Unlock instant, AI-driven research and patent intelligence for your innovation.

Monocular vision and GNSS fused SLAM positioning method and system

A positioning method and monocular vision technology, applied in the field of computer vision, can solve the problems of lack of fusion positioning algorithm, failure to use GNSS system error information, etc., to achieve the effect of reducing positioning error, improving accuracy and robustness

Pending Publication Date: 2022-03-22
CHINA CITIC BANK
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technology of fusion and positioning of global navigation satellite system (Global Navigation Satellite System, GNSS), inertial and other sensors and visual SLAM has emerged as the times require. It can operate with high precision in large scenes, but among the existing related technologies, only visual The initialization algorithm integrated with GNSS lacks the subsequent fusion positioning algorithm, and does not use the error information of the GNSS system

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
  • Monocular vision and GNSS fused SLAM positioning method and system
  • Monocular vision and GNSS fused SLAM positioning method and system
  • Monocular vision and GNSS fused SLAM positioning method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0098] In order to understand the content of the present invention more clearly, it will be described in detail with reference to the drawings and embodiments.

[0099] The following describes the SLAM method of monocular vision and GNSS fusion in the embodiment of the present invention with reference to the accompanying drawings.

[0100] figure 1 It is a flow chart of a SLAM method for monocular vision and GNSS fusion according to an embodiment of the present invention. Such as figure 1 As shown, the SLAM method of monocular vision and GNSS fusion of the embodiment of the present invention includes the following steps:

[0101] S1. Obtain image information;

[0102] S2. Perform preliminary positioning and mapping through the monocular pure vision SLAM system, and obtain key frame data;

[0103] S3. Obtain GNSS information through the GNSS system;

[0104] S4. Preprocess the acquired GNSS information, and calculate the image time stamp t of each GNSS frame by using the l...

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 monocular vision and GNSS (Global Navigation Satellite System) fused SLAM (Simultaneous Localization and Mapping) method and system, which are used for realizing high-precision positioning in an unknown environment. Through a vision and GNSS fused monocular initialization algorithm, the problem of solving a proportionality coefficient and coordinate transformation between position information and a real geographic position under monocular vision is solved. The information of a GNSS sensor is fully utilized, the error accumulation problem of a pure vision algorithm is solved through a vision and GNSS fusion positioning algorithm, and the positioning precision higher than that of the pure vision algorithm is obtained. According to the method, the proportionality coefficient and the coordinate transformation relation between the estimated position information and the real geographic position are successfully recovered, the precision and robustness of the system are improved, the positioning error is reduced by at least 25% compared with that of a pure vision SLAM system, a good map proportion can be maintained in the system operation process, and the method is suitable for operation in a large scene.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a SLAM method and system for monocular vision and GNSS fusion. Background technique [0002] In an unknown environment, the device needs to know its own precise location information to complete the task, such as the field of autonomous driving and intelligent robotics. In order to solve the problem of precise positioning of equipment in an unknown environment, Simultaneous Localization and Mapping (SLAM) technology is required. But the error drift of pure vision systems is cumulative, and the trend is gradually increasing. [0003] The fusion positioning technology of global navigation satellite system (Global Navigation Satellite System, GNSS), inertial and other sensors and visual SLAM has emerged as the times require. It can operate with high precision in large scenes, but among the existing related technologies, only visual The initialization algorithm integrated wi...

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 Applications(China)
IPC IPC(8): G06T7/70G06T5/50G06F17/16G01S19/45
CPCG06T7/70G06T5/50G06F17/16G01S19/45G06T2207/20216
Inventor 刘朔源赵锐颉
Owner CHINA CITIC BANK