CAJ | 학술논문

对移动车载激光测量LandMark系统获取的路面激光点云数据进行研究,结合激光点云的回波反射率、扫描角,以及量测距离等特征信息与道路标线的属性信息,提出了一种基于车载激光点云的道路标线自动识别与提取算法。从点云中提取道路标线,采用最小二乘线性最优拟合算法对提取的标线点云进行拟合,生成道路标线的CAD轮廓线,实现道路标线的自动化识别。以移动车载LandMark系统的Sick激光扫描仪获取的路面激光点云为例进行实验,实验结果表明该方法的可行性和有效性。
대이동차재격광측량LandMark계통획취적로면격광점운수거진행연구,결합격광점운적회파반사솔、소묘각,이급량측거리등특정신식여도로표선적속성신식,제출료일충기우차재격광점운적도로표선자동식별여제취산법。종점운중제취도로표선,채용최소이승선성최우의합산법대제취적표선점운진행의합,생성도로표선적CAD륜곽선,실현도로표선적자동화식별。이이동차재LandMark계통적Sick격광소묘의획취적로면격광점운위례진행실험,실험결과표명해방법적가행성화유효성。
The research focuses on LiDAR point clouds of road surface acquired from vehicle - borne mobile mapping system - Land- Mark. An automatic road marking detection and extraction method is proposed. Combining LiDAR features of retro, angle and distance with the properties of traffic marking, point clouds of road marking is extracted. The road marking is best fitted in a least squares poly- nomial fitting method and CAD map is generated for automatic detection. Based on the experimental data from Sick laser scanner mounted on LandMark system, the experimental results show the method is feasible and available.