基于深度图的水下图像复原

doi:10.13229/j.cnki.jdxbgxb20191064

摘要/Abstract

摘要：

水下图像深度图估计的准确性影响复原后的图像质量，为得到更加准确的深度图，提出了一种基于衰减通道结合亮度图的深度图求解算法，并利用该深度图复原水下图像。首先，根据图像像素值与场景深度的关系估计水下图像的深度图，并使用图像的亮度图对深度图进行修正和细化；然后，利用深度图计算图像的大气光值和透射率图；最后，通过逆求解水下成像模型复原退化的图像。实验证明：与现有算法相比，利用该深度图得到的模型参数更加准确，复原后的图像不仅拥有更好的对比度，而且能保持自然真实的颜色。

关键词: 信息处理技术, 水下图像复原, 水下成像模型, 深度图

Abstract:

The estimated accuracy of the depth maps of underwater images affects the quality of the restored images. In order to obtain more precise depth maps， an algorithm was proposed to calculate the depth map based on attenuated channels and luminance map， and then the depth map was used to recover underwater images. First， the depth map of underwater image is estimated according to the relationship between image pixel and scene depth. Then the depth map is further rectified and refined by using the luminance map. Third， the atmospheric light value and the transmission map of the image is calculated using the refined depth map. Finally， the degraded underwater image is restored by inversely solving the underwater imaging model. The experimental results show that compared with the existing algorithms， the model parameters calculated using the rectified depth map are more accurate， and the restored image has better contrast and can maintain more natural color.

Key words: information procession technology, underwater image restoration, underwater imaging model, depth map

中图分类号:

TP391

郭继昌,乔珊珊. 基于深度图的水下图像复原[J]. 吉林大学学报(工学版), 2021, 51(2): 677-684.

Ji-chang GUO,Shan-shan QIAO. Underwater image restoration based on depth map[J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(2): 677-684.

图/表 7

图1

图2

图3

图4

图5

表1

表2

参考文献 19

1	Akkaynak D, Treibitz T, Shlesinger T, et al. What is the space of attenuation coefficients in underwater computer vision?[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawai, 2017: 568-577.
2	徐岩, 孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报: 工学版, 2018, 48(6): 1895-1903.
	Xu Yan,Sun Mei-shuang. Enhancing underwater image based on convolutional neural networks[J]. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(6): 1895-1903.
3	郭继昌, 茹丽, 郭春乐. 基于梯度通道和优化透射率的水下图像复原[J]. 吉林大学学报: 工学版,2020, 50(4): 1435-1442.
	Guo Ji-chang, Ru Li, Guo Chun-le. Underwater image restoration based on gradient channel and optimize[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(4): 1435-1442.
4	程艳芬, 姚丽娟, 袁巧, 等. 水下视频图像清晰化方法[J].吉林大学学报: 工学版,2020, 50(2): 668-677.
	Cheng Yan-fen, Yao Li-juan, Yuan Qiao, et al. Clearing strategy of underwater video image[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(2): 668-677.
5	Akkaynak D, Treibitz T. A revised underwater image formation[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 2018: 6723-6732.
6	Paulo-Drews J R, Nascimento E, Moraes F, et al. Transmission estimation in underwater single images[C]∥IEEE International Conference on Computer Vision Workshops, Sydney, 2013: 825-830.
7	He K M, Sun J, Tang X O, et al. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011, 33(12): 2341-2353.
8	Galdran A, Pardo D, Picón A, et al. Automatic red-channel underwater image restoration[J]. Journal of Visual Communication & Image Representation, 2015, 26: 132-145.
9	Peng Y T, Cosman P C. Underwater image restoration based on image blurriness and light absorption[J]. IEEE Transactions on Image Processing, 2017, 26(4): 1579-1594.
10	Li C, Guo J. Underwater image enhancement by dehazing and color correction[J]. Journal of Electronic Imaging, 2015, 24(3): 033023.
11	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.
12	Tan R T. Visibility in bad weather from a single image[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, 2008: 1-8.
13	McGlamery B L. A computer model for underwater camera systems[J]. Society of Photo-Optical Instrumentation Engineers, 1980, 208: 221-231.
14	Zhao X, Jin T, Qu S. Deriving inherent optical properties from background color and underwater image enhancement[J]. Ocean Engineering, 2015, 94:163-172.
15	He K, Sun J, Tang X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35(6): 1397-1409.
16	Mobley C D. Radiative transfer in the ocean[J]. Encyclopedia of Ocean Sciences, 2001, 5: 379-388.
17	Wang S, Ma K, Yeganeh H, et al. A patch-structure representation method for quality assessment of contrast changed images[J]. IEEE Signal Processing Letters, 2015, 22(12): 2387-2390.
18	Panetta K, Gao C, Agaian S. Human-visual-system-inspired underwater image quality measures[J]. IEEE Journal of Oceanic Engineering, 2015, 41(3): 1-11.
19	Yang M, Sowmya A. An underwater color image quality evaluation metric[J]. IEEE Transactions on Image Processing, 2015, 24(12): 6062-6071.

