Substation scene mapping and positioning optimization method based on laser and vision fusion

A positioning optimization, substation technology, applied in image analysis, 3D modeling, surveying and navigation, etc., can solve the problem of single-line lidar being unable to perceive three-dimensional obstacles and laser penetration, and achieve the goal of improving stability and speeding up matching speed. Effect

Pending Publication Date: 2022-07-22
STATE GRID HENAN ELECTRIC POWER ELECTRIC POWER SCI RES INST +2
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A visual fusion SLAM scheme based on single-line laser radar is proposed. The invention solves the problem that single-line laser radar cannot perceive three-dimensional obstacles and laser penetration, and is optimized for the actual complex scene of the substation

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
  • Substation scene mapping and positioning optimization method based on laser and vision fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in detail below with reference to the accompanying drawings, and the objects and effects of the present invention will become more apparent.

[0037] In order to realize the purpose of inspection robots replacing manual inspections in the complex operation and maintenance environment of substations, to ensure the normal operation of substations, and to provide better readability of the navigation map for subsequent manual navigation of robots. The invention solves the problems of poor human readability, long positioning time and easy loss of maps constructed in complex environments, and provides a method for realizing stable positioning in a substation and building a navigation map with strong human readability. The implementation flow chart is as figure 1 shown. The specific implementation steps are as follows:

[0038] Step 1: The substation inspection robot scans the environment of the entire substation through the mounted si...

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 a transformer substation scene mapping and positioning optimization method based on laser and vision fusion, and the method comprises the steps: firstly obtaining a single-line laser radar, an inertial sensor IMU, an odometer and binocular image data, and carrying out the preprocessing; then carrying out local positioning and mapping, and constructing a sub-map; when laser thread positioning and mapping are carried out, binocular image processing, namely a visual thread, is synchronously carried out, feature point tracking is realized, and a key frame is judged; carrying out target detection on the obtained key frame; and finally, generating semantic landmarks and projecting the semantic landmarks to the sub-maps. And optimizing the sub-map, and carrying out global optimization. According to the method, the advantages of a positioning algorithm based on graph optimization and deep learning are combined, the complete navigation map capable of being stably positioned can be obtained, the feature matching time is greatly shortened, the positioning stability under the complex operation and maintenance scene of the transformer substation is greatly improved, and the navigation under the scene of the transformer substation is quicker and more reliable.

Description

technical field [0001] The invention relates to the field of SLAM in the complex scene of fusion of laser and vision, and is aimed at efficient and stable mapping and positioning in the complex environment of the substation. Background technique [0002] With the development of my country's economy and the improvement of people's living standards, social electricity consumption is also increasing, and the power industry has developed rapidly. Substation, transmission, distribution and other power system links are very important links in the power grid. Therefore, the substation urgently needs advanced on-site operation and maintenance technology. This puts forward higher requirements for the construction of substations, and the intelligent transformation of substations has become a hot issue. [0003] Substation equipment inspection is an important method to ensure the normal operation of substations. At present, most substations manually identify the type and model of sub...

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): G06T17/00G01C21/00G01S17/86G01S17/89G06T7/246G06T7/521G06T7/593
CPCG06T17/00G06T7/593G06T7/521G06T7/246G01C21/3841G01S17/86G01S17/89
Inventor 屠铭扬郭志民曾平良田杨阳吴秋轩毛万登经韬刘昊库永恒孟秦源张波涛袁少光刘善峰梁允
Owner STATE GRID HENAN ELECTRIC POWER ELECTRIC POWER SCI RES INST
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