Template matching-based pointer type instrument multi-condition automatic reading method

Abstract

The invention relates to a template matching based pointer type instrument multi-condition automatic reading method. The method comprises the following steps: step 1, carrying out dial plate posture correction based on angular point matching and perspective transformation; 2, positioning the center of a pointer based on template matching of a two-step method; and step 3, carrying out pointer rotation angle estimation based on the Zernike image moment.

Description

technical field [0001] The invention belongs to the field of pattern recognition and image processing, and mainly relates to image registration, image viewing angle correction, and automatic and accurate reading of a pointer instrument under the condition of ambient light changes and small objects blocking. Background technique [0002] In power system scenarios such as substations and distribution stations, because pointer meters have the characteristics of simple structure, stable performance, low cost, and strong anti-interference, compared with digital meters, environmental changes have less impact on them. Influence, so the pointer instrument is widely used. However, the pointer instrument has no electronic interface, and manual inspection is required for data reading. The efficiency and accuracy are not high, and manual reading may cause personal safety problems for the staff. Therefore, designing an algorithm suitable for robot automatic inspection plays an important...

AI Technical Summary

Problems solved by technology

For example, foreign F.Corrêa Alegria and others use the subtraction method and Hough line detection to extract the position of the hands, and use the angle method to obtain the degree of the dial. The disadvantage of this algorithm is that it generally requires sub-pixel-level precise positioning or dial registration, and is not suitable for open air. Scenes with large environmental interference; the distance method refers to expanding the polar line of the scale part of the dial into a rectangular coordinate form, and then using the vertical projection method to locate the intersection point of the hands and the scale. Typical algorithms such as Zheng et al. [4] Recognition Algorithm Using Epipolar Expansion Algorithm Combined with Projection Algorithm

This distance method based on the scale line as a reference is based on the complete extraction of the dial scale line. In the case of uneven illumination and foreign objects, the scale line may be lost, which makes the distance method impossible.

In addition, for the problem of missing tick marks in the distance method, Li et al. [5] A scale line extension method is proposed to repair the missing scale lines. This algorithm relies more on the accuracy of the extraction of the non-missing part of the scale line, and does not fundamentally solve the problems of illumination changes and small object occlusion.

[0006] To sum up, the current pointer meter reading algorithm fails to systematically solve the interference of complex lighting conditions, angle tilt, small object occlusion and other factors that may occur in the automatic recognition process of pointer meters, and its robustness is poor.

Images