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

Unmanned aerial vehicle inspection power transmission line pin defect grading image recognition method

A power transmission line and image recognition technology, which is applied in the field of image recognition, can solve problems such as the difficulty in detecting whether a screw is missing or missing a pin, and achieve the effect of simplifying the workload and improving the detection rate

Inactive Publication Date: 2019-10-08
SHANGHAI JIAO TONG UNIV +1
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Application number: 201810311146.6, applicant: University of Electronic Science and Technology of China, invention name "A method for detecting missing pins in power equipment firmware UAV inspection" solves the technical problem that it is difficult for power equipment to detect whether a screw is missing a pin in a complex scene

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
  • Unmanned aerial vehicle inspection power transmission line pin defect grading image recognition method
  • Unmanned aerial vehicle inspection power transmission line pin defect grading image recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] This embodiment implements a method for grading image recognition of pin defects in a UAV patrolling transmission lines.

[0030] Convolutional Neural Networks (CNN) is a type of feed-forward neural network that includes convolution calculations and has a deep structure. It is one of the representative algorithms for deep learning.

[0031] Support vector machine (Support Vector Machine, SVM) is a kind of generalized linear classifier for binary classification of data according to supervised learning.

[0032] SIFT, or Scale-invariant feature transform (SIFT), is a description used in the field of image processing. This description is scale-invariant and can detect key points in the image. It is a local feature descriptor.

[0033] K-means clustering algorithm (k-means clustering algorithm) is a clustering analysis algorithm for iterative solution. Its steps are to randomly select K objects as initial cluster centers, and then calculate the relationship between each ob...

Embodiment 2

[0059] This embodiment implements a method for grading image recognition of pin defects in a UAV patrolling transmission lines.

[0060] attached figure 2 The flow chart of an embodiment of the method for grading image recognition of pin defects in a UAV patrolling transmission lines. This embodiment is improved on the basis of Embodiment 1, or it is actually applied on the ground.

[0061] The system implementing this embodiment includes a camera, a region recommendation convolutional neural network, extracting SIFT features, making a bag-of-words model, and SVM classification.

[0062] Camera devices include drones, mobile phones, cameras, etc.

[0063] All pins are located by the trained area recommendation convolutional neural network, the pin image is up-sampled and grayscaled to extract SIFT features, and the K-means algorithm is used to make a bag-of-words model, which is sent to the SVM classifier to determine whether the pin is defective .

[0064] The region reco...

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 an unmanned aerial vehicle inspection power transmission line pin defect grading image recognition method. The method comprises the steps of S0, using an inspection collectionimage for pre-training a regional recommendation convolutional neural network and an SVM classifier; S1, sending the inspection collection image into the regional recommendation convolutional neuralnetwork; S2, positioning pins by using the regional recommendation convolutional neural network, and outputting a pin positioning rectangular frame image; S3, performing up-sampling and graying processing on the pin positioning rectangular frame image; S4, extracting the SIFT features of the image processed in the step S3; S5 clustering the SIFT features by a K-means algorithm, and making into a word bag model; and S6, sending the word bag model into the SVM classifier to judge whether the pins have defects or not. The beneficial effects are that the workload of the power transmission line inspection personnel is reduced, and the detection rate of the power transmission line pin defects is improved.

Description

【Technical field】 [0001] The invention relates to the technical field of image recognition, in particular to a method for grading image recognition of pin defects in transmission line inspection by an unmanned aerial vehicle. 【Background technique】 [0002] Transmission lines are an important part of the power grid and the artery of the power system. The inspection of transmission lines is related to the safe and stable operation of the power grid. The State Grid Corporation invests a lot of manpower and material resources every year to ensure the power inspection work. Due to the vast territory of our country, the large scale of the power grid, the long distance of the transmission line, the large capacity and the complex environment, manual maintenance has the problems of harsh inspection environment, heavy workload, large amount of recorded data and difficult storage, which is time-consuming and laborious. Therefore, at present, drones or helicopters are mainly used for ...

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): G06K9/62G06K9/46G06T7/00G06T7/73G01N21/88
CPCG06T7/0004G06T7/73G01N21/8851G06T2207/20081G06T2207/20084G06T2207/30164G01N2021/8883G01N2021/8854G01N2021/8861G01N2021/8887G06V10/462G06F18/23213G06F18/2411
Inventor 顾超越史晋涛李喆盛戈皞江秀臣
Owner SHANGHAI JIAO TONG UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com