Classification Based Marker Selection for Watershed Transform of Hyperspectral Images Yuliya Tarabalka 1, 2 , Jocelyn Chanussot 1 , Jón Atli Benediktsson 2 1 GIPSA-Lab, Grenoble Institute of Technology, France 2 University of Iceland, Reykjavik, Iceland e-mail: [email protected]July 15, 2009
37
Embed
Classification Based Marker Selection for Watershed ...€¦ · Introduction Marker-controlledwatershedsegmentationandclassification Conclusionsandperspectives Outline 1 Introduction
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Classification Based Marker Selection forWatershed Transform of Hyperspectral Images
Yuliya Tarabalka1,2,Jocelyn Chanussot1, Jón Atli Benediktsson2
1GIPSA-Lab, Grenoble Institute of Technology, France2University of Iceland, Reykjavik, Icelande-mail: [email protected]
July 15, 2009
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Outline
1 Introduction
2 Marker-controlled watershed segmentation and classification
3 Conclusions and perspectives
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 2
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Hyperspectral image
Every pixel contains a detailed spectrum (>100 spectral bands)
+ More information per pixel → increasing capability to distinguishobjects
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 11
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Pixel-wise classification
SVM classifier* → well suited forhyperspectral images
Output:
classification map probability map
-
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
probability estimate for each pixelto belong to the assigned class
*C. Chang and C. Lin, "LIBSVM: A library for Support Vector Machines," Software
available at http://www.csie.ntu.edu.tw/∼cjlin/libsvm, 2001.
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 12
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Selection of the most reliable classified pixelsAnalysis of classification and probability maps:
classification map probability map
1 Perform connected components labelingof the classification map
2 Analyse each connected component:
If it is large (> 20 pixels) → use P%(5%) of its pixels with the highestprobabilities as a markerIf it is small → its pixels withprobabilities > T% (90%)are used as a marker
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 13
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Selection of the most reliable classified pixelsAnalysis of classification and probability maps:
classification map probability map
1 Perform connected components labelingof the classification map
2 Analyse each connected component:
If it is large (> 20 pixels) → use P%(5%) of its pixels with the highestprobabilities as a markerIf it is small → its pixels withprobabilities > T% (90%)are used as a marker
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
HHHY
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 13
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Selection of the most reliable classified pixelsAnalysis of classification and probability maps:
classification map probability map
1 Perform connected components labelingof the classification map
2 Analyse each connected component:
If it is large (> 20 pixels) → use P%(5%) of its pixels with the highestprobabilities as a markerIf it is small → its pixels withprobabilities > T% (90%)are used as a marker
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 13
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Selection of the most reliable classified pixelsAnalysis of classification and probability maps:
classification map probability map
1 Perform connected components labelingof the classification map
2 Analyse each connected component:
If it is large (> 20 pixels) → use P%(5%) of its pixels with the highestprobabilities as a markerIf it is small → its pixels withprobabilities > T% (90%)are used as a marker
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
Must contain a marker!
HHHHHH
HHHHHH
HHHHj
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 13
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Selection of the most reliable classified pixelsAnalysis of classification and probability maps:
classification map probability map
1 Perform connected components labelingof the classification map
2 Analyse each connected component:
If it is large (> 20 pixels) → use P%(5%) of its pixels with the highestprobabilities as a markerIf it is small → its pixels withprobabilities > T% (90%)are used as a marker
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
Must contain a marker!
HHHHHH
HHHHHH
HHHHj
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 13
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Selection of the most reliable classified pixelsAnalysis of classification and probability maps:
classification map probability map
1 Perform connected components labelingof the classification map
2 Analyse each connected component:
If it is large (> 20 pixels) → use P%(5%) of its pixels with the highestprobabilities as a markerIf it is small → its pixels withprobabilities > T% (90%)are used as a marker
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
Has a marker only if it isvery reliable
HHHHHH
HHHHHH
HHHHj
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 13
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Selection of the most reliable classified pixelsAnalysis of classification and probability maps:
classification map probability map
Each connected component → 1 or 0marker (2250 regions → 107 markers)
Marker is not necessarily a connected setof pixels
Each marker has a class label
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
map of 107 markers
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 13
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Gradient
Originalhyperspectralimage
⇒
Robust ColorMorphologicalGradient*
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
*Y. Tarabalka et al., "Segmentation and classification of hyperspectral data using
watershed," in Proc. of IGARSS’08, Boston, USA, 2008.
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 14
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
Hyperspectral image (B bands)
Pixel-wise
classification Gradient
classification map gradient probability map image
map of markers Selection of the most
reliable classified pixels
Marker-controlled watershed
segmentation
Segmentation map + classification map
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 15
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
Create a marker image:
fm(x) =
{0, if x belongs to marker,
tmax , otherwise
Compute (fg + 1)∧fm
Perform minima imposition:morphological reconstruction byerosion of (fg + 1)
∧fm from fm:
fgmi = Rε(fg+1)
∧fm(fm)
Three local minima
Marker
Single minimum
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 16
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
Create a marker image:
fm(x) =
{0, if x belongs to marker,
tmax , otherwise
Compute (fg + 1)∧fm
Perform minima imposition:morphological reconstruction byerosion of (fg + 1)
∧fm from fm:
fgmi = Rε(fg+1)
∧fm(fm)
Three local minima
Marker
Single minimum
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 16
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
Create a marker image:
fm(x) =
{0, if x belongs to marker,
tmax , otherwise
Compute (fg + 1)∧fm
Perform minima imposition:morphological reconstruction byerosion of (fg + 1)
∧fm from fm:
fgmi = Rε(fg+1)
∧fm(fm)
Three local minima
Marker
Single minimum
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 16
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
Create a marker image:
fm(x) =
{0, if x belongs to marker,
tmax , otherwise
Compute (fg + 1)∧fm
Perform minima imposition:morphological reconstruction byerosion of (fg + 1)
∧fm from fm:
fgmi = Rε(fg+1)
∧fm(fm)
Three local minima
Marker
Single minimum
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 16
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
2 Apply watershed on the filteredgradient image fgmi (Vincent andSoille, 1991)
Three local minima
Marker
Single minimum
HHHHHH
HHHHHH
HHj
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 17
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
2 Apply watershed on the filteredgradient image fgmi (Vincent andSoille, 1991)
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 17
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
2 Apply watershed on the filteredgradient image fgmi (Vincent andSoille, 1991)
3 Assign every watershed pixel to thespectrally most similar neighboringregion
⇓
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 17
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
2 Apply watershed on the filteredgradient image fgmi (Vincent andSoille, 1991)
3 Assign every watershed pixel to thespectrally most similar neighboringregion
→Several minimain the filteredgradient
→
Several regionsin thesegmentationmap
⇓
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 17
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
2 Apply watershed on the filteredgradient image fgmi (Vincent andSoille, 1991)
3 Assign every watershed pixel to thespectrally most similar neighboringregion
4 Merge regions belonging to the samemarker
⇓
⇓
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 17
IntroductionMarker-controlled watershed segmentation and classification
Conclusions and perspectives
Marker-controlled watershed segmentation
1 Transform the gradient fg → markersare the only minima
2 Apply watershed on the filteredgradient image fgmi (Vincent andSoille, 1991)
3 Assign every watershed pixel to thespectrally most similar neighboringregion
4 Merge regions belonging to the samemarker
5 Class of each marker → class of thecorresponding region
⇓
⇓
Yuliya Tarabalka et al. ([email protected]) Marker Selection for Watershed of HS Images 17
IntroductionMarker-controlled watershed segmentation and classification