Browse Publications Technical Papers 2019-01-0688

Real-time Motion Segmentation of LiDAR Point Detection for Automated Vehicles 2019-01-0688

A Light Detection And Ranging (LiDAR) is now becoming an essential sensor for an autonomous vehicle. The LiDAR provides the surrounding environment information of the vehicle in the form of a point cloud. A decision-making system of the autonomous car is able to determine a safe and comfort maneuver by utilizing the detected LiDAR point cloud. The LiDAR points on the cloud are classified as dynamic or static states depending on the movement of the object being measured. If the movement states of detected points can be provided by LiDAR, the decision-making system is able to plan the appropriate motion of the autonomous vehicle according to the movement of the object. This paper proposes a real-time process to segment the motion states of LiDAR points. The basic principle of the segmentation algorithm is to classify the movement of a current LiDAR point cloud through the previously-measured point clouds, the previous vehicle poses, and a LiDAR extrinsic calibration parameter. First, we set a time window with the fixed size of the buffers and store the previous LiDAR point clouds and vehicle poses in the buffers. Second, we estimate the motion beliefs of the current points against each previous point cloud and vehicle pose in the buffers by applying probability and evidence modeling. The motion beliefs of current points for each previous point cloud and vehicle pose are described by masses of dynamic, static, and unknown. Finally, the series of motion belief masses of current points for the series of previous point cloud and pose in the time window are integrated through the Dempster-Shafer combination. The integrated motion masses of the current points represent the motion beliefs by taking into account the previous point clouds and poses in the time window. The motion of the current point can be segmented into the state of dynamic, static, and unknown based on the integrated mass value. The proposed algorithm was evaluated through the experiments using a LiDAR equipped with an autonomous vehicle. The autonomous vehicle was able to perform map-matching localization and collision avoidance with the proposed point motion segmentation.


Subscribers can view annotate, and download all of SAE's content. Learn More »


Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Members save up to 40% off list price.
Login to see discount.
Special Offer: With TechSelect, you decide what SAE Technical Papers you need, when you need them, and how much you want to pay.