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

Insulation terminal defect recognition method based on patrol robot

A technology for inspection robots and insulated terminals, which is applied in character and pattern recognition, instruments, computer components, etc., and can solve problems such as inaccurate detection and recognition, large changes in target scale and angle, and large targets affected by light.

Inactive Publication Date: 2019-03-08
NANJING UNIV OF SCI & TECH
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a method for identifying defects in insulating terminals based on inspection robots, which solves the problems of irregular robot positions, large changes in target scale and angle, and large impact of light on targets in the existing insulated terminal detection and identification technologies. Problems that lead to inaccurate detection and identification

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
  • Insulation terminal defect recognition method based on patrol robot
  • Insulation terminal defect recognition method based on patrol robot
  • Insulation terminal defect recognition method based on patrol robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0145] A method for identifying defects of insulated terminals based on inspection robots, including the following steps:

[0146] Step 1. For each inspection point, select a centered image of the insulated terminal taken at the inspection point as the template image, such as figure 2 As shown, the SVM multi-classifier is trained using the set of images of insulated terminals collected in advance;

[0147] Step 1-1. Prepare the training sample set, specifically:

[0148] (1) Collect 100,000 pictures with insulated terminals, take pictures of insulated terminals without appearance defects as a positive sample set, and take pictures of insulated terminals with appearance defects as a negative sample set;

[0149] (2) Cut out the picture and delete the redundant information except the insulated terminal graphic;

[0150] (3) Scale the picture to a rectangle with a length and width of 48 pixels;

[0151] Step 1-2, extract the HOG features of the positive and negative samples, specifically:...

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 an insulation terminal defect recognition method based on a patrol robot. The method of the invention is mainly divided into five steps of (1) training the SVM multi-classifierby using the insulation terminal image data set collected in advance; 2) enabling the patrol robot to arrive at the designate patrol point, obtaining the field insulation terminal image and reading itin the form of a gray scale image; (3) coarse positioning and precise positioning of the target area to be detected, and screening the target candidate area to obtain the insulation terminal image; (4) preprocessing the obtained field insulation terminal image; (5) extracting the HOG feature from the sliding window, and sending the HOG feature operator to the SVM multi-classifier to get the recognition result. The machine learn is utilized, the insulation terminal detection and identification task can be effectively completed under different illumination and posture conditions, the automationlevel and the accuracy rate of the image identification under the complex environment are improved, and the problem of missing detection and false detection are reduced to the utmost extent.

Description

Technical field [0001] The present invention relates to target detection and recognition technology, in particular to a method for recognizing defects of insulated terminals based on inspection robots. Background technique [0002] The power industry is closely related to people's lives. The insulated terminal of the substation is the most basic device in the power industry, and it is very important for power supply. In recent years, the inadequate detection and identification of insulated terminals has led to the inability to transmit electricity from time to time, causing huge economic losses to people's lives and industrial production. [0003] At present, there are mainly two types of inspection methods for insulated terminals. The first is a manual inspection method. However, since most of the insulated terminals of substations exist in the field, workers are generally far away, and when defects occur, they generally cannot be solved in time, resulting in the failure of the p...

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): G06T7/00G06K9/46G06K9/40G06K9/62
CPCG06T7/0004G06T2207/20024G06T2207/10024G06T2207/30108G06V10/30G06V10/507G06F18/2411G06F18/214
Inventor 李胜王艳琴王天野郭健吴益飞袁佳泉施佳伟朱禹璇危海明黄紫霄
Owner NANJING UNIV OF SCI & TECH
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