Methods and Technologies for Visual Perception of Underwater Environment
YU Junzhi1,2, KONG Shihan1, MENG Yan2
1. Department of Advanced Manufacturing and Robotics, College of Engineering, Peking University, Beijing 100871, China; 2. State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Abstract:Effective perception of underwater environment is the key to the autonomous movements and operations of underwater robots.Firstly,the common problems of underwater visual environment perception are analyzed,and for two of them,i.e.visual degradation and refractive distortion,the influences on underwater visual imaging are summarized.Secondly,the research status of mainstream underwater visual environment perception methods at home and abroad is reviewed from 3 aspects of underwater vision restoration methods,underwater 3D visual perception methods,and underwater vision enhancement methods,to tackle the above-mentioned challenges.Finally,the future development tendencies of underwater visual environment perception are prospected,focusing on the hot research directions such as clustered visual perception,information fusion of multi-modal perception,as well as bionic visual perception.
[1] 侯建平,戴娟娟,蔡灵,等. 21世纪美国国家海洋政策 变化分析[J].环境与生活, 2014, 16:99,101. Hou J P, Dai J J, Cai L, et al. An analysis of the changes in U.S. national ocean policy in the 21st century[J]. Green Living, 2014, 16:99,101. [2] Gong Z Y, Fang X, Chen X Y, et al. A soft manipulator for efficient delicate grasping in shallow water:Modeling, control, and real-world experiments[J]. International Journal of Robotics Research, 2021, 40(1):449-469. [3] Cai M X, Wang Y, Wang S, et al. Grasping marine products with hybrid-driven underwater vehicle-manipulator system[J]. IEEE Transactions on Automation Science and Engineering, 2020, 17(3):1443-1454. [4] 顾临怡,宋琦,殷宏伟,等.基于ROV等载体的水下搜救 流程综述[J].中国科学:信息科学, 2018, 48(9):1137-1151. Gu L Y, Song Q, Yin H W, et al. An overview of the underwater search and salvage process based on ROV[J]. Scientia Sinica:Informationis, 2018, 48(9):1137-1151. [5] 刘妹琴,韩学艳,张森林,等.基于水下传感器网络的 目标跟踪技术研究现状与展望[J].自动化学报, 2021, 47(2):235-251. Liu M Q, Han X Y, Zhang S L, et al. Research status and prospect of target tracking technologies via underwater sensor networks[J]. Acta Automatica Sinica, 2021, 47(2):235-251. [6] 吴杰,王志东,凌宏杰,等.深海作业型带缆水下机器 人关键技术综述[J].江苏科技大学学报(自然科学版), 2020, 34(4):1-12. Wu J, Wang Z D, Ling H J, et al. Review on technologies of work-class ROV in deep-water industry[J]. Journal of Jiangsu University of Science and Technology (Natural Science Edition), 2020, 34(4):1-12. [7] Cong Y, Gu C J, Zhang T, et al. Underwater robot sensing technology:A survey[J]. Fundamental Research, 2021, 1(3):337-345. [8] 黄琰,李岩,俞建成,等. AUV智能化现状与发展趋势[J].机器人, 2020, 42(2):215-231. Huang Y, Li Y, Yu J C, et al. State-of-the-art and development trends of AUV intelligence[J]. Robot, 2020, 42(2):215-231. [9] 张伟,高赛博,李子轩,等.基于散射模型的水下浑浊 图像增强方法[J].哈尔滨工程大学学报, 2021, 42(8):1209-1216. Zhang W, Gao S B, Li Z X, et al. Underwater turbidity image enhancement method based on scattering model[J]. Journal of Harbin Engineering University, 2021, 42(8):1209-1216. [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):426-435. Guo Y J, Wu Q, Yuan J J, et al. Research progress on underwater optical image processing[J]. Journal of Electronics&Information Technology, 2021, 43(2):426-435. [11] 王晓鸣,吴高升.基于单目视觉的水下机器人相对位姿精 确控制[J].