video1.0<iframe src="https://www.loom.com/embed/67e87037e4884eab8ab88ee5439de8d4" frameborder="0" width="1920" height="1440" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>14401920Loomhttps://www.loom.com14401920https://cdn.loom.com/sessions/thumbnails/67e87037e4884eab8ab88ee5439de8d4-d30053152225a22d.gif843.833333In this Loom, I walk you through my real time helmet violation and license plate recognition system. It processes video streams and live phone camera input using a multi stage pipeline, with FastAPI for the async backend and YOLO V8 for detection. I detect four classes, helmet, without helmet, rider, and number plate, then run PaddleOCR plus a regex validator for Indian plate formats, and store violations in files with confidence and timestamps while avoiding duplicates. I also show association logic to map plates to the correct rider and prevent false citations. No specific action was requested from viewers.