Synchronous localization and mapping method based on improved image matching strategy

An image and strategy technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as low efficiency, poor robustness, inaccurate maps, etc., and achieve the effect of improving elimination efficiency and enhancing robustness

Inactive Publication Date: 2018-08-17
BEIJING UNIV OF TECH
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the random selection of sample data in the standard RANSAC (Random Sample Consensus) algorithm, the number of iterations will increase and the efficiency will be low in the case of fewer inliers
The original ORB (Or

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
  • Synchronous localization and mapping method based on improved image matching strategy
  • Synchronous localization and mapping method based on improved image matching strategy
  • Synchronous localization and mapping method based on improved image matching strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention aims at the problems of poor robustness in the original ORB feature tracking process, high number of iterations of RANSAC and accumulation of errors in the positioning process when feature matching is performed when the proportion of inliers is low, and adopts the present invention to improve ORB features and The improved RANSAC algorithm combined with the g2o optimization library completes the tasks of positioning and mapping. Whole flow chart of the present invention is referring to explanation appendix figure 1 , the specific implementation method is divided into the following steps:

[0062] Step 1, install the open source driver libfreenect2 of Kinect, and write the corresponding program to obtain the color map and depth map of the surrounding environment through Kinect.

[0063] Step 2, use the improved ORB feature to perform feature extraction on the image, see the attached figure 2 .

[0064] Step 3 is to perform feature matching on the...

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 provides a synchronous localization and mapping method based on an improved image matching strategy. According to the method, Oriented FAST (Oriented Features from Accelerated Segment Test) angular point detection is performed on each area of the image by using the improved ORB feature, the descriptor of the feature point is calculated and then feature matching and screening are performed by using an improved RANSAC algorithm; finally the initial attitude of the robot is solved by using the PnP (Perspersctive-n-Point) method, an attitude graph is generated by using the obtained initial attitude, and then the attitude is updated by using the Levenberg-Marquardt method and the attitude is optimized by using the g2o (General Graphic Optimization, G2O) optimization library; and finally the optimized attitude and the corresponding frame are combined together so as to generate the point cloud map. According to the method, the mismatch eliminating efficiency can be enhanced andthe robustness of the tracking process can be improved so as to obtain the accurate map.

Description

technical field [0001] The invention relates to a method for synchronous positioning and mapping based on an improved image matching strategy, belonging to the fields of image matching and visual SLAM (Simultaneous Localization and Mapping). Background technique [0002] The simultaneous positioning and mapping of the robot is the key to realize the autonomous navigation of the robot. How the robot completes its own positioning and mapping in an unknown environment is a very challenging problem. Traditional GPS positioning is usually used in outdoor environments, and there is often a problem of positioning failure in indoor environments. With the continuous development of research in the field of computer vision, vision-based SLAM technology in indoor environments has gradually become a research hotspot. Since the camera can obtain richer environmental information, and with the launch of the relatively cheap Microsoft kinect depth camera, it has been applied to the field of...

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): G06K9/62G06K9/46
CPCG06V10/44G06F18/22
Inventor 贾松敏郑泽玲张祥银李明爱李秀智
Owner BEIJING UNIV OF TECH
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