AAGNet: Attribute-Aware Graph-Based Network for Occluded Pedestrian Re-Identification
IEEE Transactions on Consumer Electronics · 2024-11 · 70 (4) · 6580-6588
DOI: 10.1109/tce.2024.3453890 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2024-11. Verfasst von Shihong Yao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Central China Normal University, Open Fund of National Engineering Research Center of Geographic Information System, China University of Geosciences.
Abstract (Originalsprache)
In large consumer sites, pedestrian re-identification (Re-ID) has the potential to enhance identify loyal consumers and create a more enjoyable shopping experience. Current Re-ID models always rely on some certain pedestrian feature descriptors, including body parts matching and pose key points, to extract part-level features. However, occlusion always causes a tremendous amount of noise and affects the feature representation, thereby significantly degrading the performance of those models. To address this problem, we propose an attribute-aware graph-based network (AAGNet) for Occluded Re-ID. Specifically, we develop a part-attribute feature extractor that maps the manually labeled pedestrian features into word vectors, and combines them with specific body part to obtain both attribute features and part features. The weight information of body parts and attributes are learned through graph convolution networks. Moreover, we introduce an occluded Re-ID dataset called Occluded-Market that can support the subsequent studies of occluded Re-ID. Comparative experimental results evidently demonstrate that the AAGNet shows superior performance in terms of accuracy, efficiency, and robustness on two open-source data sets. Our study can provide data and methodological support for further research on the occluded Re-ID and technological baseline for Re-ID-based commercial analytic applications in large consumer sites. The dataset is available at: github.com/Occluded_Market.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities, Central China Normal University
- Open Fund of National Engineering Research Center of Geographic Information System, China University of Geosciences
- Fundamental Research Funds for the Central Universities
- Key Research and Development Program of Hubei Province
- Project
- China Postdoctoral Science Foundation
- Knowledge Innovation Program of Wuhan-Basic Research
Zitieren
APA
Yao, S., Pan, K., Wang, T., Zheng, Z., Jin, J., & Hu, C. (2024). AAGNet: Attribute-Aware Graph-Based Network for Occluded Pedestrian Re-Identification. IEEE Transactions on Consumer Electronics, 70(4), 6580-6588. https://doi.org/10.1109/tce.2024.3453890
Vancouver
Yao S, Pan K, Wang T, Zheng Z, Jin J, Hu C. AAGNet: Attribute-Aware Graph-Based Network for Occluded Pedestrian Re-Identification. IEEE Transactions on Consumer Electronics. 2024;70(4):6580-6588. doi:10.1109/tce.2024.3453890
BibTeX
@article{Yao2024,
author = {Yao, Shihong and Pan, Keyu and Wang, Tao and Zheng, Zhigao and Jin, Jing and Hu, Chuli},
title = {AAGNet: Attribute-Aware Graph-Based Network for Occluded Pedestrian Re-Identification},
journal = {IEEE Transactions on Consumer Electronics},
year = {2024},
volume = {70},
number = {4},
pages = {6580--6588},
doi = {10.1109/tce.2024.3453890}
}
EUVIMED