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

Panoramic vision SLAM mapping method

A panoramic vision and panorama technology, applied in the field of panoramic vision images, can solve problems such as loss of relevant information tracking and matching, narrow field of view, narrow parallax, etc., to eliminate feature point detection errors, improve mapping accuracy, efficiency, and accuracy Guaranteed effect

Pending Publication Date: 2021-11-09
成都易瞳科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The field of view of traditional monocular SLAM is narrow, and the accuracy of visual scale estimation needs a specific scanning path to meet; the parallax of traditional binocular SLAM is also relatively narrow, which is likely to cause the loss of relevant information tracking and matching when there is less information in the local imaging area, so it has low accuracy and low accuracy. The shortcomings of efficiency, so the traditional pure vision SLAM method is greatly limited in the actual application process

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
  • Panoramic vision SLAM mapping method
  • Panoramic vision SLAM mapping method
  • Panoramic vision SLAM mapping method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] refer to figure 1 , a panoramic vision SLAM mapping method, comprising the following steps:

[0037] Step S1: panoramic camera calibration, transforming the panorama and space into an ideal spherical imaging model;

[0038] In step S1, the method of converting the panoramic image into an ideal spherical imaging model is as follows, see figure 2 , transform all points P(x, y) on the panorama into points P′ (lon, lat) on the ideal sphere according to the following formula:

[0039]

[0040]

[0041] The method of transforming the space into an ideal spherical imaging model is to convert all points in the space Convert to a point p'(lon,lat) on an ideal sphere according to the following formula:

[0042]

[0043] Among them, width is the image width, height is the image height, f θ , c θ The calibration of this parameter is done in the calibration of the panoramic camera by the calibration of the inherent parameters of the camera.

[0044] Step S2: Pro...

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 panoramic vision SLAM (Simultaneous Localization and Mapping) method, aims to improve the precision and efficiency of vision SLAM, and relates to the technical field of panoramic vision image. The panoramic vision SLAM method comprises the following steps: calibrating a panoramic camera, and converting a panoramic image and a space into an ideal spherical imaging model; projecting the panoramic plane picture into a hexahedral plane image through cube expression, converting the hexahedral plane image into an ideal spherical imaging model, and performing feature point matching; performing attitude correction on the panoramic image sequence through motion attitude estimation; carrying out image feature point tracking on the panoramic image sequence, and when feature point tracking fails or the image meets other key frame selection conditions, updating a final key frame and carrying out key frame feature matching; achieving local mapping by estimating camera displacement and positioning spatial feature points; and carrying out loopback detection, achieving global mapping optimization, and achieving the high-precision and high-efficiency panoramic vision SLAM method.

Description

technical field [0001] The present invention relates to the technical field of panoramic vision images, in particular to a panoramic vision SLAM mapping method. Background technique [0002] Panoramic video is an emerging data form, especially 720° panorama. With the development of surveillance security and VR industries, the amount of panoramic data in various industries has also increased dramatically. Simultaneous positioning and map construction SLAM is an important technical implementation method in the field of visual space perception at present. Through the collection of raw visual data, image data feature processing and extraction can be used to obtain the depth information of the screen content and realize the robot's autonomous navigation environment through positioning and map construction. purpose of perception. [0003] Visual SLAM research is mainly divided into three categories: monocular, binocular or multi-purpose, and RGBD. In addition, the visual SLAM co...

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): G06T7/80G06T3/00G06K9/62G06K9/00G06F17/16
CPCG06T7/85G06F17/16G06T3/047Y02T10/40
Inventor 胡丽玉胡自航胡志发
Owner 成都易瞳科技有限公司
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