Convolutional Neural Networks for Traffic Sign Recognition

Right-of-way image-based traffic sign recognition (TSR) is an important research field in intelligent transportation systems. Convolutional neural networks (CNNs) have made breakthroughs in TSR in recent years. However, the traditional convolution lacks invariance for affine transformations such as translation, scaling, shearing and rotation of symbols. To preserve spatial invariance of traffic signs, a Spatial Transformer-Convolutional Neural Network (ST-CNN) is proposed in this paper, where a Spatial Transformer Network (STN) is placed in front of different convolution modules. This method transforms images that are not easily segmented in the original image spatial into the feature spatial which is centered on the reference image and realizes the classification function. This paper uses the German Traffic Sign Recognition Benchmark (GTSRB) dataset for training and testing. The performance of different STNs in the main network location is analyzed and the best model is selected. The accuracy in GTSRB is 99.36%.