Quantifying social distancing compliance and the effects of behavioral interventions using computer vision

• DOI: 10.1145/3459609.3460523
• Publication Date: 2021-05-17T14:53:07Z
• Authors: Derek Gloudemans; Nicole Gloudemans; Mark Abkowitz; William Barbour; Daniel B. Work
• Keywords: Social distance; Baseline (sea); Distancing; Pandemic

Social distancing has become a pressing and challenging issue during the Covid-19 pandemic. In smart cities context, it becomes possible to measure inter-personal distance using networked cameras computer vision analysis. We deploy pipeline based on Retinanet that identifies pedestrians in streaming video frames, then converts their positions GPS coordinates for calculation further This processing is applied nine camera streams at three locations from around Vanderbilt University. collect 70 hours of baseline data over course two weeks, after which time we small behavioral interventions aimed increasing compliance. Another with place will be analyzed against determine if they had an effect