DocumentCode :
253728
Title :
Switchable Deep Network for Pedestrian Detection
Author :
Ping Luo ; Yonglong Tian ; Xiaogang Wang ; Xiaoou Tang
Author_Institution :
Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
fYear :
2014
fDate :
23-28 June 2014
Firstpage :
899
Lastpage :
906
Abstract :
In this paper, we propose a Switchable Deep Network (SDN) for pedestrian detection. The SDN automatically learns hierarchical features, salience maps, and mixture representations of different body parts. Pedestrian detection faces the challenges of background clutter and large variations of pedestrian appearance due to pose and viewpoint changes and other factors. One of our key contributions is to propose a Switchable Restricted Boltzmann Machine (SRBM) to explicitly model the complex mixture of visual variations at multiple levels. At the feature levels, it automatically estimates saliency maps for each test sample in order to separate background clutters from discriminative regions for pedestrian detection. At the part and body levels, it is able to infer the most appropriate template for the mixture models of each part and the whole body. We have devised a new generative algorithm to effectively pretrain the SDN and then fine-tune it with back-propagation. Our approach is evaluated on the Caltech and ETH datasets and achieves the state-of-the-art detection performance.
Keywords :
Boltzmann machines; clutter; image representation; mixture models; object detection; pedestrians; Caltech datasets; ETH datasets; SDN; SRBM; back-propagation; background clutter; complex visual variation mixture; discriminative regions; hierarchical feature learning; mixture body part representations; pedestrian appearance; pedestrian detection; salience map estimation; switchable deep network; switchable restricted Boltzmann machine; Clutter; Detectors; Feature extraction; Logistics; Switches; Training; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
Type :
conf
DOI :
10.1109/CVPR.2014.120
Filename :
6909515
Link To Document :
بازگشت