大连海事大学 航海学院,辽宁 大连 116026
[ "商家硕(1997-),男,辽宁沈阳人,博士研究生,2022年于沈阳化工大学获得硕士学位,现为大连海事大学交通信息工程及控制专业博士研究生,主要从事水下图像处理方面的研究。E-mail: shuojs757@126.com" ]
[ "李 颖(1968-),女,辽宁锦州人,教授,博士生导师,1997年于日本东北大学获得博士学位,现为海上交通安全与空间信息技术国家重点领域创新团队负责人,主要从事海洋环境感知方面的研究。E-mail: yldmu@dlmu.edu.cn" ]
收稿:2025-05-19,
修回:2025-07-10,
纸质出版:2025-09-25
移动端阅览
商家硕,李颖,袁靖懿等.均值强度差先验驱动的水下图像复原[J].光学精密工程,2025,33(18):2962-2979.
SHANG Jiashuo,LI Ying,YUAN Jingyi,et al.Underwater image restoration driven by the mean intensity difference prior[J].Optics and Precision Engineering,2025,33(18):2962-2979.
商家硕,李颖,袁靖懿等.均值强度差先验驱动的水下图像复原[J].光学精密工程,2025,33(18):2962-2979. DOI: 10.37188/OPE.20253318.2962. CSTR: 32169.14.OPE.20253318.2962.
SHANG Jiashuo,LI Ying,YUAN Jingyi,et al.Underwater image restoration driven by the mean intensity difference prior[J].Optics and Precision Engineering,2025,33(18):2962-2979. DOI: 10.37188/OPE.20253318.2962. CSTR: 32169.14.OPE.20253318.2962.
。针对水体选择性吸收和多次散射造成的水下图像低对比度、严重色偏与细节模糊等退化现象,提出一种均值强度差先验驱动的水下图像复原模型。首先,并行计算局部窗口内“蓝~绿、红”与“绿~蓝、红”两条分支的均值强度差,并取其平均值,构建噪声鲁棒的三通道耦合衰减先验,用于强度差估计。随后,依据“强度差~景深~透射率”链式物理关系,引入自适应斜率的指数映射,并结合一阶泰勒展开与差分近似,精确估计三通道透射图。同时计算强度差最大的像素集合均值,以估计背景光。最后,将透射图与背景光代入水下成像模型逆解,实现色彩自然、细节清晰的图像复原。在真实水下图像数据集UIEB与UCCS上的定性与定量实验表明,所提模型在UIQM,UCIQE,CCF,MWF等指标上均取得综合最优成绩,显著提升了色彩还原度、对比度和细节锐度。应用实验显示,复原图像的关键点检测数量显著增加,边缘表达更加连贯清晰,分割结果目标边界更清晰且误检率较低。该模型可自适应不同水体环境,复原色彩真实、细节清晰的水下图像,为后续水下视觉感知任务提供可靠的前端数据支撑。
Underwater images are degraded by wavelength-dependent absorption and multiple scattering. As a result, they exhibit low contrast, strong color cast, and blurred detail. To address these issues, an underwater image restoration model driven by the mean intensity difference prior (MIDP) was proposed. First, the mean intensity difference between the ‘blue-green, red’ and ‘green-blue, red’ branches was calculated in parallel within each local window and averaged to construct a noise-robust three-channel coupled attenuation prior. Subsequently, based on the physical relationship of the ‘intensity difference–depth map-transmission map’ chain, exponential mapping with an adaptive slope was introduced. The three-channel transmission maps were accurately estimated through a first-order Taylor expansion combined with a finite-difference approximation. Meanwhile, the mean of the set of pixels with the largest intensity difference was calculated to estimate the background light. Finally, the transmission maps and the background light were substituted into the inverse underwater imaging model to obtain restored images with natural colors and sharp details.First, image channels were split into two spectral branches: blue-green versus red, and green-blue versus red. Mean intensity differences were computed in parallel for both branches inside every sliding window. The two branch differences were averaged, producing a coupled three-channel attenuation prior for estimating intensity difference. The intensity differences estimated by MIDP were highly robust against image noise and local outliers. Next, a chained physical relation linked intensity difference, scene depth, and transmission map. An exponential mapping with adaptive slope transformed differences