Self-adaptive substation pointer instrument recognition method

Abstract

The invention provides a self-adaptive automatic recognition method of a transformer substation pointer instrument, solves the recognition problem of the transformer substation for the outdoor pointerinstrument, and has important significance for realizing automatic management of transformer substation equipment. Implementation of the method comprises the steps that pointer instrument area positioning is carried out, and a preprocessing method with contrast normalization is mainly used; instrument recognition comprises a self-adaptive edge detection method, a Hough circle detection method anda Hough straight line detection method, average optimization is carried out on the result of Hough straight line detection, and the detection accuracy is further improved. The method has a good detection effect on the detection of the pointer instrument of the transformer substation, and has a beneficial effect on the automatic management, operation and maintenance of the transformer substation.

Description

technical field [0001] The invention belongs to the technical field of image detection and recognition, and mainly relates to an adaptive automatic recognition method of a substation pointer instrument. Background technique [0002] As the hub of the power system, the substation is very important to ensure the safety and reliability of the power equipment in the substation. Among them, there are many pointer instruments outside the substation to monitor the voltage value and safety conditions of the substation equipment, and the substation is often located in the suburbs, resulting in a high cost of manual data collection. In order to alleviate this situation, a large number of cameras can be deployed. , through the way of target detection, the reading and recording of the instrument are obtained, so that the whole process is automated. [0003] Due to the complex outdoor scene of the substation, the image is seriously affected by the weather, especially in the case of comp...

AI Technical Summary

Problems solved by technology

[0003] Due to the complex outdoor scene of the substation, the image is seriously affected by the weather, especially in the case of complex weather such as lighting conditions and fog conditions, the effect of using template matching or feature matching is often poor, and because the deep learning method requires A large number of training samples, the system does not meet this condition, in order to ensure the accuracy of detection, in this scenario, there are problems such as drastic changes in illumination, and a single template cannot be applied

Images