System Integration of Sensor-Fusion Localization Tasks Using Vision-Based Driving Lane Detection and Road-Marker Recognition

This article proposes a vision-based perception system of using a monocular camera to detect the high-level features in the form of road markers and driving lanes for providing reliable visual measurements. Road markers and driving lanes are chosen because of their visually distinctive appearance compared to other objects as well as being easily annotated in the predefined digital map. For road-marker recognition, a template-matching-based method is applied to recognize the marker type and to estimate the corresponding position and orientation as well. For driving-lane detection, the proposed gradient orientation consistency combining the inverse perspective mapping spatial constraints is used to initialize the clearly visible lanes in the initial detection. Finally, the well-known particle filter is employed to integrate the visual information, inertial measurement unit (IMU), and global position system (GPS) data complementarily for correcting GPS errors. In particular, the lane measurement and road-marker measurement provide the lateral offset and relative position information, respectively, with respect to the ego vehicle. The IMU is used to estimate the dynamic behavior of the ego vehicle. The proposed vehicle localization system is evaluated in the real driving scenario of the standard campus environment within varying illumination conditions. The experiment results show that the lane-level localization accuracy is achieved by detecting road markers and driving lanes robustly.