A three-dimensional model construction method, device, storage medium and computer equipment

The base station image positioning information transmitted by the drone is converted into the station center coordinates, a sparse point cloud is generated and a three-dimensional model is constructed, which solves the problem that the existing technology is not applicable to the modeling of base stations and other objects, and realizes efficient and low-required three-dimensional modeling.

CN113129422BActive Publication Date: 2025-03-25CM INTELLIGENT MOBILITY +2
1 Cites 0 Cited by

Patent Information

Application Number
CN201911399769.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-12-30
Publication Date
2025-03-25
Estimated Expiration
2039-12-30

AI Technical Summary

Technical Problem

The existing drone sequence image modeling technology is not suitable for three-dimensional modeling of small and medium-sized, weak textured objects such as base stations, and requires high-precision drone GPS and IMU data, resulting in high requirements for drone performance.

Method used

By receiving the multi-frame base station image sent by the drone, converting its positioning information into the station center coordinates, generating sparse point clouds, and constructing a three-dimensional base station model through cropping and backprojection, only the longitude and latitude data of the drone are needed, and IMU data is not needed.

Benefits of technology

Three-dimensional modeling of small and medium-sized, textured objects (such as mobile base stations) is realized, reducing the requirements for drone performance and improving modeling efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The embodiment of the present invention provides a three-dimensional model construction method, device, storage medium and computer equipment. In the technical solution provided by the embodiment of the present invention, multiple frames of base station images and corresponding positioning information sent by a drone are received; the positioning information of each frame of the base station image is converted into the station center coordinates under the station center coordinate system; according to the station center coordinates, the obtained target matching pairs and the station center coordinates, an absolute rotation matrix and an absolute translation matrix are generated; according to the target matching pairs, the preset initial camera intrinsic parameters, the preset initial camera extrinsic parameters, the absolute rotation matrix and the absolute translation matrix, a sparse point cloud is generated; according to the preset boundary threshold, the sparse point cloud is cropped to generate a target point cloud, and then a base station three-dimensional model is constructed. The technical solution of the present invention is used for modeling small and medium-sized objects with weak textures such as mobile base stations, and only the longitude and latitude of the drone are required, and the drone IMU data is not required, and the requirements for the drone are relatively low.
Need to check novelty before this filing date? Find Prior Art