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.

翻译：近年来，多目标跟踪（MOT）吸引了越来越多的关注，并取得了显著进展。然而，现有方法往往使用不同的基础模型（如检测器和嵌入模型）以及各种训练或推理技巧等。因此，构建一个用于公平比较的良好基线至关重要。本文首先重新审视了经典跟踪器DeepSORT，然后从目标检测、特征嵌入和轨迹关联等多个角度对其进行了显著改进。提出的跟踪器名为StrongSORT，为MOT社区贡献了一个强大且公平的基线。此外，我们提出了两种轻量级且即插即用的算法，以解决MOT中两个固有的“缺失”问题：缺失关联和缺失检测。具体而言，与大多数以高计算复杂度将短轨迹关联成完整轨迹的方法不同，我们提出了一种无外观特征的链接模型（AFLink），在不使用外观信息的情况下执行全局关联，并在速度和精度之间实现了良好平衡。此外，基于高斯过程回归，我们提出了一种高斯平滑插值方法（GSI）来缓解缺失检测问题。AFLink和GSI可轻松嵌入到各种跟踪器中，且仅带来极小的额外计算开销（在MOT17上，每张图像分别增加1.7 ms和7.1 ms）。最后，通过将StrongSORT与AFLink和GSI融合，最终的跟踪器（StrongSORT++）在多个公开基准测试上（即MOT17、MOT20、DanceTrack和KITTI）取得了最先进的结果。代码可在 https://github.com/dyhBUPT/StrongSORT 和 https://github.com/open-mmlab/mmtracking 获取。