水下无人系统学报, 2021, 29(3):299-307. Wang X M, Wu G S. Relative position and attitude precise control of underwater robot based on monocular vision[J]. Journal of Unmanned Undersea Systems, 2021, 29(3):299-307. [12] 周浩,姜述强,黄海,等.基于视觉感知的海生物吸纳 式水下机器人目标捕获控制[J].机器人, 2019, 41(2):242-249,275. Zhou H, Jiang S Q, Huang H, et al. Vision based target capture control for sea organism absorptive underwater vehicle[J]. Robot, 2019, 41(2):242-249,275. [13] Li X, Shang M, Qin H W, et al. Fast accurate fish detection and recognition of underwater images with Fast R-CNN[C]//OCEANS. Piscataway, USA:IEEE, 2015. DOI:10.23919/OCEANS.2015.7404464. [14] Sun N, Nian R, He B, et al. Consistent fish tracking via multiple underwater cameras[C]//OCEANS. Piscataway, USA:IEEE, 2014. DOI:10.1109/OCEANS-TAIPEI.2014.6964366. [15] Chen X Y, Yu J Z, Kong S H, et al. Joint anchor-feature refinement for real-time accurate object detection in images and videos[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(2):594-607. [16] Yu J Z, Chen X Y, Kong S H. Visual perception and control of underwater robots[M]. Boca Raton, USA:CRC Press, 2021. [17] Lu H M, Li Y J, Zhang Y D, et al. Underwater optical image processing:A comprehensive review[J]. Mobile Networks and Applications, 2017, 22:1204-1211. [18] Zhang W D, Pan X P, Xie X W, et al. Color correction and adaptive contrast enhancement for underwater image enhancement[J]. Computers&Electrical Engineering, 2021, 91. DOI:10.1016/j.compeleceng.2021.106981. [19] Shortis M, Harvey E, Abdo D. A review of underwater stereoimage measurement for marine biology and ecology applications[M]//Oceanography and Marine Biology:An Annual Review, Vol.47. 1st ed. Boca Raton, USA:CRC Press, 2009:257-292. [20] Bonin-Font F, Burguera A, Oliver G. Imaging systems for advanced underwater vehicles[J]. Journal of Maritime Research, 2011, 8(1):65-86. [21] 徐岩,曾祥波.基于红色暗通道先验和逆滤波的水下图 像复原[J].激光与光电子学进展, 2018, 55(2):221-228. Xu Y, Zeng X B. Underwater image restoration based on reddark channel prior and inverse filtering[J]. Laser&Optoelectronics Progress, 2018, 55(2):221-228. [22] Farbman Z, Fattal R, Lischinski D, et al. Edge-preserving decompositions for multi-scale tone and detail manipulation[J]. ACM Transactions on Graphics, 2008, 27(3):1-10. [23] 代成刚,林明星,王震,等.基于亮通道色彩补偿与融合 的水下图像增强[J].光学学报, 2018, 38(11):86-95. Dai C G, Lin M X, Wang Z, et al. Color compensation based on bright channel and fusion for underwater image enhancement[J]. Acta Optica Sinica, 2018, 38(11):86-95. [24] Kong S H, Fang X, Chen X Y, et al. A NSGA-II-based calibration algorithm for underwater binocular vision measurement system[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(3):794-803. [25] Kong S H, Fang X, Chen X Y, et al. A real-time underwater robotic visual tracking strategy based on image restoration and kernelized correlation filters[C]//Chinese Control and Decision Conference. Piscataway, USA:IEEE, 2018:6436-6441. [26] Schechner Y Y, Karpel N. Clear underwater vision[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2004. DOI:10.1109/CVPR.2004.1315078. [27] Çelebi A T, Ertürk S. Visual enhancement of underwater images using empirical mode decomposition[J]. Expert Systems with Applications, 2012, 39(1):800-805. [28] He K M, Sun J, Tang X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353. [29] 林森,白莹,李文涛,等.基于修正模型与暗通道先 验信息的水下图像复原[J].机器人, 2020, 42(4):427-435,447. Lin S, Bai Y, Li W T, et al. Underwater image restoration based on the modified model and dark channel prior[J]. Robot, 2020, 42(4):427-435,447. [30] 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. [31] 汤忠强,周波,戴先中,等.