Representative Template Set Generation Method for Pedestrian Detection

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Representative Template Set Generation Method for Pedestrian Detection
	Wu, Pei; Cao, Xian-Bin; Xu, Yan-Wu; Qiao, Hong
	2008
会议名称	5th International Conference on Fuzzy Systems and Knowledge Discovery
会议录名称	FIFTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY
会议日期	OCT 18-20, 2008
会议地点	Jinan, PEOPLES R CHINA
摘要	Template matching is an effective approach for pedestrian detection. In order to achieve real-time and accurate detection, how to obtain a suitable representative template set is still an open problem due to the large variety of pedestrian shape. This paper introduced a representative template generation method for a template matching based pedestrian detection system (PDS). Based on nonlinear manifold learning and clustering, the new approach can generate a suitable representative template subset from a large amount of original templates. First, an improved nonlinear dimensionality reduction method was proposed to map original templates to feature vectors (points) in the low-dimensional embedding space; Second, representative points were generated in the embedding space by clustering; At the end, corresponding representative template set were synthesized by mapping inversely the newly generated points from the embedding space to the visual input space. The experimental results showed that the template generation method speeds up detection procedure without considerable loss of performance.
关键词	Representative Template Set / Pedestrian Detection / Template Matching
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12815
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
通讯作者	Wu, Pei
作者单位	Univ Sci & Technol China, Key Lab Software Comp & Commun
推荐引用方式 GB/T 7714	Wu, Pei,Cao, Xian-Bin,Xu, Yan-Wu,et al. Representative Template Set Generation Method for Pedestrian Detection[C],2008.