into initial transmission map estimation. A first-order Taylor expansion and finite-difference approximation then refined per-channel transmission maps. Pixels with the largest intensity differences were selected, and their mean was used to estimate background light. The estimated transmission map and background light were inserted into the inverse underwater imaging model to restore clear images. The resulting image exhibited natural colors, stronger contrast, and sharper detail.Extensive experiments are conducted on real datasets UIEB and UCCS. Quantitative evaluation shows MIDP obtains the highest combined scores on UIQM, UCIQE, CCF, and MWF. Quantitative evaluation shows that MIDP obtains color fidelity, local contrast, and gradient sharpness rise significantly. Additional application experiments were carried out on three vision tasks. In key-point detection, the restored images yielded many more stable keypoints . In edge detection, the restored images produced clearer and more coherent results. In underwater segmentation mask, the restored images produce tighter mask boundaries and lower false positive rates. These results demonstrate that MIDP adapts to varied water conditions and restores images with high quality. These results also supply high-quality input data for downstream underwater vision tasks.
柳翠寅 , 陈元帅 , 敬腾匀 , 等 . 自适应色彩补偿和多尺度融合的水下图像增强 [J]. 光学 精密工程 , 2025 , 33 ( 5 ): 802 - 817 . doi: 10.37188/ope.20253305.0802 http://dx.doi.org/10.37188/ope.20253305.0802
LIU C Y , CHEN Y S , JING T Y , et al . Adaptive color compensation and multi-scale fusion for underwater image enhancement [J]. Opt. Precision Eng. , 2025 , 33 ( 5 ): 802 - 817 . (in Chinese) . doi: 10.37188/ope.20253305.0802 http://dx.doi.org/10.37188/ope.20253305.0802
FAN J Y , XU J , ZHOU J C , et al . See through water: heuristic modeling toward color correction for underwater image enhancement [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2025 , 35 ( 5 ): 4039 - 4054 . doi: 10.1109/tcsvt.2024.3516781 http://dx.doi.org/10.1109/tcsvt.2024.3516781
LI B C , CHEN Z Q , LU L Y , et al . Cascaded frameworks in underwater optical image restoration [J]. Information Fusion , 2025 , 117 : 102809 . doi: 10.1016/j.inffus.2024.102809 http://dx.doi.org/10.1016/j.inffus.2024.102809
WANG Y D , GUO J C , HE W R , et al . Is underwater image enhancement all object detectors need? [J]. IEEE Journal of Oceanic Engineering , 2024 , 49 ( 2 ): 606 - 621 . doi: 10.1109/joe.2023.3302888 http://dx.doi.org/10.1109/joe.2023.3302888
SONG W , WANG Y , HUANG D M , et al . A Rapid Scene Depth Estimation Model based on Underwater Light Attenuation Prior for Underwater Image Restoration [M]. Advances in Multimedia Information Processing-PCM 2018. Cham : Springer International Publishing , 2018 : 678 - 688 . doi: 10.1007/978-3-030-00776-8_62 http://dx.doi.org/10.1007/978-3-030-00776-8_62
ZHOU J C , WANG Y Y , LI C Y , et al . Multicolor light attenuation modeling for underwater image restoration [J]. IEEE Journal of Oceanic Engineering , 2023 , 48 ( 4 ): 1322 - 1337 . doi: 10.1109/joe.2023.3275615 http://dx.doi.org/10.1109/joe.2023.3275615
