Share Email Print
cover

Proceedings Paper

Multi-class target recognition based on adaptive feature selection
Author(s): Yuehuan Wang; Wei Yao; Yunfeng Song; Nong Sang; Tianxu Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, a new approach of multi-class target recognition is proposed for remote sensing image analysis. A multiclass feature model is built, which is based on sharing features among classes. In order to make the recognition process efficient, we adopted the idea of adaptive feature selection. In each layer of the integrated feature model, the most salient and stable feature are selected first, and then the less ones. Experiments demonstrated the approach proposed is efficient in computation and is adaptive to scene variation.

Paper Details

Date Published: 13 May 2010
PDF: 9 pages
Proc. SPIE 7696, Automatic Target Recognition XX; Acquisition, Tracking, Pointing, and Laser Systems Technologies XXIV; and Optical Pattern Recognition XXI, 769609 (13 May 2010); doi: 10.1117/12.850649
Show Author Affiliations
Yuehuan Wang, Huazhong Univ. of Science and Technology (China)
National Key Lab. of Science & Technology on Multi-Spectral Information Processing Technologies (China)
Wei Yao, Huazhong Univ. of Science and Technology (China)
Yunfeng Song, Huazhong Univ. of Science and Technology (China)
Nong Sang, National Key Lab. of Science & Technology on Multi-Spectral Information Processing Technologies (China)
Tianxu Zhang, National Key Lab. of Science & Technology on Multi-Spectral Information Processing Technologies (China)


Published in SPIE Proceedings Vol. 7696:
Automatic Target Recognition XX; Acquisition, Tracking, Pointing, and Laser Systems Technologies XXIV; and Optical Pattern Recognition XXI
Firooz A. Sadjadi; David P. Casasent; Steven L. Chodos; Abhijit Mahalanobis; William E. Thompson; Tien-Hsin Chao, Editor(s)

© SPIE. Terms of Use
Back to Top