Monitoring Social-distance in Wide Areas during Pandemics: a Density Map and Segmentation Approach
This work addresses the need for automated monitoring of social distancing in public spaces during pandemics, offering a solution for wide areas where existing methods are limited, though it is incremental in improving detection under occlusion.
The paper tackles the problem of monitoring social distancing in crowded wide areas with occlusions by proposing a new deep learning framework that uses density maps and segmentation to detect violations. The framework performs well on PET2009 and CityStreet datasets, effectively identifying zones where people are not following social distancing even under heavy occlusion or at a distance.
With the relaxation of the containment measurements around the globe, monitoring the social distancing in crowded public places is of grate importance to prevent a new massive wave of COVID-19 infections. Recent works in that matter have limited themselves by detecting social distancing in corridors up to small crowds by detecting each person individually considering the full body in the image. In this work, we propose a new framework for monitoring the social-distance using end-to-end Deep Learning, to detect crowds violating the social-distance in wide areas where important occlusions may be present. Our framework consists in the creation of a new ground truth based on the ground truth density maps and the proposal of two different solutions, a density-map-based and a segmentation-based, to detect the crowds violating the social-distance constrain. We assess the results of both approaches by using the generated ground truth from the PET2009 and CityStreet datasets. We show that our framework performs well at providing the zones where people are not following the social-distance even when heavily occluded or far away from one camera.