SlideShare a Scribd company logo
1 of 25
Keng-Hao Liu and Chein-I Chang Remote Sensing Signal and Image Processing Laboratory (RSSIPL) Department of Computer Science and Electrical Engineering University of Maryland, Baltimore County (UMBC) Baltimore, MD 21250 Dynamic Band Selection For Hyperspectral Imagery keng3@umbc.edu
Motivation ,[object Object],[object Object],[object Object]
Outline ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Issues of Conventional BS ,[object Object],[object Object],[object Object]
Progressive Band  Dimensionality Process  (PBDP) ,[object Object],[object Object],[object Object],[object Object]
Band Prioritization (BP)  Criteria for PBDP ,[object Object],Second order statistic-based BP criteria - Variance - Signal-to-Noise Ratio (SNR or MNF) High order statistic-based BP criteria - Skewness - Kurtosis Infinite order Statistics BP criteria -  Entropy -  Information Divergence (ID)   -  Neg-entropy (combination of 3rd and 4th order )
Virtual Dimensionality  (VD) ,[object Object],[object Object]
Band Dimensionality Allocation (BDA) ,[object Object],[object Object],[object Object]
Band Dimensionality Allocation  (BDA) for signatures ,[object Object],[object Object],[object Object],[object Object],[object Object],BDA Procedures: Determines the number  of signatures to be used  for data analysis Additional number required for m j  to distinguish itself from other signatures.
Band Dimensionality Allocation  (BDA) for signatures ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Dynamic Band Selection  (DBS) ,[object Object],[object Object],[object Object],[object Object],DBS steps:
Hyperspectral Images Used for  Experiments (1) HYDICE Data:  64x64 169 bands hyperspectral image with spatial  resolution is 20m. Ground truth (desired signatures) Image scene p 11 , p 12 , p 13 p 211 , p 22 , p 23   p 221 p 311 , p 312 , p 32 , p 33 p 411 , p 412 , p 42 , p 43   p 511 , p 52 , p 53 p 521 interferer grass tree road undesired signatures Spectral of five panels Classifier: FCLS Band De-correlation (BD) is applied after BP with σ= 0.1
HYDICE Data Experiments Shannon BDA results of HYDICE Data signature  m j n VD π j q j n j  (BDA) Shannon coding m 1 =p 1   (panels in row1) 9 SID 0.0172 15 SAM 0.0462 14 m 2 =p 2 (panels in row2) 9 SID 0.0295 15 SAM 0.0779 13 m 3 =p 3 (panels in row3) 9 SID 0.0358 14 SAM 0.0897 13 m 4 =p 4 (panels in row4) 9 SID 0.0695 13 SAM 0.1004 13 m 5 =p 5   (panels in row5) 9 SID 0.1070 13 SAM 0.1140 13 m 6  (grass) 9 SID 0.1007 13 SAM 0.1396 12 m 7  (road) 9 SID 0.0565 14 SAM 0.1035 13 m 8  (tree) 9 SID 0.2869 12 SAM 0.1479 12 m 9  (interferer) 9 SID 0.2969 11 SAM 0.1808 12
