Single-Pedestrian Detection Aided by Two-Pedestrian Detection.

Wanli Ouyang, Xingyu Zeng, Xiaogang Wang

Abstract: In this paper, we address the challenging problem of detecting pedestrians who appear in groups. A new approach is proposed for single-pedestrian detection aided by two-pedestrian detection. A mixture model of two-pedestrian detectors is designed to capture the unique visual cues which are formed by nearby 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 two-pedestrian detectors, and to refine the single-pedestrian detection result using two-pedestrian detection. The two-pedestrian detector can integrate with any single-pedestrian detector. Twenty-five state-of-the-art single-pedestrian detection approaches are combined with the two-pedestrian detector on three widely used public datasets: Caltech, TUD-Brussels, and ETH. Experimental results show that our framework improves all these approaches. The average improvement is <inline-formula><tex-math>$9$</tex-math></inline-formula> percent on the Caltech-Test dataset, <inline-formula><tex-math>$11$</tex-math></inline-formula> percent on the TUD-Brussels dataset and <inline-formula><tex-math>$17$</tex-math> </inline-formula> percent on the ETH dataset in terms of average miss rate. The lowest average miss rate is reduced from <inline-formula><tex-math>$37$ </tex-math></inline-formula> to percent on the Caltech-Test dataset, from <inline-formula><tex-math>$55$</tex-math></inline-formula> to <inline-formula><tex-math>$50$</tex-math></inline-formula> percent on the TUD-Brussels dataset and from <inline-formula><tex-math>$43$</tex-math> </inline-formula> to <inline-formula> <tex-math>$38$</tex-math> </inline-formula> percent on the ETH dataset.