QQ客服 官方微博 反馈留言

	A monocular human detection system based on eoh and oriented lbp features
	Ma yingdong; Chen xiankai; Jin liu; Chen George
	2011
会议名称	7th International Symposium on Visual Computing
会议地点	Las Vegas,USA
英文摘要	This work introduces a fast pedestrian detection method that detects humans based on the boosted cascade approach using an on-board monocular camera. The Edge Orientation Histogram (EOH) feature and a novel Oriented Local Binary Patterns (Oriented LBP) feature are used in this system. Combination of these features captures salient features of humans and, together with a rejection cascade, achieves an efficient and accurate pedestrian detection system. Temporal coherence condition is employed to reject false positives from detection results. For a video sequence with resolution of 320×240 pixels, experiment results demonstrate that the proposed approach runs at about 16 frames/second, while maintaining an detection rate similar to existing methods. © 2011 Springer-Verlag.(27 refs)
收录类别	EI
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/3633]
专题	深圳先进技术研究院_数字所
作者单位	2011
推荐引用方式 GB/T 7714	Ma yingdong,Chen xiankai,Jin liu,et al. A monocular human detection system based on eoh and oriented lbp features[C]. 见:7th International Symposium on Visual Computing. Las Vegas,USA.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。