Oil level instrument identification method based on multi-scene feature information fusion

A technology of feature information and recognition method, which is applied in the field of image processing, can solve the problems of low reading accuracy, high implementation cost, and low efficiency of manual reading, and achieve the effect of improving recognition accuracy

Pending Publication Date: 2021-10-12
国网陕西省电力公司渭南供电公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to propose a method that can automatically identify the oil quantity of the main transformer oil level gauge in a substation for a long time, which can effectively solve the problem of low efficiency of manual reading, and solve the problems of high cost and low reading accuracy of the traditional implementation

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
  • Oil level instrument identification method based on multi-scene feature information fusion
  • Oil level instrument identification method based on multi-scene feature information fusion
  • Oil level instrument identification method based on multi-scene feature information fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention is a part of the monitoring of the whole power system, and the overall relationship is as follows: an interface is agreed with the upstream, the incoming pictures are analyzed and processed, and the calculated results are returned.

[0022] Combined with the actual scene image 3 , the incoming pictures are multiple groups of main transformers, which are firstly processed by filtering.

[0023] Depending on the template matching algorithm, the scene can be determined according to its main variable name. Select the one with the highest correlation to get the current scene.

[0024] From the current scene, according to the position of the oil level gauge collected in advance, the oil level gauge is segmented out, and a certain angle correction is performed.

[0025] Send the segmented oil level gauge to the designed band-stop filter for preprocessing. The band-stop filter is mainly to filter out irrelevant elements and irrelevant frequency bands 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 an oil level meter identification method based on multi-scene feature information fusion. Due to one of various environmental factors such as light intensity, shooting angle, glass color and the like, great challenges are brought to image recognition of the liquid level instrument. The algorithm comprises the following steps of: firstly, carrying out preprocessing operations such as filtering on an input picture, then recognizing a scene and positioning an oil level gauge according to a template matching method, and finally carrying out final judgment through an algorithm judgment device. According to the method, the liquid level height of the instrument can be recognized through the image processing technology, circuit transformation is not needed, and cost is reduced. And the actual calculation amount after the algorithm is online is small, the condition of the main transformer oil level gauge can be fed back quickly and accurately, and the gauge with the low oil level can be alarmed and prompted in time.

Description

technical field [0001] The invention is used for the identification and alarm prompt of the oil level of the main transformer instrument of the substation, in particular, an oil level instrument identification method based on the fusion of multi-scene feature information. The invention mainly relates to the field of image processing, including image detection, positioning and recognition. For complex electric power actual scenes, how to quickly identify the current scene, locate the instrument to be identified, and identify the current oil quantity value of the instrument is the technical key of the present invention. Background technique [0002] For a complex power system, in order to ensure its normal operation, it is necessary to strictly control the indicators of each link. The power system usually transmits power over long distances, so it is very time-consuming and labor-intensive to check each meter on time by manpower. Moreover, the traditional monitoring method i...

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): G06K9/00G06K9/62G06K9/40
CPCG06F18/253
Inventor 杨绪坤付涛独亚军连磊陈瑞刘婧董武军孙小奇董彦龙梁快
Owner 国网陕西省电力公司渭南供电公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap