跨尺度蒸馏特征感知的轻量化水下图像增强

doi:10.3969/j.issn.1673-6141.2024.03.010

大气与环境光学学报 ›› 2024, Vol. 19 ›› Issue (3): 381-390.doi: 10.3969/j.issn.1673-6141.2024.03.010

• 海洋光学 • 上一篇

跨尺度蒸馏特征感知的轻量化水下图像增强

吴晓华 1, 李增禄 2,3, 许章华 4, 周景春 5*

1 三明学院艺术设计学院, 福建三明 365004; 2 三明学院网络技术中心, 福建三明 365004; 3 三明学院福建省资源环境监测与可持续经营利用重点实验室, 福建三明 365004; 4 福州大学地理与生态环境研究院, 福建福州 350108; 5 大连海事大学信息科学技术学院, 辽宁大连 116026

收稿日期:2023-10-31 修回日期:2024-02-03 出版日期:2024-05-28 发布日期:2024-06-11
通讯作者: E-mail: zhoujingchun03@qq.com E-mail:zhoujingchun03@qq.com
作者简介:吴晓华 (1985- ), 女, 河北石家庄人, 硕士, 讲师, 主要从事图像处理和数字媒体技术方面的研究。E-mail: 20120875@fjsmu.edu.cn
基金资助:
国家自然科学基金青年基金 (62301105), 教育部教师函 [2021]13 号第二批人工智能助推教师队伍建设试点项目 (三明学院), 教育部产学合作协同育人项目 (220503924155959), 三明市社科规划项目 (22062)

Lightweight Underwater Image Enhancement Network Based on Cross-Scale Deep Distillation Feature Perception

WU Xiaohua 1, LI Zenglu 2,3, XU Zhanghua 4, ZHOU Jingchun 5*

1 School of Art & Design, Sanming University, Sanming 365004, China; 2 Network Technology Center, Sanming University, Sanming 365004, China; 3 Fujian Provincial Key Laboratory of Resources and Environment Monitoring & Sustainable Management and Utilization, Sanming University, Sanming 365004, China; 4 Academy of Geography and Ecological Environment, Fuzhou University, Fuzhou 350108, China; 5 Information Science and Technology College, Dalian Maritime University, Dalian 116026, China

Received:2023-10-31 Revised:2024-02-03 Online:2024-05-28 Published:2024-06-11

摘要/Abstract

摘要： 水下图像增强技术能够提升水下图像的质量和可视性，在丰富数字媒体资源、水下探测、水下通信等领域具有重要应用价值。近年来，深度学习方法在水下图像增强方面取得了显著的效果。然而，现有的方法计算复杂度高，限制了它们在计算资源有限的场景中的使用。针对这一问题，提出了一种轻量化的水下图像增强方法，该方法基于跨尺度深度蒸馏特征感知，采用U型网络结构，在保证非线性抽象层级抽取的同时，大幅减少了模型参数量。实验结果表明，所提出方法在视觉效果和客观评价指标上均取得了具有竞争力的结果。

关键词: 水下图像增强, 轻量化, 跨尺度, 蒸馏特征, U型网络

Abstract: Underwater image enhancement technology has the potential to improve the quality and visibility of underwater images, which has important application value in enriching digital media resources, underwater exploration, underwater communication, and other fields. In recent years, deep learning methods have achieved remarkable results in underwater image enhancement. However, the existing methods suffer from high computational complexity, which limits their application in scenarios with limited computational resources. To address this problem, a lightweight underwater image enhancement method is proposed. The method is based on cross-scale depth distillation feature perception and adopts a U-shaped network structure, which can significantly reduce the model parameter size while ensuring the extraction of nonlinear abstract layers. The experimental results show that the proposed method has achieved competitive results in both visual effects and objective evaluation metrics.

Key words: underwater image enhancement, lightweight, cross-scale, distillation feature, U-shaped network

中图分类号:

TP391

吴晓华, 李增禄, 许章华, 周景春 . 跨尺度蒸馏特征感知的轻量化水下图像增强[J]. 大气与环境光学学报, 2024, 19(3): 381-390.

WU Xiaohua , LI Zenglu , XU Zhanghua , ZHOU Jingchun . Lightweight Underwater Image Enhancement Network Based on Cross-Scale Deep Distillation Feature Perception[J]. Journal of Atmospheric and Environmental Optics, 2024, 19(3): 381-390.

