Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2022, Vol. 56 Issue (8): 1648-1655    DOI: 10.3785/j.issn.1008-973X.2022.08.019
计算机与控制工程     
基于改进γ-CLAHE算法的水下机器人图像识别
成宏达1(),骆海明1,夏庆超1,2,*(),杨灿军1,2
1. 浙江大学宁波研究院，浙江 宁波 315100
2. 浙江大学 机械工程学院，浙江 杭州 310027
Recognition of images for underwater vehicle based on improved γ-CLAHE algorithm
Hong-da CHENG1(),Hai-ming LUO1,Qing-chao XIA1,2,*(),Can-jun YANG1,2
1. Ningbo Research Institute, Zhejiang University, Ningbo 315100, China
2. College of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China
 全文: PDF(2093 KB)   HTML
摘要：

水体及悬浮粒子对光的吸收、折射及反射导致水下图像对比度低及细节模糊，单一图像增强算法难以适用于水下复杂环境识别.为了解决该问题，提出基于小波变换和改进的γ-CLAHE相融合的图像增强算法.通过快速中值滤波去除图像中噪声，向CLAHE算法中加入自适应伽马变换，解决CLAHE算法处理水下图像色彩失真，丢失孤立点、细线，画面突变等问题. 利用改进的γ-CLAHE算法处理小波变换分解后的低频部分，增强图像并加快运行速度. 通过小波逆变换将γ-CLAHE算法处理后的低频部分和双边滤波处理后的高频部分相融合，得到最终的增强图像. 将实验图像同传统CLAHE、Retinex、Singh融合算法的处理图像进行对比，验证本研究算法在水下图像处理方面的有效性和优越性.
关键词： 水下机器人;  图像增强;  小波变换;  自适应伽马变换;  CLAHE算法    
Abstract:

The absorption, refraction and reflection of light by water and suspended particles lead to low contrast and blurred details of underwater images. Therefore, it is difficult to apply a single image enhancement algorithm to the recognition of complex underwater environments. An enhancement algorithm based on wavelet transform and an improved γ-CLAHE algorithm was proposed to solve this problem. Firstly, fast median filter was used to remove the noise in the image, and adaptive gamma transform was added to CLAHE to solve the problems of color distortion and loss of details information such as isolated points, thin lines and sudden changes in the underwater image. Secondly, the improved γ-CLAHE method was used to process the low frequency part after wavelet transform decomposition to enhance the image and speed up the algorithm. Then, the wavelet inverse transform was used to get the final enhanced image by fusing the low-frequency part processed by the γ-CLAHE algorithm and the high-frequency part processed by bilateral filtering. Finally, the final image was compared with the images processed by traditional CLAHE, Retinex, and Singh’s fusion algorithm, verifying the effectiveness and superiority of the proposed algorithm in the underwater image processing.
Key words: underwater vehicle    image enhancement    wavelet transform    adaptive gamma transform    CLAHE algorithm
收稿日期: 2021-08-23 出版日期: 2022-08-30
CLC:  TP 317.4  
基金资助: 国家自然科学基金资助项目(52071292)；浙江省自然科学基金资助项目(LQ20E090008)；宁波市“科技创新2025”重大专项(2021E008)
通讯作者: 夏庆超     E-mail: ysdxysu7046@163.com;mynameisxia@zju.edu.cn
作者简介: 成宏达（1996—），男，硕士生，从事水下机器人视觉研究. orcid.org/0000-0002-2855-2662. E-mail： ysdxysu7046@163.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
成宏达
骆海明
夏庆超
杨灿军

引用本文:

成宏达,骆海明,夏庆超,杨灿军. 基于改进γ-CLAHE算法的水下机器人图像识别[J]. 浙江大学学报(工学版), 2022, 56(8): 1648-1655.

