Modeling Mutual Visibility Relationship in Pedestrian Detection

• Published in: 2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 3222 - 3229
• Main Authors: Wanli Ouyang, Xingyu Zeng, Xiaogang Wang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2013
• Subjects: Computational modeling; Data models; deep; deep belief net; deep learning; deep model; Detectors; Estimation; Face recognition; human detection; object detection; part based model; Pedestrian Detection; Training; Training data
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2013.414

Detecting pedestrians in cluttered scenes is a challenging problem in computer vision. The difficulty is added when several pedestrians overlap in images and occlude each other. We observe, however, that the occlusion/visibility statuses of overlapping pedestrians provide useful mutual relationship for visibility estimation - the visibility estimation of one pedestrian facilitates the visibility estimation of another. In this paper, we propose a mutual visibility deep model that jointly estimates the visibility statuses of overlapping pedestrians. The visibility relationship among pedestrians is learned from the deep model for recognizing co-existing pedestrians. Experimental results show that the mutual visibility deep model effectively improves the pedestrian detection results. Compared with existing image-based pedestrian detection approaches, our approach has the lowest average miss rate on the Caltech-Train dataset, the Caltech-Test dataset and the ETH dataset. Including mutual visibility leads to 4% - 8% improvements on multiple benchmark datasets.