Birds Eye View Social Distancing Analysis System

TL;DR

This paper presents B-SDA, a privacy-preserving bird's-eye view system that detects and analyzes social distancing behavior at traffic intersections using modified computer vision techniques, showing reduced violation rates during the pandemic.

Contribution

The paper introduces a novel bird's-eye view social distancing analysis system with tailored algorithms for small object detection and pedestrian grouping, suitable for real-world deployment.

Findings

Pedestrian detection achieved 63.0% AP50.

Tracking performance was 47.6% MOTA.

Social distancing violations decreased from 31.4% pre-pandemic to 15.6% during pandemic.

Abstract

Social distancing can reduce the infection rates in respiratory pandemics such as COVID-19. Traffic intersections are particularly suitable for monitoring and evaluation of social distancing behavior in metropolises. We propose and evaluate a privacy-preserving social distancing analysis system (B-SDA), which uses bird's-eye view video recordings of pedestrians who cross traffic intersections. We devise algorithms for video pre-processing, object detection and tracking which are rooted in the known computer-vision and deep learning techniques, but modified to address the problem of detecting very small objects/pedestrians captured by a highly elevated camera. We propose a method for incorporating pedestrian grouping for detection of social distancing violations. B-SDA is used to compare pedestrian behavior based on pre-pandemic and pandemic videos in a major metropolitan area. The accomplished pedestrian detection performance is $63.0\%$ $AP_{50}$ and the tracking performance is $47.6\%$ MOTA. The social distancing violation rate of $15.6\%$ during the pandemic is notably lower than $31.4\%$ pre-pandemic baseline, indicating that pedestrians followed CDC-prescribed social distancing recommendations. The proposed system is suitable for deployment in real-world applications.