相关文章 15

[1]	史再峰,李金卓,曹清洁,李慧龙,胡起星. 基于生成对抗网络的低剂量能谱层析成像去噪算法[J]. 吉林大学学报(工学版), 2020, 50(5): 1755-1764.
[2]	王柯俨,王迪,赵熹,陈静怡,李云松. 基于卷积神经网络的联合估计图像去雾算法[J]. 吉林大学学报(工学版), 2020, 50(5): 1771-1777.
[3]	刘国华,周文斌. 基于卷积神经网络的脉搏波时频域特征混叠分类[J]. 吉林大学学报(工学版), 2020, 50(5): 1818-1825.
[4]	谌华,郭伟,闫敬文,卓文浩,吴良斌. 基于深度学习的SAR图像道路识别新方法[J]. 吉林大学学报(工学版), 2020, 50(5): 1778-1787.
[5]	程艳芬,姚丽娟,袁巧,陈先桥. 水下视频图像清晰化方法[J]. 吉林大学学报(工学版), 2020, 50(2): 668-677.
[6]	张薇,韩勇,金铭,乔晓林. 基于托普利兹矩阵集重构的相干信源波达方向估计[J]. 吉林大学学报(工学版), 2020, 50(2): 703-710.
[7]	刘富, 权美静, 王柯, 刘云, 康冰, 韩志武, 侯涛. 仿蝎子振源定位机理的位置指纹室内定位方法[J]. 吉林大学学报(工学版), 2019, 49(6): 2076-2082.
[8]	于晓辉,张志成,李新波,孙晓东. 基于状态空间模型的指数衰减正弦信号参数估计[J]. 吉林大学学报(工学版), 2019, 49(6): 2083-2088.
[9]	马子骥,卢浩,董艳茹. 双通道单图像超分辨率卷积神经网络[J]. 吉林大学学报(工学版), 2019, 49(6): 2089-2097.
[10]	郭继昌,吴洁,郭春乐,朱明辉. 基于残差连接卷积神经网络的图像超分辨率重构[J]. 吉林大学学报(工学版), 2019, 49(5): 1726-1734.
[11]	曹运合,曾丽,王宇. 基于特征空间的子阵级自适应和差波束测角方法[J]. 吉林大学学报(工学版), 2019, 49(5): 1735-1744.
[12]	卢洋,王世刚,赵文婷,赵岩. 基于离散Shearlet类别可分性测度的人脸表情识别方法[J]. 吉林大学学报(工学版), 2019, 49(5): 1715-1725.
[13]	董超,刘晶红,徐芳,王仁浩. 光学遥感图像舰船目标快速检测方法[J]. 吉林大学学报(工学版), 2019, 49(4): 1369-1376.
[14]	王柯俨,胡妍,王怀,李云松. 结合天空分割和超像素级暗通道的图像去雾算法[J]. 吉林大学学报(工学版), 2019, 49(4): 1377-1384.
[15]	托乎提努尔,张海龙,王杰,王娜,冶鑫晨,王万琼. 基于图形处理器的高速中值滤波算法[J]. 吉林大学学报(工学版), 2019, 49(3): 979-985.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

指标	文献[6]算法	文献[8]算法	文献[9]算法	文献[11]算法	本文算法
Entropy	7.049	6.982	7.315	7.614	7.618
UICM	8.741	5.841	7.996	11.834	8.528
PCQI	0.862	0.981	1.114	1.111	1.168
UCIQE	0.591	0.534	0.604	0.655	0.660

指标	文献[6]算法	文献 [8]算法	文献[9]算法	文献[11]算法	本文算法
Entropy	6.936	6.945	7.054	6.924	7.073
UICM	5.048	5.573	5.684	7.502	5.923
PCQI	1.084	1.077	1.124	1.045	1.153
UCIQE	0.503	0.571	0.542	0.522	0.548