多尺度注意力机制的水下图像增强算法
Underwater Image Enhancement Based on Multi-Scale Attention Mechanism
DOI: 10.12677/CSA.2021.1110254, PDF,  被引量   
作者: 王士川, 杜 玲：天津工业大学计算机科学与技术学院，天津
关键词: 水下图像增强；生成对抗网络；深度学习；Underwater Image Enhancement； Generative Adversarial Network； Deep Learning
摘要: 由于不同波长的光在水环境中的衰减差异，原始的水下图像会出现偏绿、偏蓝和白雾的问题。针对水下图像增强出现的上述问题，本文通过结合多尺度密集块和注意力机制，提出了一个生成式对抗网络。在生成器中使用多尺度残差密集块，在后端使用注意力机制块来关注前端的特征，前者用来提高网络学习能力，后者增强网络的特征选择能力。判别器的每一层都使用谱归一化，放宽判别标准，以减少异常数据引起的梯度崩溃。同时，结合多种损失函数来增强生成对抗网络的泛化能力。提出的算法在公共数据集上进行了测试，并在实际应用中得到了验证。实验结果表明，该算法比现有算法有更好的性能。
Abstract: Due to the attenuation difference of different wavelengths of light in the water environment, the original underwater images show greenish, bluish and white haze problems. For underwater image enhancement, this paper proposes a generative adversarial network by combining multi-scale dense blocks and attention mechanism. The residual multiscale dense block is used in the generator, and the attention mechanism block is used in the back-end to focus on the front-end features, which can improve the learning ability and enhance the network’s ability to select features, respectively. Each layer of the discriminator uses spectral normalization and relaxes the discriminant criteria to reduce the gradient collapse caused by anomalous data. At the same time, multiple loss functions are combined to enhance the generalization ability of GAN networks. The proposed algorithm is tested on public datasets and validated in practical applications. Experimental results show better performance than existing algorithms.
文章引用：王士川, 杜玲. 多尺度注意力机制的水下图像增强算法[J]. 计算机科学与应用, 2021, 11(10): 2506-2516. https://doi.org/10.12677/CSA.2021.1110254

参考文献

[1] Mobley, C.D. (1994) Light and Water: Radiative Transfer in Natural Waters. Academic Press, Cambridge.
[2] Xiong, W., et al. (2019) Foreground-Aware Image Inpainting. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 16-20 June 2019, 5833-5841. [Google Scholar] [CrossRef] 
[3] Morel, A. (1978) Marine Optics. Earth Science Reviews, 14, 170-171. [Google Scholar] [CrossRef] 
[4] Jae, J.S. (1990) Computer Modeling and the Design of Optimal Underwater Imaging Systems. IEEE Journal of Oceanic Engineering, 15, 101-111. [Google Scholar] [CrossRef] 
[5] Song, W., et al. (2018) A Rapid Scene Depth Estimation Model Based on Underwater Light Attenuation Prior for Underwater Image Restoration. Advances in Multimedia Information Processing, Hefei, 21-22 September 2018, 678-688. [Google Scholar] [CrossRef] 
[6] Huang, D., Yan, W., Wei, S., et al. (2018) Shallow-Water Image Enhancement Using Relative Global Histogram Stretching Based on Adaptive Parameter Acquisition. In: Interna-tional Conference on Multimedia Modeling, Springer, Cham, 453-465. [Google Scholar] [CrossRef] 
[7] Ancuti, C., Ancuti, C.O., Haber, T. and Bekaert, P. (2012) Enhancing Underwater Images and Videos by Fusion. 2012 IEEE Conference on Computer Vision and Pattern Recogni-tion, Providence, 16-21 June 2012, 81-88. [Google Scholar] [CrossRef] 
[8] Li, C., et al. (2020) An Underwater Image Enhancement Benchmark Dataset and Beyond. IEEE Transactions on Image Processing, 29, 4376-4389. [Google Scholar] [CrossRef] 
[9] Hou, M., Liu, R., Fan, X. and Luo, Z. (2018) Joint Residual Learning for Underwater Image Enhancement. 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, 7-10 October 2018, 4043-4047. [Google Scholar] [CrossRef] 
[10] Islam, M.J., Luo, P. and Sattar, J. (2020) Simultaneous Enhance-ment and Super-Resolution of Underwater Imagery for Improved Visual Perception.
[11] Uplavikar, P., Wu, Z. and Wang, Z. (2019) All-in-One Underwater Image Enhancement Using Domain-Adversarial Learning.
[12] Li, C., Guo, J. and Guo, C. (2017) Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer. IEEE Signal Processing Letters, 25, 323-327.
[13] Fabbri, C., Islam, M.J. and Sattar, J. (2018) Enhancing Underwater Imagery Using Generative Adversarial Networks. 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, 21-25 May 2018, 7159-7165. [Google Scholar] [CrossRef] 
[14] Trucco, E. and Olmos-Antillon, A.T. (2006) Self-Tuning Un-derwater Image Restoration. IEEE Journal of Oceanic Engineering, 31, 511-519. [Google Scholar] [CrossRef] 
[15] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolu-tional Networks for Biomedical Image Segmentation. [Google Scholar] [CrossRef] 
[16] Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolu-tional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 640-651. [Google Scholar] [CrossRef] 
[17] Szegedy, C., et al. (2015) Going Deeper with Convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 1-9. [Google Scholar] [CrossRef] 
[18] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Ve-gas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[19] Guo, Y., Li, H. and Zhuang, P. (2019) Underwater Image Enhance-ment Using a Multiscale Dense Generative Adversarial Network. IEEE Journal of Oceanic Engineering, 45, 862-870.
[20] Liu, F., Shen, C., Lin, G., et al. (2015) Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields. IEEE Transactions on Pattern Analysis & Machine Intelligence, 38, 2024-2039. [Google Scholar] [CrossRef] 
[21] Miyato, T., Kataoka, T., Koyama, M., et al. (2018) Spectral Normalization for Generative Adversarial Networks. International Conference on Learning Representations, Vancouver, 30 April-3 May 2018.
[22] Li, H., Li, J. and Wang, W. (2019) A Fusion Adversarial Underwater Image Enhancement Network with a Public Test Dataset.
[23] Wang, Z., Bovik, A.C., Sheikh, H.R., et al. (2004) Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13, 600-612. [Google Scholar] [CrossRef] 
[24] Zuiderveld, K. (1994) Contrast Limited Adaptive Histogram Equali-zation. In: Graphics Gems, Morgan Kaufmann Publishers, Burlington, 474-485. [Google Scholar] [CrossRef] 
[25] Panetta, K., Gao, C. and Agaian, S. (2016) Hu-man-Visual-System-Inspired Underwater Image Quality Measures. IEEE Journal of Oceanic Engineering, 41, 541-551. [Google Scholar] [CrossRef] 
[26] Mittal, A., et al. (2013) Making a “Completely Blind” Image Qual-ity Analyzer. IEEE Signal Processing Letters, 20, 209-212. [Google Scholar] [CrossRef]