Mexican traffic sign detection and classification using deep learning

作者：

Highlights：

• A new data set with 1426 Mexican traffic signs is presented.

• We compare an R-CNN with YoloV3 for the stage of traffic sign detection.

• The stage of image classification is implemented using a modified ResNet-50.

• We present tests with traffic signs occluded and randomly inserted in the scene.

• The results obtained are in light of the obtained in the state-of-the-art.

摘要

•A new data set with 1426 Mexican traffic signs is presented.•We compare an R-CNN with YoloV3 for the stage of traffic sign detection.•The stage of image classification is implemented using a modified ResNet-50.•We present tests with traffic signs occluded and randomly inserted in the scene.•The results obtained are in light of the obtained in the state-of-the-art.

论文关键词：Traffic signs,Convolutional neural networks,Region-based convolutional neural network,YOLO v3 detector,ResNet-50

论文评审过程：Received 19 April 2021, Revised 6 February 2022, Accepted 11 April 2022, Available online 25 April 2022, Version of Record 4 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117247