HYDICE Data Experiments Unmixed abundance fractions of 19 panel pixels by FCLS  VD BDA n VD Shannon coding Huffman coding Hamming coding 2 n VD total Optimal p  = Number of selected bands 9 15 14 13 18 65 to 70 p 11 Variance 0.44 0.63 0.6 0.54 0.73 0.78( 65 ) 0.78( 32 ) Skewness 0.27 0.84 0.84 0.82 0.85 0.81( 70 ) 0.92( 36 ) Entropy 0.83 0.87 0.85 0.84 0.88 0.77( 68 ) 1( 24 ) p 12 Variance 0.66 0.46 0.48 0.51 0.43 0.56( 65 ) 0.68( 11 ) Skewness 0.54 0.53 0.36 0.3 0.52 0.56( 70 ) 0.68( 38 ) Entropy 0.93 0.9 0.86 0.86 0.72 0.53( 68 ) 0.93( 10 ) p 13 Variance 0 0 0 0 0 0( 65 ) 0( 10 ) Skewness 0 0 0 0 0 0.05( 70 ) 0.23( 34 ) Entropy 0.68 0.69 0.67 0.69 0.67 0.01( 68 ) 0.83( 12 ) p  = Number of selected bands 9 15 14 13 18 p 211 Variance 0.85 0.87 0.87 0.87 0.87 0.89( 65 ) 0.89( 65 ) Skewness 0.84 0.95 0.96 0.95 0.95 0.89( 70 ) 0.99( 36 ) Entropy 1.2 0.88 0.87 0.87 0.88 0.92( 68 ) 1.2( 9 ) p 221 Variance 0.53 0.71 0.7 0.7 0.72 0.75( 65 ) 0.75( 65 ) Skewness 0.72 0.95 0.96 0.96 0.96 0.77( 70 ) 1( 37 ) Entropy 0 0.21 0.19 0.25 0.22 0.81( 68 ) 1( 38 ) p 22 Variance 0.75 0.86 0.86 0.85 0.81 0.78( 65 ) 0.86( 14 ) Skewness 0.87 0.74 0.75 0.8 0.7 0.79( 70 ) 0.87( 9 ) Entropy 0.64 0.6 0.62 0.61 0.6 0.77( 68 ) 0.78( 67 ) p 23 Variance 0.46 0.49 0.49 0.49 0.48 0.46( 65 ) 0.49( 14 ) Skewness 0.38 0.24 0.24 0.24 0.22 0.45( 70 ) 0.45( 70 ) Entropy 0 0.23 0.19 0.18 0.19 0.44( 68 ) 0.44( 68 )
HYDICE Data Experiments ROC performance of 5 row panels using FCLS Panels in row 1 Panels in row 2 Panels in row 3 Panels in row 4 Panels in row 5 BDA VD Y axis: Area under curve of ROC ( P D   versus  P F  ) X axis: Number of selected bands,  p
HYDICE Data Experiments Average ROC performance of 5 row panels Average performance of 5 row panels BDA range VD 2VD
Some notes for HYDICE Data Experiments ,[object Object],[object Object],[object Object]
Hyperspectral Images Used for  Experiments (2) Class map AVIRIS (Purdue) Data:  145x145 202 bands hyperspectral image.  Image scene class1 class2 class3 class4 class5 class6 class7 class8 class9 class10 class11 class12 class13 class14 class15 class16 17 Classes maps Data samples are heavily-mixed Classifier: MLC Band De-correlation (BD) is applied after BP with σ= 0.1
Purdue Data Experiments BDA results of Purdue Data signature  m j n VD π j q j j n j  (BDA) Shannon coding m 1  (class 1) 29 SID 0.0128 36 m 2   (class 2) 29 SID 0.0437 34 m 3  (class 3) 29 SID 0.0392 34 m 4  (class 4) 29 SID 0.0140 36 m 5  (class 5) 29 SID 0.1341 32 m 6  (class 6) 29 SID 0.0316 34 m 7  (class 7) 29 SID 0.0042 37 m 8  (class 8) 29 SID 0.0104 36 m 9  (class 9) 29 SID 0.0154 36 m 10  (class 10) 29 SID 0.0543 34 m 11   (class 11) 29 SID 0.0480 34 m 12   (class 12) 29 SID 0.0430 34 m 13   (class 13) 29 SID 0.0277 35 m 14   (class 14) 29 SID 0.2293 32 m 15   (class 15) 29 SID 0.0580 34 m 16   (class 16) 29 SID 0.2105 32 m 17   (BKG) 29 SID 0.0239 35
Purdue Data Experiment MLC classification results of 16 classes class1 class2  class3  class4  class5  class6 class7  class8  class9  class10  BDA VD Y axis: MLC classification rate in percent% X axis: Number of selected bands,  p Classes 1 to 10
Purdue Data Experiment Average performance of 16 classes MLC classification results class11 class12  class13  class14  class15  class16  VD 2VD BDA range Classes 11 to 16
Some Notes for Purdue Data Experiments ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Summary of DBS ,[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],Conclusions
Thank You ! keng3@umbc.edu  http://www.umbc.edu/rssipl/

