Multi-Vehicle Tracking and Speed Estimation Model using Deep Learning

Abstract

Speed estimation of vehicles is one of the prime application of speed estimation of moving objects. The YOLOv5 model has proven to have a very good accuracy in detecting moving objects in real-time. The vehicles on the road are extracted from each frame of the video by running it through a custom YOLOv5 object detector. The YOLO model splits the frame into a grid and each grid detects a vehicle within itself. An instance identifier tracks the vehicle across the frames. The tracking algorithm computes deep features for every bounding box and utilizes the similarities within the deep features to identify and track the object. The pixel per meter metric has to adjusted based on perspective after which the speed of the vehicle can be estimated. Finally a comparison of our model metrics with the existing state of the art models is provided.