Hong-da CHENG,Hai-ming LUO,Qing-chao XIA,Can-jun YANG. Recognition of images for underwater vehicle based on improved γ-CLAHE algorithm. Journal of ZheJiang University (Engineering Science), 2022, 56(8): 1648-1655.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2022.08.019    或    https://www.zjujournals.com/eng/CN/Y2022/V56/I8/1648

使用方法 优点 缺点
伽马函数 图像上的非线性运算 对比度增强不足
拉普拉斯滤波 可突出显示图像中的离群值或线端点 噪音敏感
Retinex方法 不受照明不均匀的影响、自适应各种场景图像 光晕敏感度、失真
直方图均衡化 改变图片直方图调整对比度、可逆操作 过增强、噪音敏感
表 1  对比度增强方法对比
使用方法 优点 缺点
白平衡算法 原理简单易行 不同场景适应能力差
颜色空间变换 易获得矫正后图像颜色 结构相似的图像并非始终可用
灰度世界算法 简单快速 无法适应动态场景
灰度世界和白平衡混合算法 在保持图像饱和度和平衡图像颜色之间折中 仅当失真不严重并且在光线充足的条件下拍摄图像时，效果良好
表 2  色彩修正方法对比
图 1  Iqbal算法流程图
图 2  Iqabl算法结果图
图 3  水下图像增强算法步骤
图 4  水下珊瑚图像处理效果
图 5  水下管道图像处理效果
图 6  图像增强算法效果对比
图 7  AG评价指标对比
图 8  PSNR评价指标对比
图 9  SSIM评价指标对比
图像 Singh融合 CLAHE Retinex 本研究算法
礁石 2.1 0.88 0.52 1.01
潜水员 1.4 0.90 0.63 1.05
弯管1 1.2 0.84 1.10 0.87
直管 1.2 0.75 0.77 0.56
弯管2 1.7 0.65 0.83 0.92
表 3  图像处理时间
1 KANG W, XIWU G Design of optimal scheme for industrial network monitoring of ocean energy power generation system[J]. IOP Conference Series: Earth and Environmental Science, 2021, 647 (1): 012120
doi: 10.1088/1755-1315/647/1/012120
2 彭飞, 富宁宁, 胡伟, 等 国内外海洋资源研究知识图谱解析及启示[J]. 资源科学, 2020, 42 (11): 2047- 2061
PENG Fei, Fu Ning-ning, HU Wei, et al Analysis and enlightenment of knowledge map of marine resources research at home and abroad[J]. Resources Science, 2020, 42 (11): 2047- 2061
doi: 10.18402/resci.2020.11.01
3 陈永华, 于非, 张林林, 等 深海综合观测浮标研制及其在热带西太平洋的应用[J]. 海洋科学, 2020, 44 (8): 215- 222
CHEN Yong-hua, YU Fei, ZHANG Lin-lin, et al Design and development of deep-sea buoys and their applications in the tropical western Pacific[J]. Marine Sciences, 2020, 44 (8): 215- 222
4 王庆琳, 陈水浩, 陈冬妮, 等 中国南海海洋真菌资源及其活性次级代谢产物研究评述[J]. 生物资源, 2020, 42 (5): 505- 514
WANG Qing-lin, CHEN Shui-hao, CHEN Dong-ni, et al Review on the research of marine fungus resources and their bioactive secondary metabolites from the South China Sea[J]. Biotic Resources, 2020, 42 (5): 505- 514
5 宋泽明, 宁凌 基于 DPSIR-TOPSIS 模型的我国沿海省份海洋资源环境承载力评价及障碍因素研究[J]. 生态经济, 2020, 36 (8): 154- 160
SONG Ze-ming, NING Ling Evaluation and obstacle factors of marine resources and environment carrying capacity of coastal provinces and cities in China based on DPSIR-TOPSIS model[J]. Ecological Economy, 2020, 36 (8): 154- 160
6 朱光文 我国海洋探测技术五十年发展的回顾与展望(三)[J]. 海洋技术, 2000, (1): 23- 31
ZHU Guang-wen Review and prospect for the marine survey technology development in the past 50 years of china[J]. Journal of Ocean Technology, 2000, (1): 23- 31
doi: 10.3969/j.issn.1003-2029.2000.01.003
