Unlock instant, AI-driven research and patent intelligence for your innovation.

Salient edge guided insulator region detection method

A region detection, edge-guided technology, applied in image analysis, instrumentation, computing, etc., to remove interference, improve accuracy, and reduce false detection rates

Active Publication Date: 2021-03-02
HOHAI UNIV CHANGZHOU
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is the problem that the positioning efficiency and accuracy of the edge detection of the insulator area in the prior art need to be improved. An intelligent method for detecting insulators in power equipment is proposed, and through the analysis of image information, the realization of Quickly locate and detect the insulator area in the visible light image to achieve accurate and efficient detection of the insulator area

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
  • Salient edge guided insulator region detection method
  • Salient edge guided insulator region detection method
  • Salient edge guided insulator region detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described below in conjunction with the accompanying drawings.

[0021] Such as figure 2 As shown, the specific operation process of the saliency edge-guided insulator region detection method is as follows:

[0022] For a pre-collected image of a power accessory, the structured random forest edge detection algorithm is used to quickly extract the image edge probability map Edge 1 , Edge 1 The value of each pixel in is the intensity of the edge point, and the obtained coordinates are (i p ,j p ) edge point intensity is In the edge probability map, the outer edge of the insulator shows a strong edge state, which can be effectively distinguished from the background, and the inner edge of the insulator shows a weak edge state, which does not affect the integrity of the insulator. Then use the gradient information to suppress the non-maximum value to realize the refinement of the insulator probability map: in a specific embodiment...

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 region detection method based on saliency edge guidance, and the method comprises the steps: employing a structured random forest edge detection algorithm to quickly extract an image edge probability graph, and refining an image edge through non-maximum suppression; calculating the saliency value of each edge by using a Bayesian framework; screening out high-saliency edges, carrying out secondary judgment according to insulator edge distribution fluctuation morphological characteristics, and determining an insulator edge section; an SLIC algorithm being used to acquire insulator image superpixels, and the growth of color and texture features being used to realize the segmentation of the insulator string. According to the invention, the salient edge is used for insulator area detection, the sensitivity to the environment and insulator types is low, the method can be applied to detection of various environments and various insulators, the universalityis good, and a lot of manpower and material resources can be saved.

Description

technical field [0001] The invention relates to an insulator region detection method based on a saliency edge guidance, and belongs to the field of computer vision and transmission line inspection. [0002] technical background [0003] With the rapid development of my country's national economy, the continuous growth of people's daily life, industrial and commercial electricity demand, and the continuous advancement of the construction of the global energy Internet, more stringent requirements have been put forward for the safety and reliability of various power equipment. As an important part of the power grid, the transmission line's stable operation is an important guarantee for the safe use of electricity by the people. Insulators are important power accessories on overhead transmission lines. However, because transmission lines operate in high-voltage, strong-field open-air environments for a long time, insulators must not only bear normal mechanical and electrical load...

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): G06T7/00G06T7/11G06T7/13G06K9/46
CPCG06T7/0004G06T7/13G06T7/11G06V10/50
Inventor 李庆武周亚琴马云鹏雷萍储露露
Owner HOHAI UNIV CHANGZHOU