Estimating Distances Between People using a Single Overhead Fisheye Camera with Application to Social-Distancing Oversight
This addresses the need for pandemic oversight by providing a practical tool for social-distancing monitoring, though it is incremental as it builds on existing camera-based methods with a new camera type.
The paper tackled the problem of unobtrusively monitoring distances between people indoors using a single overhead fisheye camera, achieving 1-2 ft distance error and over 95% accuracy in detecting social-distancing violations.
Unobtrusive monitoring of distances between people indoors is a useful tool in the fight against pandemics. A natural resource to accomplish this are surveillance cameras. Unlike previous distance estimation methods, we use a single, overhead, fisheye camera with wide area coverage and propose two approaches. One method leverages a geometric model of the fisheye lens, whereas the other method uses a neural network to predict the 3D-world distance from people-locations in a fisheye image. To evaluate our algorithms, we collected a first-of-its-kind dataset using single fisheye camera, that comprises a wide range of distances between people (1-58 ft) and will be made publicly available. The algorithms achieve 1-2 ft distance error and over 95% accuracy in detecting social-distance violations.