StrongSORT: Make DeepSORT Great Again

TL;DR

StrongSORT significantly enhances DeepSORT for multi-object tracking by improving detection, embedding, and association, and introduces lightweight algorithms AFLink and GSI to address missing data issues, achieving state-of-the-art results.

Contribution

The paper presents StrongSORT, a robust baseline for MOT, and introduces AFLink and GSI algorithms that improve association and detection with minimal computational overhead.

Findings

Achieves state-of-the-art results on MOT17, MOT20, DanceTrack, and KITTI benchmarks.

Provides a lightweight, plug-and-play solution for missing association and detection problems.

Demonstrates improved speed-accuracy trade-offs in multi-object tracking.

Abstract

Recently, Multi-Object Tracking (MOT) has attracted rising attention, and accordingly, remarkable progresses have been achieved. However, the existing methods tend to use various basic models (e.g, detector and embedding model), and different training or inference tricks, etc. As a result, the construction of a good baseline for a fair comparison is essential. In this paper, a classic tracker, i.e., DeepSORT, is first revisited, and then is significantly improved from multiple perspectives such as object detection, feature embedding, and trajectory association. The proposed tracker, named StrongSORT, contributes a strong and fair baseline for the MOT community. Moreover, two lightweight and plug-and-play algorithms are proposed to address two inherent "missing" problems of MOT: missing association and missing detection. Specifically, unlike most methods, which associate short tracklets into complete trajectories at high computation complexity, we propose an appearance-free link model (AFLink) to perform global association without appearance information, and achieve a good balance between speed and accuracy. Furthermore, we propose a Gaussian-smoothed interpolation (GSI) based on Gaussian process regression to relieve the missing detection. AFLink and GSI can be easily plugged into various trackers with a negligible extra computational cost (1.7 ms and 7.1 ms per image, respectively, on MOT17). Finally, by fusing StrongSORT with AFLink and GSI, the final tracker (StrongSORT++) achieves state-of-the-art results on multiple public benchmarks, i.e., MOT17, MOT20, DanceTrack and KITTI. Codes are available at https://github.com/dyhBUPT/StrongSORT and https://github.com/open-mmlab/mmtracking.