentation using wvlt trnsfrmtn and fuzzy logic. ppt
Image segmentation using wvlt trnsfrmtn and fuzzy logic. ppt
 
IMAGE SEGMENTATION TECHNIQUES
IMAGE SEGMENTATION TECHNIQUESIMAGE SEGMENTATION TECHNIQUES
IMAGE SEGMENTATION TECHNIQUES
 
Comparison of image segmentation
Comparison of image segmentationComparison of image segmentation
Comparison of image segmentation
 
Presentation on deformable model for medical image segmentation
Presentation on deformable model for medical image segmentationPresentation on deformable model for medical image segmentation
Presentation on deformable model for medical image segmentation
 
Image segmentation ajal
Image segmentation ajalImage segmentation ajal
Image segmentation ajal
 
GRAY SCALE IMAGE SEGMENTATION USING OTSU THRESHOLDING OPTIMAL APPROACH
GRAY SCALE IMAGE SEGMENTATION USING OTSU THRESHOLDING OPTIMAL APPROACHGRAY SCALE IMAGE SEGMENTATION USING OTSU THRESHOLDING OPTIMAL APPROACH
GRAY SCALE IMAGE SEGMENTATION USING OTSU THRESHOLDING OPTIMAL APPROACH
 
A comparison of image segmentation techniques, otsu and watershed for x ray i...
A comparison of image segmentation techniques, otsu and watershed for x ray i...A comparison of image segmentation techniques, otsu and watershed for x ray i...
A comparison of image segmentation techniques, otsu and watershed for x ray i...
 
Digital Image Processing: Image Segmentation
Digital Image Processing: Image SegmentationDigital Image Processing: Image Segmentation
Digital Image Processing: Image Segmentation
 
Review of Image Segmentation Techniques based on Region Merging Approach
Review of Image Segmentation Techniques based on Region Merging ApproachReview of Image Segmentation Techniques based on Region Merging Approach
Review of Image Segmentation Techniques based on Region Merging Approach
 
Digital image classification
Digital image classificationDigital image classification
Digital image classification
 
COLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATION
COLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATIONCOLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATION
COLOUR BASED IMAGE SEGMENTATION USING HYBRID KMEANS WITH WATERSHED SEGMENTATION
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation ppt
 
Image parts and segmentation
Image parts and segmentation Image parts and segmentation
Image parts and segmentation
 
Marker Controlled Segmentation Technique for Medical application
Marker Controlled Segmentation Technique for Medical applicationMarker Controlled Segmentation Technique for Medical application
Marker Controlled Segmentation Technique for Medical application
 
A version of watershed algorithm for color image segmentation
A version of watershed algorithm for color image segmentationA version of watershed algorithm for color image segmentation
A version of watershed algorithm for color image segmentation
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
IMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSINGIMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSING
 
A New Approach of Medical Image Fusion using Discrete Wavelet Transform
A New Approach of Medical Image Fusion using Discrete Wavelet TransformA New Approach of Medical Image Fusion using Discrete Wavelet Transform
A New Approach of Medical Image Fusion using Discrete Wavelet Transform
 
Image Segmentation (Digital Image Processing)
Image Segmentation (Digital Image Processing)Image Segmentation (Digital Image Processing)
Image Segmentation (Digital Image Processing)
 
Band ratioing presentation
Band ratioing presentationBand ratioing presentation
Band ratioing presentation
 

Similar a Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation Parameters for Very High Resolution Remotely Sensed Satellite Imagery

Similar a Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation Parameters for Very High Resolution Remotely Sensed Satellite Imagery (20)

Satellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor
Satellite Image Classification using Decision Tree, SVM and k-Nearest NeighborSatellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor
Satellite Image Classification using Decision Tree, SVM and k-Nearest Neighbor
 
Super-Resolution of Multispectral Images
Super-Resolution of Multispectral ImagesSuper-Resolution of Multispectral Images
Super-Resolution of Multispectral Images
 
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
 
SAR ICE IMAGE CLASSIFICATION USING PARALLELEPIPED CLASSIFIER BASED ON GRAM-SC...
SAR ICE IMAGE CLASSIFICATION USING PARALLELEPIPED CLASSIFIER BASED ON GRAM-SC...SAR ICE IMAGE CLASSIFICATION USING PARALLELEPIPED CLASSIFIER BASED ON GRAM-SC...
SAR ICE IMAGE CLASSIFICATION USING PARALLELEPIPED CLASSIFIER BASED ON GRAM-SC...
 
