Density-Aware Pedestrian Proposal Networks for Robust People Detection in Crowded Scenes

Sangdoo Yun, Kimin Yun, Jongwon Choi, Jin Young Choi

Abstract: In this paper, we propose a density-aware pedestrian proposal network (DAPPN) for robust people detection in crowded scenes. Conventional pedestrian detectors and object proposal algorithms easily fail to find people in crowded scenes because of severe occlusions among people. Our method utilizes a crowd density map to resolve the occlusion problem. The proposed network is composed of two networks: the proposal network and the selection network. First, the proposal network predicts the initial pedestrian detection proposals and the crowd density map. After that, the selection network selectively picks the final proposals by considering the initial proposals and the crowd density. To validate the performance of the proposed method, experiments are conducted on crowd-scene datasets: WorldExpo10 and PETS2009. The experimental results show that our method outperforms the conventional method and achieves near real-time speed on a GPU (25 fps).