7 BOUDHANE M, NSIRI B Underwater image processing method for fish localization and detection in submarine environment[J]. Journal of Visual Communication and Image Representation, 2016, 39: 226- 238
doi: 10.1016/j.jvcir.2016.05.017
8 董鹏, 周烽, 赵悰悰, 等 基于双目视觉的水下海参尺寸自动测量方法[J]. 计算机工程与应用, 2021, 57: 271- 278
DONG Peng, ZHOU Feng, ZHAO Cong-cong, et al Automatic measurement of underwater sea cucumber size based on binocular vision[J]. Computer Engineering and Applications, 2021, 57: 271- 278
doi: 10.3778/j.issn.1002-8331.2005-0096
9 CHEN H, CHUANG W, WANG C Vision-based line detection for underwater inspection of breakwater construction using an ROV[J]. Ocean Engineering, 2015, 109: 20- 33
doi: 10.1016/j.oceaneng.2015.09.007
10 郭银景, 吴琪, 苑娇娇, 等 水下光学图像处理研究进展[J]. 电子与信息学报, 2021, 43 (2): 1- 10
GUO Yin-jing, WU Qi, YUAN Jiao-jiao, et al Research progress on underwater optical image processing[J]. Journal of Electronics and Information Technology, 2021, 43 (2): 1- 10
doi: 10.11999/JEIT190803
11 方明, 刘小晗, 付飞蚺 基于注意力的多尺度水下图像增强网络[J]. 电子与信息学报, 2021, 43 (12): 1- 9
FANG Ming, LIU Xiao-han, FU Fei-ran Multi-scale underwater image enhancement network based on attention mechanism[J]. Journal of Electronics and Information Technology, 2021, 43 (12): 1- 9
doi: 10.11999/JEIT200311
12 SCHARSTEIN D, SZELISKI R A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47 (1): 7- 42
13 袁利毫, 昝英飞, 钟声华, 等 基于YOLOv3的水下小目标自主识别[J]. 海洋工程装备与技术, 2018, 5 (Suppl.1): 118- 123
YUAN Li-hao, ZAN Ying-fei, ZHONG Sheng-hua, et al Small underwater target recognition based on YOLOv3[J]. Ocean Engineering Equipment and Technology, 2018, 5 (Suppl.1): 118- 123
14 徐萌. 基于机器视觉的水下海参图像识别技术研究[D]. 济南: 山东大学, 2020: 1-10.
XU Meng. Research on underwater sea cucumber image recognition technology based on machine vision [D]. Jinan: Shandong University, 2020: 1-10.
15 王若谦. 基于图像融合的水下图像增强算法研究[D]. 大连: 大连海事大学, 2016: 7−24.
WANG Ruo-qian. Underwater image enhancement algorithm based on image fusion [D]. Dalian: Dalian Maritime University, 2016: 7−24.
16 HAN M, LYU Z, QIU T, et al A review on intelligence dehazing and color restoration for underwater images[J]. IEEE Transactions on Systems Man Cybernetics-Systems, 2020, 50 (5): 1820- 1832
doi: 10.1109/TSMC.2017.2788902
17 颜阳, 王颖, 丁雪妍, 等 基于图像融合的自适应水下图像增强[J]. 计算机工程与设计, 2021, 42 (1): 1- 6
YAN Yang, WANG Ying, DING Xue-yan, et al Adaptive underwater image enhancement method via image fusion[J]. Computer Engineering and Design, 2021, 42 (1): 1- 6
18 SINGH G, JAGGI N, VASAMSETTI S, et al. Underwater image/video enhancement using wavelet based color correction (WBCC) method [C]// IEEE Underwater Technology (UT). Chennai: IEEE, 2015: 1−5.
