During the driving process, it is common for drivers to misjudge the traffic signs due to extreme weather, poor lighting conditions, and damaged traffic signs, leading to serious traffic accidents. A traffic sign recognition method based on YOLOv5 algorithm was proposed to solve these issues. Utilizing the coordinate attention mechanism to reduce complex background interference, increase the model’s attention to important features, and improve the loss function to reduce the degree of freedom of the prediction box during the convergence process, thereby improving detection performance. Experimental results show that the proposed method achieves significant performance improvement for traffic sign detection under different conditions.
Research on Traffic Target Recognition Algorithm Based on Deep Learning
21.10.2023
983272 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Traffic signs recognition with deep learning
IEEE | 2018
|Traffic Signal Recognition System Using Deep Learning
IEEE | 2023
|Traffic Sign Recognition Algorithm Model Based on Machine Learning
Springer Verlag | 2020
|