More Related Content

Similar to Igarss1792_v2.ppt

20Dieterich-SRSSRTDosimetry.pdf
20Dieterich-SRSSRTDosimetry.pdf20Dieterich-SRSSRTDosimetry.pdf
20Dieterich-SRSSRTDosimetry.pdfNishant835443
 
SLOPE 1st workshop - presentation 2
SLOPE 1st workshop - presentation 2SLOPE 1st workshop - presentation 2
SLOPE 1st workshop - presentation 2SLOPE Project
 
Depth estimation do we need to throw old things away
Depth estimation do we need to throw old things awayDepth estimation do we need to throw old things away
Depth estimation do we need to throw old things awayNAVER Engineering
 
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS

FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS

FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
Maxim Kazantsev
 
CSI Acquisition for FDD-based Massive MIMO Systems
CSI Acquisition for FDD-based Massive MIMO SystemsCSI Acquisition for FDD-based Massive MIMO Systems
CSI Acquisition for FDD-based Massive MIMO SystemsCPqD
 
Cycle’s topological optimizations and the iterative decoding problem on gener...
Cycle’s topological optimizations and the iterative decoding problem on gener...Cycle’s topological optimizations and the iterative decoding problem on gener...
Cycle’s topological optimizations and the iterative decoding problem on gener...Usatyuk Vasiliy
 
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSISFUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSISIrene Pochinok
 
5_1555_TH4.T01.5_suwa.ppt
5_1555_TH4.T01.5_suwa.ppt5_1555_TH4.T01.5_suwa.ppt
5_1555_TH4.T01.5_suwa.pptgrssieee
 
Big data matrix factorizations and Overlapping community detection in graphs
Big data matrix factorizations and Overlapping community detection in graphsBig data matrix factorizations and Overlapping community detection in graphs
Big data matrix factorizations and Overlapping community detection in graphsDavid Gleich
 
Mimo radar detection in compound gaussian clutter using orthogonal discrete f...
Mimo radar detection in compound gaussian clutter using orthogonal discrete f...Mimo radar detection in compound gaussian clutter using orthogonal discrete f...
Mimo radar detection in compound gaussian clutter using orthogonal discrete f...ijma
 
Surface-related multiple elimination through orthogonal encoding in the laten...
Surface-related multiple elimination through orthogonal encoding in the laten...Surface-related multiple elimination through orthogonal encoding in the laten...
Surface-related multiple elimination through orthogonal encoding in the laten...Oleg Ovcharenko
 
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Reza Sadeghi
 
Project Presentation
Project PresentationProject Presentation
Project Presentationbutest
 
AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...
AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...
AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...Ravi Kiran B.
 
4-Navarro-SanchezIGARSS2011.ppt
4-Navarro-SanchezIGARSS2011.ppt4-Navarro-SanchezIGARSS2011.ppt
4-Navarro-SanchezIGARSS2011.pptgrssieee
 
CVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest Points
CVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest PointsCVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest Points
CVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest Pointszukun
 
Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...
Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...
Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...CSCJournals
 
Multi-Dimensional Parameter Estimation and Prewhitening
Multi-Dimensional Parameter Estimation and PrewhiteningMulti-Dimensional Parameter Estimation and Prewhitening
Multi-Dimensional Parameter Estimation and PrewhiteningStefanie Schwarz
 

Similar to Igarss1792_v2.ppt (20)

20Dieterich-SRSSRTDosimetry.pdf
20Dieterich-SRSSRTDosimetry.pdf20Dieterich-SRSSRTDosimetry.pdf
20Dieterich-SRSSRTDosimetry.pdf
 
SLOPE 1st workshop - presentation 2
SLOPE 1st workshop - presentation 2SLOPE 1st workshop - presentation 2
SLOPE 1st workshop - presentation 2
 
Depth estimation do we need to throw old things away
Depth estimation do we need to throw old things awayDepth estimation do we need to throw old things away
Depth estimation do we need to throw old things away
 
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS

FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS

FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS

 
CSI Acquisition for FDD-based Massive MIMO Systems
CSI Acquisition for FDD-based Massive MIMO SystemsCSI Acquisition for FDD-based Massive MIMO Systems
CSI Acquisition for FDD-based Massive MIMO Systems
 
Cycle’s topological optimizations and the iterative decoding problem on gener...
Cycle’s topological optimizations and the iterative decoding problem on gener...Cycle’s topological optimizations and the iterative decoding problem on gener...
Cycle’s topological optimizations and the iterative decoding problem on gener...
 
