EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Composite Augmentation and Feature Integration Reconstruction for Occluded Person Re-Identification

Hao Tie, Chentao Hu, Yibo Chen, Lingbing Tao, Yanbing Chen iD

Sensors · 15.05.2026 · 26 (10) · 3114

DOI: 10.3390/s26103114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.05.2026. Verfasst von Hao Tie und 4 weiteren Autor:innen. Beteiligte Einrichtung: Keyi College, Zhejiang Sci-Tech University, Shaoxing 312369, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most existing occluded person re-identification (Re-ID) methods rely on external cues to separate the visible parts of the person from the occluded regions, aiming to achieve alignment based on visible body parts. However, such methods often overlook the complexity of different occlusion scenarios. Moreover, there exists a severe imbalance between the training and testing sets in current occlusion datasets, which further undermines the model’s generalization ability. In this paper, we propose a method named Composite Augmentation and Feature Integration Reconstruction For Occluded Person Re-Identification. Firstly, a Composite Data Augmentation Module is designed to increase the number of occluded samples in the training set, thus alleviating data imbalance. Next, a feature interaction module is introduced to perform bidirectional interactions between global and local features, which helps reduce the impact of occlusion-induced noise and feature redundancy in complex scenes, thereby improving feature representation efficiency. Finally, a Feature Reconstruction Module retrieves the top-k nearest neighbor images from the gallery to reconstruct the occluded body parts, enabling more complete person matching. Experimental results on five challenging occlusion datasets demonstrate that the proposed method achieves superior performance.

Schlagwörter

Stichwörter der Autor:innen

data augmentationfeature interactionfeature reconstructionoccluded person re-idvision transformer

Autor:innen und Institutionen

  • Keyi College, Zhejiang Sci-Tech University, Shaoxing 312369, China.
  • School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China.

ORCID-Profile: Yanbing Chen

Zitieren

APA

Tie, H., Hu, C., Chen, Y., Tao, L., & Chen, Y. (2026). Composite Augmentation and Feature Integration Reconstruction for Occluded Person Re-Identification. Sensors, 26(10), 3114. https://doi.org/10.3390/s26103114

Vancouver

Tie H, Hu C, Chen Y, Tao L, Chen Y. Composite Augmentation and Feature Integration Reconstruction for Occluded Person Re-Identification. Sensors. 2026;26(10):3114. doi:10.3390/s26103114

BibTeX
@article{Tie2026,
  author = {Tie, Hao and Hu, Chentao and Chen, Yibo and Tao, Lingbing and Chen, Yanbing},
  title = {Composite Augmentation and Feature Integration Reconstruction for Occluded Person Re-Identification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3114},
  doi = {10.3390/s26103114}
}
Kostenlos starten →