基于改进DCP算法的水下 机器人视觉增强[J].机器人, 2018, 40(2):222-230. Tang Z Q, Zhou B, Dai X Z, et al. Underwater robot visual enhancements based on the improved DCP algorithm[J]. Robot, 2018, 40(2):222-230. [32] 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. [33] Chiang J Y, Chen Y C. Underwater image enhancement by wavelength compensation and dehazing[J]. IEEE Transactions on Image Processing, 2012, 21(4):1756-1769. [34] Shin Y S, Cho Y, Pandey G, et al. Estimation of ambient light and transmission map with common convolutional architecture[C]//OCEANS. Piscataway, USA:IEEE, 2016. DOI:10.1109/OCEANS.2016.7761342. [35] Galdran A, Pardo D, Picón A, et al. Automatic red-channel underwater image restoration[J]. Journal of Visual Communication and Image Representation, 2015, 26:132-145. [36] Zhao X W, Jin T, Qu S. Deriving inherent optical properties from background color and underwater image enhancement[J]. Ocean Engineering, 2015, 94:163-172. [37] Peng Y T, Zhao X Y, Cosman P C. Single underwater image enhancement using depth estimation based on blurriness[C]//IEEE International Conference on Image Processing. Piscataway, USA:IEEE, 2015:4952-4956. [38] Ancuti C, Ancuti C O, Haber T, et al. Enhancing underwater images and videos by fusion[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2012:81-88. [39] Bennett E P, Mason J L, McMillan L. Multispectral bilateral video fusion[J]. IEEE Transactions on Image Processing, 2007, 16(5):1185-1194. [40] Ancuti C O, Ancuti C, de Vleeschouwer C, et al. Color balance and fusion for underwater image enhancement[J]. IEEE Transactions on Image Processing, 2018, 27(1):379-393. [41] Li J, Skinner K A, Eustice R M, et al. WaterGAN:Unsupervised generative network to enable real-time color correction of monocular underwater images[J]. IEEE Robotics and Automation Letters, 2018, 3(1):387-394. [42] Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2017:2242-2251. [43] 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. [44] Chen X Y, Yu J Z, Kong S H, et al. Towards real-time advancement of underwater visual quality with GAN[J]. IEEE Transactions on Industrial Electronics, 2019, 66(12):9350-9359. [45] Sagara S, Ambar R B, Takemura F. A stereo vision system for underwater vehicle-manipulator systems-Proposal of a novel concept using pan-tilt-slide cameras[J]. Journal of Robotics and Mechatronics, 2013, 25(5):785-794. [46] Yang X, Wu Z X, Liu J C, et al. Design of a camera stabilizer system for robotic fish based on feedback-feedforward control[C]//35th Chinese Control Conference. Piscataway, USA:IEEE, 2016:6044-6049. [47] Zhang P F, Wu Z X, Wang J, et al. 2-DOF camera stabilization platform for robotic fish based on active disturbance rejection control[C]//IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems. Piscataway, USA:IEEE, 2019:283-288. [48] Pan J, Zhang P F, Liu J C, et al. A novel visual sensor stabilization platform for robotic sharks based on improved LADRC and digital image algorithm[J]. Sensors, 2020, 20(14). DOI:10.3390/s20144062. [49] Sedlazeck A, Koch R. Perspective and non-perspective camera models in underwater imaging-Overview and error analysis[M]//Lecture Notes in Computer Science, Vol.7474. Berlin, Germany:Springer, 2012:212-242. [50] Boutros N, Shortis M R, Harvey E S. A comparison of calibration methods and system configurations of underwater stereovideo systems for applications in marine ecology[J]. Limnology and Oceanography:Methods, 