Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dot-line feature selection method and system for binocular vision SLAM

A feature selection and binocular vision technology, applied in the field of computer vision, can solve problems such as spatial structure information and distribution information considerations

Active Publication Date: 2020-06-19
SHANGHAI JIAO TONG UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method only considers the appearance information, and does not consider the spatial structure information and distribution information

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
  • Dot-line feature selection method and system for binocular vision SLAM
  • Dot-line feature selection method and system for binocular vision SLAM
  • Dot-line feature selection method and system for binocular vision SLAM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0101] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0102] Such as figure 1 As shown, in this embodiment, a method for selecting point-line features for binocular vision SLAM according to the present invention includes any one or more steps as follows:

[0103] The removal of abnormal point and line features based on RANSAC is denoted as step S1, specifically: first randomly extract a certain proportion of point and line feature matching pairs, solve the relative poses of the front and rear frames, and then obtain the set of interior points under the pos...

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 provides a dot-line feature selection method and system for binocular vision SLAM. The method comprises four main steps of abnormal dotted line feature removal based on RANSAC, error transfer model construction of dotted line features, dotted line feature selection based on an error transfer model and dotted line feature selection based on feature space uniform distribution. The method comprises the steps that firstly, the abnormal dotted line features are removed based on RANSAC; secondly, through supposing measurement error distribution of the image, solving a covariance matrixof a pose solving error introduced by the feature; then, based on the covariance matrix, screening out dot-line features with relatively large uncertainty by adopting a greedy algorithm; and finally,clustering the dotted line features in the artificial feature space, and enabling the dotted line features to be uniformly distributed in each class of the feature space. According to the method, abnormal points are screened out, and the precision of the visual SLAM system is improved by using fewer effective points.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a point-line feature selection method and system for binocular vision SLAM. Background technique [0002] The visual SLAM system usually first extracts image features and establishes the feature matching relationship between the front and back frames, then determines the optimization objective equation according to the geometric relationship, and finally uses the Gauss-Newton iterative method to solve the nonlinear optimization problem. However, the accuracy of the system is very dependent on the quality of the system input data, such as whether the matching relationship is correct, the size of the feature measurement error, and so on. [0003] There have been many studies on improving system input, which can be mainly divided into two categories. [0004] One is outlier elimination based on RANSAC: The RANSAC method repeatedly selects a set of random subsets of ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/46G06K9/62G06T7/246G06T7/80
CPCG06T7/246G06T7/80G06T2207/10016G06V10/462G06F18/24
Inventor 王贺升乔志健
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com