A three-dimensional gauss space-ground cross-view vehicle positioning method and system based on vector line guidance

The 3D Gaussian air-to-ground cross-view vehicle localization method guided by vector lines solves the problems of insufficient robustness and accuracy of air-to-ground cross-view localization technology under complex visual conditions, achieves higher accuracy vehicle localization, reduces the influence of artifacts and texture blurring, and improves the geometric accuracy of pose calculation.

CN121883600BActive Publication Date: 2026-06-26SHENZHEN UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN UNIV
Filing Date
2026-03-23
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing air-to-ground cross-view positioning technologies lack robustness and accuracy under complex visual conditions. In particular, when dealing with differences in viewpoint, viewpoint distortion, scale changes, and illumination between aerial and ground images, traditional local feature descriptors struggle to establish stable matching relationships. Furthermore, artifacts, blurring, and texture stretching issues exist during 3D reconstruction, and ghosting or depth smoothing effects are prone to occur during depth map generation, affecting the geometric accuracy of pose calculation.

Method used

A vector-line-guided 3D Gaussian air-ground cross-view vehicle localization method is adopted. Vector lines are extracted through sparse reconstruction and dense point cloud generation to determine the pose of the ground camera and generate a virtual view. The image is repaired using a diffusion model and a depth map is generated. Combined with pose calculation technology, the localization accuracy and robustness are improved.

Benefits of technology

It improves the robustness and accuracy of cross-view positioning between air and ground under complex visual conditions, ensures the accuracy and stability of vehicle positioning, reduces the impact of artifacts and texture blurring, and improves the geometric accuracy of pose calculation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121883600B_ABST
    Figure CN121883600B_ABST
Patent Text Reader

Abstract

The application belongs to the technical field of geographic information, and discloses a vector line guided three-dimensional Gauss space-ground cross-view vehicle positioning method and system, which comprises the following steps: obtaining a target area aerial image, performing sparse reconstruction of a three-dimensional Gauss scene, dense point cloud generation and vector line extraction on the aerial image; determining camera poses of a group of ground cameras in the three-dimensional Gauss scene based on the extracted vector lines, and generating a virtual view corresponding to the camera poses; repairing the virtual view based on a diffusion model to obtain a repaired image, generating a depth map corresponding to the repaired image according to the dense point cloud; performing pose solving on the virtual view, the repaired image and the depth map to obtain target six-degree-of-freedom pose parameters of the ground cameras; positioning the vehicle to be positioned according to the target six-degree-of-freedom pose parameters, and outputting position information of the corresponding vehicle; and the application improves the robustness and precision of the space-ground cross-view positioning method under complex visual conditions.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Three-dimensional Gaussian visual positioning method for sparse visual angle

    CN120339380A

  • Camera pose estimation method based on 2D Gaussian splashing

    CN121661143A