Towards enforcing social distancing regulations with occlusion-aware crowd detection

In this paper, we present a video analysis method that automatically detects crowds violating social distancing regulations in public spaces, which is widely accepted to be essential to minimise the spreading of COVID-19. While various approaches have been published online to tackle this problem, our work presents a systematic study with comprehensive quantitative analysis of different deep learning models on multiple datasets. We experimented with two types of one-stage pedestrian detection models and further optimised their performance with a repulsion loss to address occlusions in crowds. We also propose a distance computation technique with locally adaptive threshold to approximate the actual spatial distance between pedestrians in the real world. In addition, since there is no existing dataset providing ground truth annotations of distances, we manually annotated three public datasets with such information to perform quantitative evaluation of our crowd detection method. Our comprehensive evaluation shows that our method achieves good detection performance with improvement provided by repulsion loss. Our code and ground truth annotations can be obtained from https://github.com/thomascong121/SocialDistance.