Automatic positioning method of insulator strings based on collinear and equidistant constraints of image feature points

A technology of image feature points and insulator strings, which is applied in the field of state maintenance of power transmission and transformation equipment, can solve the problems of not considering the shape characteristics of insulator strings in binary images, high computational complexity, low precision, etc., so as to improve automation performance, High positioning accuracy, solving the effect of low accuracy

Active Publication Date: 2018-11-06
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In complex, noisy, and low-resolution aerial images, the existing insulator string location methods have limitations such as low accuracy, mislocation, and high computational complexity, and do not consider the shape characteristics of the insulator string in the binary image

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
  • Automatic positioning method of insulator strings based on collinear and equidistant constraints of image feature points
  • Automatic positioning method of insulator strings based on collinear and equidistant constraints of image feature points
  • Automatic positioning method of insulator strings based on collinear and equidistant constraints of image feature points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Such as figure 1 As shown, a method for automatic positioning of aerial insulator strings based on collinear and equidistant constraints of image feature points includes the following steps:

[0061] Step a: Image preprocessing: preprocessing the image containing the aerial insulator string to obtain a binary image with smooth edges after filtering noise;

[0062] Step b: Curvature scale space corner point extraction: extract the edge image of the binary image, extract the contour curve from the edge image; calculate the curvature of each pixel point on the contour curve under the scale σ=3, and convert the local The point with the maximum curvature is used as a candidate corner point; if the curvature value of the candidate corner point is greater than the preset curvature threshold and greater than twice the local minimum value of its neighborhood, it is the correct corner point; in the original image, accurate positioning is related to the The curvature scale space ...

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 an insulator string automatic positioning method based on image feature point collinear and equidistant constraints, including image preprocessing, curvature scale space corner point extraction, collinear equidistant point extraction, hierarchical clustering and insulator string positioning steps . The present invention is simple and practical, and utilizes the collinear and equidistant constraints of the space corner points of the curvature scale of the insulator strings to realize the automatic positioning of the insulator strings in any direction of the main axis in complex, noisy, and low-resolution aerial images, and is time-consuming It is robust to partial occlusion and string drop, and solves the problems of low accuracy, mislocation and high computational complexity in current insulator string positioning methods.

Description

technical field [0001] The invention belongs to the field of operation state maintenance of power transmission and transformation equipment, and in particular relates to an automatic positioning method for insulator strings based on collinear and equidistant constraints of image feature points. Background technique [0002] Insulators are indispensable components in power transmission lines, with functions such as mechanical support and electrical insulation. Once the insulator is damaged, it will lose its effective function and cause huge irreparable losses. Therefore, timely detection of insulators is necessary. Automatically locating insulator strings from aerial images is an important prerequisite for realizing their state detection and fault diagnosis. At present, the automatic positioning methods of aerial insulator strings can be roughly divided into four categories: (1) methods based on segmentation, which divide the original image into multiple regions, and mark t...

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): G06K9/54
CPCG06V10/20
Inventor 赵振兵刘宁戚银城
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
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