Association Between Social Distancing Compliance and Public Place Crowding During the COVID-19 Pandemic: Cross-Sectional Observational Study Using Computer Vision to Analyze Surveillance Footage.

Background: Social distancing behavior has been a critical nonpharmaceutical measure for mitigating the COVID-19 pandemic. For this reason, there has been widespread interest in the factors determining social distancing violations, with a particular focus on individual-based factors. Objective: In this paper, we examine an alternative and less appreciated indicator of social distancing violations: the situational opportunity for maintaining interpersonal distance in crowded settings. This focus on situational opportunities is borrowed from criminology, where it offers an alternative to individual-based explanations of crime and rule violations. We extend this approach to the COVID-19 pandemic context, suggesting its relevance in understanding distancing compliance behavior. Methods: Our data comprise a large collection of video clips (n=56,429) from public places in Amsterdam, the Netherlands, captured by municipal surveillance cameras throughout the first year of the pandemic. We automatized the analysis of this footage using a computer vision algorithm designed for pedestrian detection and estimation of metric distances between individuals in the video still frames. This method allowed us to record social distancing violations of over half a million individuals (n=539,127) across more and less crowded street contexts. Results: The data revealed a clear positive association between crowding and social distancing violations, evident both at the individual level and when aggregated per still frame. At the individual level, the analysis estimated that each additional 10 people present increased the likelihood of a distancing violation by 9 percentage points for a given pedestrian. At the aggregated level, there was an estimated increase of approximately 6 additional violations for every 10 additional individuals present, with a very large R² of 0.80. Additionally, a comparison with simulation data indicated that street spaces should, in principle, provide sufficient room for people to pass each other while maintaining a 1.5-meter distance. This suggests that pedestrians tend to gravitate toward others, even when ample space exists to maintain distance. Conclusions: The direct positive relationship between crowding and distancing violations suggests that potential transmission encounters can be identified by simply counting the number of people present in a location. Our findings thus provide a reliable and scalable proxy measure of distancing noncompliance that offers epidemiologists a tool to easily incorporate real-life behavior into predictive models of airborne contagious diseases. Furthermore, our results highlight the need for scholars and public health agencies to consider the situational factors influencing social distancing violations, especially those related to crowding in public settings.