In order to improve the convenience and the efficiency of the asphalt pavement surface wear test, we provided a intelligent detection method based on 3D and 2D pavement surface texture information. We collected the actual pavement surface texture data by a handheld laser 3D scanner and a smartphone. With the 3D points data cloud, we calculated the pavement wear index (PWI) to grade the road surface wear status and extracted of several interested parameters. According to the grading of road surface wear status from the 3D data cloud, the corresponding 2D mobile images were labeled and the training set and test set for neural network training were established. Finally we used a improved ResNet50 network to build a classifier, and tested the classifier performance. The result showed that this method could quickly and effectively predict and classify the road wear state with an accuracy of 94.17% which was adequate for road wear detection.