Classification Method of Road Surface Condition and Type with LiDAR Using Spatiotemporal Information

TL;DR

This paper introduces a spatiotemporal deep neural network architecture that classifies road surface conditions and types using LiDAR data, achieving high accuracy and real-time applicability on embedded hardware.

Contribution

It presents a novel spatiotemporal DNN approach utilizing LiDAR features and vehicle data for accurate, real-time road surface classification.

Findings

Achieved up to 98.6% accuracy in classification.

Outperformed five other algorithms in comparative tests.

Validated real-time implementation on Jetson TX2.

Abstract

This paper proposes a spatiotemporal architecture with a deep neural network (DNN) for road surface conditions and types classification using LiDAR. It is known that LiDAR provides information on the reflectivity and number of point clouds depending on a road surface. Thus, this paper utilizes the information to classify the road surface. We divided the front road area into four subregions. First, we constructed feature vectors using each subregion's reflectivity, number of point clouds, and in-vehicle information. Second, the DNN classifies road surface conditions and types for each subregion. Finally, the output of the DNN feeds into the spatiotemporal process to make the final classification reflecting vehicle speed and probability given by the outcomes of softmax functions of the DNN output layer. To validate the effectiveness of the proposed method, we performed a comparative study with five other algorithms. With the proposed DNN, we obtained the highest accuracy of 98.0\% and 98.6\% for two subregions near the vehicle. In addition, we implemented the proposed method on the Jetson TX2 board to confirm that it is applicable in real-time.