一种基于三维点云的快速多目标分割与捕获方法

By using grayscale thresholding and iterative distance weighting methods based on 3D point clouds, the problem of the satellite platform being unable to process high-resolution point cloud data in real time was solved, enabling rapid multi-target segmentation and capture, obtaining target location information, and meeting the rapid capture requirements of sample containers.

CN121685562BActive Publication Date: 2026-07-17BEIJING INST OF CONTROL ENG
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202511656477.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-11-12
Publication Date
2026-07-17
Estimated Expiration
2045-11-12

Smart Images

  • Figure CN121685562B_ABST
    Figure CN121685562B_ABST
Patent Text Reader

Abstract

本发明公开了一种基于三维点云的快速多目标分割与捕获方法，通过获取表面反射特性不同的两个目标的三维点云数据以及对应的二维数据，得到投影后二维图像，利用灰度值对投影后二维图像进行两次二值化处理，实现对空间多目标进行快速分割；多目标分割后，对图像进行降采样，统计降采样栅格内前景像素数量，进而确定目标中心并迭代更新；以最终获得的目标中心对应的二维角度值和距离值，反推目标对应的三维点云，从而得到目标空间位置。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Robot semantic map object recognition method based on deep learning

    CN112288857A

  • 2D image and 3D point cloud combined mechanical arm target grabbing detection system and method

    CN117437216A