Check patentability & draft patents in minutes with Patsnap Eureka AI!

Fast relocation algorithm for slam system based on line features

A relocation and line feature technology, applied in the field of computer vision, can solve problems such as algorithm time-consuming, and achieve the effect of improving efficiency, improving the accuracy of pose estimation, efficient positioning and mapping work

Active Publication Date: 2021-10-22
NORTHWESTERN POLYTECHNICAL UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Inevitably, the algorithm is more time-consuming

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
  • Fast relocation algorithm for slam system based on line features
  • Fast relocation algorithm for slam system based on line features
  • Fast relocation algorithm for slam system based on line features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to better understand the present invention, the technical solution of the present invention will be specifically described below through specific embodiments in conjunction with the accompanying drawings.

[0045] The applicable object of the present invention is the point-line SLAM system in visual SLAM, and it is required to obtain at least 10 sets of map lines and the matching of current image frame line features before use (to ensure the stability of relocation). This algorithm intends to propose a relocation algorithm based on the midpoint of the map line - EPnL, which can be integrated into the EPnP algorithm framework, but uses the midpoint information of the line feature, because the reprojection error between the midpoint of the line feature and the line has Good suppression effect, so there is no need to perform two-step pose estimation like the EPnPL algorithm, thereby improving the efficiency of the relocalization algorithm.

[0046] The invention p...

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 fast relocation algorithm for a SLAM system based on line features, comprising the following steps: step 1, performing point-line feature matching on a candidate key frame and a current image frame by thread; judging the preliminary point-line matching based on the number of point-line matches Whether the quantity is required to reach the set quantity, if it is satisfied, then perform step 2; step 2, set the parameters of the random consistency algorithm, and execute the EPnL algorithm to estimate the preliminary pose; step 3, based on the preliminary estimated pose, remove the midpoint feature of step 1 Mis-match; step 4, perform point-line feature matching and use pose optimization estimation at the same time to obtain the number of interior points and interior lines; step 5, according to the optimized number of effective interior points and interior lines, discuss whether to perform projection matching according to the situation, and complete the final reset. The invention provides a faster relocation pose estimation algorithm that can use the line features in the image in an artificial environment, and can play a complementary role with the EPnP algorithm.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a fast relocation algorithm for SLAM systems based on line features. Background technique [0002] Simultaneous localization and mapping (SLAM) has become more and more important with the development of unmanned driving and drone technology. It refers to the subject equipped with a specific sensor, without the prior information of the environment, to establish a model of the environment during the movement process, and at the same time estimate its own movement. If the camera is used as the sensor, it is called "visual SLAM". [0003] Due to the lack of prior environmental information and the complexity of problems that the system may encounter, such as sudden changes in its own motion or the appearance of many dynamic objects in the camera, these problems may cause the system to lose its current position, that is, it cannot be in the established map. Find the location of the sys...

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 Patents(China)
IPC IPC(8): G06F16/29G01C21/00G01C21/20G01C21/30G09B29/00
CPCG01C21/005G01C21/20G01C21/30G09B29/004G06F16/29
Inventor 朱战霞马廷宸王铮
Owner NORTHWESTERN POLYTECHNICAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com