Development of a sensor platform for high-accuracy mapping of roadway lane markings

This paper documen the development and evaluation of a low-cost, vehicle-mounted sensor suite and processing algorithms capable of automatically detecting and determining the position of lane markings accurate to the 10-cm (4-in.) level. Such map data can be used for many applications, including lane departure avoidance systems based on the global navigation satellite system (GNSS) or GPS, road curvature calculations, automated systems for reapplying lane markings, and high-accuracy road mapping including improving the local base map. The sensor suite used consists of a high-accuracy GNSS receiver, a side-facing video camera, a computer, and mounting hardware. The side-facing camera is used to record video of the ground adjacent to the passenger side of the vehicle. The video is processed with a computer vision algorithm that locates the fog line within the video frame. Vehicle position data (provided by GNSS) and previously collected calibration data are used to locate the fog line in real-world coordinates. The system was tested on two roads (primarily two-lane, undivided highway) for which high-accuracy (<10 cm) maps were available. The offset between the reference data and the computed fog line position was generally better than 7.5 cm (3 in.). The results of this work demonstrate that it is feasible to use a GNSS combined with a camera to detect the position of a road's fog lines for the development of high-accuracy maps that are useful for many applications.