A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes
IET Image Processing · 2024-06 · 18 (8) · 2064-2077
DOI: 10.1049/ipr2.13083 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 26.03.2024. Verfasst von Lewei He und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China, Foundation for Distinguished Young Talents in Higher Education of Guangdong.
Abstract (Originalsprache)
Currently, traffic sign recognition techniques have been brought into the assistive driving of automobiles. However, small traffic sign recognition in real scenes is still a challenging task due to the class imbalance issue and the size limit of the traffic signs. To address the above issues, a feature‐enhanced hybrid attention network is proposed based on YOLOv5s for a small, fast, and accurate traffic sign detector. First, a series of online data augmentation strategies are designed in the preprocessing module for the model training. Second, the hybrid channel and spatial attention module CSAM are integrated into the backbone for a better feature extraction ability. Third, the channel attention module CAM is used in the detection head for a more efficient feature fusion ability. To validate the approach, extensive experiments are conducted based on the Tsinghua‐Tencent 100K dataset. It is found that the novel method achieves state‐of‐the‐art performance with only negligible increases in the model parameter and computational overhead. Specifically, the , parameters, and FLOPs are 85.8%, 7.13 M, and 16.1 G, respectively.
Förderung
- National Natural Science Foundation of China
- Foundation for Distinguished Young Talents in Higher Education of Guangdong
Zitieren
APA
He, L., Lan, F., Zhou, C., Ye, Y., Zhang, W., Chen, B., & Pan, J. (2024). A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes. IET Image Processing, 18(8), 2064-2077. https://doi.org/10.1049/ipr2.13083
Vancouver
He L, Lan F, Zhou C, Ye Y, Zhang W, Chen B, et al. A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes. IET Image Processing. 2024;18(8):2064-2077. doi:10.1049/ipr2.13083
BibTeX
@article{He2024,
author = {He, Lewei and Lan, Fucai and Zhou, Chuanzhe and Ye, Yaoguang and Zhang, Wencong and Chen, Bingzhi and Pan, Jiahui},
title = {A feature‐enhanced hybrid attention network for traffic sign recognition in real scenes},
journal = {IET Image Processing},
year = {2024},
volume = {18},
number = {8},
pages = {2064--2077},
doi = {10.1049/ipr2.13083}
}
EUVIMED