测绘学报 ›› 2020, Vol. 49 ›› Issue (4): 480-488.doi: 10.11947/j.AGCS.2020.20190241

• 摄影测量学与遥感 • 上一篇    下一篇

车载激光点云的道路标线提取及语义关联

姚连璧, 秦长才, 张邵华, 陈启超, 阮东旭, 聂顺根   

  1. 同济大学测绘与地理信息学院, 上海 200092
  • 收稿日期:2019-06-17 修回日期:2019-11-16 发布日期:2020-04-17
  • 作者简介:姚连璧(1964-),男,教授,主要研究方向为多传感器集成以及在道路与交通工程中的应用。E-mail:lianbi@tongji.edu.cn
  • 基金资助:
    “十三五”国家重点研发计划资助项目(2016YFB1200602-02);国家自然科学基金资助项目(41771482)

Road marking extraction and semantic correlation based on vehicle-borne laser point cloud

YAO Lianbi, QIN Changcai, ZHANG Shaohua, CHEN Qichao, RUAN Dongxu, NIE Shungen   

  1. College of Surveying and Geo-informatics, TongJi University, Shanghai 200092, China
  • Received:2019-06-17 Revised:2019-11-16 Published:2020-04-17
  • Supported by:
    The National Key Research and Development Program of China (No. 2016YFB1200602-02);The National Natural Science Foundation of China(No. 41771482)

摘要: 自动驾驶技术已成为未来智能交通的发展方向之一,高精度地图为L3级及以上自动驾驶实现高精度定位和路径规划提供先验信息,是自动驾驶车辆传感器在遮挡或观测距离受限情况下的重要补充。道路标线的位置和语义信息,比如实线和虚线的绝对位置是高精度地图的基本组成部分。本文从车载激光点云中提取扫描线,根据道路边缘位置几何形态的突变从扫描线中提取道路路面,在此基础上首先利用反距离加权插值的方法把路面点云图像以一定的分辨率转换为栅格图像,其次利用基于积分图的自适应阈值分割方法把栅格图像转化为二值图像,然后利用欧氏聚类的方法从二值图像中提取标线点云,并利用特征属性筛选的方法对提取的标线点云进行语义识别,最后建立交通标线和交通规则之间的语义关联。

关键词: 点云, 反距离加权插值, 自适应阈值分割, 欧氏聚类, 特征属性筛选, 语义关联

Abstract: At present, automatic driving technology has become one of the development direction of the future intelligent transportation system. The high-precision map, which is an important supplement of the on-board sensors under the condition of shielding or the restriction of observing distance, provides a priori information for high-precision positioning and path planning of the automatic driving with the level of L3 and above. The position and semantic information of the road markings, such as the absolute coordinates of the solid line and the broken line, are the basic components of the high-precision map. In this paper, scan lines are extracted from the vehicle-borne laser point cloud data, and the road surfaces are extracted from scan lines according to the mutation of the geometry of road edge. On this basis, the road surface point cloud image is transformed into raster image with a certain resolution by using the method of inverse distance weighted interpolation, and the grid image is converted into binary image by using the method of adaptive threshold segmentation based on the integral graph. Then the method of the Euclidean clustering is used to extract the road markings point cloud from the binary image. Semantic information can be extracted from the road markings point cloud using the method of the characteristic attribute selection. Finally, semantic association is established between the traffic markings and the traffic regulation.

Key words: point cloud, inverse distance weighted interpolation, adaptive threshold segmentation, Euclidean clustering, feature attribute selection, semantic correlation

中图分类号: