QQ客服 官方微博 反馈留言

	Pedestrian Parsing via Deep Decompositional Network
	Ping Luo; Xiaogang Wang; Xiaoou Tang
	2013
会议名称	2013 14th IEEE International Conference on Computer Vision, ICCV 2013
会议地点	Sydney, NSW, Australia
英文摘要	We propose a new Deep Decompositional Network (DDN) for parsing pedestrian images into semantic regions, such as hair, head, body, arms, and legs, where the pedestrians can be heavily occluded. Unlike existing methods based on template matching or Bayesian inference, our approach directly maps low-level visual features to the label maps of body parts with DDN, which is able to accurately estimate complex pose variations with good robustness to occlusions and background clutters. DDN jointly estimates occluded regions and segments body parts by stacking three types of hidden layers: occlusion estimation layers, completion layers, and decomposition layers. The occlusion estimation layers estimate a binary mask, indicating which part of a pedestrian is invisible. The completion layers synthesize low-level features of the invisible part from the original features and the occlusion mask. The decomposition layers directly transform the synthesized visual features to label maps. We devise a new strategy to pre-train these hidden layers, and then fine-tune the entire network using the stochastic gradient descent. Experimental results show that our approach achieves better segmentation accuracy than the state-of-the-art methods on pedestrian images with or without occlusions. Another important contribution of this paper is that it provides a large scale benchmark human parsing dataset that includes 3,673 annotated samples collected from 171 surveillance videos. It is 20 times larger than existing public datasets.
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/172644/4501]
专题	深圳先进技术研究院_集成所
作者单位	2013
推荐引用方式 GB/T 7714	Ping Luo,Xiaogang Wang,Xiaoou Tang. Pedestrian Parsing via Deep Decompositional Network[C]. 见:2013 14th IEEE International Conference on Computer Vision, ICCV 2013. Sydney, NSW, Australia.

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。