Saved in:
Bibliographic Details
Main Authors: Wu, Zewei, Wang, Longhao, Wang, Cui, Teixeira, César, Ke, Wei, Xiong, Zhang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.05172
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916885096824832
author Wu, Zewei
Wang, Longhao
Wang, Cui
Teixeira, César
Ke, Wei
Xiong, Zhang
author_facet Wu, Zewei
Wang, Longhao
Wang, Cui
Teixeira, César
Ke, Wei
Xiong, Zhang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05172
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering
Wu, Zewei
Wang, Longhao
Wang, Cui
Teixeira, César
Ke, Wei
Xiong, Zhang
Computer Vision and Pattern Recognition
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.
title Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.05172