Method for improving resolution of infrared image and application thereof

Abstract

The invention discloses a method for improving the resolution of an infrared image and application of the method, and belongs to the technical field of infrared image resolution improvement. The method is based on support of an improved block compressed sensing theory, and comprises the following steps: a, establishing an original compressed sensing image super-resolution basic model; b, introducing an image degradation model; c, establishing an improved compressed sensing image super-resolution model; d, establishing a super-resolution image reconstruction objective function based on an improved block compressed sensing theory; and e, optimizing the objective function, and obtaining a reconstructed high-resolution image signal. The method is applied to detection of power equipment faults. According to the method, image details can be recovered more effectively in a short time, the edge contour of the infrared image is enhanced, and image segmentation is facilitated. The application has the characteristics of convenience in fault area positioning, fault type identification and the like.

Description

technical field [0001] The invention relates to the technical field of infrared image resolution improvement. Background technique [0002] In recent years, infrared thermal imaging technology has been widely used in power grids because of its convenience and non-contact advantages. Through infrared detection of each power equipment in the power system, the operating status of the power equipment can be judged by combining certain image processing methods after obtaining the distribution map of the surface temperature of the power equipment. It avoids the direct contact between the staff and the power equipment, realizes the live detection of the equipment, and can discover the potential hidden dangers of the equipment in time; in addition, it can also promote the digitization and intelligence of the operation and maintenance of the power system, and realize the automatic diagnosis of faults through computer vision technology , rather than traditional manual diagnosis. How...

AI Technical Summary

Problems solved by technology

Among the methods based on interpolation, representative methods such as the nearest neighbor method, bilinear, and bicubic all use the information of surrounding points to obtain the value of the point to be estimated. Such a simple estimation method will lead to blurred, jagged, and blurred images. Issues such as blurry edges and loss of detail

Based on the classic iterative back projection method in the modeling method, it is difficult to introduce prior knowledge, and the result is unstable

The learning-based method requires a large number of training samples. The pre-model training requires a large number of high-definition images and high-performance hardware equipment support, and the reconstructed high-resolution images may have false textures. This defect will affect the infrared monitoring and diagnosis process. Operations such as image segmentation, target recognition, and fault location have extremely adverse effects

Images