The latest articles on DEV Community by Qusai Onali (@qusaionali). https://dev.to/qusaionali https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F592965%2F321b3363-73d1-4176-8d76-f4145ee7a5b6.jpeg https://dev.to/qusaionali en Qusai Onali Tue, 09 Mar 2021 07:55:08 +0000 https://dev.to/qusaionali/socialdistancingmeasurer-498a https://dev.to/qusaionali/socialdistancingmeasurer-498a <p>Computer Vision and AI are used to detect if people are at a specific distance and adhere to social distancing or not.<br> 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.<br> Used CLAHE preprocessing algorithm for better detections.<br> Requirements Python 3.6, Opencv 4.2.0 or above numpy 1.14.5 and argparse<br> Weights not added for sizes you can download from this link: <a href="https://pjreddie.com/media/files/yolov3.weights">https://pjreddie.com/media/files/yolov3.weights</a><br> Image for post<br> Output<br> Image for post<br> You can find the source code on my GitHub account. (<a href="https://github.com/qusaionali/Social_Distancing">https://github.com/qusaionali/Social_Distancing</a>)</p>