Multi-object Tracking with Tracked Object Bounding Box Association

TL;DR

This paper improves multi-object tracking by replacing the association method in CenterTrack with an IOU-based cost, significantly reducing identity switches and enhancing tracking accuracy.

Contribution

It introduces an IOU-based association method into CenterTrack, reducing identity switches and improving tracking performance.

Findings

Reduced identity switches by 22.6%.

Improved IDF1 score by 1.5%.

Enhanced tracking accuracy on MOT17 dataset.

Abstract

The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint detection and tracking method still suffers from high identity switches due to the inferior association method. To reduce the high number of identity switches and improve the tracking accuracy, in this paper, we propose to incorporate a simple tracked object bounding box and overlapping prediction based on the current frame onto the CenterTrack algorithm. Specifically, we propose an Intersection over Union (IOU) distance cost matrix in the association step instead of simple point displacement distance. We evaluate our proposed tracker on the MOT17 test dataset, showing that our proposed method can reduce identity switches significantly by 22.6% and obtain a notable improvement of 1.5% in IDF1 compared to the original CenterTrack's under the same tracklet lifetime. The source code is released at https://github.com/Nanyangny/CenterTrack-IOU.