Share Email Print
cover

Proceedings Paper

Framework for feature selection for cast shadow removal
Author(s): Guilin Zhang; Ying Chu; Song Tian; Yufei Zha; Gengming Zhu
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

Cast shadow cause serious problem in the extracting of moving objects because shadow pixels are liable to be misclassified as foreground. Many methods of cast shadow removal have been proposed and many features are selected in these methods. But since, moving object (MO) and cast shadow are classified by a single linear classifier. As it is known, each feature has its strength and weakness and is particularly applicable for handling a certain type of variation. In this paper, a novel framework for feature selection for cast shadow removal based on AdaBoost is proposed. Experiments are conducted on many scenes and the results prove the validation of the proposed method.

Paper Details

Date Published: 15 November 2007
PDF: 6 pages
Proc. SPIE 6786, MIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition, 678606 (15 November 2007); doi: 10.1117/12.748631
Show Author Affiliations
Guilin Zhang, Huazhong Univ. of Science and Technology (China)
Ying Chu, Huazhong Univ. of Science and Technology (China)
Song Tian, ChongQing Communication College (China)
Yufei Zha, Air Force Engineering Univ. (China)
Gengming Zhu, Huazhong Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 6786:
MIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition

© SPIE. Terms of Use
Back to Top