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

Abstract

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.

arXiv commentAccepted by ECCV 2018

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• YOLO9000: Better, Faster, Stronger
• CityPersons: A Diverse Dataset for Pedestrian Detection
• Learning Complexity-Aware Cascades for Deep Pedestrian Detection
• Filtered Channel Features for Pedestrian Detection
• FaceBoxes: A CPU Real-time Face Detector with High Accuracy
• Repulsion Loss: Detecting Pedestrians in a Crowd

Cited by in corpus (7)

• Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
• PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
• Robust Object Detection under Occlusion with Context-Aware CompositionalNets
• Semantic Head Enhanced Pedestrian Detection in a Crowd
• Attribute-aware Pedestrian Detection in a Crowd
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• Occluded Pedestrian Detection with Visible IoU and Box Sign Predictor