Pedestrian Parsing via Deep Decompositional Network
Refereed conference paper presented and published in conference proceedings


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(1) that includes 3, 673 annotated samples collected from 171 surveillance videos. It is 20 times larger than existing public datasets.
著者Luo P, Wang XG, Tang XO
會議名稱IEEE International Conference on Computer Vision (ICCV)
詳細描述organized by Larry Davis, Richard Hartley,
頁次2648 - 2655
Web of Science 學科類別Computer Science; Computer Science, Artificial Intelligence

上次更新時間 2021-09-01 於 00:56