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

Power pole tower image detection method based on apparent texture structure

A power tower and image technology, applied in the field of power tower image detection based on the apparent texture structure, to achieve the effect of reducing dimensions

Inactive Publication Date: 2014-02-12
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the apparent texture structure can effectively represent the similarity of the appearance of the power tower, the overall structure information of a power tower cannot effectively represent the power tower with a large difference in shape structure and texture. In view of this problem, the inventor introduced a hybrid structure to handle this more complex shape and appearance variation

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 pole tower image detection method based on apparent texture structure
  • Power pole tower image detection method based on apparent texture structure
  • Power pole tower image detection method based on apparent texture structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The preferred embodiments will be described in detail below with reference to the accompanying drawings. It should be emphasized that the following description is exemplary only, and is not intended to limit the scope of the invention and its application.

[0036] figure 1 is the flow chart of the power tower image detection method based on the apparent texture structure, such as figure 1 As shown, the power tower image detection method based on the apparent texture structure provided by the present invention includes:

[0037] Step 1: Select a set number of images that are determined to have power towers and images that are determined to be non-existent.

[0038] Step 2: Preprocess the image for which the power tower is determined to exist and the image for which it is determined that there is no power tower, respectively, to obtain the overall filter of each image and the filter of the reference area with the largest value.

[0039] In this embodiment, taking the 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 pole tower image detection method based on an apparent texture structure, and belongs to the technical field of power circuit polling. The method comprises the following steps: selecting a set number of images which are confirmed that power pole towers do exist, and images which are confirmed that no power pole tower exists; respectively preprocessing the selected images so as to obtain an overall filter of each image and a filter of a reference area with a maximum value; substituting the overall filter of each image and the filter of the reference area with the maximum value into a target function to be trained; preprocessing images to be recognized so as to obtain overall filters of the images to be recognized and filters of reference areas with the maximum values; substituting the overall filters of the images to be recognized and the filters of the reference areas with the maximum values into the trained target function, and judging whether power pole towers exist in the images to be recognized according to the output result of the target function. According to the power pole tower image detection method, characteristics of repeatability of each part of the power pole tower are shared, and potential information of variable parts of the apparent texture structure of the power pole tower can be sufficiently utilized.

Description

technical field [0001] The invention belongs to the technical field of power line inspection, and in particular relates to a power tower image detection method based on an apparent texture structure. Background technique [0002] The reliable operation of the power transmission system in today's society is an important prerequisite for the stable development of society. Therefore, it is self-evident that the power transmission system provides reliable and high-quality power energy. However, the main mode of long-distance transmission and distribution lines is high-voltage and ultra-high-voltage overhead lines. Power companies need to conduct regular inspections of power line equipment, especially power lines and power towers, to ensure the stable and safe operation of the power transmission system and the normal progress of social production and life. [0003] Regular inspection of the environment of transmission and transformation lines and collection of operating status ...

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): G06K9/54G06K9/62
Inventor 吴华杨国田张晔柳长安刘春阳叶文
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)