彭雅慧,潘树国,高 旺,乔龙雷,谭 涌,孙迎春.基于直线检测和数字地图匹配的车辆航向角估计[J].电子测量与仪器学报,2022,36(3):194-201
基于直线检测和数字地图匹配的车辆航向角估计
Heading angle estimation for vehicles based online detection and digital map matching
  
DOI:
中文关键词:  数字地图匹配  直线检测  回归预测  航向角估计
英文关键词:digital map matching  line detection  regression prediction  heading angle estimation
基金项目:中国移动科研基金(MCM20200J01)、东南大学至善青年学者资助计划项目(2242021R41134)资助
作者单位
彭雅慧 1.东南大学仪器科学与工程学院 
潘树国 1.东南大学仪器科学与工程学院 
高 旺 1.东南大学仪器科学与工程学院 
乔龙雷 1.东南大学仪器科学与工程学院 
谭 涌 1.东南大学仪器科学与工程学院 
孙迎春 1.东南大学仪器科学与工程学院 
AuthorInstitution
Peng Yahui 1.School of Instrument Science and Engineering, Southeast University 
Pan Shuguo 1.School of Instrument Science and Engineering, Southeast University 
Gao Wang 1.School of Instrument Science and Engineering, Southeast University 
Qiao Longlei 1.School of Instrument Science and Engineering, Southeast University 
Tan Yong 1.School of Instrument Science and Engineering, Southeast University 
Sun Yingchun 1.School of Instrument Science and Engineering, Southeast University 
摘要点击次数: 1511
全文下载次数: 1171
中文摘要:
      为减少车辆行驶过程中由于卫星信号失锁及惯导累计误差对航向角的影响,结合场景特征的提取、表达和数字地图信 息,提出了一种基于直线检测和数字地图匹配的车辆航向角估计方法。 首先,根据地图匹配的坐标点计算车道线地图对应点的 方位角,计算车辆航向角与车道线方位角的角度差;其次,通过改进的 FLD 直线检测方法识别并计算道路图像中车道线直线的 角度;将双侧车道线直线角度作为 BP 神经网络的输入,以预测角度差作为网络输出;最后,结合预测角度差和车道线方位角得 到实时车辆航向角。 经实验验证,所提方法的航向角估计精度与现有估计方法及普通传感器测量结果相比具有一定的优势。
英文摘要:
      In order to reduce the impact of satellite signal loss and cumulative error of inertial navigation during vehicle driving, a vehicle heading angle estimation method based on line detection and digital map matching is proposed by combining scene feature extraction and expression with digital map information. Firstly, according to the coordinate points of the map matching, the corresponding points azimuth of the lane line map is calculated, and the angle difference between the vehicle heading angle and the lane line point azimuth is calculated. Secondly, the angle of lane line in image is recognized and calculated by the improved FLD line detection method. The angle of bilateral lane lines is taken as the input of BP neural network, and the predicted angle difference is taken as the output of the network. Finally, the vehicle heading angle is obtained by combining the angle difference and lane line azimuth. The results of the experiments show that the proposed heading angle estimation algorithm has certain advantages over the existing methods and ordinary measurement sensors.
查看全文  查看/发表评论  下载PDF阅读器