Substation Infrared Image Segmentation Method Based on Improved Two-Dimensional Otsu

Abstract

The invention discloses a transformer substation infrared image segmentation method based on an improved two-dimensional Otsu algorithm, solves the problem that the conventional two-dimensional Otsu algorithm has error segmentation and incomplete target segmentation; the method lies in that the weight adaptive algorithm of the morphology is adopted for performing denoising on an input image, and the improved two-dimensional Otsu algorithm is finally adopted for performing image segmentation. According to the transformer substation infrared image segmentation method provided by the invention, target regions can be divided completely and effectively, and a good foundation is laid for characteristic extraction of subsequent target regions.

Description

technical field [0001] The invention belongs to the field of image processing of electric power system substation equipment, and in particular relates to an improved two-dimensional Otsu-based substation infrared image segmentation method. Background technique [0002] Since infrared imaging technology is a non-contact and long-distance thermal imaging detection of infrared light radiated from the surface of the equipment, it is not subject to electric field interference, so it has the characteristics of intuition, accuracy, high sensitivity, fast, safe, and wide application range. It has become a substation equipment An important means of health status monitoring and fault diagnosis. [0003] Infrared image segmentation technology is an important part of the intelligent software module in the fault monitoring and diagnosis of electrical equipment in substations, and it is also an important link in the system to complete fault monitoring and diagnosis. Target extraction and...

AI Technical Summary

Problems solved by technology

[0004] Although the traditional two-dimensional Otsu threshold segmentation method considers the local spatial information of the image, suppresses the interference of part of the noise, and the segmentation effect is ideal, but it does not consider the deviation of the gray value of the pixel point from its surrounding area, and according to the two The three-dimensional histogram roughly treats a small number of pixels as edges and noise, which causes errors in image segmentation.

Images