2015, 13(5):224-236. [51] Shortis M. Calibration techniques for accurate measurements by underwater camera systems[J]. Sensors, 2015, 15(12):30810-30826. [52] Sánchez-Ferreira C, Mori J Y, Llanos C H, et al. Development of a stereo vision measurement architecture for an underwater robot[C]//IEEE 4th Latin American Symposium on Circuits and Systems. Piscataway, USA:IEEE, 2013:1-4. [53] Schechner Y Y, Karpel N. Recovery of underwater visibility and structure by polarization analysis[J]. IEEE Journal of Oceanic Engineering, 2005, 30(3):570-587. [54] Treibitz T, Schechner Y Y. Active polarization descattering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3):385-399. [55] Kwon Y H, Casebolt J B. Effects of light refraction on the accuracy of camera calibration and reconstruction in underwater motion analysis[J]. Sports Biomechanics, 2006, 5(2):315-340. [56] Ferreira R, Costeira J P, Santos J A. Stereo reconstruction of a submerged scene[M]//Lecture Notes in Computer Science, Vol.3522. Berlin, Germany:Springer, 2005:102-109. [57] Meline A, Triboulet J, Jouvencel B. A camcorder for 3D underwater reconstruction of archeological objects[C]//OCEANS. Piscataway, USA:IEEE, 2010. DOI:10.1109/OCEANS.2010. 5664572. [58] Menna F, Nocerino E, Troisi S, et al. A photogrammetric approach to survey floating and semi-submerged objects[C]//Videometrics, Range Imaging, and Applications XII; and Automated Visual Inspection. Bellingham, USA:SPIE, 2013. DOI:10.1117/12.2020464. [59] Li R X, Li H H, Zou W H, et al. Quantitative photogrammetric analysis of digital underwater video imagery[J]. IEEE Journal of Oceanic Engineering, 1997, 22(2):364-375. [60] Treibitz T, Schechner Y, Kunz C, et al. Flat refractive geometry[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(1):51-65. [61] Jordt-Sedlazeck A, Koch R. Refractive structure-from-motion on underwater images[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2013:57-64. [62] Jordt-Sedlazeck A, Koch R. Refractive calibration of underwater cameras[M]//Lecture Notes in Computer Science, Vol.7576. Berlin, Germany:Springer, 2012:846-859. [63] Agrawal A, Ramalingam S, Taguchi Y, et al. A theory of multilayer flat refractive geometry[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2012:3346-3353. [64] Chen X D, Yang Y H. Two-view camera housing parameters calibration for multi-layer flat refractive interface[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2014:524-531. [65] Yau T, Gong M L, Yang Y H. Underwater camera calibration using wavelength triangulation[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2013:2499-2506. [66] Telem G, Filin S. Photogrammetric modeling of underwater environments[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 65(5):433-444. [67] Dolereit T, von Lukas U F, Kuijper A. Underwater stereo calibration utilizing virtual object points[C]//OCEANS. Piscataway, USA:IEEE, 2015. DOI:10.1109/OCEANS-Genova. 2015.7271593. [68] Qiu C L, Wu Z X, Kong S H, et al. An underwater micro cabledriven pan-tilt binocular vision system with spherical refraction calibration[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70:1-13. [69] Massot-Campos M, Oliver-Codina G. Underwater laser-based structured light system for one-shot 3D reconstruction[C]//SENSORS. Piscataway, USA:IEEE, 2014:1138-1141. [70] 许丽,周永昊,张帆,等.基于光平面约束的水下三维 视觉测量系统[J].