Point cloud registration method using rectangle and oblateness information and storage medium

Abstract

The invention discloses a point cloud registration method using rectangle and flatness information and a storage medium, and the method comprises the steps: obtaining a first frame of point cloud data, carrying out the clustering of the first frame of point cloud data, obtaining a point cloud segment, obtaining an oblateness value of the point cloud segment, performing rectangular fitting on the point cloud segment to obtain a rectangular structure, obtaining four vertex coordinates of the rectangular structure, acquiring second frame point cloud data, and registering the first frame point cloud data and the second frame point cloud data according to the coordinates of the four vertexes of the rectangular structure and the oblateness values of the point cloud fragments. According to the method, the first frame of point cloud data is segmented by using a clustering method, so that the first frame of point cloud data can be increased according to a certain sequence, and then the flatnessinformation of the segmented point cloud fragments is obtained to match the two frames of point cloud data, so that the flatness information is improved to accurately express the structures of the point cloud fragments, therefore, the stability and reliability of point cloud registration in scene change are improved. 本发明公开了一种利用矩形及扁率信息的点云配准方法及存储介质，所述方法包括：获取第一帧点云数据，对所述第一帧点云数据进行聚类，得到点云片段；获取所述点云片段的扁率值；对所述点云片段进行矩形拟合，得到矩形结构，获取所述矩形结构的四个顶点坐标；获取第二帧点云数据，根据所述矩形结构的四个顶点坐标以及所述点云片段的扁率值对所述第一帧点云数据以及所述第二帧点云数据进行配准。本发明利用聚类的方法对第一帧点云数据进行分割，使得所述第一帧点云数据可以按照一定顺序增长，再获取分割后的点云片段的扁率信息对两帧点云数据进行匹配，提高扁率信息准确表达点云片段的结构，从而提高了场景变换中点云配准的稳定性和可靠性。