TRD-YOLO: A Real-Time, High-Performance Small Traffic Sign Detection Algorithm
Sensors · 10.04.2023 · 23 (8) · 3871
DOI: 10.3390/s23083871 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.04.2023. Verfasst von Jinqi Chu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The General Program of the National Natural Science Foundation of China, National Natural Science Foundation of China, funding project of advantageous disciplines of universities in Jiangsu Province.
Abstract (Originalsprache)
Traffic sign detection is an important part of environment-aware technology and has great potential in the field of intelligent transportation. In recent years, deep learning has been widely used in the field of traffic sign detection, achieving excellent performance. Due to the complex traffic environment, recognizing and detecting traffic signs is still a challenging project. In this paper, a model with global feature extraction capabilities and a multi-branch lightweight detection head is proposed to increase the detection accuracy of small traffic signs. First, a global feature extraction module is proposed to enhance the ability of extracting features and capturing the correlation within the features through self-attention mechanism. Second, a new, lightweight parallel decoupled detection head is proposed to suppress redundant features and separate the output of the regression task from the classification task. Finally, we employ a series of data enhancements to enrich the context of the dataset and improve the robustness of the network. We conducted a large number of experiments to verify the effectiveness of the proposed algorithm. The accuracy of the proposed algorithm is 86.3%, the recall is 82.1%, the mAP@0.5 is 86.5% and the mAP@0.5:0.95 is 65.6% in TT100K dataset, while the number of frames transmitted per second is stable at 73, which meets the requirement of real-time detection.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China.
- Jiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing 210044, China.
Förderung
- The General Program of the National Natural Science Foundation of China
- National Natural Science Foundation of China
- funding project of advantageous disciplines of universities in Jiangsu Province
Zitieren
APA
Chu, J., Zhang, C., Yan, M., Zhang, H., & Ge, T. (2023). TRD-YOLO: A Real-Time, High-Performance Small Traffic Sign Detection Algorithm. Sensors, 23(8), 3871. https://doi.org/10.3390/s23083871
Vancouver
Chu J, Zhang C, Yan M, Zhang H, Ge T. TRD-YOLO: A Real-Time, High-Performance Small Traffic Sign Detection Algorithm. Sensors. 2023;23(8):3871. doi:10.3390/s23083871
BibTeX
@article{Chu2023,
author = {Chu, Jinqi and Zhang, Chuang and Yan, Mengmeng and Zhang, Haichao and Ge, Tao},
title = {TRD-YOLO: A Real-Time, High-Performance Small Traffic Sign Detection Algorithm},
journal = {Sensors},
year = {2023},
volume = {23},
number = {8},
pages = {3871},
doi = {10.3390/s23083871}
}
EUVIMED