SLAM method and system for weak texture scene, navigation vehicle and storage medium

A weak texture and scene technology, applied in navigation calculation tools and other directions, can solve the problems of lack of point features, too few feature points and mismatching, unable to complete 3D mapping, etc., to achieve good stability and robustness, improve accuracy and The effect of accuracy

Active Publication Date: 2019-11-22
TECH & ENG CENT FOR SPACE UTILIZATION CHINESE ACAD OF SCI
View PDF23 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the field of exoplanet exploration, deep space mapping tasks are aimed at weakly textured scenes, which usually have no or very few line features and lack obvious point features, so the current 3D mapping The method is not suitable for weakly textured scenes, and it is prone to problems such as too few feature points extracted and too many mismatches, resulting in the inability to complete 3D mapping

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 method and system for weak texture scene, navigation vehicle and storage medium
  • SLAM method and system for weak texture scene, navigation vehicle and storage medium
  • SLAM method and system for weak texture scene, navigation vehicle and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The principles and features of the present invention will be described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0035] like figure 1 As shown, it is a schematic flow chart provided by an embodiment of the SLAM method for weak texture scenes in the present invention. The SLAM method is suitable for weak texture scenes. When a monocular camera collects image sequences, it processes and maps images in real time. ,include:

[0036] S1, acquiring the image sequence collected by the monocular camera;

[0037] It should be understood that the present invention is suitable for weak texture scene recognition, therefore, the image sequence collected by the monocular camera can be an image sequence containing weak texture scenes, and the monocular camera can be placed on a navigation vehicle or a robot, for example, it can collect ...

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 SLAM method and system for a weak texture scene, a navigation vehicle and a storage medium, and relates to the field of instant positioning and map construction. The methodcomprises the steps of reading an image sequence, and extracting and matching feature points in the image sequence according to a preset deep learning model; carrying out camera pose calculation to obtain pose transformation parameters; carrying out map point calculation on the feature point pairs in the matching result; generating a three-dimensional point cloud map at the current moment; and repeating the above steps until all images in the image sequence are read, generating a three-dimensional point cloud map at all moments, and completing real-time positioning and map construction of theimage sequence. The method is suitable for a weak texture scene, the application of the SLAM method in the weak texture scene is realized, and the mapping precision and accuracy can be improved.

Description

technical field [0001] The invention relates to the field of real-time positioning and map construction, in particular to a SLAM method, system, navigation vehicle and storage medium for weak texture scenes. Background technique [0002] SLAM (Simultaneous Localization And Mapping, real-time positioning and map construction) problem can be described as: put a robot in an unknown location in an unknown environment, is there a way for the robot to gradually draw a complete map of the environment while moving. Existing vision-based monocular SLAM methods mainly include the steps of feature point detection and extraction, camera pose estimation, camera pose optimization, and local map construction. [0003] At present, the research on autonomous navigation and positioning of robots is still mainly focused on solving the problem of mapping structured scenes, which often contain a large number of man-made objects, such as tables and chairs, floor tiles, railings, and building exte...

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 & AuthorityApplications(China)
IPC IPC(8): G01C21/20
CPCG01C21/20
Inventor万雪王晨卉李盛阳
OwnerTECH & ENG CENT FOR SPACE UTILIZATION CHINESE ACAD OF SCI