3D Modeling of Lane Marks Using a Combination of Images and Mobile Mapping Data

When we drive a car, the white lines on the road show us where the lanes are. The lane marks act as a reference for where to steer the vehicle. Naturally, in the field of advanced driver-assistance systems and autonomous driving, lane-line detection has become a critical issue. In this research, we propose a fast and precise method that can create a three-dimensional point cloud model of lane marks. Our datasets are obtained by a vehicle-mounted mobile mapping system (MMS). The input datasets include point cloud data and color images generated by laser scanner and CCD camera. A line-based point cloud region growing method and image-based scan-line method are used to extract lane marks from the input. Given a set of mobile mapping data outputs, our approach takes advantage of all important clues from both the color image and point cloud data. The line-based point cloud region growing is used to identify boundary points, which guarantees a precise road surface region segmentation and boundary points extraction. The boundary points are converted into 2D geometry. The image-based scan line algorithm is designed specifically for environments where it is difficult to clearly identify lane marks. Therefore, we use the boundary points acquired previously to find the road surface region from the color image. The experiments show that the proposed approach is capable of precisely modeling lane marks using information from both images and point cloud data.