LIDAR-based Vehicle Recognition with Global Cylindrical-coordinate Histogram Descriptor

Vehicle Recognition is crucial for an Autonomous Land Vehicle (ALV) navigation in urban environments. In this paper, we proposed a novel Global Cylindrical Coordination Histogram Descriptor(GCCHD) to recognize vehicles in urban environments. This description is created for the centre point of each object. In order to achieve independence with respect to the rotation around $z$ axis, a global reference frame is introduced in GCCHD, and all the three-dimensional points in the cylindrical support region are projected into the three-dimensional histogram according to their three cylindrical coordinates. Experiments on the public Sydney Urban Object dataset and the dataset we prepare and label manually verify the performance of the GCCHD in vehicle recognition.