Pointer instrument correction identification method and device based on deep learning

Abstract

The invention provides a pointer instrument correction identification method and device based on deep learning. The method comprises the following steps: obtaining a dial mask image; performing ellipse fitting on the dial plate mask image and detecting a minimum circumcircle to obtain a perspective transformation matrix, and performing preliminary correction on the instrument image by using the perspective transformation matrix; removing a pointer in the instrument image, and obtaining a character minimum bounding rectangular frame according to the obtained character information; performing rotation correction on the instrument image containing the pointer according to the deflection angle of the minimum bounding rectangular frame of the characters; obtaining a corrected pointer mask image; carrying out refining processing on the pointer mask image, and carrying out straight line detection on the refined pointer skeleton; and calculating an instrument reading result according to the deflection angle of the straight line in the plane coordinate system. According to the invention, comprehensive correction of the tilt distortion problem of the instrument in a three-dimensional space in an actual scene can be realized, and a series of three-dimensional correction problems such as stretching, compression and rotation of the acquired instrument image can be processed.

Description

technical field [0001] The invention relates to the field of pointer-type meter reading recognition, in particular to a pointer-type meter correction identification method and device based on deep learning. Background technique [0002] The installation and use of pointer instruments are usually relatively simple, the environment has little impact on them, and they are not easily disturbed by some external factors, and have a long life cycle. Therefore, it is widely used in substations. However, since the volume of the dial is relatively small for the convenience of installation and maintenance, when the range is large, the value of each division becomes larger, which can easily make the error in reading the number larger, and the meter will also be read manually. There are unavoidable reading errors. With the development and improvement of image processing technology and deep learning, intelligent inspection robots gradually replace manual recognition of pointer meter rea...

AI Technical Summary

Problems solved by technology

[0003]The existing image processing technology realizes the reading recognition process of the pointer instrument. Due to the limited installation position of the instrument panel and the limited angle adjustment of the camera, it is difficult to obtain the reading of the instrument. For the image, whether it is a traditional image processing method or an image processing method based on deep learning, the image correction of the circular instrument is often not corrected completely, and the rotation correction of the circular instrument cannot be well realized, so the instrument is in the image. When there is a problem of tilting the rotation angle, the reading error of the angle method is large, which is difficult to meet the requirements of actual industrial applications

Images