A low-light image enhancement method based on saliency foreground content

Abstract

The invention discloses a low-light image enhancement method based on salient foreground content, which learns the salient foreground content information in the low-light image and fuses it with the enhancement process, and inputs the low-light image into the low-light salient attention depth network model SAM to obtain The output saliency map; input the low-light image to the depth prediction network model and output the corresponding depth map; use the obtained depth map as a guide map to guide the saliency map to obtain a salient foreground map; for the input low-light image, use the salient The foreground image is used as the weight of the enhancement degree, and the LIME enhancement algorithm is used to enhance the low-light image to different degrees, and finally the result image based on the salient foreground content enhancement is obtained. The invention can effectively enhance the salient foreground content area in the low-light image, and at the same time suppress the excessive enhancement of the background and irrelevant content areas and suppress noise.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a low-light image enhancement method based on salient foreground content. Background technique [0002] With the development and update of image sensor equipment and technology, people can obtain high-quality images more conveniently. However, in low-light environments, image sensors will suffer from low contrast, random noise, and color distortion due to insufficient light. These problems often hinder the development of subsequent computer vision and image processing tasks such as object recognition, detection and tracking. In order to solve the above-mentioned problems of low-light images, people have proposed many low-light enhancement methods, which can be divided into three categories according to the theories and models based on them: the first category is based on contrast enhancement methods such as grayscale histograms Image equalization and adaptiv...

AI Technical Summary

Problems solved by technology

[0003] Although the existing image enhancement methods have achieved satisfactory results for some low-light datasets, they often expose the image over-enhancement and Amplify issues such as random noise

Specifically, whether it is contrast enhancement or Retinex model enhancement, these methods uniformly enhance all areas of the entire image, so that the dark sky, ground or wall that people do not pay attention to will often be over-represented. is more likely to cause overexposure enhancement in areas such as street lights and car lights

On the other hand, due to the overall enhancement, the random noise previously hidden in the dark is exposed, which will not only destroy the important structural information inside the image, but also seriously affect the subjective evaluation of the image.

[0004] The main reason for the above problems is that the existing low-light image enhancement methods often ignore the salient content and foreground and background content in the image during the enhancement process, and only directly enhance the entire image, which will lead to excessive enhancement and enlargement. Noise etc.

Images