EUVIMEDEUVIMED entdecken
Crossref

A Coarse-to-Fine Deep Learning Based Framework for Traffic Light Recognition

Zikai Yao, Qiang Liu, Jie Fu, Qian Xie, Bo Li, Qing Ye, Qing Li

IEEE Transactions on Intelligent Transportation Systems · 2024-10 · 25 (10) · 13887-13899

DOI: 10.1109/tits.2024.3390576 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-10. Verfasst von Zikai Yao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Science and Technology Innovation Key Research and Development Program of Chongqing, Guangdong Province Key Field Research and Development Plan Project, Guangdong Basic and Applied Basic Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate recognition of traffic light plays a crucial role in ensuring road traffic safety. Due to the wide variety of traffic light classes and the inherent conflict between location determination and intra-class classification of traffic lights, existing deep learning-based methods cannot obtain satisfactory results, making them still unreliable as traffic light recognizers. To address this issue, we propose an effective Coarse-to-fine framework for traffic light recognition, which is consisted of an enhanced super class detector and a fine-grained classifier. The main contributions lie in three aspects. Firstly, we determine the optimal number of super class by adopting a clustering algorithm. It can alleviate the effect caused by similar classes of traffic light. Secondly, we enhance the super class detector by introducing an additional prediction layer, which enable utilizing the shadow features and improving the detection performance of traffic light super class. Lastly, we propose a fine-grained classifier based on depth-wise separable convolution and expansion layer for super class candidate classification. It can achieve superior recognition performance of different traffic lights especially for similar classes. To evaluate the effectiveness of our method, we conduct experiments on WPI (Worcester Polytechnic Institute) traffic light dataset. With an input size of $416\,\,{\times }\,\,416$ pixels, the proposed method can achieve a precision of 99.04% and a recall of 97.40% with a speed of 9.9ms. Compared with other state-of-the-art methods, the results demonstrate the significant competitiveness of our method and its high effectiveness for traffic light recognition.

Förderung

  • Science and Technology Innovation Key Research and Development Program of Chongqing
  • Guangdong Province Key Field Research and Development Plan Project
  • Guangdong Basic and Applied Basic Research Foundation
  • International Program Fund for Young Talent Scientific Research People, Sun Yat-sen University
  • Fourth Xijiang Innovation and Entrepreneurship Team and Leader Project of Zhaoqing, China

Zitieren

APA

Yao, Z., Liu, Q., Fu, J., Xie, Q., Li, B., Ye, Q., & Li, Q. (2024). A Coarse-to-Fine Deep Learning Based Framework for Traffic Light Recognition. IEEE Transactions on Intelligent Transportation Systems, 25(10), 13887-13899. https://doi.org/10.1109/tits.2024.3390576

Vancouver

Yao Z, Liu Q, Fu J, Xie Q, Li B, Ye Q, et al. A Coarse-to-Fine Deep Learning Based Framework for Traffic Light Recognition. IEEE Transactions on Intelligent Transportation Systems. 2024;25(10):13887-13899. doi:10.1109/tits.2024.3390576

BibTeX
@article{Yao2024,
  author = {Yao, Zikai and Liu, Qiang and Fu, Jie and Xie, Qian and Li, Bo and Ye, Qing and Li, Qing},
  title = {A Coarse-to-Fine Deep Learning Based Framework for Traffic Light Recognition},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2024},
  volume = {25},
  number = {10},
  pages = {13887--13899},
  doi = {10.1109/tits.2024.3390576}
}
Kostenlos starten →