26 October 2013 Hyperspectral remote sensing classification based on SVM with end-member extraction
Author Affiliations +
Proceedings Volume 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 89210B (2013) https://doi.org/10.1117/12.2031271
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China
Abstract
In order to enhance the accuracy of hyperspectral remote sensing classification, a classification method based on SVM with end-member extraction is presented. Firstly, the end-members are extracted using pure pixel index approach, and then the ground target is identified based on the spectral feature fitting , followed by the spectral classification of the hyperspectral remote sensing images with the Support Vector Machines. The experiment results indicated that the validity and efficiency of our method are more accurately than the traditional SVM solutions which simply use the regions of interest selected from image as the training samples.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xinlu Ma, Weidong Yan, Hui Bian, Bin Sun, Peizhong Wang, "Hyperspectral remote sensing classification based on SVM with end-member extraction", Proc. SPIE 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 89210B (26 October 2013); doi: 10.1117/12.2031271; https://doi.org/10.1117/12.2031271
PROCEEDINGS
5 PAGES


SHARE
Back to Top