Single-Pedestrian Detection Aided by Multi-pedestrian Detection

• Published in: 2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 3198 - 3205
• Main Authors: Wanli Ouyang, Xiaogang Wang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2013
• Subjects: Context; deformable model; Deformable models; Detectors; Feature extraction; human detection; object detection; part based model; Pedestrian Detection; Training; Training data; Visualization
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2013.411

In this paper, we address the challenging problem of detecting pedestrians who appear in groups and have interaction. A new approach is proposed for single-pedestrian detection aided by multi-pedestrian detection. A mixture model of multi-pedestrian detectors is designed to capture the unique visual cues which are formed by nearby multiple pedestrians but cannot be captured by single-pedestrian detectors. A probabilistic framework is proposed to model the relationship between the configurations estimated by single-and multi-pedestrian detectors, and to refine the single-pedestrian detection result with multi-pedestrian detection. It can integrate with any single-pedestrian detector without significantly increasing the computation load. 15 state-of-the-art single-pedestrian detection approaches are investigated on three widely used public datasets: Caltech, TUD-Brussels and ETH. Experimental results show that our framework significantly improves all these approaches. The average improvement is 9% on the Caltech-Test dataset, 11% on the TUD-Brussels dataset and 17% on the ETH dataset in terms of average miss rate. The lowest average miss rate is reduced from 48% to 43% on the Caltech-Test dataset, from 55% to 50% on the TUD-Brussels dataset and from 51% to 41% on the ETH dataset.