Introduction Multi-object tracking (MOT) is a task in which an algorithm must detect and track multiple objects in a video. Most known algorithms are based on using simple detectors (e.g. YOLO) designed for processing individual images. The overall method involves separately using a detector on consecutive video frames and then matching the corresponding bounding boxes […] The post The Hungarian Algorithm and Its Applications in Computer Vision appeared first on Towards Data Science.
Original: https://towardsdatascience.com/hungarian-algorithm-and-its-applications-in-computer-vision/