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

Electric power system switch state detection method based on image characteristic template matching

A template matching and power system technology, applied in character and pattern recognition, instruments, calculations, etc., to achieve the effect of strong practicability, guaranteed operation, and increased reliability

Inactive Publication Date: 2016-12-21
WUHAN UNIV
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to propose an image feature template matching method applied to power system switch state detection, which solves the problem of how to realize real-time, automatic and accurate identification of different types of switch states in the process of automatic dispatching of power systems

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
  • Electric power system switch state detection method based on image characteristic template matching
  • Electric power system switch state detection method based on image characteristic template matching
  • Electric power system switch state detection method based on image characteristic template matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0048] During initialization, it is necessary to set the template image, set the range of the target area and record the status of the template, and then take real-time pictures of the switches that need to be judged by controlling the video surveillance. The target area is used to frame the target area during detection to reduce the interference of irrelevant targets. With the help of this algorithm, the captured pictures are processed and analyzed to obtain the current real-time status. Since there are four types of switches to be tested (see the attached Figure 3-6 ), including switch type (three types) and text type. The initialization and identification process of each switch are different, combined below figure 1 , 2 , and the specific detection process is described by type:

[0049] Type 1, horizontal thick rod:

[0050] 1-1. Firstl...

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 provides an electric power system switch state detection method based on image characteristic template matching. According to the method, template initialization of to-be-detected switches is firstly required to accomplish, including storing original states and corresponding state pictures, framing movement scopes of to-be-detected targets in video images and framing categories of the to-be-detected switches. For each to-be-detected switch, calculating a trait value of a switch state of the image is only required, the trait value is compared with a characteristic value of the template, if an error of the trait value and the characteristic value is smaller than a threshold, the characteristic value identical to a template state is returned, otherwise, a state value opposite to the template state is returned, and an automatic detection process is accomplished. The method is advantaged in that automatic and accurate switch state identification of an electric power system in an automation process is realized, manpower cost is reduced, system reliability is improved, operation of the system is guaranteed, and relatively strong practicality is realized.

Description

technical field [0001] The invention is applied to switch state detection in the safe operation process of electric facilities, and relates to a power system switch state detection method based on image feature template matching. Background technique [0002] The discovery and application of electricity has greatly improved human production and living conditions. Without electricity, human civilization would continue to grope in the dark. As the process of human informatization continues to accelerate, the demand for power is also increasing, and power equipment is gradually developing towards semi-automation and automation. During the operation of power equipment, once some abnormality occurs, it will affect the whole system. In the entire power system layout, the most important thing is the switch part, which has rich styles and huge quantities. The detection of the power switch status in the system has always been done manually, which is not only time-consuming, but also...

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): G06K9/54G06K9/00
CPCG06V10/20G06F2218/12
Inventor 种衍文潘少明林云郑炜玲李爽
Owner WUHAN UNIV