Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd

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.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


Ranked #10 on Pedestrian Detection on Caltech (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Pedestrian Detection Caltech OR-CNN + CityPersons dataset Reasonable Miss Rate 4.1 # 10
Pedestrian Detection CityPersons OR-CNN Reasonable MR^-2 12.8 # 16
Heavy MR^-2 55.7 # 17
Partial MR^-2 15.3 # 9
Bare MR^-2 6.7 # 7

Methods


No methods listed for this paper. Add relevant methods here