Research on Automatic Recognition of Multi-class Pavement Disease Based on Convolutional Neural Network
In recent years,convolutional neural networks have been widely used in the field of image recognition because their artificial neurons can respond to a part of the coverage of the surrounding units,which has excellent performance in large-scale image processing. In this paper,the YOLOX-MobileNetV3 model in the lightweight convolutional neural network model is applied for intelligent recognition of the pavement disease images detected on actual roads. The results show that the average accuracy of the lightweight network model is low when the number of samples is small,and the average accuracy of the whole class of diseases is greatly improved when the number of diseases in a certain class reaches 5000.
万方数据
维普
