Citation

Liu S, Cai T, Tang X, Zhang Y, Wang C. Entropy (Basel) 2022; 24(1): e112.

Copyright

(Copyright © 2022, MDPI: Multidisciplinary Digital Publications Institute)

DOI

10.3390/e24010112

PMID

35052138

Abstract

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.

Language: en

Keywords

group normalization; natural scenes; ResNeXt; RetinaNet; traffic signs