Multi-target Tracking Algorithm SORT

Simple Online and Realtime Tracking (SORT) is a practical multi-target tracking method that focuses on simple and efficient algorithms. It was proposed by researchers from Queensland University of Technology and the University of Sydney at the 2016 IEEE International Conference on Image Processing (ICIP). The SORT algorithm uses target detection results, combined with Kalman filtering and the Hungarian algorithm to achieve object association and tracking between video frames. A notable feature of SORT is that it does not require the use of appearance features within the detection box, but only associates objects in the previous and next frames based on the position and size of the bounding box.