Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering

TL;DR

This paper introduces a novel multi-tracklet tracking framework that adaptively clusters detections into robust tracklets and improves long-term association for generic targets, addressing challenges like low-confidence detections and occlusions.

Contribution

The proposed Multi-Tracklet Tracking (MTT) framework integrates adaptive clustering and multi-clue association to enhance tracking robustness for unseen categories.

Findings

Demonstrates competitive performance on benchmark datasets.

Effectively handles low-confidence detections and occlusions.

Improves long-term tracking accuracy.

Abstract

Tracking specific targets, such as pedestrians and vehicles, has been the focus of recent vision-based multitarget tracking studies. However, in some real-world scenarios, unseen categories often challenge existing methods due to low-confidence detections, weak motion and appearance constraints, and long-term occlusions. To address these issues, this article proposes a tracklet-enhanced tracker called Multi-Tracklet Tracking (MTT) that integrates flexible tracklet generation into a multi-tracklet association framework. This framework first adaptively clusters the detection results according to their short-term spatio-temporal correlation into robust tracklets and then estimates the best tracklet partitions using multiple clues, such as location and appearance over time to mitigate error propagation in long-term association. Finally, extensive experiments on the benchmark for generic multiple object tracking demonstrate the competitiveness of the proposed framework.