LASER RADAR POINT CLOUD DATA CLASSIFICATION METHOD, APPARATUS AND DEVICE, AND STORAGE MEDIUM

摘要

A laser radar point cloud data classification method, apparatus and device, and a storage medium. The method comprises: acquiring sample point cloud data, and laser radar point cloud data to be classified (101); establishing a point cloud classifier according to the sample point cloud data (102); and classifying the laser radar point cloud data to be classified by means of the point cloud classifier (103). According to the method, a cloud point classifier is trained by means of sample point cloud data, and laser radar point cloud data to be classified is automatically classified by means of the point cloud classifier, thereby greatly reducing a manual intervention component during a classification process, and achieving a high automation degree and a low cost. Sample point cloud data used for training the point cloud classifier covers pole tower data of various tower types and power line data of various line types, the data is comprehensive, and the point cloud classifier trained by means of the sample point cloud data has a high accuracy and is unlikely to make mistakes. In addition, after a classification result is obtained by means of automatic classification, speckle combination and optimization are carried out, and optimization is carried out according to a pole tower position file and a pre-set optimization rule, so as to further improve the classification accuracy.