Active Crowd Analysis for Pandemic Risk Mitigation for Blind or Visually Impaired Persons

During pandemics like COVID-19, social distancing is essential to combat the rise of infections. However, it is challenging for the visually impaired to practice social distancing as their low vision hinders them from maintaining a safe physical distance from other humans. In this paper, we propose a smartphone-based computationally-efficient deep neural network to detect crowds and relay the associated risks to the Blind or Visually Impaired (BVI) user through directional audio alerts. The system first detects humans and estimates their distances from the smartphone’s monocular camera feed. Then, the system clusters humans into crowds to generate density and distance maps from the crowd centers. Finally, the system tracks detections in previous frames creating motion maps predicting the motion of crowds to generate an appropriate audio alert. Active Crowd Analysis is designed for real-time smartphone use, utilizing the phone’s native hardware to ensure the BVI can safely maintain social distancing.