Ground Point Cloud Segmentation Algorithm with Cyclic Growth Based on Adaptive Threshold
In the scene of uneven slope and road surface,a point cloud segmentation method based on adaptive selection of thresh-old values was proposed to solve the problems of insufficient sensitivity of a single threshold value,redundancy calculation of simple combination of multiple thresholds,and impact on segmentation accuracy and robustness.Cyclic growth judgment was introduced into grid segmentation to give consideration to both local features and global features.A trigger dual-feature judgment mechanism was de-signed,and the segmentation efficiency and accuracy of the algorithm were improved by adaptive determination of the height threshold of segmentation by fitting the amplitude of ground fluctuation.Finally,simulation tests were carried out based on open source data set to verify the accuracy and timeliness of the proposed algorithm in ground point cloud segmentation.