车队可通行性探测项目中电力线检测算法研究

Research on Power Line Detection Algorithm in Motorcade Trafficability Estimate Project

为保障大型车辆编队的安全和速度,可以让先导智能感知车辆自动检测前方路况。电力线是国家重要基础设施,由于特种车辆驾驶舱视野窄,且电力线悬于空中没有对照物,驾驶人员很难肉眼辨别其高度是否可以通行,论文着手于先导车辆的电力线实时检测。论文采用了多种型号雷达采集了电力线点云数据,研究了电力线点云特征,提出了一种基于车载激光雷达的实时电力线检测方法。该方法首先通过先验知识选定感兴趣区域后对点云进行法线方向滤波,然后对点云进行聚类,在有效的聚类点云中进行直线拟合,并提出一种电力线后验方法。实验证明论文算法能以较高准确率的检测电力线,并保证实时性。

In order to ensure the safety and speed of large vehicle formations,a pilot intelligent perception vehicle can automatically detect the road conditions ahead. The power line is an important national infrastructure. Due to the narrow field of view of the cockpit of the large special vehicle,and the power line is suspended in the air,it is difficult for the driver to identify whether the height is passable or not. The paper starts real-time detection of the power line of the pilot vehicle. Various types of radar are used to collect power line point cloud data,studied the characteristics of power line point cloud,and proposed a real-time power line detection method based on vehicle lidar. The method first selects the region of interest through prior knowledge and then filters the point cloud in the normal direction,then clusters the point cloud,and performs straight line fitting in the effective clustered point cloud,and proposes a power line posterior method. Experiments show that the algorithm in this paper can detect power lines with high accuracy and ensure real-time performance.