Share Email Print
cover

Proceedings Paper

Spectral-spatial hyperspectral image classification using super-pixel-based spatial pyramid representation
Author(s): Jiayuan Fan; Hui Li Tan; Maria Toomik; Shijian Lu
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Spatial pyramid matching has demonstrated its power for image recognition task by pooling features from spatially increasingly fine sub-regions. Motivated by the concept of feature pooling at multiple pyramid levels, we propose a novel spectral-spatial hyperspectral image classification approach using superpixel-based spatial pyramid representation. This technique first generates multiple superpixel maps by decreasing the superpixel number gradually along with the increased spatial regions for labelled samples. By using every superpixel map, sparse representation of pixels within every spatial region is then computed through local max pooling. Finally, features learned from training samples are aggregated and trained by a support vector machine (SVM) classifier. The proposed spectral-spatial hyperspectral image classification technique has been evaluated on two public hyperspectral datasets, including the Indian Pines image containing 16 different agricultural scene categories with a 20m resolution acquired by AVIRIS and the University of Pavia image containing 9 land-use categories with a 1.3m spatial resolution acquired by the ROSIS-03 sensor. Experimental results show significantly improved performance compared with the state-of-the-art works. The major contributions of this proposed technique include (1) a new spectral-spatial classification approach to generate feature representation for hyperspectral image, (2) a complementary yet effective feature pooling approach, i.e. the superpixel-based spatial pyramid representation that is used for the spatial correlation study, (3) evaluation on two public hyperspectral image datasets with superior image classification performance.

Paper Details

Date Published: 18 October 2016
PDF: 7 pages
Proc. SPIE 10004, Image and Signal Processing for Remote Sensing XXII, 100040W (18 October 2016); doi: 10.1117/12.2241033
Show Author Affiliations
Jiayuan Fan, Agency for Science, Technology and Research (A*STAR) (Singapore)
Hui Li Tan, Agency for Science, Technology and Research (A*STAR) (Singapore)
Maria Toomik, Agency for Science, Technology and Research (A*STAR) (Singapore)
Univ. College London (United Kingdom)
Shijian Lu, Agency for Science, Technology and Research (A*STAR) (Singapore)


Published in SPIE Proceedings Vol. 10004:
Image and Signal Processing for Remote Sensing XXII
Lorenzo Bruzzone; Francesca Bovolo, Editor(s)

© SPIE. Terms of Use
Back to Top