Real-time ground filtration method for a loader crane environment monitoring system using sparse LIDAR data

摘要

The segmentation and analysis of the environment using three-dimensional (3D) data (point clouds) is a dynamically developing area. This article presents a real-time ground filtration method for the loader crane environment monitoring system. The falling prices of depth sensors based on light detection and ranging (LIDAR), time of flight (ToF), radio detection and ranging (RADAR) technologies, and growth-computing power led us to use the Velodyne VLP-16 sensor in the developed system. In the presented filtering solution, we use characteristic scan pattern properties, the dot product of vectors, and interpolation using the RANSAC method. Algorithm performance was evaluated based on real data acquired under different conditions, and the results were compared to known filtration methods. The described algorithm is developed for real-time operation; therefore, the computation time is critical. Furthermore, in this article, we discuss other methods used to extract ground points from the entire point cloud in real time, describe Velodyne VLP-16 scanner and data acquisition methods.