BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning
Not on the map. Why?
Abstract (arXiv)
Social distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas, with wide field-of-view cameras, is considered. A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify high-risk regions where social distancing is violated. BEV-Net combines detection of head and feet locations, camera pose estimation, a differentiable homography module to map image into BEV coordinates, and geometric reasoning to produce a BEV map of the people locations in the scene. Experiments on complex crowded scenes demonstrate the power of the approach and show superior performance over baselines derived from methods in the literature. Applications of interest for public health decision makers are finally discussed. Datasets, code and pretrained models are publicly available at GitHub.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 72 references that are in the map. First posted on arXiv 10 Oct 2021.
Builds on
29 of 72 references.
References · 29
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2017Mask R-CNNcited by 7,277
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
- 2015Fast R-CNNcited by 2,933
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
- 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
- 2017End-to-end Recovery of Human Shape and Posecited by 885
17 more
- 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
- 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
- 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
- 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 298
- 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
- 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 172
- 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 123
- 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 121
- 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
- 2016Hierarchical Deep Temporal Models for Group Activity Recognitioncited by 89
- 2020Recursive Social Behavior Graph for Trajectory Predictioncited by 66
- 2019Crowd Counting with Deep Structured Scale Integration Networkcited by 46
- 2017Context-Aware Trajectory Predictioncited by 31
- 2020Decentralized Privacy-Preserving Proximity Tracingcited by 5
- 2020Inter-Homines: Distance-Based Risk Estimation for Human Safetycited by 4
- 2016Fully Convolutional Crowd Counting On Highly Congested Scenescited by 2
Built on by
Not cited yet.