Visual Recognition of Traffic Signs in Natural Scenes Based on Improved RetinaNet

Aiming at recognizing small proportion, blurred and complex traffic sign in natural scenes, a traffic sign detection method based on RetinaNet-NeXt is proposed. First, to ensure the quality of dataset, the data were cleaned and enhanced to denoise. Secondly, a novel backbone network ResNeXt was employed to improve the detection accuracy and effection of RetinaNet. Finally, transfer learning and group normalization were adopted to accelerate our network training. Experimental results show that the precision, recall and mAP of our method, compared with the original RetinaNet, are improved by 9.08%, 9.09% and 7.32%, respectively. Our method can be effectively applied to traffic sign detection.

Automated summary

This paper proposes a traffic sign detection method based on RetinaNet-NeXt, aiming at recognizing small proportion, blurred and complex traffic signs in natural scenes. The method improves the detection accuracy and effection of RetinaNet by utilizing the ResNeXt backbone network, transfer learning, and group normalization. Experimental results show significant improvements in precision, recall, and mAP compared to the original RetinaNet, indicating the effectiveness of the proposed method for traffic sign detection.