基于雷达的列车直轨运行前方障碍物检测方法研究  

Research on detection method of obstacle in front of straight track operation of train based on radar

作　　者：郭双全 董昱 GUO Shuangquan;DONG Yu(College of Automation and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)

机构地区：[1]兰州交通大学自动化与电气工程学院

出　　处：《铁道科学与工程学报》2020年第1期224-231,共8页Journal of Railway Science and Engineering

基　　金：国家自然科学基金资助项目(61763023)

摘　　要：针对视觉传感器检测列车运行前方障碍物时存在环境适应能力差及对距离判别能力弱的缺陷,提出一种基于雷达的列车直轨运行前方障碍物检测判别方法。通过最小二乘法进行雷达测量数据误差矫正得到较准确的目标位置信息。结合铁路机车车辆限界、雷达方位角及雷达测量量程,构建检测区模型。将预处理后的目标点位置信息代入构建的检测区模型中进行障碍物检测判别。现场测试结果显示,利用该方法检测不仅具有较高的准确性,而且克服了环境因素的影响。To address the problem of poor environmental adaptability and weak distance discrimination in the detection for obstacle based on visual sensors, a radar-based method for detecting obstacles in front of straight track operation of trains was proposed. Firstly, the method performed the error correction of the radar measurement data by the least squares method to obtain more accurate target position information. Secondly, combined with the railway locomotive vehicle limit, radar azimuth and radar measurement range, the detection zone model was constructed. Finally, the pre-processed target point position information was substituted into the constructed detection area model for obstacle detection and discrimination. The field test results show that the method is not only highly accurate but also overcomes the influence of environmental factors.

关 键 词：列车前方环境理解 最小二乘法 检测区域模型 障碍物检测 

分 类 号：U213.2[交通运输工程—道路与铁道工程]