Pulsed eddy current thermal imaging high-resolution sharpening method based on deep learning

Abstract

The invention discloses a pulsed eddy current thermal imaging high-resolution sharpening method based on deep learning. The method comprises the following steps: 1) collecting an image; 2) obtaining alow-resolution image; 3) carrying out ESRGAN network training; 4) constructing and training a gradient conversion network module; 5) constructing and training a fusion network module; 6) model testing; performing super-resolution reconstruction on the pulsed eddy current thermal imaging image based on deep learning; fusing the initial high-resolution image and the gradient high-resolution image through a fusion module to generate a final high-resolution image. According to the invention, the gradient is introduced on the basis of the high-resolution image reconstructed by the ESRGAN network to improve the high-frequency information of the image, enhance the contour and detail information of the image, and improve the image reconstruction effect; high-resolution sharpness of pulsed eddy current thermal imaging can be achieved, the requirement for the resolution of a thermal infrared imager is lowered, cost is lowered, the requirement for pulsed eddy current power and action time is lowered, energy consumption is reduced, damage to a target is reduced, and measurement rapidity is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision and image super-resolution reconstruction, and specifically relates to a high-resolution clearing method of pulsed eddy current thermal imaging based on deep learning. Background technique [0002] As a kind of infrared detection technology, pulsed eddy current thermal imaging technology is gradually being applied to the health detection of metal component structures due to its advantages of high efficiency, non-contact, controllability, simple operation, and intuition, especially for metal subsurface defects due to its Features are not easy to observe and detect directly on the material surface, so pulsed eddy current thermal imaging is an effective method. However, the low resolution of pulsed eddy current thermography results in poor analysis and visualization. When using pulsed eddy current thermal imaging technology to detect metal defects, there are problems such as poor setting of ...

AI Technical Summary

Problems solved by technology

However, the low resolution of pulsed eddy current thermography results in poor analysis and visualization

When using pulsed eddy current thermal imaging technology to detect metal defects, there are problems such as poor setting of excitation parameters, small defect size and environmental factors, resulting in low signal-to-noise ratio of the original infrared image and blurred defect features.

Images