Active contour model image segmentation method based on SLIC superpixel segmentation and saliency detection algorithm

Abstract

The invention discloses an active contour model image segmentation method based on SLIC superpixel segmentation and a saliency detection algorithm. The method comprises the following steps: firstly, preprocessing an image by using an SLIC algorithm to obtain a superpixel segmentation result; for a superpixel segmentation result, calculating the contrast between irregular superpixel blocks to estimate a saliency value so as to obtain a salient region, and then the obtained salient information and the spatial correlation between pixels being subjected to weighted fusion to obtain a saliency map; then extracting a region boundary of the saliency map by using a Canny operator, and constructing an initial level set phi by taking the saliency region boundary as an initial curve. The problems of too many parameters and the like existing in an existing active contour CV model are improved, the improved active contour CV model is used for further processing an ultraviolet image, and finally an accurate and ideal ultraviolet segmentation image is obtained.

Description

technical field [0001] The invention relates to the fields of electric equipment discharge detection and image processing, in particular to an active contour model image segmentation method based on SLIC superpixel segmentation and saliency detection algorithm. Background technique [0002] At present, ultraviolet imaging technology is an important means to detect insulation discharge outside the line. This technology can detect the ultraviolet light signal emitted by the discharge with a wavelength of 240-280nm, output the ultraviolet image of the discharge, and gradually use the number of photons as the quantification of the discharge intensity. parameter. However, due to the white noise points caused by inherent shot noise in the UV image, it will affect the evaluation of the equipment discharge state. Accordingly, how to segment the actual discharge area from the UV image and use it for the insulator discharge state Effective detection is the key to this technology. ...

AI Technical Summary

Problems solved by technology

It can overcome the problems of too many iterations of the traditional active contour model, long processing time, and insufficient accuracy. The saliency detection algorithm based on SLIC superpixel segmentation is combined with the active contour model, and the active contour model is improved. The image segmentation accuracy and segmentation speed have been improved

Images