Supercharge Your Innovation With Domain-Expert AI Agents!

SLAM rapid repositioning method based on local key frame matching and image processing device

A key frame and relocation technology, applied in image data processing, image enhancement, image analysis, etc., can solve the problems of large database and matching time increase, and achieve good experience, increase speed, and reduce stuttering effects

Active Publication Date: 2019-07-30
NANJING HUAJIE IMI TECH CO LTD
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But as the map increases, the database will become larger and larger, and the matching time will also increase

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
  • SLAM rapid repositioning method based on local key frame matching and image processing device
  • SLAM rapid repositioning method based on local key frame matching and image processing device
  • SLAM rapid repositioning method based on local key frame matching and image processing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] Based on the ORB-SLAM2 algorithm framework, the present invention proposes a SLAM fast relocation method based on local key frame matching. The algorithm includes: 1) Image processing: In the vision-based ORB SLAM2 algorithm framework, extract the ORB feature points of the image; 2) Image blur detection: perform blur detection on the image, and filter blurred pictures; 3) Search for relocation Local candidate frames of : Construct an image set, which is obtained by screening all the first n frames of images that observe the feature points of the reference key frame; 4) Image matching and optimization: use the current frame to match the images in the image set and For pose optimization, if the specified constraints are met, the relocation is considered successful. In the actual AR scene, this algorithm can improve the speed of relocation after tracking failure, reduce the stuttering phenomenon, and give users a better experience.

[0017] The specific implementation man...

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 relates to an SLAM rapid repositioning method based on local key frame matching. A user turns a camera to a most recently shot scene after ORB SLAM2 tracking fails. The method comprisesthe following steps: 1) image processing: extracting ORB feature points of an image in an ORB SLAM2 algorithm framework based on vision; 2) image blurring detection: carrying out blurring detection onthe image, and filtering blurred pictures; 3) searching local candidate frames for repositioning: constructing an image set, wherein the image set is obtained by screening the first n frames of images of which the characteristic points of the reference key frame are observed; and 4) image matching and optimization: performing matching and pose optimization by using the current frame and images in the image set, and if a specified constraint condition is met, considering repositioning to be successful.

Description

technical field [0001] The invention belongs to the field of visual simultaneous positioning and mapping, relates to computer vision image processing, and can be used in augmented reality scenes. Background technique [0002] SLAM (Simultaneous Localization and Mapping) is synchronous positioning and map construction. Its principle is: when the robot is in an unknown environment, it obtains the motion state and surrounding environment information through its own sensors, reconstructs the three-dimensional structure of the surrounding environment in real time and at the same time monitors the robot. Position yourself. In visual SLAM, the camera is used to achieve simultaneous positioning and map reconstruction. [0003] In visual SLAM systems, in order to obtain accurate maps, a robust tracking module is necessary. Errors in tracking can lead to errors in 3D reconstruction. At the same time, the AR system based on the SLAM algorithm often places a virtual object in the rea...

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): G06T7/73G06T7/80G06K9/00
CPCG06T7/73G06T7/80G06T2207/10024G06T2207/10016G06V20/46
Inventor 马浩凯黄骏周晓军王行孙赛陶明李骊盛赞李朔杨淼
Owner NANJING HUAJIE IMI TECH CO LTD
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