11 July 2016 Pedestrian detection based on diverse margin distribution ensemble
Author Affiliations +
Proceedings Volume 10011, First International Workshop on Pattern Recognition; 1001107 (2016) https://doi.org/10.1117/12.2243135
Event: First International Workshop on Pattern Recognition, 2016, Tokyo, Japan
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.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fanyong Cheng, Jing Zhang, Cuihong Wen, Zuoyong Li, "Pedestrian detection based on diverse margin distribution ensemble", Proc. SPIE 10011, First International Workshop on Pattern Recognition, 1001107 (11 July 2016); doi: 10.1117/12.2243135; https://doi.org/10.1117/12.2243135
PROCEEDINGS
6 PAGES


SHARE
Back to Top