Method for improving reliability of monocular vision localization through environmental model integrity assessment

An environment model and monocular vision technology, applied in navigation computing tools and other directions, can solve the problem that the correct matching of feature points is difficult to achieve, and achieve the effect of improving reliability and accuracy

Active Publication Date: 2019-05-24
GUANGDONG UNIV OF TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the data matching problem, due to the uncertainty of feature point descriptors in the face of vi

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
  • Method for improving reliability of monocular vision localization through environmental model integrity assessment
  • Method for improving reliability of monocular vision localization through environmental model integrity assessment
  • Method for improving reliability of monocular vision localization through environmental model integrity assessment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with specific embodiment:

[0041] see figure 1 As shown, a method for improving the reliability of monocular vision positioning by evaluating the integrity of the environmental model described in this embodiment first establishes an environmental expression model; then evaluates the integrity of the established environmental expression model; uses the integrity evaluation Based on the results, it is judged whether the environment modeling is completed or not, and the exploration is stopped when the requirements are met.

[0042] Specifically, the established model is expressed in the topological form of a graph; the nodes of the graph represent the collected images; the edges in the graph express the relative relationship of existing nodes; each node corresponds to a collected image in the established model; The establishment of the edge is obtained through the association calculation of the pixel da...

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 method for improving reliability of monocular vision localization through environmental model integrity assessment. The method comprises, firstly, establishing an environmentexpression model; secondly, performing integrity assessment on the established environment expression model; lastly, according to the result of integrity assessment, determining whether environment modeling is completed, if so, stopping searching. Therefore, the data integrity of a finally established environment model can be improved. According to the method for improving reliability of monocular vision localization through environmental model integrity assessment, by means of the model with rich environment data, the association probability of correct data in the environment model can be improved, and further reliability of monocular vision localization can be improved.

Description

technical field [0001] The invention relates to the technical field of robot vision positioning, in particular to a method for improving the reliability of monocular vision positioning by evaluating the integrity of an environment model. Background technique [0002] Using monocular vision to achieve localization in an existing environment model is an important part of visual navigation for mobile robots. In visual navigation problems, it is crucial to obtain real-time localization of mobile robots. [0003] The current monocular vision positioning scheme often uses the matching of feature points and feature point descriptors to realize the visual positioning of mobile robots. [0004] However, in the data matching problem, due to the uncertainty of feature point descriptors in the face of viewing angle changes, illumination changes, etc., it is difficult to achieve the correct matching of feature points. Contents of the invention [0005] The purpose of the present inve...

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): G01C21/20
Inventor 张宏陈炜楠朱蕾何力管贻生
Owner GUANGDONG UNIV OF TECH
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