ACTIVE SHAPE MODEL PRECISION ANALYSIS OF VEHICLE DETECTION IN 3D LIDAR POINT CLOUDS

Abstract. LiDAR systems are frequently used for driver assistance systems. The minimal distance to other objects and the exact pose of a vehicle is important for ego movement prediction. Therefore, in this work, we extract the poses of vehicles from LiDAR point clouds. To this end, we measure them with LiDAR, segment the vehicle points and extract the pose. Further, we analyze the influence of LiDAR resolutions on the pose extraction by active shape models (ASM) and by the center of bounding boxes combined with the principal component analysis (BC-PCA).