As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
The ability to extract road boundary in the outside scene is key for autonomous vehicle navigation. This paper proposed a novel road boundary detection method for autonomous vehicle based on spatial knowledge and consistency of road boundary exploiting a 3D LiDAR. More specifically, a novel method was first used to separate the ground points so as to remove obstacles and speed up the processing of road boundary points selection. Secondly, we extract boundary candidate points from individual scan lines based on spatial knowledge, and a two-pass filter was used to eliminate fake boundary points based on consistency of road boundary. Finally, polynomial fitting and boundary update strategies were exploited to produce smoother transition and prevent line-jumping. A challenging realistic traffic scene dataset was collected to evaluate this proposed method and the experimental results demonstrate that the proposed method can detect road boundary with strong robustness at real time for both static and dynamic scenes. The proposed method has been successfully applied to our autonomous vehicle.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.