19 KASHIF I, SALAM R A, AZAM O, et al Underwater image enhancement using an integrated colour model[J]. IAENG International Journal of Computer Science, 2007, 34 (2): 239- 244
20 邹沛煜, 张卫东, 史金余, 等 基于高低频分量融合的水下图像增强算法[J]. 激光与光电子学进展, 2020, 1- 18
ZOU Pei-yu, ZHANG Wei-dong, SHI Jin-yu, et al Underwater image enhancement algorithm based on fusion of high and low frequency components[J]. Laser and Optoelectronics Progress, 2020, 1- 18
21 刘奕晖. 基于AUV的水下管道检测及位置估算方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2017: 1−10.
LIU Yi-hui. Research on method of underwater pipeline detection and location estimation based on AUV [D]. Harbin: Harbin Engineering University, 2017: 1−10.
22 SHI Z, FENG Y, ZHAO M, et al Normalised gamma transformation-based contrast-limited adaptive histogram equalisation with colour correction for sand-dust image enhancement[J]. IET Image Processing, 2020, 14 (4): 747- 756
doi: 10.1049/iet-ipr.2019.0992
[1] 温竹鹏,陈捷,刘连华,焦玲玲. 基于小波变换和优化CNN的风电齿轮箱故障诊断[J]. 浙江大学学报(工学版), 2022, 56(6): 1212-1219.
[2] 温佩芝,陈君谋,肖雁南,温雅媛,黄文明. 基于生成式对抗网络和多级小波包卷积网络的水下图像增强算法[J]. 浙江大学学报(工学版), 2022, 56(2): 213-224.
[3] 程训,余建波. 基于机器视觉的加工刀具磨损监测方法[J]. 浙江大学学报(工学版), 2021, 55(5): 896-904.
[4] 雍子叶,郭继昌,李重仪. 融入注意力机制的弱监督水下图像增强算法[J]. 浙江大学学报(工学版), 2021, 55(3): 555-562.
[5] 费云,蒙涛,金仲和. 皮纳卫星姿控系统分层式故障检测[J]. 浙江大学学报(工学版), 2020, 54(4): 824-832.
[6] 王万良,杨小涵,赵燕伟,高楠,吕闯,张兆娟. 采用卷积自编码器网络的图像增强算法[J]. 浙江大学学报(工学版), 2019, 53(9): 1728-1740.
[7] 张承志, 冯华君, 徐之海, 李奇, 陈跃庭. 图像噪声方差分段估计法[J]. 浙江大学学报(工学版), 2018, 52(9): 1804-1810.
[8] 赵杰梅, 胡忠辉. 基于动态反馈的AUV水平面路径跟踪控制[J]. 浙江大学学报(工学版), 2018, 52(8): 1467-1473.
[9] 王尧尧, 顾临怡, 陈柏, 吴洪涛. 水下机器人-机械手系统非奇异终端滑模控制[J]. 浙江大学学报(工学版), 2018, 52(5): 934-942.
[10] 陈学军, 杨永明. 采用经验小波变换的风力发电机振动信号消噪[J]. 浙江大学学报(工学版), 2018, 52(5): 988-995.
[11] 项贻强, 郏亚坤. 基于小波总能量相对变化的拱桥吊杆损伤识别[J]. 浙江大学学报(工学版), 2017, 51(5): 870-878.
[12] 王扬威, 闫勇程, 刘凯, 赵东标. 仿生机器魟鱼研制与游动性能实验研究[J]. 浙江大学学报(工学版), 2017, 51(1): 106-112.
[13] 叶肖伟, 丁朋, 周诚, 李勇军, 倪一清, 董小鹏. 基于光纤传感技术的地铁隧道冻结法施工监测[J]. J4, 2013, 47(6): 1072-1080.
[14] 刘涛, 赵巨峰, 徐之海, 冯华君, 陈慧芳. 基于卡尔曼滤波的红外图像增强算法[J]. J4, 2012, 46(8): 1534-1539.
[15] 孔凡立,李霁,邹乐君,沈晓华,吴文渊,苏楠. 基于Haar小波变换的渐弃型废弃河道相识别[J]. J4, 2012, 46(3): 568-576.