改进的自适应学习注意力网络的水下图像增强

doi:10.3778/j.issn.1002-8331.2308-0173

摘要/Abstract

摘要： 针对水下图像噪声大、色偏严重和细节模糊等问题，提出了一种基于监督学习的自适应学习注意力网络的水下图像增强算法。利用多尺度融合加强通道之间空间信息的联系；通过并行注意力机制平衡照明特征和颜色信息；采用自适应学习保留浅层信息，学习重要特征信息；构造多项损耗函数，改善网络性能。实验结果表明，相对于已有算法，该算法的峰值信噪比（peak signal-to-noise ratio，PSNR）指标提高了8.99%，结构相似性（structural similarity index，SSIM）指标提高了15.39%，水下彩色图像评价（underwater color image quality evaluation，UCIQE）指标提高了1.92%，具有更好的视觉效果。

关键词: 注意力机制, 损失函数, 机器视觉, 水下图像增强, 多尺度

Abstract: An underwater image enhancement algorithm based on supervised learning and adaptive learning attention network (adaptive learning attention network for underwater image enhancement, LANet) is proposed to solve the problems of high noise, serious color bias and blurred details in underwater images. Firstly, multi-scale fusion is used to strengthen the spatial information connection between channels. Then, the lighting features and color information are balanced by parallel attention mechanism. Then adaptive learning is used to retain shallow information and learn important feature information adaptively. Finally, multiple loss functions are constructed to improve the network performance. The experimental results show that compared with the existing algorithm, the peak signal-to-noise ratio (PSNR) index and the structural similarity index (SSIM) index of the proposed algorithm are increased by 8.99% and 15.39% respectively. The underwater color image quality evaluation (UCIQE) index has been improved by 1.92%, with better visual effects.

Key words: attention mechanisms, loss function, machine vision, underwater image enhancement, multi-scale

许袁, 李锋, 闫家祥. 改进的自适应学习注意力网络的水下图像增强[J]. 计算机工程与应用, 2024, 60(24): 243-249.

XU Yuan, LI Feng, YAN Jiaxiang. Improved Adaptive Learning Attention Network for Underwater Image Enhancement[J]. Computer Engineering and Applications, 2024, 60(24): 243-249.

参考文献

[1] 陈辉, 王硕, 许家昌, 等. 基于多尺度特征融合生成对抗网络的水下图像增强[J]. 计算机工程与应用, 2023, 59(21): 231-241.
CHEN H, WANG S, XU J C, et al. Underwater image enhancement based on generate adversarial network with multiscale feature fusion[J]. Computer Engineering and Applications, 2023, 59(21): 231-241.
[2] 常戬, 陈洪福, 王冰冰. Transformer与CNN并行引导的水下图像增强[J]. 计算机工程与应用, 2024, 60(4): 280-288.
CHANG J, CHEN H F, WANG B B. Underwater image enhancement based on parallel guidance of Transformer and CNN[J]. Computer Engineering and Applications, 2024, 60(4): 280-288.
[3] 常戬, 韩旭. 结合导向滤波与自适应算子的水下图像增强[J]. 计算机工程与应用, 2023, 59(4): 216-223.
CHANG J, HAN X. Underwater image enhancement combining guide filtering with adaptive operator[J]. Computer Engineering and Applications, 2023, 59(4): 216-223.
[4] 晋玮佩, 郭继昌, 祁清. 基于条件生成对抗网络的水下图像增强[J]. 激光与光电子学进展, 2020, 57(14): 33-44.
JIN W P, GUO J C, QI Q. Underwater image enhancement based on conditional generative adversarial network[J]. Laser & Optoelectronics Progress, 2020, 57(14): 33-44.
[5] LI C, GUO C, REN W, et al. An underwater image enhancement benchmark dataset and beyond[J]. IEEE Transactions on Image Processing, 2019, 29: 4376-4389.
[6] GUO Y, LI H, ZHUANG P. Underwater image enhancement using a multiscale dense generative adversarial network[J]. IEEE Journal of Oceanic Engineering, 2019, 45(3): 862-870.
[7] CHEN X, YU J, KONG S, et al. Towards real-time advancement of underwater visual quality with GAN[J]. IEEE Transactions on Industrial Electronics, 2019, 66(12): 9350-9359.
[8] YE X, XU H, JI X, et al. Underwater image enhancement using stacked generative adversarial networks[C]//Advances in Multimedia Information Processing, 2018: 514-524.
[9] DU R, LI W, CHEN S, et al. Unpaired underwater image enhancement based on cyclegan[J]. Information, 2021, 13(1): 1.
[10] FABBRI C, ISLAM M J, SATTAR J. Enhancing underwater imagery using generative adversarial networks[C]//Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018: 7159-7165.
[11] WANG N, ZHOU Y B, HAN F L, et al. UWGAN: underwater GAN for realworld underwater color restoration and dehazing[J]. arXiv:1912.10269, 2019.
[12] LI C Y, ANWAR S, HOU J H, et al. Underwater image enhancement via medium transmission-guided multicolor space embedding[J]. IEEE Transactions on Image Processing, 2021, 30: 4985-5000.
[13] LIU X, GAO Z, CHEN B M. MLFcGAN: multilevel feature fusion-based conditional GAN for underwater image color correction[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(9): 1488-1492.
[14] ZHOU W, JIN J, LEI J, et al. CIMFNet: cross-layer interaction and multiscale fusion network for semantic segmentation of high-resolution remote sensing images[J]. IEEE Journal of Selected Topics in Signal Processing, 2022, 16(4): 666-676.
[15] 胡振宇, 陈琦, 朱大奇. 基于颜色平衡和多尺度融合的水下图像增强[J]. 光学精密工程, 2022, 30(17): 2133-2146.
HU Z Y, CHEN Q, ZHU D Q. Underwater image enhancement based on color balance and multi-scale fusion[J]. Optics and Precision Engineering, 2022, 30(17): 2133-2146.
[16] JIA F, MA L, YANG Y, et al. Pixel-attention CNN with color correlation loss for color image denoising[J]. IEEE Signal Processing Letters, 2021, 28: 1600-1604.
[17] 彭土有, 吴洁, 彭俊. 拉普拉斯边缘检测算法的改进及其在探地雷达中的应用[J]. 现代雷达, 2020, 42(8): 41-45.
PENG T Y, WU J, PENG J. Improvement of laplace edge detection algorithm and its application on GPR[J]. Modern Radar, 2020, 42(8): 41-45.
[18] CHOI Y, PARK H. Improving ESRGAN with an additional image quality loss[J]. Multimedia Tools and Applications, 2023, 82(2): 3123-3137.
[19] FU Z, FU X, HUANG Y, et al. Twice mixing: a rank learning based quality assessment approach for underwater image enhancement[J]. Signal Processing: Image Communication, 2022, 102: 116622.
[20] LI C, GUO C, REN W, et al. An underwater image enhancement benchmark dataset and beyond[J]. IEEE Transactions on Image Processing, 2019, 29: 4376-4389.
[21] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(12): 2341-2353.
[22] HUMMEL R. Image enhancement by histogram transfo-rmation[J]. Computer Graphics and Image Processing, 1977, 6(2): 184-195.
[23] ZUIDERVELD K. Contrast limited adaptive histogram equalization[J]. Graphics Gemss, 1994: 474-485.
[24] CHEN Y W, PEI S C. Domain adaptation for underwater image enhancement via content and style separation[J]. IEEE Access, 2022, 10: 90523-90534.
[25] ISLAM M J, XIA Y, SATTAR J. Fast underwater image enhancement for improved visual perception[J]. IEEE Robotics and Automation Letters, 2020, 5(2): 3227-3234.
[26] SALEH A, SHEAVES M, JERRY D, et al. Adaptive uncert-ainty distribution in deep learning for unsupervised underwater image enhancement[J]. arXiv:2212.08983, 2022.
[27] LIU S, FAN H, LIN S, et al. Adaptive learning attention network for underwater image enhancement[J]. IEEE Robotics and Automation Letters, 2022, 7(2): 5326-5333.