|Table of Contents|

[1] Yu Jing, Zhang Le, Wu Meng, Jiang Shanghang, et al. Two-stage attention for rapid underwater image enhancement [J]. Journal of Southeast University (English Edition), 2023, 39 (4): 410-415. [doi:10.3969/j.issn.1003-7985.2023.04.010]
Copy

Two-stage attention for rapid underwater image enhancement()
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
39
Issue:
2023 4
Page:
410-415
Research Field:
Computer Science and Engineering
Publishing date:
2023-12-20

Info

Title:
Two-stage attention for rapid underwater image enhancement
Author(s):
Yu Jing;  Zhang Le;  Wu Meng;  Jiang Shanghang;  Li Daojiang
School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China
Keywords:
underwater image enhancement;  self-attention;  cross-attention;  transmission map
PACS:
TP391
DOI:
10.3969/j.issn.1003-7985.2023.04.010
Abstract:
A fast underwater image enhancement algorithm is proposed based on a two-stage attention mechanism to improve the quality of underwater degraded images. First, the proposed algorithm adopts a self-attention mechanism within features for enhancing the attention of the network to important information. Subsequently, a physical prior-based underwater transmission map is integrated into the network through a cross-attention mechanism for further enhancing the feature representation toward quality-degraded areas. Finally, a multiple joint loss function is designed using subjective and objective criteria for guiding the network to better visual enhancement effects. The experimental results on three benchmark datasets show that compared with five other underwater image enhancement methods, the proposed method obtains higher peak signal-to-noise ratio and structural similarity scores, exhibiting better performance. Therefore, the proposed method can effectively restore image color and texture details along with possessing real-time processing speed.

References:

