Share Email Print
cover

Proceedings Paper

Pedestrian detection based on diverse margin distribution ensemble
Author(s): Fanyong Cheng; Jing Zhang; Cuihong Wen; Zuoyong Li
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

This paper studies the impact of margin distribution on detection performance and proposes Diverse Margin Distribution Ensemble (DMDE) for pedestrian detection, based on HOG descriptor. Large margin Distribution Machine (LDM) introduces the margin mean and margin variance. Large margin mean is relevant to the strong generalization performance and large margin variance is relevant to the more balanced detection rate between two classes. Inspired by this recognition, DMDE is proposed to obtain greater robustness and balance for pedestrian detection. It is a blending of SVM and two LDMs with different parameter orders and can aggregate the merits of the three classifiers. Experimental results show that DMDE is more robust and balanced than single SVM or LDM for pedestrian detection.

Paper Details

Date Published: 11 July 2016
PDF: 6 pages
Proc. SPIE 10011, First International Workshop on Pattern Recognition, 1001107 (11 July 2016); doi: 10.1117/12.2243135
Show Author Affiliations
Fanyong Cheng, Hunan Univ. (China)
Minjiang Univ. (China)
Fujian Provincial Key Lab. of Information Processing and Intelligent Control (China)
Jing Zhang, Hunan Univ. (China)
Cuihong Wen, Hunan Univ. (China)
Zuoyong Li, Minjiang Univ. (China)
Fujian Provincial Key Lab. of Information Processing and Intelligent Control (China)


Published in SPIE Proceedings Vol. 10011:
First International Workshop on Pattern Recognition
Xudong Jiang; Guojian Chen; Genci Capi; Chiharu Ishll, Editor(s)

© SPIE. Terms of Use
Back to Top