Spaceborne lidar point cloud and image feature joint extraction method, multi-level reference image construction method and electronic device

By constructing a sliding window for signal photon denoising in the fusion of spaceborne lidar and optical image data, screening stable regions and identifying hard surfaces by combining spectral texture features, and using robust statistical methods to process elevation samples, the problems of noise interference and terrain undulation effects are solved, and high-precision multi-level benchmark image construction is achieved.

CN122265664APending Publication Date: 2026-06-23AEROSPACE INFORMATION RES INST CAS

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
AEROSPACE INFORMATION RES INST CAS
Filing Date
2026-05-25
Publication Date
2026-06-23

Smart Images

  • Figure CN122265664A_ABST
    Figure CN122265664A_ABST
Patent Text Reader

Abstract

This application provides a method for joint extraction of point clouds and image features from spaceborne lidar, a method for constructing multi-level reference images, and an electronic device, relating to the fields of remote sensing mapping and geographic information technology. The extraction method includes: acquiring optical remote sensing images and radar data; constructing multiple sliding windows along the orbital direction, performing denoising processing based on the multiple sliding windows to obtain multiple candidate signal photons; calculating the local terrain features of the candidate signal photons within each sliding window, and filtering out photons corresponding to candidate spots located in stable regions based on the local terrain features; determining whether the pixels corresponding to the multiple candidate spot photons within the spot range meet preset conditions; filtering out the representative elevations of multiple signal photon elevation samples within the target spot range that meet the preset conditions, and combining the pixel coordinates of hard surface pixels in the optical remote sensing image within the target spot range with the representative elevations to obtain joint feature points.
Need to check novelty before this filing date? Find Prior Art