Sar ice image classification using parallelepiped classifier based on gram sc...
Sar ice image classification using parallelepiped classifier based on gram sc...Sar ice image classification using parallelepiped classifier based on gram sc...
Sar ice image classification using parallelepiped classifier based on gram sc...
 
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
 
E017443136
E017443136E017443136
E017443136
 
sheeba 1.pptx
sheeba 1.pptxsheeba 1.pptx
sheeba 1.pptx
 
IRJET-A Review on Implementation of High Dimension Colour Transform in Domain...
IRJET-A Review on Implementation of High Dimension Colour Transform in Domain...IRJET-A Review on Implementation of High Dimension Colour Transform in Domain...
IRJET-A Review on Implementation of High Dimension Colour Transform in Domain...
 
Spectral Density Oriented Feature Coding For Pattern Recognition Application
Spectral Density Oriented Feature Coding For Pattern Recognition ApplicationSpectral Density Oriented Feature Coding For Pattern Recognition Application
Spectral Density Oriented Feature Coding For Pattern Recognition Application
 
Modified adaptive bilateral filter for image contrast enhancement
Modified adaptive bilateral filter for image contrast enhancementModified adaptive bilateral filter for image contrast enhancement
Modified adaptive bilateral filter for image contrast enhancement
 
Review paper on segmentation methods for multiobject feature extraction
Review paper on segmentation methods for multiobject feature extractionReview paper on segmentation methods for multiobject feature extraction
Review paper on segmentation methods for multiobject feature extraction
 
Digital image processing
Digital image processingDigital image processing
Digital image processing
 
Matching algorithm performance analysis for autocalibration method of stereo ...
Matching algorithm performance analysis for autocalibration method of stereo ...Matching algorithm performance analysis for autocalibration method of stereo ...
Matching algorithm performance analysis for autocalibration method of stereo ...
 
An ensemble classification algorithm for hyperspectral images
An ensemble classification algorithm for hyperspectral imagesAn ensemble classification algorithm for hyperspectral images
An ensemble classification algorithm for hyperspectral images
 
Detection of urban tree canopy from very high resolution imagery using an ob...
Detection of urban tree canopy from very high resolution  imagery using an ob...Detection of urban tree canopy from very high resolution  imagery using an ob...
Detection of urban tree canopy from very high resolution imagery using an ob...
 
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...
Object Classification of Satellite Images Using Cluster Repulsion Based Kerne...
 
An Improved Way of Segmentation and Classification of Remote Sensing Images U...
An Improved Way of Segmentation and Classification of Remote Sensing Images U...An Improved Way of Segmentation and Classification of Remote Sensing Images U...
An Improved Way of Segmentation and Classification of Remote Sensing Images U...
 
IRJET- Exploring Image Super Resolution Techniques
IRJET- Exploring Image Super Resolution TechniquesIRJET- Exploring Image Super Resolution Techniques
IRJET- Exploring Image Super Resolution Techniques
 
Image fusion using nsct denoising and target extraction for visual surveillance
Image fusion using nsct denoising and target extraction for visual surveillanceImage fusion using nsct denoising and target extraction for visual surveillance
Image fusion using nsct denoising and target extraction for visual surveillance
 

Último

Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Kandungan 087776558899
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
dollysharma2066
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
notes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.pptnotes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.ppt
MsecMca
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 

Último (20)

Thermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VThermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - V
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPT
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
22-prompt engineering noted slide shown.pdf
22-prompt engineering noted slide shown.pdf22-prompt engineering noted slide shown.pdf
22-prompt engineering noted slide shown.pdf
 
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
 
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
 
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
 
notes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.pptnotes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.ppt
 
Hostel management system project report..pdf
Hostel management system project report..pdfHostel management system project report..pdf
Hostel management system project report..pdf
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.ppt
 

Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation Parameters for Very High Resolution Remotely Sensed Satellite Imagery

