Repulsion Loss: Detecting Pedestrians in a Crowd
Top Cited Papers
- 1 June 2018
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7774-7783
- https://doi.org/10.1109/cvpr.2018.00811
Abstract
Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians often gather together and occlude each other in real-world scenarios. In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem. Then, we propose a novel bounding box regression loss specifically designed for crowd scenes, termed repulsion loss. This loss is driven by two motivations: the attraction by target, and the repulsion by other surrounding objects. The repulsion term prevents the proposal from shifting to surrounding objects thus leading to more crowd-robust localization. Our detector trained by repulsion loss outperforms the state-of-the-art methods with a significant improvement in occlusion cases.Keywords
This publication has 26 references indexed in Scilit:
- Deep Learning Strong Parts for Pedestrian DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Fast R-CNNPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Convolutional Channel FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Filtered channel features for pedestrian detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Taking a deeper look at pedestriansPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Fast Feature Pyramids for Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- A discriminative deep model for pedestrian detection with occlusion handlingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Discriminative Models for Multi-Class Object LayoutInternational Journal of Computer Vision, 2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009