Behavioural changes in open space during COVID-19 with deep learning-based video analytics

Abstract

While numerous studies have been done to examine the general trend of urban mobility during COVID-19, there is not enough research on changes in pedestrian behavioural characteristics and crowd dynamics in public space. Understanding and monitoring such changes are critical for the better management and design of public open space in case of future outbreaks of infectious diseases. To fill this gap, pedestrian movements are tracked and analysed with deep learning-based video analytics based on anonymized video footage along a major promenade in Hong Kong before and during COVID-19. Specifically, comparisons were made on pedestrian flow characteristics, pedestrian activities, and social distancing. Then, this study examines the dynamics of pedestrian crowding under different scenarios, using agent-based simulation. Model results suggest that the public space was characterized by fewer visitors, a higher average walking speed, a higher percentage of people exercising, and a lower percentage of people conducting stationary activities during COVID-19. In addition, a higher level of voluntary social distancing was observed. Several hotspots for pedestrian crowding were also identified. Learning from the above, it is suggested that multifunctional public space should be designed; and data-driven visitor management systems should be established to prepare for different scenarios in future cities.