[1] Zhao W, Qi H, Jiang Y, et al. A convolutional neural network accelerator for real-time underwater image recognition of autonomous underwater vehicle[J].Proceedings of the Institution of Mechanical Engineers, Part Ⅰ: Journal of Systems and Control Engineering, 2021, 235(10): 1839-1848. DOI: 10.1177/0959651820958208.
[2] Akkaynak D, Treibitz T, Shlesinger T, et al. What is the space of attenuation coefficients in underwater computer vision[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, HI, USA, 2017: 568-577. DOI: 10.1109/CVPR.2017.68.
[3] Zhuang P, Wu J, Porikli F, et al. Underwater image enhancement with hyper-Laplacian reflectance prior[J]. IEEE Transactions on Image Processing, 2022, 31: 5442-5455. DOI: 10.1109/TIP.2022.3196546.
[4] Hummel R. Image enhancement by histogram transformation[J].Computer Graphics and Image Processing, 1977, 6(2): 184-195. DOI: 10.1016/S0146- 664X(77)80011-7.
[5] Fu X, Fan Z, Ling M, et al. Two-step approach for single underwater image enhancement[C]//2017 International Symposium on Intelligent Signal Processing and Communication Systems(ISPACS). Xiamen, China, 2017: 789-794. DOI: 10.1109/ISPACS.2017.8266583.
[6] Zhuang P, Ding X. Underwater image enhancement using an edge-preserving filtering Retinex algorithm[J]. Multimedia Tools and Applications, 2020, 79(25/26): 17257-17277. DOI: https://doi.org/10.1007/s11042-019-08404-4.
[7] Dhivya R, Prakash R, Mohanraj M R. Color balance and fusion for underwater image enhancement[J].IEEE Transactions on Image Processing, 2018, 27(1): 379-393. DOI: 10.1109/TIP.2017.2759252.
[8] Li C, Guo J, Cong R, et al. Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior[J].IEEE Transactions on Image Processing, 2016, 25(12): 5664-5677. DOI: 10.1109/TIP.2016.2612882.
[9] Zhou Y, Wu Q, Yan K, et al. Underwater image restoration using color-line model[J].IEEE Transactions on Circuits and Systems for Video Technology, 2018, 29(3): 907-911. DOI: 10.1109/TCSVT.2018.2884615.
[10] Wang Y, Zhang J, Cao Y, et al. A deep CNN method for underwater image enhancement[C]//2017 IEEE International Conference on Image Processing(ICIP). Beijing, China, 2017: 1382-1386. DOI: 10.1109/ICIP.2017.8296508.
[11] Li C, Anwar S, Hou J, et al. Underwater image enhancement via medium transmission-guided multi-color space embedding[J]. IEEE Transactions on Image Processing, 2021, 30: 4985-5000. DOI: 10.1109/TIP.2021.3076367.
[12] Fabbri C, Jahidul Islam M, Sattar J. Enhancing underwater imagery using generative adversarial networks[C]//2018 IEEE International Conference on Robotics and Automation(ICRA). Brisbane, Australia, 2018: 7159-7165. DOI: 10.1109/ICRA.2018.8460552.
[13] 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. DOI: 10.1109/LRA.2020.2974710.
[14] Peng L, Zhu C, Bian L. U-shape transformer for underwater image enhancement[J].IEEE Transactions on Image Processing, 2023, 32: 3066-3079. DOI: 10.1109/TIP.2023.3276332.
[15] Naik A, Swarnakar A, Mittal K. Shallow-UWnet: Compressed model for underwater image enhancement(student abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(18): 15853-15854. DOI: 10.1609/aaai.v35i18.17923.
[16] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems(NIPS’17). Red Hook, NY, USA, 2017: 6000-6010. DOI: 10.48550/arXiv.1706.03762.
[17] Trucco E, Olmos-Antillon A T. Self-tuning underwater image restoration[J].IEEE Journal of Oceanic Engineering, 2006, 31(2): 511-519. DOI: 10.1109/JOE.2004.836395.
[18] Peng Y T, Cao K, 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.
[19] Chen C F, Fan Q, Panda R. CrossViT: Cross-attention multi-scale vision transformer for image classification[C]//2021 IEEE/CVF International Conference on Computer Vision(ICCV). Montreal, Canada, 2021: 347-356. DOI: 10.1109/ICCV48922.2021.00041.
[20] Lai W-S, Huang J-B, Ahuja N, et al. Fast and accurate image super-resolution with deep laplacian pyramid networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(11): 2599-2613. DOI: 10.1109/TPAMI.2018.2865304.
[21] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [EB/OL].(2019-09-04)[2023-06-29]. https://arxiv.org/abs/1409.1556.
[22] Deng J, Dong W, Socher R, et al. ImageNet: A large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA. 2009: 248-255. DOI: 10.1109/CVPR.2009.5206848.
[23] Islam M J, Luo P, Sattar J. Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception[EB/OL].(2020-07-16)[2023-06-29].https://arxiv.org/abs/2002.01155.
[24] Gupta H and Mitra K. Unsupervised single image underwater depth estimation[C]//2019 IEEE International Conference on Image Processing(ICIP). Taipei, China, 2019: 624-628. DOI: 10.1109/ICIP.2019.8804200.
[25] Islam M J, Edge C, Xiao Y, et al. Semantic segmentation of underwater imagery: Dataset and benchmark[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). Las Vegas, NV, USA, 2020: 1769-1776. DOI: 10.1109/IROS45743.2020.9340821.

Memo

Memo:
Biographies: Yu Jing(1982—), female, doctor, associate research fellow, yujing@nwpu.edu.cn.
Foundation item: The Natural Science Basic Research Plan in Shaanxi Province of China(No.2020JQ-208), Key Research and Development Program of Shaanxi(No.2022GY-285, No.2020SF-391), Foundation of Key Laboratory of Road Construction Technology and Equipment of Chang’an University(No.300102259507).
Citation: Yu Jing, Zhang Le, Wu Meng, et al.Two-stage attention for rapid underwater image enhancement[J].Journal of Southeast University(English Edition), 2023, 39(4):410-415.DOI:10.3969/j.issn.1003-7985.2023.04.010.
Last Update: 2023-12-20