Crowd density estimation is the task of determining the number or spatial distribution of people within a given area, typically expressed as a density map that encodes the concentration of individuals across a scene or environment. In the context of WiFi/CSI sensing, this problem is significant because it enables passive, non-intrusive monitoring of human occupancy without cameras or wearable devices, making it valuable for applications such as public safety, smart building management, and emergency response. Key variants of the problem include coarse-grained occupancy counting, which estimates total headcount within a region, and fine-grained density mapping, which localizes the spatial distribution of crowds at higher resolution.

Source Papers

  • A survey of recent advances in CNN-based single image crowd counting and density estimation — A survey of recent advances in CNN-based single image crowd
  • Physics of Human Crowds — Physics of Human Crowds
  • Recent trends in crowd analysis: A review — Recent trends in crowd analysis: A review