Unstructured Road Region Detection and Road Classification Algorithm Based on Machine Vision

Abstract

<div class="section abstract"><div class="htmlview paragraph">Accurate sensing of road conditions is one of the necessary technologies for safe driving of intelligent vehicles. Compared with the structured road, the unstructured road has complex road conditions, and the response characteristics of vehicles under different road conditions are also different. Therefore, accurately identifying the road categories in front of the vehicle in advance can effectively help the intelligent vehicle timely adjust relevant control strategies for different road conditions and improve the driving comfort and safety of the vehicle. However, traditional road identification methods based on vehicle kinematics or dynamics are difficult to accurately identify the road conditions ahead of the vehicle in advance.</div><div class="htmlview paragraph">Therefore, this paper proposes an unstructured road region detection and road classification algorithm based on machine vision to obtain the road conditions ahead. Firstly, a vehicle data acquisition platform is built based on a Logitech HD camera, which is used to synchronously collect road image information and vehicle status signals. Secondly, aiming at the problem of unclear road edges of unstructured roads, threshold segmentation and connected domain analysis method are used to detect the road region in the image, and Canny operator is combined to realize road edge detection and road boundary fitting. Then, a road classification and post-processing algorithm based on vision and mileage information is proposed to resist the impact of sudden change of recognition results on continuous sections of complex unstructured roads.</div><div class="htmlview paragraph">Finally, the algorithm is tested and verified based on the collected real vehicle data playback. The results show that the designed unstructured road classification algorithm can accurately identify the changes of road categories, with an average accuracy of 94.57% on asphalt road, brick road, dirt road, and gravel road.</div></div>