Spectral–Spatial Classification of Hyperspectral Data Based on a Stochastic Minimum Spanning Forest Approach
作者： K. Bernard , Y. Tarabalka , J. Angulo , J. Chanussot , J. A. Benediktsson
关键词:
摘要: In this paper, a new method for supervised hyperspectral data classification is proposed. particular, the notion of stochastic minimum spanning forest (MSF) introduced. For given image, pixelwise first performed. From map, M marker maps are generated by randomly selecting pixels and labeling them as markers construction MSFs. The next step consists in building an MSF from each maps. Finally, all realizations aggregated with maximum vote decision rule order to build final map. proposed tested on three different sets airborne images resolutions contexts. influences number results investigated experiments. performance compared several techniques (both spectral-spatial) using standard quantitative criteria visual qualitative evaluation.
harvard.edu
archives-ouvertes.fr
acm.org 
sci-hub.se 参考文章(54)
Mathieu Fauvel, Spectral and spatial methods for the classification of urban remote sensing data ,(2007)
David A. Landgrebe, Signal Theory Methods in Multispectral Remote Sensing ,(2003)
Nello Cristianini, John Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods ,(2000)
Carlos Hernández-Espinosa, Mercedes Fernández-Redondo, Joaquín Torres-Sospedra, Some Experiments with Ensembles of Neural Networks for Classification of Hyperspectral Images Advances in Neural Networks – ISNN 2004. pp. 912- 917 ,(2004) , 10.1007/978-3-540-28647-9_150
Joseph B. Kruskal, On the shortest spanning subtree of a graph and the traveling salesman problem Proceedings of the American Mathematical Society. ,vol. 7, pp. 48- 50 ,(1956) , 10.1090/S0002-9939-1956-0078686-7
Xue Bai, Guillermo Sapiro, Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and Matting International Journal of Computer Vision. ,vol. 82, pp. 113- 132 ,(2009) , 10.1007/S11263-008-0191-Z
Jesús Angulo, Santiago Velasco-Forero, Semi-supervised hyperspectral image segmentation using regionalized stochastic watershed Proceedings of SPIE. ,vol. 7695, ,(2010) , 10.1117/12.850187
Suresh Subramanian, Nahum Gat, Michael Sheffield, Jacob Barhen, Nikzad Toomarian, Methodology for hyperspectral image classification using novel neural network SPIE international conference, Orlando, FL (United States), 21-25 Apr 1997. ,vol. 3071, pp. 128- 137 ,(1997) , 10.1117/12.280589
J. A. BENEDIKTSSON, P. H. SWAIN, O. K. ERSOY, Conjugate-gradient neural networks in classification of multisource and very-high-dimensional remote sensing data International Journal of Remote Sensing. ,vol. 14, pp. 2883- 2903 ,(1993) , 10.1080/01431169308904316
Chein-I Chang, An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis IEEE Transactions on Information Theory. ,vol. 46, pp. 1927- 1932 ,(2000) , 10.1109/18.857802