Computer Vision and AI are used to detect if people are at a specific distance and adhere to social distancing or not.
This algorithm estimates the social distance between humans. Social distancing is very important for protecting against COVID-19. We must follow the rules for our health. This algorithm created for analyzing social distancing rules. The algorithm calculates the distance between humans. Distance is bounded by 180 centimetres. If humans close each other fewer than 150 cm, you can see humans in the red bounding box. Otherwise, between 150–180, you can see humans in the yellow bounding box. Others safe zone in the green bounding box. This algorithm uses YOLO-v3 for human detection.
Used CLAHE preprocessing algorithm for better detections.
Requirements Python 3.6, Opencv 4.2.0 or above numpy 1.14.5 and argparse
Weights not added for sizes you can download from this link: https://pjreddie.com/media/files/yolov3.weights
Image for post
Output
Image for post
You can find the source code on my GitHub account. (https://github.com/qusaionali/Social_Distancing)
For further actions, you may consider blocking this person and/or reporting abuse
Top comments (0)