Point cloud data processing method and apparatus, and computing device cluster

Through camera acquisition and comparison, the changing areas are determined and the point cloud data is updated using constraint optimization algorithm, which solves the problem of low point cloud data update efficiency in the existing technology, and achieves fast and accurate point cloud data updates, improving positioning and navigation efficiency.

CN119205485APending Publication Date: 2024-12-27HUAWEI CLOUD COMPUTING TECHNOLOGIES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311330044.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-06-25
Filing Date
2023-10-13
Publication Date
2024-12-27

Smart Images

  • Figure CN119205485A_ABST
    Figure CN119205485A_ABST
Patent Text Reader

Abstract

The invention discloses a point cloud data processing method and device and a computing device cluster, and relates to the field of artificial intelligence. The method comprises the steps that a camera shoots and collects a first image and a second image of a scene, the first image is a two-dimensional image before the scene changes, and the second image is a two-dimensional image after the scene changes; as the scene changes, the second image also changes relative to the first image, and the first image and the second image are compared to determine a change area of the second image relative to the first image. And when the scene changes, updating the first point cloud data of the scene into the second point cloud data by using the change area. And updating the point cloud data before the scene change based on the image of the change area to obtain the point cloud data after the scene change. Compared with the method of using the laser radar to re-scan the point cloud data after the scene change, the method of using the camera to acquire the two-dimensional image has the advantages of low cost, simple and fast acquisition process, fast updating of the point cloud data before the scene change, and improvement of the updating efficiency of the point cloud data.
Need to check novelty before this filing date? Find Prior Art