Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li
Pedestrian detection in crowded scenes is a challenging problem since the pedestrians often gather together and occlude each other. In this paper, we propose a new occlusion-aware R-CNN (OR-CNN) to improve the detection accuracy in the crowd. Specifically, we design a new aggregation loss to enforce proposals to be close and locate compactly to the corresponding objects. Meanwhile, we use a new part occlusion-aware region of interest (PORoI) pooling unit to replace the RoI pooling layer in order to integrate the prior structure information of human body with visibility prediction into the network to handle occlusion. Our detector is trained in an end-to-end fashion, which achieves state-of-the-art results on three pedestrian detection datasets, i.e., CityPersons, ETH, and INRIA, and performs on-pair with the state-of-the-arts on Caltech.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Autonomous Vehicles | Caltech | Reasonable Miss Rate | 4.1 | OR-CNN + CityPersons dataset |
| Autonomous Vehicles | CityPersons | Bare MR^-2 | 6.7 | OR-CNN |
| Autonomous Vehicles | CityPersons | Heavy MR^-2 | 55.7 | OR-CNN |
| Autonomous Vehicles | CityPersons | Partial MR^-2 | 15.3 | OR-CNN |
| Autonomous Vehicles | CityPersons | Reasonable MR^-2 | 12.8 | OR-CNN |
| Pedestrian Detection | Caltech | Reasonable Miss Rate | 4.1 | OR-CNN + CityPersons dataset |
| Pedestrian Detection | CityPersons | Bare MR^-2 | 6.7 | OR-CNN |
| Pedestrian Detection | CityPersons | Heavy MR^-2 | 55.7 | OR-CNN |
| Pedestrian Detection | CityPersons | Partial MR^-2 | 15.3 | OR-CNN |
| Pedestrian Detection | CityPersons | Reasonable MR^-2 | 12.8 | OR-CNN |