抄録
This paper presents a tracking (estimating position, velocity and size) of moving objects, such as cars, two-wheeled vehicles, and pedestrians, using a multilayer laser scanner mounted on a two-wheeled vehicle. The vehicle obtains its own pose (position and attitude) by on-board GNSS/INS unit and correct the distortion of the laser-scan data by interpolating the pose information. The corrected laser-scan data is mapped onto 3D voxel map represented in the world coordinate flame. Subsequently, the vehicle extracts the interested laser-scan data from the current laser-scan data using NDT scan matching based map-subtraction method. The extracted scan data are mapped onto the elevation map, and moving objects are detected based on an occupancy grid method. Finally, detected moving objects are tracked based on the Bayesian Filter. Experimental results show the performance of the proposed method.
