TrackRefine: A Plug-and-Play Decoupled Enhancement Framework for Online Multi-Object Tracking and Segmentation
Sensors · 10.06.2026 · 26 (12) · 3696
DOI: 10.3390/s26123696 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.06.2026. Verfasst von Longfei Qie und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Nova Program.
Abstract (Originalsprache)
Multi-object tracking and segmentation (MOTS) aims to jointly perform pixel-level instance segmentation and temporal identity association for multiple objects in video sequences. Existing online decoupled MOTS methods face several challenges in complex scenarios, including limited front-end mask quality, corruption of memory representations under prolonged occlusion, and unstable data association and trajectory recovery. To address these limitations, we propose TrackRefine, a plug-and-play decoupled enhancement framework. TrackRefine enhances overall performance through back-end refinement without modifying the architecture of the front-end instance segmenter or relying on additional end-to-end joint training. Specifically, we introduce a lightweight Fast GrabCut-based mask refinement module to optimize mask boundaries, a multimodal long-short-term memory bank that integrates appearance, semantic, and shape cues for identity modeling, and a progressive three-stage association strategy for stable matching and long-term trajectory recovery. Experimental results on MOTS20 show that TrackRefine achieves 69.4 sMOTSA, 82.7 MOTSA, and 478 Frag. Experimental results on KITTI MOTS show that it achieves 62.4/73.7 sMOTSA and 78.0/85.4 MOTSA for pedestrians and cars, respectively. Extensive experiments with different front-end instance segmenters verify its plug-and-play flexibility and decoupled design, while ablation studies confirm the effectiveness of each core module. These results show that TrackRefine provides an efficient and practical solution for online MOTS in complex scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing 100029, China.
- College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China.
ORCID-Profile: Jiakui Tang
Förderung
- Beijing Nova Program
Zitieren
APA
Qie, L., Chai, C., Wang, R., Bi, C., Ma, R., Zhang, A., & Tang, J. (2026). TrackRefine: A Plug-and-Play Decoupled Enhancement Framework for Online Multi-Object Tracking and Segmentation. Sensors, 26(12), 3696. https://doi.org/10.3390/s26123696
Vancouver
Qie L, Chai C, Wang R, Bi C, Ma R, Zhang A, et al. TrackRefine: A Plug-and-Play Decoupled Enhancement Framework for Online Multi-Object Tracking and Segmentation. Sensors. 2026;26(12):3696. doi:10.3390/s26123696
BibTeX
@article{Qie2026,
author = {Qie, Longfei and Chai, Chunlei and Wang, Ruixue and Bi, Chao and Ma, Ruiqi and Zhang, Aijun and Tang, Jiakui},
title = {TrackRefine: A Plug-and-Play Decoupled Enhancement Framework for Online Multi-Object Tracking and Segmentation},
journal = {Sensors},
year = {2026},
volume = {26},
number = {12},
pages = {3696},
doi = {10.3390/s26123696}
}
EUVIMED