Effective and robust corrugated beam guardrail detection based on mobile laser scanning data

Yu Jiang, Bei He, Li Liu, Rui Ai, Xianpeng Lang

Abstract: The Highly Automated Driving Map (HAD Map), is an essential and significant research topic in automated driving. In the meanwhile, the corrugated beam guardrail, known as one kind of the traffic crash barrier, is one of the most important elements in the HAD Map. Our novel contribution in this paper is proposing a method to detect corrugated beam guardrail automatically from mobile laser scanning data, which can largely reduce the time cost of manual guardrail labeling during the production of the HAD Map. Firstly, we segment individual mobile laser scanning lines to extract the candidate guardrail sweeps. Secondly, the guardrail feature points are estimated from the candidate guardrail sweeps mentioned above. Finally, we present a guardrail tracing algorithm to refine the guardrail feature points and obtain the final detecting results. The effectiveness and robustness of the proposed method is clarified and demonstrated by the experimental results.