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

Visible light and infrared sensor data fusion method for inspection robot

A technology of infrared sensors and inspection robots, which is applied in image data processing, instruments, computer components, etc., can solve the problems of multi-modal image matching, which have not been solved well, and achieve high accuracy and automatic acquisition. Effect

Inactive Publication Date: 2017-12-19
STATE GRID CORP OF CHINA +3
View PDF7 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So far, the registration problem of single-modal images has been basically solved, but for multi-modal (including visible light, infrared and other modalities) image matching problems, it has not been well solved so far.
The above-mentioned multi-modal image matching problem also exists in the multi-modal data application of the existing inspection robot, especially for specific object equipment and parts in the inspection image, there is no good solution

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
  • Visible light and infrared sensor data fusion method for inspection robot
  • Visible light and infrared sensor data fusion method for inspection robot
  • Visible light and infrared sensor data fusion method for inspection robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0020] Image registration is the process of matching and superimposing two or more images acquired in different time periods, different sensors (imaging devices), and under different conditions (weather, illumination, camera position and angle, etc.), and is widely used In computer vision, image processing, remote sensing data analysis and other fields.

[0021] Such as figure 1 As shown, a method for fusion of visible light and infrared sensor data of an inspection robot of the present invention comprises the following steps:

[0022] Step S1, acquiring multiple sets of infrared images and visible light images of equipment and its components in the same scene.

[0023] The inspection robot u...

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 visible light and infrared sensor data fusion method for an inspection robot. The method comprises the following steps of 1, obtaining multiple groups of infrared images and visible light images of equipment and equipment parts in a same scene; 2, performing image registration on the infrared images and the visible light images by adopting affine transformation; 3, training the visible light images by utilizing a deep convolutional neural network, and identifying the equipment and the equipment parts in the visible light images and corresponding type and position information; and 4, fusing the infrared images and the visible light images to generate a fused image, and tagging temperature values corresponding to the equipment and the equipment parts in the fused image to form a temperature graph. According to the method, automatic registration of the equipment and the equipment parts in the visible light and infrared images of the inspection robot can be realized; and automatic obtaining of temperature data of the power equipment and the equipment parts is realized.

Description

technical field [0001] The invention relates to the technical field of signal processing, and in particular relates to a data fusion method for visible light and infrared sensors of an inspection robot based on image processing. Background technique [0002] Inspection robots play an important role in power grid production and are widely used in substations and transmission lines. Inspection robots can be used for autonomous inspection and data collection of substations and transmission line equipment. Inspection robots have autonomous navigation and inspection functions. With infrared thermal imaging and high-definition video dual-view technology, relying on dual-view technology, it can initially display the current and voltage heating phenomenon of power equipment, and initially find equipment defects. [0003] Since the infrared thermal imaging and the high-definition optical camera have different focal lengths and viewing angles, the equipment in the infrared and visible...

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): G06K9/62G06T7/33
CPCG06T7/33G06T2207/20084G06T2207/20081G06F18/25
Inventor 罗旺张佩崔漾夏源樊强彭启伟赵高峰郭艳雪毛光辉郝小龙冯敏余磊
Owner STATE GRID CORP OF CHINA
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