参考文献 23

[1]	Raveendran S, Patil M D, Birajdar G K. Underwater image enhancement: A comprehensive review, recent trends, challenges
	and applications [J]. Artificial Intelligence Review, 2021, 54(7): 5413-5467.
[2]	Zhou T H, Fan T W, Ma J, et al. Influence of beam parameters on propagation of blue green laser underwater [J]. Journal of
	Atmospheric and Environmental Optics, 2020, 15(1): 40-47.
	周田华, 范婷威, 马剑, 等. 光束发射参数对蓝绿激光海洋传输特性的影响 [J]. 大气与环境光学学报, 2020, 15(1): 40-47.
[3]	Peng Y T, Cosman P C. Underwater image restoration based on image blurriness and light absorption [J]. IEEE Transactions
	on Image Processing: A Publication of the IEEE Signal Processing Society, 2017, 26(4): 1579-1594.
[4]	Li C Y, Guo J C, Cong R M, 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.
[5]	Liu J Y, Wu G Y, Luan J S, et al. HoLoCo: Holistic and local contrastive learning network for multi-exposure image fusion [J].
	Information Fusion, 2023, 95(C): 237-249.
[6]	Liu J Y, Fan X, Huang Z B, et al. Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to
	fuse infrared and visible for object detection [C]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
	(CVPR). New Orleans, LA, USA. IEEE, 2022: 5792-5801.
[7]	Liu J Y, Shang J J, Liu R S, et al. Attention-guided global-local adversarial learning for detail-preserving multi-exposure image
	fusion [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(8): 5026-5040.
[8]	Ma L, Jin D, An N, et al. Bilevel fast scene adaptation for low-light image enhancement [J/OL]. International Journal of
	Computer Vision, 2023 [2023-11-17]. https://link.springer.com/content/pdf/10.1007/s11263-023-01900-z.pdf.
[9]	Ma L, Liu R S, Zhang J A, et al. Learning deep context-sensitive decomposition for low-light image enhancement [J]. IEEE
	Transactions on Neural Networks and Learning Systems, 2022, 33(10): 5666-5680.
[10]	Li C Y, Anwar S, Porikli F. Underwater scene prior inspired deep underwater image and video enhancement [J]. Pattern
	Recognition, 2020, 98: 107038.
[11]	Li C Y, Guo J C, Guo C L. Emerging from water: Underwater image color correction based on weakly supervised color
	transfer [J]. IEEE Signal Processing Letters, 2018, 25(3): 323-327.
[12]	Qi Q, Li K Q, Zheng H Y, et al. SGUIE-net: Semantic attention guided underwater image enhancement with multi-scale
	perception [J]. IEEE Transactions on Image Processing, 2022, 31: 6816-6830.
[13]	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.
[14]	Fabbri C, Islam M J, Sattar J. Enhancing underwater imagery using generative adversarial networks [C]. 2018 IEEE
	International Conference on Robotics and Automation (ICRA). Brisbane, QLD, Australia. IEEE, 2018: 7159-7165.
[15]	Peng L T, Zhu C L, Bian L H. U-shape transformer for underwater image enhancement [J]. IEEE Transactions on Image
	Processing, 2023, 32: 3066-3079.
[16]	Zhou J C, Liu Q, Jiang Q P, et al. Underwater camera: Improving visual perception via adaptive dark pixel prior and color
	correction [J/OL]. International Journal of Computer Vision, 2023 [2023-10-01]. https://link.springer.com/content/pdf/10.1007/
	s11263-023-01853-3.pdf.
[17]	Zhou J C, Li B S, Zhang D H, et al. UGIF-net: An efficient fully guided information flow network for underwater image
	enhancement [J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 4206117.
[18]	Zhou J C, Sun J M, Zhang W S, et al. Multi-view underwater image enhancement method via embedded fusion mechanism [J].
	Engineering Applications of Artificial Intelligence, 2023, 121: 105946.
[19]	Zhou J C, Yang T Y, Zhang W S. Underwater vision enhancement technologies: A comprehensive review, challenges, and
	recent trends [J]. Applied Intelligence, 2023, 53(3): 3594-3621.
[20]	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, 29: 4376-4389.
[21]	Zhang D H, Wu C Y, Zhou J C, et al. Hierarchical attention aggregation with multi-resolution feature learning for GAN-based
	underwater image enhancement [J]. Engineering Applications of Artificial Intelligence, 2023, 125: 106743.
[22]	Oceanex. Image Gallery [EB/OL]. [2023-10-01]. https://oceanexplorer.noaa.gov/image-gallery/welcome.html.
[23]	Zhao H S, Shi J P, Qi X J, et al. Pyramid scene parsing network [C]. 2017 IEEE Conference on Computer Vision and Pattern
	Recognition (CVPR). Honolulu, HI, USA. IEEE, 2017: 6230-6239.
	390

跨尺度蒸馏特征感知的轻量化水下图像增强

Lightweight Underwater Image Enhancement Network Based on Cross-Scale Deep Distillation Feature Perception

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 23

相关文章 1

编辑推荐

Metrics

本文评价