机器人2026，Vol.48Issue(1)：163-173,11.DOI:10.13973/j.cnki.robot.240331
基于轻量级U形网络的颜色空间优化水下图像增强方法
Underwater Image Enhancement Method with Color Space Optimization Based on Lightweight U-Net
摘要
Abstract
To address the issues of color deviation,contrast reduction,and detail blurring in underwater images caused by light refraction and absorption,this paper proposes an underwater image enhancement method with color space optimization based on a lightweight U-shaped network(DU2Net).Firstly,the U-shaped network is optimized leveraging a large-scale dataset of real underwater scenes(DSUI)containing 11 739 images,along with high-quality reference images,semantic segmentation maps,and medium transmission maps.Axial depth-wise convolution and dense attention blocks are employed to effectively reduce computational complexity and parameter quantity,thereby significantly enhancing DU2Net processing speed and image enhancement quality.Secondly,a multi-color-space loss function combining RGB,LAB,and LCH color spaces is introduced to better align with human visual perception characteristics,further improving the color fidelity and contrast of the restored images.Experimental validation demonstrates that compared to state-of-the-art underwater image enhancement techniques such as UDCP and CRUHL,DU2Net achieves improvements of 0.367,0.072,26.165,and 7.833 on the UIQM(underwater image quality measure),UCIQE(underwater color image quality evaluation),CCF(color cast factor),and AG(average gradient)metrics,respectively.Furthermore,DU2Net attains a processing speed 8 times faster than UDCP.These results validate the applicability and efficacy of the proposed method across diverse underwater scenarios.关键词
水下图像增强/轴向深度卷积/密集注意力/多颜色空间损失函数Key words
underwater image enhancement/axial depth convolution/dense attention/multi-color space loss function引用本文复制引用
李明桂,周焕银,龚利文..基于轻量级U形网络的颜色空间优化水下图像增强方法[J].机器人,2026,48(1):163-173,11.基金项目
江西省科技厅重点基金(20224ACB204022) （20224ACB204022）
国家自然科学基金(62063001) （62063001）
人工智能四川省重点实验室开放基金(2023RYY02). （2023RYY02）
