Monocular SLAM-based multi-keyframe cooperation ground target positioning method of unmanned aerial vehicle platform

A positioning method and ground target technology, which are applied in the field of multi-key frame cooperative ground target positioning based on monocular SLAM on UAV platforms, can solve problems such as low positioning accuracy, and achieve the effects of high accuracy, high measurement accuracy and fast speed.

Inactive Publication Date: 2017-06-06
RES & DEV INST OF NORTHWESTERN POLYTECHNICAL UNIV IN SHENZHEN +1
View PDF4 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of low positioning accuracy of existing target positioning methods, the present

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Monocular SLAM-based multi-keyframe cooperation ground target positioning method of unmanned aerial vehicle platform
  • Monocular SLAM-based multi-keyframe cooperation ground target positioning method of unmanned aerial vehicle platform
  • Monocular SLAM-based multi-keyframe cooperation ground target positioning method of unmanned aerial vehicle platform

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0036] The specific steps of the multi-key frame coordinated ground target positioning method based on monocular SLAM for the drone platform of the present invention are as follows:

[0037] 1. Calibration of the internal parameters of the monocular camera.

[0038] Zhang's calibration method: adjust the calibration board, continuously collect 20 images, perform corner detection, calculate the homography transformation H between the image and the checkerboard, and use the geometric relationship of the checkerboard to establish the correspondence of the corners in each view image Relation, the space coordinates of all corner points on the checkerboard meet the coplanarity constraint. Assuming that the Z coordinate is 0, the homography is calculated:

[0039]

[0040] Among them, u, v are the pixel coordinates of the corner point, and X, Y are the space coordinates of the corner point on the chessboard. Decompose H as follows:

[0041] H=sK[r 1 r 2 t] (4)

[0042] Where r 1 ,r 2 ,t is...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The Invention discloses a monocular SLAM-based multi-keyframe cooperation ground target positioning method of an unmanned aerial vehicle platform, and is used for solving the technical problem that positioning accuracy of an existing target positioning method is low. The technical scheme is as follows: first an unmanned aerial vehicle and a monocular camera embedded therein are used as an acquisition platform of data, then combined with a vision ORB-SLAM algorithm, multi-keyframe selection and pose resolving are completed, since ORB-SLAM can obtain the precise pose of the camera in real time, the characteristics of fast speed and high precision are achieved compared with plane solving through static scene three-dimensional points, and finally, a projection reconstruction theory is utilized to solve three-dimensional coordinates of a target through a multi-keyframe cooperation method. The method is suitable for various complex environments, and has relatively high measurement accuracy. Through testing, the method provided by the invention has centimeter-level positioning accuracy indoors, and has a 20-meter flight height positioning error of smaller than 0.3m outdoors.

Description

technical field [0001] The present invention relates to a target positioning method, in particular to a multi-keyframe collaborative ground target positioning method based on monocular SLAM for an unmanned aerial vehicle platform. Background technique [0002] The UAV earth observation system has developed rapidly in earth observation due to its notable characteristics such as low cost, simple operation, quick deployment and strong mobility. The precise spatial positioning of the target can effectively obtain the three-dimensional coordinates of the target space, so it has broad application prospects in the fields of disaster reconnaissance, military defense, and civilian production. [0003] The document "A localization method of UAV flying around for ground moving target. The National Conference on Experimental Mechanics. 2012." proposed a ground scene information-assisted monocular positioning method for moving targets. The method first uses the UAV to fly around the tar...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/70G06T7/80G06T7/292
Inventor 杨涛李治李广坡张艳宁刘小飞
Owner RES & DEV INST OF NORTHWESTERN POLYTECHNICAL UNIV IN SHENZHEN
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap