Power meter detection method based on fusion of inspection robot positioning information

An inspection robot and positioning information technology, which is applied to instruments, calculations, inspection time patrols, etc., can solve the problems of target scale, large angle change, inaccurate detection, and the target is greatly affected by light, and achieves high position repeatability, The effect of reducing false detection problems

Active Publication Date: 2021-09-28
NANJING UNIV OF SCI & TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a power meter detection method that integrates the positioning information of the inspection robot to solve the problems in the existing meter detection technology that the position of the robot is not fixed, the target scale and angle change greatly, and the target is greatly affected by the light, which leads to Detect inaccurate problems

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
  • Power meter detection method based on fusion of inspection robot positioning information
  • Power meter detection method based on fusion of inspection robot positioning information
  • Power meter detection method based on fusion of inspection robot positioning information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] A power meter detection method that integrates the positioning information of an inspection robot, the specific steps are:

[0069] Step 1-1. Collect the pictures of the on-site inspection points collected by the inspection robot, extract the images of the electric meters from them, and make a 48*48 grayscale image data set according to the classification of the meters, such as figure 2 As shown, the image data set is sent to the classifier for training;

[0070] Step 1-2. Select an image in the center of the inspection instrument from the pictures taken at each inspection point, such as image 3 Shown as the template image for detection;

[0071] Step 1-3. The inspection robot reaches the designated inspection point through positioning and navigation, with a navigation error of 5cm, and takes an image A for instrument inspection;

[0072] Step 2. Perform Merlin Fourier transform and phase correlation calculation on the image A taken by the inspection robot and the t...

Embodiment 2

[0088] A power meter detection method that integrates the positioning information of an inspection robot, the specific steps are:

[0089] Step 1. The inspection robot reaches the designated inspection point through positioning and navigation, with a navigation error of 5cm, and takes an image A for instrument inspection;

[0090] Step 2. Perform Merlin Fourier transform and phase correlation calculation on the image A taken by the inspection robot and the template image B of the current inspection point, and obtain the image displacement index (-12,33) of the abscissa and ordinate, Calculate the estimated position of the instrument in image A (984,502,103,86);

[0091] Step 3. Use the pre-trained machine learning Adaboost classifier to accurately locate the image to be detected, and obtain multiple target candidate areas such as Figure 5 As shown; according to the Adaboost classifier, one candidate box (with numbers) is obtained, and the boxes without numbers are obtained i...

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 power meter detection method which integrates the positioning information of a patrol inspection robot. The present invention is mainly divided into four steps: (1) the inspection robot arrives at the designated position to obtain pictures; (2) combines the positioning information of the inspection robot, and uses Fourier and phase correlation technology to roughly locate the target instrument area; (3) Using machine learning to accurately locate the target instrument area, multiple target candidate areas are obtained; (4) Fuse the positioning information of the inspection robot to calculate the characteristic parameters of multi-feature fusion such as IoU, mutual information, visual hash, etc., and use these parameters to screen candidate areas. Candidate area to get the final target. The invention utilizes machine learning to detect instruments under various illumination and posture changes.

Description

technical field [0001] The invention relates to a target detection method, in particular to a power meter detection method which integrates positioning information of a patrol inspection robot. Background technique [0002] The power inspection robot needs to realize the basic functions such as autonomous positioning and navigation in the substation, field instrument display number recognition, and automatic charging. The core function is to detect and identify the indications of instruments and meters of on-site power equipment, such as discharge counters, oil level gauges, voltmeters, thermometers and other instruments. These instruments are basically mechanical instruments, and robots need to rely on visual sensors. Take meter readings. The premise of accurate recognition of the instrument number is to accurately detect the position of the instrument in the visual image, and most of the instruments are outdoors. Most of the current methods use traditional image processin...

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): G07C1/20G06K9/00G06K9/52
CPCG07C1/20G06V20/20G06V10/431
Inventor 茅耀斌陆亚涵郭健李胜李萌项文波胥安东潘云云王天野
Owner NANJING UNIV OF SCI & 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