Incep-FrictionNet-Based Pavement Texture Friction Level Classification Prediction Method

Abstract

Pavement skid resistance is crucial for driving safety, and pavement texture significantly impacts skid resistance performance. To realize the application of pavement texture data in assessing pavement skid resistance performance, this paper proposes a convolutional neural network model based on the InceptionV4 module to predict the pavement friction level from the pavement texture dataset. The surface texture data of indoor test-rutted slabs were collected using a portable laser scanner. The surface friction coefficient of rutted slabs was measured using a pendulum tribometer. After data pre-processing, a total of nine types of texture data that are in the range of 0.4 to 0.8 skid resistance levels are selected at an interval of 0.05 for training, validation, and testing of the network model. The same dataset and training parameters were also used to train a conventional convolutional network model for comparison. The results showed that the proposed network model achieved 97.89% classification accuracy on the test set, which was 11.94 percentage points higher than the comparison model. This demonstrates that the proposed model in this paper can evaluate pavement friction levels by non-contact scanning of textures and has higher evaluation accuracy.