Atnaujinkite slapukų nuostatas

El. knyga: Spectral-Spatial Classification of Hyperspectral Remote Sensing Images

,
  • Formatas: 280 pages
  • Išleidimo metai: 31-Jan-2015
  • Leidėjas: Artech House Publishers
  • ISBN-13: 9781608078134
Kitos knygos pagal šią temą:
Spectral-Spatial Classification of Hyperspectral Remote Sensing ImagesDidesnis paveikslėlis
  • Formatas: 280 pages
  • Išleidimo metai: 31-Jan-2015
  • Leidėjas: Artech House Publishers
  • ISBN-13: 9781608078134
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

This comprehensive new resource presents recent developments in the classification of hyperspectral images using both spectral and spatial information, including advanced statistical approaches and methods. The inclusion of spatial information to traditional approaches for hyperspectral classification has been one of the most active and relevant innovative lines of research in remote sensing during recent years. This book gives insight into several important challenges when performing hyperspectral image classification related to the imbalance between high dimensionality and limited availability of training samples, or the presence of mixed pixels in the data. This book also shows the reader how to integrate spatial and spectral information in order to take advantage of the benefits that both sources of information provide.
Foreword xi
Acknowledgments xv
Chapter 1 Introduction
1(32)
1.1 Introduction to Hyperspectral Imaging Systems
1(3)
1.2 High-Dimensional Data
4(27)
1.2.1 Geometrical and Statistical Properties of High Dimensional Data and the Need for Feature Reduction
5(6)
1.2.2 Conventional Spectral Classifiers and the Importance of Considering Spatial Information
11(20)
1.3 Summary
31(2)
Chapter 2 Classification Approaches
33(22)
2.1 Classification
33(3)
2.2 Statistical Classification
36(8)
2.2.1 Support Vector Machines
37(4)
2.2.2 Neural Network Classifiers
41(2)
2.2.3 Decision Tree Classifiers
43(1)
2.3 Multiple Classifiers
44(6)
2.3.1 Boosting
44(2)
2.3.2 Bagging
46(2)
2.3.3 Random Forest
48(2)
2.4 The ECHO Classifier
50(1)
2.5 Estimation of Classification Error
51(3)
2.5.1 Confusion Matrix
51(1)
2.5.2 Average Accuracy (AA)
52(2)
2.6 Summary
54(1)
Chapter 3 Feature Reduction
55(36)
3.1 Feature Extraction (FE)
56(13)
3.1.1 Principal Component Analysis (PCA)
58(2)
3.1.2 Independent Component Analysis
60(2)
3.1.3 Discriminant Analysis Feature Extraction (DAFE)
62(2)
3.1.4 Decision Boundary Feature Extraction (DBFE)
64(3)
3.1.5 Nonparametric Weighted Feature Extraction (NWFE)
67(2)
3.2 Feature Selection
69(21)
3.2.1 Supervised and Unsupervised Feature Selection Techniques
71(1)
3.2.2 Evolutionary-Based Feature Selection Techniques
72(3)
3.2.3 Genetic Algorithm (GA)-Based Feature Selection
75(2)
3.2.4 Particle Swarm Optimization (PSO)-Based Feature Selection
77(6)
3.2.5 Hybrid Genetic Algorithm Particle Swarm Optimization (HGAPSO)-Based Feature Selection
83(1)
3.2.6 FODPSO-Based Feature Selection
84(6)
3.3 Summary
90(1)
Chapter 4 Spatial Information Extraction Using Segmentation
91(50)
4.1 Some Approaches for the Integration of Spectral and Spatial Information
94(7)
4.1.1 Feature Fusion into a Stacked Vector
94(1)
4.1.2 Composite Kernel
95(1)
4.1.3 Spectral-Spatial Classification Using Majority Voting
96(5)
4.2 Clustering Approaches
101(4)
4.2.1 K-Means
101(2)
4.2.2 Fuzzy C-Means Clustering (FCM)
103(1)
4.2.3 Particle Swarm Optimization (PSO)-Based FCM (PSO-FCM)
104(1)
4.3 Expectation Maximization (EM)
105(3)
4.4 Mean-shift Segmentation (MSS)
108(1)
4.5 Watershed Segmentation (WS)
109(4)
4.6 Hierarchical Segmentation (HSeg)
113(2)
4.7 Segmentation and Classification Using Automatically Selected Markers
115(9)
4.7.1 Marker Selection Using Probabilistic SVM
116(3)
4.7.2 Multiple Classifier Approach for Marker Selection
119(3)
4.7.3 Construction of a Minimum Spanning Forest (MSF)
122(2)
4.8 Thresholding-Based Segmentation Techniques
124(14)
4.8.1 Image Thresholding
127(4)
4.8.2 Classification Based on Thresholding-Based Image Segmentation
131(1)
4.8.3 Experimental Evaluation of Different Spectral-Spatial Classification Approaches Based on Different Segmentation Methods
132(6)
4.9 Summary
138(3)
Chapter 5 Morphological Profile
141(24)
5.1 Mathematical Morphology (MM)
142(20)
5.1.1 Morphological Operators
142(7)
5.1.2 Morphological Profile (MP)
149(4)
5.1.3 Morphological Neighborhood
153(3)
5.1.4 Spectral-Spatial Classification
156(6)
5.2 Summary
162(3)
Chapter 6 Attribute Profiles
165(34)
6.1 Fundamental Properties
166(1)
6.2 Morphological Attribute Filter (AF)
167(13)
6.2.1 Attribute Profile and Its Extension to Hyperspectral Images
173(7)
6.3 Spectral-Spatial Classification Based on AP
180(18)
6.3.1 Strategy 1
180(1)
6.3.2 Strategy 2
181(17)
6.4 Summary
198(1)
Chapter 7 Conclusion and Future Works
199(6)
7.1 Conclusions
199(1)
7.2 Perspectives
200(5)
Appendix A CEM Clustering 205(2)
Appendix B Spectral Angle Mapper (SAM) 207(2)
Appendix C Prim's Algorithm 209(2)
Appendix D Data Sets Description 211(6)
Abbreviations and Acronyms 217(2)
Bibliography 219(30)
About the Authors 249(2)
Index 251
Jon Atli Benediktsson is currently Pro-Rector of Science and Academic Affairs and Professor of Electrical and Computer Engineering at the University of Iceland, Reykjavik, Iceland. He received the Cand.Sci. degree in Electrical Engineering from the University of Iceland, Reykjavik, in 1984, and the M.S.E.E. and Ph.D. degrees in Electrical Engineering from Purdue University, West Lafayette, Indiana, USA in 1987 and 1990. Pedram Ghamisi graduated with a B.Sc. degree in Civil (Survey) Engineering from the Tehran South Campus of Azad University. He also received his M. Sc. Degree with first Class Honors in Remote Sensing at KN Toosi University of Technology in 2012.
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97816080781342e.html
Raktažodžiai: