An rgb-d visual slam method based on point and line features

A RGB-D, visual technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of low accuracy, large illumination changes, low semantics, etc., to reduce drift errors.

Active Publication Date: 2022-08-02
SHANGHAI UNIV OF ENG SCI
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned problems existing in the prior art, the purpose of the present invention is to provide a RGB-D visual SLAM method based on point-line features, so as to solve the problem that the current visual SLAM technology has low precision in low semantics, large illumination changes, and dynamic environments. The problem

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
  • An rgb-d visual slam method based on point and line features
  • An rgb-d visual slam method based on point and line features
  • An rgb-d visual slam method based on point and line features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0087] likefigure 1 and figure 2 As shown, a RGB-D visual SLAM method based on point and line features provided by the present invention includes the following steps:

[0088] S1, RGB-D camera internal parameter calibration: The RGB-D camera is used as the image acquisition device to calibrate the internal parameters of the RGB-D camera. The internal parameters of the RGB-D camera include the camera's principal point, focal length and distortion coefficient:

[0089] S11. Take the RGB-D camera as the image acquisition device, and use the RGB-D camera to shoot fixed-size calibration boards (checkerboards) at different angles to obtain image data required for calibration; the RGB-D camera is used as the image in the present invention. Acquisition equipment, the RGB-D camera can provide a pair of registered RGB images and depth images in real time, and the depth images can provide accurate depth information for the subsequent conversion of pixel coordinates to three-dimensional ...

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 an RGB-D visual SLAM method based on point and line features, comprising the following steps: S1, RGB-D camera internal parameter calibration; S2, line feature extraction; S3, obtaining the initial transformation pose of the camera; S4, key frame Linear projection to the current frame; S5, the error function of the visual odometry module; S6, iterative optimization of the initial transformation pose of the camera in the current frame and solution of the pose of the camera in the current frame; S7, judgment of key frames; S8, local BA Optimization; S9, loopback detection; S10, relocation; S11, map construction; S12, result output. The SLAM method provided by the present invention uses an RGB-D camera as an image acquisition device, uses the points and edge lines of objects in the scene as positioning features to realize SLAM, and has better accuracy in challenging scenes such as low semantics and low texture. sex.

Description

technical field [0001] The invention relates to an RGB-D visual SLAM method based on point and line features, and belongs to the technical field of visual SLAM (simultaneous positioning and map construction). Background technique [0002] SLAM (simultaneous localization and mapping, simultaneous localization and map construction) can be summarized as: a certain mobile device (such as a robot, drone, mobile phone, etc.) starts from an unknown location in an unknown environment, and moves through sensors (such as Lidar, camera, etc.) observe and locate its own position, attitude, and motion trajectory, and then perform incremental map construction according to its own position, so as to achieve the purpose of simultaneous positioning and map construction. The development of SLAM technology has a history of more than 30 years, involving many technical fields, and has become a popular research direction in the field of robotics and computer vision. [0003] Generally speaking, ...

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): G06T7/80G06T7/521G01C21/00
CPCG06T7/80G06T7/521G01C21/005G06T2207/20068G06T2207/30244
Inventor 方志军卢俊鑫高永彬杨淑群方荣辉
Owner SHANGHAI UNIV OF ENG SCI
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