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

A method for extracting tower targets in UAV inspection transmission line images

A transmission line and target extraction technology, which is applied to computer components, instruments, calculations, etc., can solve the problems of long running time, low extraction accuracy, and inability to extract images of power towers in real time, achieving real-time extraction, fast operation speed, and extraction high precision effect

Active Publication Date: 2018-11-23
安徽工业大学科技园有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the disadvantages that the existing power tower image recognition method cannot effectively extract the power tower image in the transmission line, the extraction accuracy is low, and the running time is long, resulting in the inability to perform real-time extraction of the power tower image. Provides a method for extracting tower targets in UAV inspection transmission line images

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
  • A method for extracting tower targets in UAV inspection transmission line images
  • A method for extracting tower targets in UAV inspection transmission line images
  • A method for extracting tower targets in UAV inspection transmission line images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] The characteristics of power towers in aerial images are as follows: (1) power towers occupy more pixels in aerial images, and the brightness value is larger; (2) power towers appear as visible axisymmetric polygons in aerial images ; (3) The connection point of the outline of the power tower is a dense area of ​​corner points.

[0045] A method for extracting pole and tower targets in the image of power transmission lines inspected by drones in this embodiment is developed in combination with the above characteristics of power poles and towers in aerial images. The process is as follows figure 1 As shown, the specific steps are:

[0046] Step 1. The power tower occupies more pixels in the aerial image, and the overall luminance value of the tower is larger than the background. Therefore, the captured image is converted from the RGB color space to the HSI chromaticity saturation luminance space, and the HSI chromaticity is extracted The I component image of the saturat...

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 method for extracting a tower target in an image of an unmanned aerial vehicle inspecting a transmission line, and belongs to the technical field of pattern recognition and intelligent computing. The method for extracting a tower target of the present invention includes the following steps: converting an image obtained by aerial photography from RGB color space to HSI chroma saturation brightness space, and performing a second filtering on the I component image of the HSI chroma saturation brightness space after median filtering. The binary image of the outline of the power tower is obtained by value processing; the improved Susan corner detection method is used to detect the corners of the binary image of the outline of the power tower, and the positions of all corners are marked in the binary image of the outline of the power tower; The moment-invariant centroid detection algorithm detects the centroid of the corner sequence, and uses this as the center to mark the position of the power tower in the original image. By using the technical solution of the present invention, the power tower can be accurately extracted in real time, and the fault diagnosis of the insulator, hardware and other power components on the tower can be guaranteed.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and intelligent computing, and more specifically relates to a method for extracting pole and tower targets in an image of a transmission line inspected by an unmanned aerial vehicle. Background technique [0002] With the sustained and rapid development of my country's national economy and the increasing scale of urban construction, the rapid and intensive development of high-tech industries, finance, medical and health industries, and the increasing demand for electric energy, economic development not only increases the load of urban and rural power grids, but also affects The reliability and quality of power supply put forward higher requirements. Therefore, 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 produ...

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): G06K9/34G06K9/46
CPCG06V10/267G06V10/462G06V10/44
Inventor 方挺韩家明
Owner 安徽工业大学科技园有限公司
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