  • 1. Comparison of Segmentation Algorithms and Estimation of Optimal Segmentation Parameters for Very High Resolution Satellite Imagery P. R. Sarkar1 P. Srinivas2 J .Srinivasulu3 D. Sita4 1Department of Avionics Indian Institute of Space Science and Technology 2Head,GRD 3Scientist- ‘F’ 4Scientist - ’E’ Advanced Data Processing Research Institute
  • 2. Outline New paradigm in remote sensing, GEOBIA Image Segmentation, the first and critical step Segmentation algorithms Objective of this Study Preparatory work Study area & Quality assessment technique Methodologies Selection of optimal segmentation parameters Estimation of segmentation parameters Existing methods Proposed approach Results Evaluation of segmentation algorithms Evaluation of Automatic Estimation of Segmentation Parameter Technique Conclusions
  • 3. Why GEOBIA? Geographic Object Based Image Analysis 1. The latest breed of very high resolution (VHR) commercial satellite imagery (<2.0m) imagery, which has dramatically increased new possibilities in remote sensing and cartographic applications. 2. Pixel based analysis neglects the spatial information of very high resolution images. 3. Several study demonstrated that geographic object based classifier is a significantly better approach than the classical pixel classifier. 4. A dramatic increase in availability of affordable powerful computing systems. 5. Need of the multi-scale approaches in the monitoring, modelling and management of the environment. GEOBIA is the best choice for this.
  • 4. Image Segmentation Segmentation is a process of completely partitioning an image into non-overlapping regions based on homogeneity parameters or on differentiation of heterogeneity parameters. Mathematically, it can be defined as follows: if F is the set of all pixels and P( ) is a homogeneity defined on group of connected pixels, then segmentation is a partitioning of the set F into a set of connected regions (S1, S2, ..., Sn) such that:
  • 5. Why Segmentation? 1. In GEOBIA, we treat a remotely sensed image as union of meaningful image objects. To extract each image objects, we need to use segmentation techniques. 2. As discussed in slide: 3, considering an image as objects gives better classification accuracy and also opportunity to use spatial information.
  • 6. Segmentation Algorithms 1. Mean-shift Segmentation 2. Multi-resolution Segmentation 3. k-means Segmentation 4. Watershed Segmentation
  • 7. Mean-shift segmentation Mean-shift algorithm was introduced by Fukunaga and Hostetler in 1975. It is a versatile, non-parametric density gradient estimation for mode finding or clustering procedure. Idea: For each data point, mean shift defines a window around it and computes the mean of the data point. Then it shifts the center of the window to the mean and repeats the algorithm till it converges. After each iteration, we can consider that the window shifts to a more denser region of the dataset.
  • 8. Mean-shift segmentation At the high level, we can specify Mean Shift as follows: 1. Fix a window around each data point. 2. Compute the mean of data within the window. 3. Shift the window to the mean and repeat till convergence
  • 11.
  • 12. Multi-resolution segmentation 1. It is a bottom-up region merging technique, which starts from one-pixel object. 2. Throughout this clustering process, the underlying optimisation procedure minimizes the weighted heterogeneity nh in the image objects where, n is the number of the pixels of image segment h is the definition of heterogeneity measure. 3. The increment of heterogeneity (f) is calculated before the merging of two adjacent object happens. 4. No further fusion takes place when the increment in heterogeneity exceeds a threshold or scale.
  • 14. k-means segmentation This algorithm has been the most popular unsupervised learning algorithm which is widely used for image segmentation. The k-means clustering algorithm is as follows: 1. Initialize the cluster centroids µ1, µ2, ..., µk randomly. 2. Repeat till convergence
  • 15. Watershed segmentation 1. The watershed transform is a region based segmentation approach. 2. Imagine the landscape is being immersed in a lake, with holes pierced in topical minima. The process of filling water is stopped when water reaches the highest peak in the landscape. This process finally gives a portioned region or basins separated by dams also called watershed lines. 3. Flow diagram of this algorithm is given in the next slide.
  • 18. Objective of this study 1. Study of various segmentation algorithms and deciding which algorithm works better than the existing techniques for different h-resolution terrain surfaces. 2. Comparing the quality of the segmentation algorithms for very high spatial multi-spectral remotely sensed satellite imagery. 3. Automatic estimation of optimal parameter for segmentation algorithms
  • 19. Study Area & Quality Assessment Technique
  • 20. Study area The study area analysed for this research downloaded from Digitalglobe website. Figure: Main study area with 16384 × 16384 resolution
  • 21. Regions of study Rural area Urban area Forest area Residential area
  • 22. Quality assessment technique 1. Visual assessment is taken into account for quality checking of segmentation techniques. 2. In this paper, we decided upon visual assessment on the human eye is considered as strong and experienced source for evaluation of segmentation techniques
  • 23. Selection of the Optimal Segmentation Parameters
  • 24. Segmentation algorithms and parameters in ORFEO Mean-shift environment Watershed environment
  • 25. Segmentation algorithm and parameters in eCogniton Parameters in eCognition
