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

Feature-based fast initialization method for monocular slam

An initialization method and single-purpose technology, applied in the field of SLAM initialization, can solve the problems of slow initialization process and large amount of calculation, and achieve the effect of speeding up and reducing the amount of calculation

Active Publication Date: 2019-12-13
上海玄彩美科网络科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The amount of calculation for initialization is very large, resulting in a very slow initialization process, and because the 3D point cloud needs to be reconstructed, due to the distance problem, it will be limited by the depth of field

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
  • Feature-based fast initialization method for monocular slam
  • Feature-based fast initialization method for monocular slam
  • Feature-based fast initialization method for monocular slam

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below.

[0041] A feature-based fast initialization method for monocular SLAM, comprising the following steps:

[0042] 1) Start SLAM and obtain the first frame of pictures, and extract ORB feature points P(x,y) from the pictures.

[0043] ORB (Oriented FAST and Rotated BRIEF, oriented to fast rotation invariance algorithm) is a fast feature point extraction and description algorithm, which has rotation invariance and good anti-noise ability. The main direction of feature points is through the moment ( moment) is calculated, that is to say, the centroid of the feature point within the radius of r is calculated through the moment, and the coordinates of the feature point to the centroid form a vector as the direction of the feature point.

[0044] 2) Perform image dedistortion on P(x,y)

[0045] The process of camera imaging is essentially the conversion of several coordinate systems. First, a point in space is converted ...

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 a feature based monocular SLAM (Simultaneous Localization and Mapping) quick initialization method, which comprises the steps of 1) starting SLAM, acquiring a first frame picture and extracting ORB feature points P(x, y) for the picture; 2) performing image distortion removing on the ORB feature points P(x, y); 3) performing normalization on image coordinates of the distortion removed feature points in the step 2); 4) building a random depth for each feature point in the step 3); 5) combining results of the step 3) and the step 4) so as to build map points corresponding to the feature points, and acquiring an initial map; and 6) performing optimization on a matching result of subsequent adjacent frames and an existing map, and executing the normal feature SLAM process for each next newly increased frame so as to continuously adjust and expand the map and realize continuous tracking for SLAM. The feature based monocular SLAM quick initialization method provided by the invention is high in speed, small in calculation amount and not restricted by the depth of field.

Description

technical field [0001] The invention relates to a SLAM initialization method. Background technique [0002] SLAM (simultaneous localization and mapping, real-time positioning and map construction) refers to the creation of maps by robots in a completely unknown environment under the condition of uncertain positions, and at the same time use maps for autonomous positioning and navigation. Positioning based on visual sensors has become a hot research topic at home and abroad in recent years, and it is divided into monocular, binocular and multi-eye positioning. Since one observation of monocular SLAM cannot obtain all information relative to environmental features, only direction information can be obtained, and distance information cannot be extracted. It is a method with only direction information. Therefore, there is a feature initialization method for building feature maps. The initial position of the feature is estimated, and the estimated depth information is obtained. ...

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): G06T11/00
CPCG06T11/00
Inventor 张少波张剑华钱胜刘盛
Owner 上海玄彩美科网络科技有限公司
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