A Convolutional Neural Network-based Video Image Recognition Method for Wheel Tread Damage

The wheel tread condition of rail transportation directly affects the operation safety and quality of the vehicle, so it is of great significance to monitor the wheel tread condition to ensure the safe operation of the train. In this paper, we use convolutional neural network, which has shown powerful ability in image recognition field, to realize the detection of wheel tread damage, firstly, we use the training samples to train the model, and select the ResNet50 neural network model which has the highest recognition rate, and then we used Python computer language combined with OpenCV Python video image processing software library to write a video image detection program for tread damage identification, and finally verified that the prepared video image recognition program has a better effect of tread damage identification through field test.