  • 26. Segmentation algorithms and parameters in Matlab 1. Mean-shift algorithm has only one bandwidth parameter. 2. k-means has only class parameter. 3. Watershed algorithm does not have any parameter.
  • 27. Parameter selection for mean-shift segmentation We used spatial profile to select optimal parameters Spatial profile in horizontal axis
  • 28. Spatial profile in vertical axis
  • 29. 1. From these spatial profiles we can notice peaks in all bands which indicates transition between two different classes. The range between the pixel positions at left side maximum value and right side maximum value, is taken as range radius. 2. Spatial radius is taken by a trial-and-error method. 3. The other three parameters are taken as constants for all the images under consideration. 4. The optimal parameters are chosen based on visual assessments. The windowing method is described in the next slide.
  • 30. Parameter selection at different window size
  • 31. Optimal output of mean-shift Parameter selection at 761 X 577 Parameter selection at 780 x 577
  • 32. Optimal output of multi-resolution WinSize = 128 X 128 WinSize = 352 X 352 WinSize = 468 X 468 WinSize = 212 X 212
  • 33. Parameter selection for k-means and watershed segmentation k-means: 1. The only parameter here is class. Selection of proper class is not difficult when the test image is small, but it produce slots of ambiguity when it comes for big remote images. 2. One approach to learn the class is to use Elbows method. Watershed segmentation: The two parameters for watershed segmentation are chosen based on visual inspection.
  • 34. Estimation of the Optimal Segmentation Parameters
  • 35. Existing methods Post-estimation of segmentation parameters: 1. Kim et. al has used the concept of local variance to determine optimal segmentation parameters of alliance-level forest classification. 2. Dragut et. al used local variance in image object level and extended it into multi- scale analysis based on single layer and later in multiple layers. 3. Zhao et. al has used the rate of change of local variance which is similar to the ESP tool, to estimate the optimal parameter. 4. Emary et. al used a similarity measure between two image objects in set of successive scales. 5. Karl and Maurer et. Al have used semi-variogram based spatial dependency prediction. Pre-estimation of segmentation parameters: Ming et. al applies spatial statistics to select optimal parameters for mean- shift segmentation algorithm.
  • 37. Input features extraction Calculation of spatial statistics before feeding in BPNN
  • 38. Training of the BPNN Training BPNN for estimating parameters
  • 39.
  • 42. Rural area Multi-resolution in eCognition Mean-shift in ORFEO Mean-shift in Matlab K-means in Matlab Watershed in Matlab Multi-resolution parameters Mean-shift parameters
  • 43. Residential area Multi-resolution in eCognition Mean-shift in ORFEO Mean-shift in Matlab K-means in Matlab Watershed in Matlab Multi-resolution parameters Mean-shift parameters
  • 44. Urban area Multi-resolution in eCognition Mean-shift in ORFEO Mean-shift in Matlab K-means in Matlab Watershed in Matlab Multi-resolution parameters Mean-shift parameters
  • 45. Forest area Multi-resolution in eCognition Mean-shift in ORFEO Mean-shift in Matlab K-means in Matlab Watershed in Matlab Multi-resolution parameters Mean-shift parameters
  • 46. Evaluation of Automatic Estimation of Segmentation Parameter Technique
  • 47. Mean Square Error plot for the Trained Network
  • 48. Average local variance v/s band for four regions of study
  • 49. Test Images Rural area Residential area Urban area Forest area
  • 50. Estimation of Segmentation Parameters of Multi-resolution Rural area Residential area Urban area Forest area
  • 51. Estimation of Segmentation Parameters of Multi-resolution Rural area Residential area Urban area Forest area
  • 53. Assessment of Segmentation Algorithm • we see that the watershed algorithm is poor. • k-means gives a good segmentation solution though it is affected by salt and paper noise due to within-field variability. • Multi-resolution segmentation is now becoming very famous due to its robust nature and fast processing using multi-threading. From the outcomes, we see that it gives very good segmentation in object level. • Mean-shift segmentation is also a multi-scale segmentation like multi- resolution, but it take a huge amount of time to process in both ORFEO and Matlab.
  • 54. Comparison between multi-resolution and mean-shift segmentation
  • 55. Automatic Estimation of the Optimal Segmentation Parameters Advantages • The proposed method is a pre-estimation method while other studies are related to post-estimation. Only one approach is there which does pre- estimation, but it only limits its scale selection to certain segmentation algorithm. • This proposed approach is not limited to any particular segmentation algorithm. It can estimate any number of parameters for any segmentation algorithm. • Different remote sensing analysis vendors provide different implementation of segmentation algorithms. This approach tries to map between any VHR landcover and optimal segmentation parameter. • Geo-statistics of every band is being considered which makes it more robust to any multi-spectral data.
  • 56. Limitations • Training the BPNN network is a difficult task. Discussion about BPNN network is beyond of the scope of this project. • Calculation of local variance in multiple scale takes a long time. Due to the advancement of high performance computing this limitation can be overcome. • The most important disadvantage is to make a training set for learning the network. Initial human effort is needed but once the network is learnt, the automation process is done