一种基于局部背景光的水下非均匀光图像增强方法和系统

By constructing an underwater non-uniform light image enhancement method with local background light, the problem of unsatisfactory image processing effect in the existing technology under the scene of changing illumination is solved, and high-quality enhancement of underwater images is achieved, which is applicable to complex illumination conditions.

CN118212167BActive Publication Date: 2026-07-17HUAZHONG UNIV OF SCI & TECH

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUAZHONG UNIV OF SCI & TECH
Filing Date
2024-03-07
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing underwater image enhancement methods do not perform well in handling complex lighting scenarios with both ambient and artificial light, especially when the lighting parameters are not accurately estimated, which makes it difficult to guarantee image quality.

Method used

An underwater non-uniform light image enhancement method based on local background light is adopted. Through preprocessing, weighted fusion of brightness, gradient and saturation maps, a weight score map is constructed, local artificial light and global ambient light are searched, and the depth map is optimized and converted into a transmittance map by combining the Lambert-Beer law, and finally the enhanced image is retrieved.

Benefits of technology

It effectively improves the quality of underwater non-uniform lighting images, is suitable for scenes with complex lighting conditions, maintains image boundaries and detail information, and enhances image clarity and contrast.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118212167B_ABST
    Figure CN118212167B_ABST
Patent Text Reader

Abstract

本申请属于图像增强技术领域,具体公开了一种基于局部背景光的水下非均匀光图像增强方法和系统。通过本申请,利用环境光和人工光结合的局部背景光替代现有物理成像模型中的全局背景光,从而改进物理成像模型,基于此前提,使用亮度图、梯度图和饱和度图构建权重得分图,并以此为依据,对包含非均匀光的输入图像进行光照估计,得到局部背景光分布图,再根据局部背景光分布图和粗略深度图进行优化,生成优化深度图,并将其转换为透射率图,接着根据局部背景光分布图、透射率图和原始图像,反演增强图像,本申请不仅考虑了非均匀光的影响,同时一定程度上保证图像的边界和细节信息,有效提高水下非均匀光图像的质量,尤其适用于光照条件复杂的场景。
Need to check novelty before this filing date? Find Prior Art