EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hierarchical Multi-Prototype Appearance Memory: A Plug-and-Play Module for Identity-Stable Online Multi-Object Tracking

Wenning Zhang, Mintao Liu, Yangjie Cao, Jihao Cai, Chao Wang, Huili Xia, Kunming Xu

Electronics · 29.05.2026 · 15 (11) · 2357

DOI: 10.3390/electronics15112357 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 29.05.2026. Verfasst von Wenning Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Henan Province Science and Technology Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Online multi-object tracking (MOT) aims to maintain consistent target identities across video frames, yet it remains vulnerable to identity switches under occlusion and appearance variation. Many existing trackers rely on single-prototype exponential moving average (EMA) memory, which is efficient but prone to contamination, over-smoothing, and staleness. To address this issue, we propose Hierarchical Multi-Prototype Appearance Memory (HMP), a plug-and-play module for online MOT. HMP separates stable long-term identity anchors from short-term transitional evidence through a multi-prototype long-term memory and a short first-in-first-out (FIFO) queue. A unified joint reliability score governs memory writing and maintenance, and a frozen two-stage association strategy first performs stable primary matching and then allows conservative short-term recovery only on residual cases. Experiments on MOT17 and MOT20 show that HMP improves identity continuity while preserving competitive overall tracking quality. Controlled ablations further support the effectiveness of the proposed memory representation, reliability control, and staged evidence usage under fixed upstream modules.

Förderung

  • Henan Province Science and Technology Research Project

Zitieren

APA

Zhang, W., Liu, M., Cao, Y., Cai, J., Wang, C., Xia, H., & Xu, K. (2026). Hierarchical Multi-Prototype Appearance Memory: A Plug-and-Play Module for Identity-Stable Online Multi-Object Tracking. Electronics, 15(11), 2357. https://doi.org/10.3390/electronics15112357

Vancouver

Zhang W, Liu M, Cao Y, Cai J, Wang C, Xia H, et al. Hierarchical Multi-Prototype Appearance Memory: A Plug-and-Play Module for Identity-Stable Online Multi-Object Tracking. Electronics. 2026;15(11):2357. doi:10.3390/electronics15112357

BibTeX
@article{Zhang2026,
  author = {Zhang, Wenning and Liu, Mintao and Cao, Yangjie and Cai, Jihao and Wang, Chao and Xia, Huili and Xu, Kunming},
  title = {Hierarchical Multi-Prototype Appearance Memory: A Plug-and-Play Module for Identity-Stable Online Multi-Object Tracking},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {2357},
  doi = {10.3390/electronics15112357}
}
Kostenlos starten →