Skip to content

A real-time social distancing monitoring system is developed. The video footage uses a mono camera setup and the object detection step is improved in crowded settings using the soft NMS approach to suppress bounding boxes in the YOLO algorithm.

Notifications You must be signed in to change notification settings

Pratyay211/Social-distance-monitoring

Repository files navigation

Social-distance-monitoring

In this project, we present a real-time system for social distancing monitoring in public places. We use a mono camera setup that only provides the spatial coordinates of objects to the monitoring system. The You Only Look Once (YOLO) algorithm is used for object detection. We improve the YOLO algorithm by implementing the soft-non-maximum supression (soft NMS) algorithm over the usual NMS approach for enhanced bounding box suppression. The overall monitoring system is demonstrated to be suitable for monitoring social distancing in public places using video surveillance camera.

Output

Output

Paper

Contacts:

About

A real-time social distancing monitoring system is developed. The video footage uses a mono camera setup and the object detection step is improved in crowded settings using the soft NMS approach to suppress bounding boxes in the YOLO algorithm.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published