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSISFUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
FUNCTION OF RIVAL SIMILARITY IN A COGNITIVE DATA ANALYSIS
 
5_1555_TH4.T01.5_suwa.ppt
5_1555_TH4.T01.5_suwa.ppt5_1555_TH4.T01.5_suwa.ppt
5_1555_TH4.T01.5_suwa.ppt
 
Big data matrix factorizations and Overlapping community detection in graphs
Big data matrix factorizations and Overlapping community detection in graphsBig data matrix factorizations and Overlapping community detection in graphs
Big data matrix factorizations and Overlapping community detection in graphs
 
Mimo radar detection in compound gaussian clutter using orthogonal discrete f...
Mimo radar detection in compound gaussian clutter using orthogonal discrete f...Mimo radar detection in compound gaussian clutter using orthogonal discrete f...
Mimo radar detection in compound gaussian clutter using orthogonal discrete f...
 
Surface-related multiple elimination through orthogonal encoding in the laten...
Surface-related multiple elimination through orthogonal encoding in the laten...Surface-related multiple elimination through orthogonal encoding in the laten...
Surface-related multiple elimination through orthogonal encoding in the laten...
 
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...Strengthening support vector classifiers based on fuzzy logic and evolutionar...
Strengthening support vector classifiers based on fuzzy logic and evolutionar...
 
Project Presentation
Project PresentationProject Presentation
Project Presentation
 
PSO.ppt
PSO.pptPSO.ppt
PSO.ppt
 
AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...
AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...
AUTO AI 2021 talk Real world data augmentations for autonomous driving : B Ra...
 
4-Navarro-SanchezIGARSS2011.ppt
4-Navarro-SanchezIGARSS2011.ppt4-Navarro-SanchezIGARSS2011.ppt
4-Navarro-SanchezIGARSS2011.ppt
 
CVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest Points
CVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest PointsCVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest Points
CVPR2010: Advanced ITinCVPR in a Nutshell: part 2: Interest Points
 
Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...
Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...
Soft Decision Scheme for Multiple Descriptions Coding over Rician Fading Chan...
 
23AFMC_Beamer.pdf
23AFMC_Beamer.pdf23AFMC_Beamer.pdf
23AFMC_Beamer.pdf
 
Multi-Dimensional Parameter Estimation and Prewhitening
Multi-Dimensional Parameter Estimation and PrewhiteningMulti-Dimensional Parameter Estimation and Prewhitening
Multi-Dimensional Parameter Estimation and Prewhitening
 

More from grssieee

Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...grssieee
 
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODELSEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODELgrssieee
 
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...grssieee
 
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIESTHE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIESgrssieee
 
GMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUSGMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUSgrssieee
 
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETERPROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETERgrssieee
 
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...grssieee
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...grssieee
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...grssieee
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...grssieee
 
test 34mb wo animations
test  34mb wo animationstest  34mb wo animations
test 34mb wo animationsgrssieee
 
2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdf2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdfgrssieee
 
DLR open house
DLR open houseDLR open house
DLR open housegrssieee
 
DLR open house
DLR open houseDLR open house
DLR open housegrssieee
 
DLR open house
DLR open houseDLR open house
DLR open housegrssieee
 
Tana_IGARSS2011.ppt
Tana_IGARSS2011.pptTana_IGARSS2011.ppt
Tana_IGARSS2011.pptgrssieee
 
Solaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.pptSolaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.pptgrssieee
 

More from grssieee (20)

Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
Tangent height accuracy of Superconducting Submillimeter-Wave Limb-Emission S...
 
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODELSEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
SEGMENTATION OF POLARIMETRIC SAR DATA WITH A MULTI-TEXTURE PRODUCT MODEL
 
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
TWO-POINT STATISTIC OF POLARIMETRIC SAR DATA TWO-POINT STATISTIC OF POLARIMET...
 
