EUVIMEDEUVIMED entdecken
Crossref

Dual Backbone Multi-Attention Hierarchical Fusion and Feature Enhancement Network for Crowd Counting

Chunling Zheng, Zhenyu Chen, Xingyu Gao, Lei Lyu

IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 3279-3293

DOI: 10.1109/tce.2025.3557449 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Chunling Zheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 75 Literaturangaben. Gefördert von: Science and Technology Innovation 2030—Major Projects, National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, significant progress has been made in crowd counting with the development of convolutional neural networks (CNNs). However, while CNNs excel at extracting local features, their limited receptive fields restrict their ability to model global context. In contrast, Transformers can effectively model long-distance dependencies, but are inferior to CNN in capturing local detail features. Local details and global context information are crucial to handle large-scale changes in crowds. To address this problem, we propose a novel dual backbone network (DBNet) that integrates CNN and Transformer architectures, aiming to capture and aggregate both global semantic information and local detail features at multiple levels. Specifically, the dual backbone structure is designed to extract fine-grained local features while modeling long-range contextual relationships. Additionally, we introduce a multi-attention hierarchical fusion module (MAHF) that integrates global and local features from the two backbones while suppressing background noise. To further enhance accuracy in the presence of multi-scale variations, we also employ a Feature Enhancement Module (FEM), which enables the network to more effectively identify edge features and facilitates more effective multi-scale feature modeling. Extensive experiments on ShanghaiTech, UCF-QNRF, and JHU-Crowd++ datasets demonstrate that DBNet achieves competitive performance, validating the effectiveness of our approach.

Förderung

  • Science and Technology Innovation 2030—Major Projects
  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province
  • Taishan Scholar Program of Shandong Province

Zitieren

APA

Zheng, C., Chen, Z., Gao, X., & Lyu, L. (2025). Dual Backbone Multi-Attention Hierarchical Fusion and Feature Enhancement Network for Crowd Counting. IEEE Transactions on Consumer Electronics, 71(2), 3279-3293. https://doi.org/10.1109/tce.2025.3557449

Vancouver

Zheng C, Chen Z, Gao X, Lyu L. Dual Backbone Multi-Attention Hierarchical Fusion and Feature Enhancement Network for Crowd Counting. IEEE Transactions on Consumer Electronics. 2025;71(2):3279-3293. doi:10.1109/tce.2025.3557449

BibTeX
@article{Zheng2025,
  author = {Zheng, Chunling and Chen, Zhenyu and Gao, Xingyu and Lyu, Lei},
  title = {Dual Backbone Multi-Attention Hierarchical Fusion and Feature Enhancement Network for Crowd Counting},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {2},
  pages = {3279--3293},
  doi = {10.1109/tce.2025.3557449}
}
Kostenlos starten →