All driver assistance systems rely on a comprehensive perception of the vehicle state and the vehicle environment. For example Lane Departure Warning and Lane Keeping are based on information provided by a lane estimationalgorithm. Purpose of this function is to automatically detect the lane and estimate its shape using automotive environment perceiving sensors. Lane estimation has for many years been under heavy development using a gray scale camera. Passive camera based systems can be degraded on its performance under certain circumstances, e.g. at dynamic changes of ambient brightness. The fusion with an active sensor can here increase the robustness of these systems significantly. In this paper an approach is presented to detect lane marks using an active light detection and ranging device (lidar). Lidar sensors are powerful devices with multiple measurement capabilities, like the ability to acquire long distance measurements in combinationwith a high angular resolution. It will be shown that the road surface and high reflective lane marks can be reliably detected by the lidar sensor.By evaluating the intensity channel of the lidar data the high-reflectivelane marks have been extracted using an adaptive thresholding approach. An Unscented Kalman Filter was used to estimate the lane parameters based on the lane mark measurements provided by the lidar data processing.
Abstract