SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth
Exploring robust and efficient association methods has always been an important issue in multiple-object tracking (MOT). Although existing tracking methods have achieved impressive performance, congestion and frequent occlusions still pose challenging problems in multi-object tracking. We reveal that performing sparse decomposition on dense scenes is a crucial step to enhance the performance of associating occluded targets. To this end, we propose a pseudo-depth estimation method for obtaining the relative depth of targets from 2D images. Secondly, we design a depth cascading matching (DCM) algorithm, which can use the obtained depth information to convert a dense target set into multiple sparse target subsets and perform data association on these sparse target subsets in order from near to far. By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack. SparseTrack provides a new perspective for solving the challenging crowded scene MOT problem. Only using IoU matching, SparseTrack achieves comparable performance with the state-of-the-art (SOTA) methods on the MOT17 and MOT20 benchmarks. Code and models are publicly available at \url{https://github.com/hustvl/SparseTrack}.
PDF AbstractCode
Datasets
Results from the Paper
Ranked #1 on Multi-Object Tracking on MOT20 (using extra training data)
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
---|---|---|---|---|---|---|---|
Multi-Object Tracking | DanceTrack | SparseTrack | HOTA | 55.7 | # 17 | ||
DetA | 79.2 | # 16 | |||||
AssA | 39.3 | # 16 | |||||
MOTA | 91.3 | # 10 | |||||
IDF1 | 58.1 | # 16 | |||||
Multi-Object Tracking | MOT17 | SparseTrack | MOTA | 81.0 | # 2 | ||
IDF1 | 80.1 | # 6 | |||||
HOTA | 65.1 | # 4 | |||||
Multi-Object Tracking | MOT20 | SparseTrack | MOTA | 78.2 | # 1 | ||
IDF1 | 77.3 | # 6 | |||||
HOTA | 63.4 | # 3 |