智能系统学报2025，Vol.20Issue(2)：475-485,11.DOI:10.11992/tis.202312004
基于多色域特征与物理模型的水下图像增强
Underwater image enhancement based on multicolor space features and physical models
摘要
Abstract
Underwater intelligent robots are susceptible to interference from suspended particles and light attenuation phenomena when detecting oceanic information,which leads to the degradation of visual images,causing color distor-tion and blurring of details.An underwater image enhancement method based on multicolor domain features and physic-al models is proposed to address these issues.First,a multicolor space feature aggregation network is designed to lever-age information from different color spaces to aid in color recovery.Then,a generalized white balance algorithm is ap-plied to achieve a more realistic visual performance,and deep learning algorithms are combined with underwater optic-al imaging models to produce clear images in a data-driven manner.Finally,a multicolor space alternation model is in-troduced to train the network and optimize parameters across different color spaces.Experiment results demonstrate that this method effectively improves color balance and detail recovery,outperforming classical and novel algorithms.The proposed method meets the image clarity requirements of underwater intelligent robot vision systems in tasks such as feature point matching and saliency detection.关键词
水下图像增强/成像模型/深度学习/多色域空间/特征聚合/轮换训练/算法推广/卷积神经网络Key words
underwater image enhancement/image formation model/deep learning/multicolor space/feature aggrega-tion/alternate training/algorithm generalization/convolutional neural network分类
计算机与自动化引用本文复制引用
张瑞航,林森..基于多色域特征与物理模型的水下图像增强[J].智能系统学报,2025,20(2):475-485,11.基金项目
国家重点研发计划项目(2018YFB1403303) （2018YFB1403303）
辽宁省教育厅高等学校基本科研项目(LJKMZ20220615) （LJKMZ20220615）
沈阳理工大学引进高层次人才科研支持计划项目(1010147000915). （1010147000915）