ZHOU J C , LIU Q , JIANG Q P , et al . Underwater camera: improving visual perception via adaptive dark pixel prior and color correction [J]. International Journal of Computer Vision , 2023 : 1 - 19 . doi: 10.1007/s11263-023-01853-3 http://dx.doi.org/10.1007/s11263-023-01853-3
MISHRA A K , KUMAR M , CHOUDHRY M S . Underwater image enhancement by using transmission optimization and background light estimation via principal component analysis fusion [J]. Signal, Image and Video Processing , 2024 , 18 ( 4 ): 3855 - 3865 . doi: 10.1007/s11760-024-03047-x http://dx.doi.org/10.1007/s11760-024-03047-x
LIU Q , HE Z X , ZHANG D H , et al . DRC: Chromatic aberration intensity priors for underwater image enhancement [J]. Journal of Visual Communication and Image Representation , 2024 , 98 : 104065 . doi: 10.1016/j.jvcir.2024.104065 http://dx.doi.org/10.1016/j.jvcir.2024.104065
ZHANG W D , WANG Y D , LI C Y . Underwater image enhancement by attenuated color channel correction and detail preserved contrast enhancement [J]. IEEE Journal of Oceanic Engineering , 2022 , 47 ( 3 ): 718 - 735 . doi: 10.1109/joe.2022.3140563 http://dx.doi.org/10.1109/joe.2022.3140563
ZHANG W D , ZHOU L , ZHUANG P X , et al . Underwater image enhancement via weighted wavelet visual perception fusion [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 ( 4 ): 2469 - 2483 . doi: 10.1109/tcsvt.2023.3299314 http://dx.doi.org/10.1109/tcsvt.2023.3299314
LIANG Z , ZHANG W D , RUAN R , et al . Underwater image quality improvement via color, detail, and contrast restoration [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 ( 3 ): 1726 - 1742 . doi: 10.1109/tcsvt.2023.3297524 http://dx.doi.org/10.1109/tcsvt.2023.3297524
林森 , 查子月 . 结合色彩补偿与双背景光融合的水下图像复原 [J]. 光学 精密工程 , 2024 , 32 ( 7 ): 1059 - 1074 . doi: 10.37188/ope.20243207.1059 http://dx.doi.org/10.37188/ope.20243207.1059
LIN S , ZHA Z Y . Underwater image restoration method combining color compensation and dual background light fusion [J]. Opt. Precision Eng. , 2024 , 32 ( 7 ): 1059 - 1074 . (in Chinese) . doi: 10.37188/ope.20243207.1059 http://dx.doi.org/10.37188/ope.20243207.1059
ISLAM M J , XIA Y Y , SATTAR J . Fast underwater image enhancement for improved visual perception [J]. IEEE Robotics and Automation Letters , 2020 , 5 ( 2 ): 3227 - 3234 . doi: 10.1109/lra.2020.2974710 http://dx.doi.org/10.1109/lra.2020.2974710
NAIK A , SWARNAKAR A , MITTAL K . Shallow-UWnet: compressed model for underwater image enhancement (student abstract) [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 18 ): 15853 - 15854 . doi: 10.1609/aaai.v35i18.17923 http://dx.doi.org/10.1609/aaai.v35i18.17923
XUE X W , LI Z X , MA L , et al . Investigating intrinsic degradation factors by multi-branch aggregation for real-world underwater image enhancement [J]. Pattern Recognition , 2023 , 133 : 109041 . doi: 10.1016/j.patcog.2022.109041 http://dx.doi.org/10.1016/j.patcog.2022.109041
WANG H W , YANG M , YIN G , et al . Self-adversarial generative adversarial network for underwater image enhancement [J]. IEEE Journal of Oceanic Engineering , 2024 , 49 ( 1 ): 237 - 248 . doi: 10.1109/joe.2023.3297731 http://dx.doi.org/10.1109/joe.2023.3297731