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIESTHE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
THE SENTINEL-1 MISSION AND ITS APPLICATION CAPABILITIES
 
GMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUSGMES SPACE COMPONENT:PROGRAMMATIC STATUS
GMES SPACE COMPONENT:PROGRAMMATIC STATUS
 
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETERPROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
PROGRESSES OF DEVELOPMENT OF CFOSAT SCATTEROMETER
 
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
DEVELOPMENT OF ALGORITHMS AND PRODUCTS FOR SUPPORTING THE ITALIAN HYPERSPECTR...
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
 
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
EO-1/HYPERION: NEARING TWELVE YEARS OF SUCCESSFUL MISSION SCIENCE OPERATION A...
 
Test
TestTest
Test
 
test 34mb wo animations
test  34mb wo animationstest  34mb wo animations
test 34mb wo animations
 
Test 70MB
Test 70MBTest 70MB
Test 70MB
 
Test 70MB
Test 70MBTest 70MB
Test 70MB
 
2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdf2011_Fox_Tax_Worksheets.pdf
2011_Fox_Tax_Worksheets.pdf
 
DLR open house
DLR open houseDLR open house
DLR open house
 
DLR open house
DLR open houseDLR open house
DLR open house
 
DLR open house
DLR open houseDLR open house
DLR open house
 
Tana_IGARSS2011.ppt
Tana_IGARSS2011.pptTana_IGARSS2011.ppt
Tana_IGARSS2011.ppt
 
Solaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.pptSolaro_IGARSS_2011.ppt
Solaro_IGARSS_2011.ppt
 

Recently uploaded

Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 

Recently uploaded (20)

Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 

Igarss1792_v2.ppt

  • 1. Keng-Hao Liu and Chein-I Chang Remote Sensing Signal and Image Processing Laboratory (RSSIPL) Department of Computer Science and Electrical Engineering University of Maryland, Baltimore County (UMBC) Baltimore, MD 21250 Dynamic Band Selection For Hyperspectral Imagery keng3@umbc.edu
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12. Hyperspectral Images Used for Experiments (1) HYDICE Data: 64x64 169 bands hyperspectral image with spatial resolution is 20m. Ground truth (desired signatures) Image scene p 11 , p 12 , p 13 p 211 , p 22 , p 23 p 221 p 311 , p 312 , p 32 , p 33 p 411 , p 412 , p 42 , p 43 p 511 , p 52 , p 53 p 521 interferer grass tree road undesired signatures Spectral of five panels Classifier: FCLS Band De-correlation (BD) is applied after BP with σ= 0.1
  • 13. HYDICE Data Experiments Shannon BDA results of HYDICE Data signature m j n VD π j q j n j (BDA) Shannon coding m 1 =p 1 (panels in row1) 9 SID 0.0172 15 SAM 0.0462 14 m 2 =p 2 (panels in row2) 9 SID 0.0295 15 SAM 0.0779 13 m 3 =p 3 (panels in row3) 9 SID 0.0358 14 SAM 0.0897 13 m 4 =p 4 (panels in row4) 9 SID 0.0695 13 SAM 0.1004 13 m 5 =p 5 (panels in row5) 9 SID 0.1070 13 SAM 0.1140 13 m 6 (grass) 9 SID 0.1007 13 SAM 0.1396 12 m 7 (road) 9 SID 0.0565 14 SAM 0.1035 13 m 8 (tree) 9 SID 0.2869 12 SAM 0.1479 12 m 9 (interferer) 9 SID 0.2969 11 SAM 0.1808 12
  • 14. HYDICE Data Experiments Unmixed abundance fractions of 19 panel pixels by FCLS VD BDA n VD Shannon coding Huffman coding Hamming coding 2 n VD total Optimal p = Number of selected bands 9 15 14 13 18 65 to 70 p 11 Variance 0.44 0.63 0.6 0.54 0.73 0.78( 65 ) 0.78( 32 ) Skewness 0.27 0.84 0.84 0.82 0.85 0.81( 70 ) 0.92( 36 ) Entropy 0.83 0.87 0.85 0.84 0.88 0.77( 68 ) 1( 24 ) p 12 Variance 0.66 0.46 0.48 0.51 0.43 0.56( 65 ) 0.68( 11 ) Skewness 0.54 0.53 0.36 0.3 0.52 0.56( 70 ) 0.68( 38 ) Entropy 0.93 0.9 0.86 0.86 0.72 0.53( 68 ) 0.93( 10 ) p 13 Variance 0 0 0 0 0 0( 65 ) 0( 10 ) Skewness 0 0 0 0 0 0.05( 70 ) 0.23( 34 ) Entropy 0.68 0.69 0.67 0.69 0.67 0.01( 68 ) 0.83( 12 ) p = Number of selected bands 9 15 14 13 18 p 211 Variance 0.85 0.87 0.87 0.87 0.87 0.89( 65 ) 0.89( 65 ) Skewness 0.84 0.95 0.96 0.95 0.95 0.89( 70 ) 0.99( 36 ) Entropy 1.2 0.88 0.87 0.87 0.88 0.92( 68 ) 1.2( 9 ) p 221 Variance 0.53 0.71 0.7 0.7 0.72 0.75( 65 ) 0.75( 65 ) Skewness 0.72 0.95 0.96 0.96 0.96 0.77( 70 ) 1( 37 ) Entropy 0 0.21 0.19 0.25 0.22 0.81( 68 ) 1( 38 ) p 22 Variance 0.75 0.86 0.86 0.85 0.81 0.78( 65 ) 0.86( 14 ) Skewness 0.87 0.74 0.75 0.8 0.7 0.79( 70 ) 0.87( 9 ) Entropy 0.64 0.6 0.62 0.61 0.6 0.77( 68 ) 0.78( 67 ) p 23 Variance 0.46 0.49 0.49 0.49 0.48 0.46( 65 ) 0.49( 14 ) Skewness 0.38 0.24 0.24 0.24 0.22 0.45( 70 ) 0.45( 70 ) Entropy 0 0.23 0.19 0.18 0.19 0.44( 68 ) 0.44( 68 )
  • 15. HYDICE Data Experiments ROC performance of 5 row panels using FCLS Panels in row 1 Panels in row 2 Panels in row 3 Panels in row 4 Panels in row 5 BDA VD Y axis: Area under curve of ROC ( P D versus P F ) X axis: Number of selected bands, p
  • 16. HYDICE Data Experiments Average ROC performance of 5 row panels Average performance of 5 row panels BDA range VD 2VD
  • 17.
  • 18. Hyperspectral Images Used for Experiments (2) Class map AVIRIS (Purdue) Data: 145x145 202 bands hyperspectral image. Image scene class1 class2 class3 class4 class5 class6 class7 class8 class9 class10 class11 class12 class13 class14 class15 class16 17 Classes maps Data samples are heavily-mixed Classifier: MLC Band De-correlation (BD) is applied after BP with σ= 0.1
  • 19. Purdue Data Experiments BDA results of Purdue Data signature m j n VD π j q j j n j (BDA) Shannon coding m 1 (class 1) 29 SID 0.0128 36 m 2 (class 2) 29 SID 0.0437 34 m 3 (class 3) 29 SID 0.0392 34 m 4 (class 4) 29 SID 0.0140 36 m 5 (class 5) 29 SID 0.1341 32 m 6 (class 6) 29 SID 0.0316 34 m 7 (class 7) 29 SID 0.0042 37 m 8 (class 8) 29 SID 0.0104 36 m 9 (class 9) 29 SID 0.0154 36 m 10 (class 10) 29 SID 0.0543 34 m 11 (class 11) 29 SID 0.0480 34 m 12 (class 12) 29 SID 0.0430 34 m 13 (class 13) 29 SID 0.0277 35 m 14 (class 14) 29 SID 0.2293 32 m 15 (class 15) 29 SID 0.0580 34 m 16 (class 16) 29 SID 0.2105 32 m 17 (BKG) 29 SID 0.0239 35
  • 20. Purdue Data Experiment MLC classification results of 16 classes class1 class2 class3 class4 class5 class6 class7 class8 class9 class10 BDA VD Y axis: MLC classification rate in percent% X axis: Number of selected bands, p Classes 1 to 10
  • 21. Purdue Data Experiment Average performance of 16 classes MLC classification results class11 class12 class13 class14 class15 class16 VD 2VD BDA range Classes 11 to 16
  • 22.
  • 23.
  • 24.
  • 25. Thank You ! keng3@umbc.edu http://www.umbc.edu/rssipl/