Zusammenfassung
This paper proposes a novel multiple vehicle-like
target tracking method based on a Velodyne HDL64E
light detection and ranging (LiDAR) system. The
proposed method combines multiple hypothesis
tracking (MHT) algorithm with dynamic point cloud
registration (DPCR), which is able to solve the
multiple vehicle-like target tracking in highly
dynamic urban environments without any auxiliary
information from GPS or IMU. Specifically, to track
targets consistently, the DPCR is developed to
calculate accurately the pose of the ego-vehicle for
the transformation of raw measurements taken in the
moving coordinate systems into a static absolute
coordinate system; while in turn, MHT helps to
improve the performance of DPCR by discriminating
and removing the dynamic points from the
scene. Furthermore, the proposed MHT method is also
able to solve the occlusion problem existing in the
point cloud. Experiments on sets of urban
environments prove that the presented method is
effective and robust, even in highly dynamic
environments.
Nutzer