Social Distancing detector
I was one of the three data scientist to be allotted the task of completing the use case of social distancing detector.
My colleagues are very knowledgeable and hardworking.
We used YOLOv5 algorithm for object detection as it gives acceptable accuracy.
The YOLO algorithms, unlike other algorithms, involve the splitting of the image into multiple cells and depending upon how many objects are covered in the image, multiple bounding boxes are predicted by each cell. This causes the creation of a large number of bounding boxes, and in this process, there may arise bounding boxes that do not contain any object at all or also intersected bounding boxes that share the same spaces of the image. To get rid of this issue, a non-max suppression technique is used wherein such shared spaces are nullified, and also
The Probability that there is an object in the bounding box, pc value is predicted to identify the boxes with no objects and ensure their removal.
We used this algorithm to detect people in each frame, calculate the distance between their bounding boxes. If the distance is below a certain threshold, the box around the pair of people turns red to indicate violation of social distancing.
In every other case, the bounding box remains green