中国激光, 2020, 47(9). DOI:10.3788/CJL202047.0904004. Xu L, Zhou Y H, Zhang F, et al. Underwater three-dimensional measurement vision system using light-plane constraint[J]. Chinese Journal of Lasers, 2020, 47(9). DOI:10.3788/CJL202047.0904004. [71] Massot-Campos M, Oliver G, Bodenmann A, et al. Submap bathymetric SLAM using structured light in underwater environments[C]//IEEE/OES Autonomous Underwater Vehicles. Piscataway, USA:IEEE, 2016:181-188. [72] Bleier M, van der Lucht J, Nüchter A. Scout3D-An underwater laser scanning system for mobile mapping[J]. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019, XLII-2/W18:13-18. [73] Palomer A, Ridao P, Ribas D.Inspection of an underwater structure using point-cloud SLAM with an AUV and a laser scanner[J]. Journal of Field Robotics, 2019, 36(8):1333-1344. [74] Palomer A, Ridao P, Forest J, et al. Underwater laser scanner:Ray-based model and calibration[J]. IEEE/ASME Transactions on Mechatronics, 2019, 24(5):1986-1997. [75] Gu C J, Cong Y, Sun G. Three birds, one stone:Unified laser-based 3-D reconstruction across different media[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 70:1-12. [76] Köser K, Frese U. Challenges in underwater visual navigation and SLAM[M]//Intelligent Systems, Control and Automation:Science and Engineering, Vol.96. Berlin, Germany:Springer, 2020:125-135. [77] Ferrera M, Creuze V, Moras J, et al. AQUALOC:An underwater dataset for visual-inertial-pressure localization[J]. International Journal of Robotics Research, 2019, 38(14):1549-1559. [78] Amarasinghe C, Ratnaweera A, Maitripala S. Monocular visual SLAM for underwater navigation in turbid and dynamic environments[J]. American Journal of Mechanical Engineering, 2020, 8(2):76-87. [79] Burguera A, Bonin-Font F. A trajectory-based approach to multi-session underwater visual SLAM using global image signatures[J]. Journal of Marine Science and Engineering, 2019, 7(8). DOI:10.3390/jmse7080278. [80] 张阳,欧阳犬平,李进军,等.水下视觉SLAM相机成 像畸变纠正研究[J].海洋技术学报, 2019, 38(6):24-29. Zhang Y, Ouyang Q P, Li J J, et al. Research on image distortion correction of underwater vision SLAM camera[J]. Journal of Ocean Technology, 2019, 38(6):24-29. [81] Yin J Y, Wang Y, Lü J Q, et al. Study on underwater simultaneous localization and mapping based on different sensors[C]//IEEE 10th Data Driven Control and Learning Systems Conference. Piscataway, USA:IEEE, 2021:728-733. [82] Fan H, Qi L, Chen C H, et al. Underwater optical 3-D reconstruction of photometric stereo considering light refraction and attenuation[J]. IEEE Journal of Oceanic Engineering, 2022,47(1):47-58. [83] Cho Y, Kim A. Visibility enhancement for underwater visual SLAM based on underwater light scattering model[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2017:710-717. [84] Burguera A, Bonin-Font F. An unsupervised neural network for loop detection in underwater visual SLAM[J]. Journal of Intelligent&Robotic Systems, 2020, 100:1157-1177. [85] Alay J B. Underwater navigation and mapping with an omnidirectional optical sensor[D]. Girona, Spain:University of Girona, 2018. [86] Bosch J, Gracias N, Ridao P, et al. Omnidirectional underwater camera design and calibration[J]. Sensors, 2015, 15(3):6033-6065. [87] Jiang P, Wei Q X, Chen Y H, et al. Real-time panoramic system for underwater cleaning robot[C]//IEEE 9th International Conference on Mechanical and Intelligent Manufacturing Technologies. Piscataway, USA:IEEE, 2018:155-159. [88] Li Q Z, Zhang Y, Zang F N. Fast multicamera video stitching for underwater wide field-of-view observation[J]. Journal of Electronic Imaging, 2014, 23(2). DOI:10.1117/1.JEI.23.2.023008. [89] Bosch J, Ridao P, Ribas D, et al. Creating 360? underwater virtual tours using an omnidirectional camera integrated in an AUV[C]//OCEANS. Piscataway, USA:IEEE, 2015. DOI:10. 