An Improved Lidar Data Segmentation Algorithm Based on Euclidean Clustering

Abstract

Segmentation of Lidar Data is an essential part of automatic tasks, such as object detection, classification, recognition and localization. The segmentation results pose a direct impact on the further processing. In this paper, we present an improved Euclidean clustering algorithm for points cloud data segmentation. The k-d tree and voxel grid are used to improve data processing speed. The point cloud of ground is removed from the original dataset by using RANSAC algorithm. Then we use clustering method to get the objects by setting different thresholds at different distance. The experiment states that the proposed algorithm can improve the accuracy of point cloud segmentation.