Traffic sign detection based on multi-scale feature extraction and cascade feature fusion

Existing algorithms have difficulty in solving the two tasks of localization and classification simultaneously when performing traffic sign detection on realistic images of complex traffic scenes. In order to solve the above problems, a new road traffic sign dataset is created, and based on the YOLOv4 algorithm, for the complexity of realistic traffic scene images and the large variation in the size of traffic signs in the images, the multi-scale feature extraction module, cascade feature fusion module and attention mechanism module are designed to improve the algorithm's ability to locate and classify traffic signs simultaneously. Experimental results on the newly created dataset show that the improved algorithm achieves a mean average precision of 84.44%, which is higher than several major CNN-based object detection algorithms for the same type of task.

Automated summary

In this study, a new approach is proposed to address the challenges of traffic sign detection in complex traffic scenes. By designing a multi-scale feature extraction module, cascade feature fusion module, and attention mechanism module based on YOLOv4 algorithm, the algorithm's ability to simultaneously locate and classify traffic signs is significantly improved. Experimental results on a newly created dataset demonstrate that the improved algorithm achieves a mean average precision of 84.44%, outperforming several major CNN-based object detection algorithms for the same task.