Method and device for obtaining lane line

The invention discloses a method and device for obtaining a lane line. In one specific implementation mode, the method includes the steps that road data are collected, wherein the road data at least comprise the two-dimensional image data and the three-dimensional laser point cloud data; a machine learning method is adopted for recognizing the lane line in the two-dimensional image data; based on the spatial position relation between the two-dimensional image data and the three-dimensional laser point cloud data, a lane line recognition result is converted into three-dimensional lane line disperse points; according to statistical characteristics, the three-dimensional lane line disperse points are filtered; the filtered lane line disperse points are clustered so as to obtain the lane line. By means of the implementation mode, the lane line can be accurately and efficiently obtained, and it is avoided that vehicles or road edges or other marking lines in a road image influence the process of obtaining the lane line. When applied to map drawing, the drawing speed can be obviously increased, and the drawing precision can be obviously improved.