Learning Mutual Visibility Relationship for Pedestrian Detection with a Deep Model.

Wanli Ouyang, Xingyu Zeng, Xiaogang Wang

Abstract: 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. Then the evidence of co-existing pedestrians is used for improving the single pedestrian detection results. Compared with existing image-based pedestrian detection approaches, our approach has the lowest average miss rate on the Caltech-Train dataset and the ETH dataset. Experimental results show that the mutual visibility deep model effectively improves the pedestrian detection results. The mutual visibility deep model leads to 6–15 % improvements on multiple benchmark datasets.