Mesh-SORT: Simple and effective location-wise tracker with lost management strategies

TL;DR

Mesh-SORT introduces a location-aware tracking method that improves multi-object tracking accuracy by managing detection errors and occlusions through a novel mesh-based approach, showing significant performance gains on MOT17 datasets.

Contribution

The paper presents a new location-wise sub-region recognition method and loss management strategies that enhance tracking robustness against detection noise and occlusions.

Findings

3% reduction in fragmentation

7.2% decrease in ID switches

0.4% improvement in MOTA on MOT17

Abstract

Multi-Object Tracking (MOT) has gained extensive attention in recent years due to its potential applications in traffic and pedestrian detection. We note that tracking by detection may suffer from errors generated by noise detectors, such as an imprecise bounding box before the occlusions, and observed that in most tracking scenarios, objects tend to move and lost within specific locations. To counter this, we present a novel tracker to deal with the bad detector and occlusions. Firstly, we proposed a location-wise sub-region recognition method which equally divided the frame, which we called mesh. Then we proposed corresponding location-wise loss management strategies and different matching strategies. The resulting Mesh-SORT, ablation studies demonstrate its effectiveness and made 3% fragmentation 7.2% ID switches drop and 0.4% MOTA improvement compared to the baseline on MOT17 datasets. Finally, we analyze its limitation on the specific scene and discussed what future works can be extended.