1109/OCEANS-Genova.2015.7271525. [90] 王昕平,张森林,刘妹琴,等.基于多尺度图像融合和 SIFT特征的水下图像拼接研究[J].计算机应用与软件, 2021, 38(5):213-217,230. Wang X P, Zhang S L, Liu M Q, et al. Underwater image stitching based on multi-scale image fusion and SIFT feature[J]. Computer Applications and Software, 2021, 38(5):213-217, 230. [91] Sheng M W, Tang S Q, Cui Z, et al. A joint framework for underwater sequence images stitching based on deep neural network convolutional neural network[J]. International Journal of Advanced Robotic Systems, 2020, 17(2). DOI:10.1177/1729881420915062. [92] Jatmiko D A, Prini S U. Study and performance evaluation binary robust invariant scalable keypoints (BRISK) for underwater image stitching[C]//IOP Conference Series:Materials Science and Engineering, Vol.879. Bristol, UK:IOP Publishing, 2020. DOI:10.1088/1757-899X/879/1/012111. [93] 胡晓阳.鱼眼镜头的水下双目视觉定位系统研究[D].秦 皇岛:燕山大学, 2017. Hu X Y. The research of underwater positioning in fisheye stereovision system[D]. Qinhuangdao:Yanshan University, 2017. [94] Lynch D K. Snell's window in wavy water[J]. Applied Optics, 2015, 54(4):B8-B11. [95] 魏利胜,周圣文,张平改,等.基于双经度模型的鱼眼图 像畸变矫正方法[J].仪器仪表学报, 2015, 36(2):377-385. Wei L S, Zhou S W, Zhang P G, et al. Double longitude model based correction method for fish-eye image distortion[J]. Chinese Journal of Scientific Instrument, 2015, 36(2):377-385. [96] 冯为嘉.基于鱼眼镜头的全方位视觉及全景立体球视觉 研究[D].天津:天津大学, 2012. Feng W J. Study on omnidirectional vision and panoramic stereo sphere vision based on fish-eye lens[D]. Tianjin:Tianjin University, 2012. [97] Delibasis K K, Plagianakos V P, Maglogiannis I. Real time indoor robot localization using a stationary fisheye camera[M]//IFIP Advances in Information and Communication Technology, Vol.412. Berlin, Germany:Springer, 2013:245-254. [98] Choi Y W, Kwon K K, Lee S I, et al. Multi-robot mapping using omnidirectional-vision SLAM based on fisheye images[J]. ETRI Journal, 2014, 36(6):913-923. [99] Ji S P, Qin Z J, Shan J, et al. Panoramic SLAM from a multiple fisheye camera rig[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159:169-183. [100] Yogamani S, Hughes C, Horgan J, et al. WoodScape:A multi-task, multi-camera fisheye dataset for autonomous driving[C]//IEEE/CVF International Conference on Computer Vision. Piscataway, USA:IEEE, 2019:9307-9317. [101] Berlinger F, Gauci M, Nagpal R. Implicit coordination for 3D underwater collective behaviors in a fish-inspired robot swarm[J]. Science Robotics, 2021, 6(50). DOI:10.1126/scirobotics. abd8668. [102] Billings G, Johnson-Roberson M. SilhoNet-fisheye:Adaptation of a ROI based object pose estimation network to monocular fisheye images[J]. IEEE Robotics and Automation Letters, 2020, 5(3):4241-4248. [103] Sakamoto K, Moro A, Fujii H, et al. Three-dimensional measurement of objects in liquid with an unknown refractive index using fisheye stereo camera[C]//IEEE/SICE International Symposium on System Integration. Piscataway, USA:IEEE, 2014:281-286. [104] Meng L, Hirayama T, Oyanagi S. Underwater-drone with panoramic camera for automatic fish recognition based on deep learning[J]. IEEE Access, 2018, 6:17880-17886. [105] Nakajoh H, Miyazaki T, Sawa T, et al. Development of 7000m work class ROV "KAIKO Mk-IV"[C]//OCEANS. Piscataway, USA:IEEE, 2016. DOI:10.1109/OCEANS.2016.7761063.