Image optimization method integrating deep learning night vision enhancement and filtering noise reduction

Abstract

The invention relates to an image optimization method integrating deep learning night vision enhancement and filtering noise reduction. The enhancement quality of the light enhancement network is evaluated through a non-reference loss function, a to-be-enhanced image is used as input, high-order curves are generated as output, then the curves are used for adjusting the input dynamic range pixel by pixel to obtain a night vision enhanced image, noise reduction processing is performed on the enhanced image by using non-local mean filtering, while the color and details of the enhanced image are kept, a large amount of noise caused by night vision enhancement is filtered out, so that the image obtains a better optimization effect. According to the invention, no obvious noise is generated under the condition that images shot at night are clear.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to an image optimization method that combines deep learning night vision enhancement and filtering noise reduction. Background technique [0002] With the increasing improvement of people's lives, the requirements for the quality of captured pictures are gradually increasing. How to better process images has become a hot research field at present, and night image enhancement technology has become the mainstream of the times. However, due to the heat generated by the photosensitive sensor when it works for a long time, it will destroy some pixels during imaging, which will make the night vision image dark overall and the details are not obvious, and will inevitably introduce a lot of noise, causing the night vision image to be sharp. deterioration. [0003] Although traditional nighttime enhancement algorithms such as histogram equalization, gamma transform, and adaptive hist...

AI Technical Summary

Problems solved by technology

However, due to the heat generated by the photosensitive sensor when it works for a long time, some pixels will be destroyed during imaging, which will make the night vision image dark overall and the details are not obvious, and will inevitably introduce a lot of noise, resulting in sharp night vision images. deterioration

[0003] Although traditional nighttime enhancement algorithms such as histogram equalization, gamma transformation, and adaptive histogram equalization can enhance nighttime images, the noise amplification effect caused by enhancement seriously affects the effect of enhanced night vision images.

Images