A method for automatic identification of pointer instruments

An automatic recognition, pointer technology, applied in the field of image recognition, can solve the problems of low positioning accuracy and recognition accuracy, and achieve the effect of improving adaptability and stability, improving recognition accuracy, and compact connection

Active Publication Date: 2021-02-19
南京鑫和汇通电子科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem of low positioning accuracy and recognition accuracy in the automatic identification of pointer instruments in the prior art, the present invention proposes an automatic identification method for pointer instruments

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0021] Embodiment: a method for automatic identification of pointer instruments, comprising the following steps: Step 1, collecting template images of each type of instrument in the substation, obtaining the scale distribution and pointer position of each template image, any template image and the scale on it The distribution and pointer position are saved in a file, each file has a different name, and is recorded as a model file to distinguish the model category; step 2, zoom in, zoom out and rotate each template image to obtain the model in the same coordinate system Multi-angle and multi-scale homologous images of the same type, and extract the features of the homologous images that are conducive to tracking (Good Feature To Track) (referred to as GFTT features), save the feature points and calculate the feature vectors for normalization processing, and perform similar The image modeling of the instrument realizes the modeling of similar instruments with multiple angles and ...

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 present invention proposes an automatic identification method for pointer meters, which collects template images of each type of meter in a substation and obtains its scale distribution and pointer position and stores them in categories; each template image is enlarged, reduced and rotated to obtain the same type of multi-angle Multi-scale homologous images for image modeling of similar instruments; input the image of the instrument to be detected and extract the elliptical and rectangular areas, match the extracted areas with different template images and calculate the area matching degree, and match the areas If the degree of pointer matching is higher than the threshold of the pointer, it is judged as the meter region; the line segment detection of the meter region is carried out and the pointer matching degree is calculated. Two pointer scales, and the pointer reading is calculated against the corresponding template image. The invention solves the problems of low automatic identification positioning accuracy and identification accuracy of the instrument, and improves the identification accuracy.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an automatic recognition method for a pointer instrument. Background technique [0002] Pointer meters have the advantages of simple structure and high reliability, and are widely used in substations to monitor the operating status of power equipment. For the automatic identification of pointer instruments, the existing research includes using the hough transform to identify the pointer and the scale at the same time, but using the hough transform to locate the instrument is prone to positioning errors; when performing instrument modeling, many current methods need to identify each substation Modeling a single electric meter requires heavy workload and low practicability. Moreover, in the actual application process, affected by the external environment and equipment conditions, the images of the same kind of meters collected are different, and the angle, size and expos...

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): G06K9/46G06K9/62
CPCG06V10/44G06V10/751G06V2201/02G06F18/23G06F18/24
Inventor 汪辉任大明刘晶丁飞任昌
Owner 南京鑫和汇通电子科技有限公司
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