ZHANG D H , ZHOU J C , ZHANG W S , et al . ReX-Net: a reflectance-guided underwater image enhancement network for extreme scenarios [J]. Expert Systems with Applications , 2023 , 231 : 120842 . doi: 10.1016/j.eswa.2023.120842 http://dx.doi.org/10.1016/j.eswa.2023.120842
SHANG J S , LI Y , XING H , et al . LGT: Luminance-guided transformer-based multi-feature fusion network for underwater image enhancement [J]. Information Fusion , 2025 , 118 : 102977 . doi: 10.1016/j.inffus.2025.102977 http://dx.doi.org/10.1016/j.inffus.2025.102977
姚婷婷 , 冯子豪 , 肇恒鑫 . 融合域迁移和注意力机制的水下图像增强 [J]. 光学 精密工程 , 2025 , 33 ( 2 ): 298 - 310 . doi: 10.37188/ope.20253302.0298 http://dx.doi.org/10.37188/ope.20253302.0298
YAO T T , FENG Z H , ZHAO H X . Underwater image enhancement by integrating domain transfer and attention mechanisms [J]. Opt. Precision Eng. , 2025 , 33 ( 2 ): 298 - 310 . (in Chinese) . doi: 10.37188/ope.20253302.0298 http://dx.doi.org/10.37188/ope.20253302.0298
JAFFE J S . Computer modeling and the design of optimal underwater imaging systems [J]. IEEE Journal of Oceanic Engineering , 1990 , 15 ( 2 ): 101 - 111 . doi: 10.1109/48.50695 http://dx.doi.org/10.1109/48.50695
HE K M , SUN J , TANG X O . Single image haze removal using dark channel prior [C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition . 20-25,2009 , Miami , FL, USA . IEEE , 2009 : 1956 - 1963 . doi: 10.1109/cvpr.2009.5206515 http://dx.doi.org/10.1109/cvpr.2009.5206515
Jr DREWS P , NASCIMENTO EDO , MORAES F , et al . Transmission estimation in underwater single images [C]. 2013 IEEE International Conference on Computer Vision Workshops . 2-8,2013 , Sydney, NSW, Australia . IEEE , 2013 : 825 - 830 . doi: 10.1109/iccvw.2013.113 http://dx.doi.org/10.1109/iccvw.2013.113
GALDRAN A , PARDO D , PICÓN A , et al . Automatic Red-Channel underwater image restoration [J]. Journal of Visual Communication and Image Representation , 2015 , 26 : 132 - 145 . doi: 10.1016/j.jvcir.2014.11.006 http://dx.doi.org/10.1016/j.jvcir.2014.11.006
PENG Y T , CAO K M , COSMAN P C . Generalization of the dark channel prior for single image restoration [J]. IEEE Transactions on Image Processing , 2018 , 27 ( 6 ): 2856 - 2868 . doi: 10.1109/tip.2018.2813092 http://dx.doi.org/10.1109/tip.2018.2813092
SONG W , WANG Y , HUANG D M , et al . Enhancement of underwater images with statistical model of background light and optimization of transmission map [J]. IEEE Transactions on Broadcasting , 2020 , 66 ( 1 ): 153 - 169 . doi: 10.1109/tbc.2019.2960942 http://dx.doi.org/10.1109/tbc.2019.2960942
JIN Z M , MA Y , MIN L H , et al . Variational image dehazing with a novel underwater dark channel prior [J]. Inverse Problems and Imaging , 2024 . doi: 10.3934/ipi.2024035 http://dx.doi.org/10.3934/ipi.2024035
CARLEVARIS-BIANCO N , MOHAN A , EUSTICE R M . Initial results in underwater single image dehazing [C]. OCEANS 2010 MTS/IEEE SEATTLE . 20-23,2010 , Seattle , WA , USA . IEEE , 2010 : 1 - 8 . doi: 10.1109/oceans.2010.5664428 http://dx.doi.org/10.1109/oceans.2010.5664428
YU H F , LI X B , LOU Q , et al . Underwater image enhancement based on DCP and depth transmission map [J]. Multimedia Tools and Applications , 2020 , 79 ( 27 ): 20373 - 20390 . doi: 10.1007/s11042-020-08701-3 http://dx.doi.org/10.1007/s11042-020-08701-3
LI C Y , GUO C L , REN W Q , et al . An underwater image enhancement benchmark dataset and beyond [J]. IEEE Transactions on Image Processing , 2019 . doi: 10.1109/tip.2019.2955241 http://dx.doi.org/10.1109/tip.2019.2955241
LIU R S , FAN X , ZHU M , et al . Real-world underwater enhancement: challenges, benchmarks, and solutions under natural light [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2020 , 30 ( 12 ): 4861 - 4875 . doi: 10.1109/tcsvt.2019.2963772 http://dx.doi.org/10.1109/tcsvt.2019.2963772
YANG M , SOWMYA A . An underwater color image quality evaluation metric [J]. IEEE Transactions on Image Processing , 2015 , 24 ( 12 ): 6062 - 6071 . doi: 10.1109/tip.2015.2491020 http://dx.doi.org/10.1109/tip.2015.2491020
PANETTA K , GAO C , AGAIAN S . Human-visual-system-inspired underwater image quality measures [J]. IEEE Journal of Oceanic Engineering , 2016 , 41 ( 3 ): 541 - 551 . doi: 10.1109/joe.2015.2469915 http://dx.doi.org/10.1109/joe.2015.2469915
WANG Y , LI N , LI Z Y , et al . An imaging-inspired no-reference underwater color image quality assessment metric [J]. Computers & Electrical Engineering , 2018 , 70 : 904 - 913 . doi: 10.1016/j.compeleceng.2017.12.006 http://dx.doi.org/10.1016/j.compeleceng.2017.12.006
CANNY J . A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1986 , PAMI-8( 6 ): 679 - 698 . doi: 10.1109/tpami.1986.4767851 http://dx.doi.org/10.1109/tpami.1986.4767851
BAY H , TUYTELAARS T , VAN GOOL L . SURF: speeded up robust features [C]. Computer Vision-ECCV 2006. Berlin, Heidelberg : Springer Berlin Heidelberg , 2006 : 404 - 417 . doi: 10.1007/11744023_32 http://dx.doi.org/10.1007/11744023_32
周玲 , 刘庆敏 , 金凯杰 , 等 . 水下图像复原和增强方法研究进展 [J]. 中国图象图形学报 , 2025 , 30 ( 1 ): 51 - 65 . doi: 10.11834/jig.240050 http://dx.doi.org/10.11834/jig.240050
ZHOU L , LIU Q M , JIN K J , et al . Research progress of underwater image restoration and enhancement methods [J]. Journal of Image and Graphics , 2025 , 30 ( 1 ): 51 - 65 . (in Chinese) . doi: 10.11834/jig.240050 http://dx.doi.org/10.11834/jig.240050
CHENG Z , FAN G D , ZHOU J C , et al . FDCE-net: underwater image enhancement with embedding frequency and dual color encoder [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2025 , 35 ( 2 ): 1728 - 1744 . doi: 10.1109/tcsvt.2024.3482548 http://dx.doi.org/10.1109/tcsvt.2024.3482548
ISLAM M J , EDGE C , XIAO Y Y , et al . Semantic segmentation of underwater imagery: dataset and benchmark [C]. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 24-24,2021 , Las Vegas, NV, USA. IEEE , 2020 : 1769 - 1776 . doi: 10.1109/iros45743.2020.9340821 http://dx.doi.org/10.1109/iros45743.2020.9340821
LIN T Y , DOLLÁR P , GIRSHICK R , et al . Feature pyramid networks for object detection [C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 21-26,2017 , Honolulu, HI, USA. IEEE , 2017 : 936 - 944 . doi: 10.1109/cvpr.2017.106 http://dx.doi.org/10.1109/cvpr.2017.106
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
