无人艇具有机动灵活、隐蔽性好、活动区域广、使用成本低等优点，因而具有广阔的应用前景。这使得无人艇成为国内外的研究热点，其中感知技术是无人艇执行任务的基础。基于光视觉的感知技术具有应用方便，成本相对较低，数据获取容易及信息量大等优点，得到了国内外学者的广泛研究。本文主要从五个方面探讨光视觉在无人艇中的研究：一是基于水面无人艇的水面图像预处理，主要包括水面图像稳像研究及去雾增强研究；二水界线的检测；三是利用光视觉目标检测；四是水面目标跟踪方法。最后，对无人艇的光视觉研究进行了总结及展望。
With the advantages of high flexibility, good concealment, long cruise range and low cost, the unmanned surface vehicle (USV) has a vast prospect of application. The USV becomes a research hotspot in the world, in which perception technology is the basis of mission accomplishing for USV. The perception technology based on optical vision has the advantages of convenient application, relatively low cost, easy data acquisition and large amount of information, which has been widely studied by scholars in the world. This paper mainly discusses the research of optical vision for USV in five aspects: first, the preprocessing of water surface images on USV, mainly including water surface image stabilization and enhancement by defogging; second, the detection of water boundary; third, the target detection utilizing optical vision; fourth, the tracking method of surface targets. Finally, the optical vision research of USV is summarized and prospected.
2019,41(12): 44-49 收稿日期：2019-07-31
DOI：10.3404/j.issn.1672-7649.2019.12.010
分类号：U664
作者简介：王博(1985-),男,副教授,硕士生导师,主要研究领域是海洋环境智能认知技术、海洋无人系统的轻量化深度学习与智能计算、机器学习与模式识别技术等
参考文献：
[1] CAMPBELL S, NAEEM W, IRWIN G W. A review on improving the autonomy of unmanned surface vehicles through intelligent collision avoidance manoeuvres[J]. Annual Reviews in Control, 2012, 36(2): 267–283
[2] ZHENG L, BEETZ M, GEDIKLI S. Visual tracking system for water surface moving targets[C]// International Symposium on Multispectral Image Processing and Pattern Recognition. International Society for Optics and Photonics, 2007.
[3] 王志民, 徐晓刚. 电子稳像技术综述[J]. 中国图象图形学报, 2010, 15(3): 470–480
[4] 韩绍坤, 赵跃进, 刘明奇. 电子稳像技术及其发展[J]. 光学技术, 2001, 27(1): 71–73
[5] 薛言太. 基于水天线的电子稳像技术研究[D]. 长沙：国防科学技术大学, 2010.
[6] 李慧凤. (2013). 移动机器人视觉系统电子稳像关键技术研究. (Doctoral dissertation, 哈尔滨工程大学).
[7] 吴迪, 朱青松. 图像去雾的最新研究进展[J]. 自动化学报, 2015, 41(2): 221–239
[8] NARASIMHAN S G, NAYAR S K. Contrast restoration of weather degraded images[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2003, 25(6): 713–724
[9] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[C]// Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 2009: 1956-1963.
[10] 夏桂林, 尹勇, 神和龙, 等. 改进的海上目标高效去雾算法[J]. 大连海事大学学报, 2014(4): 85–88
[11] 马忠丽, 文杰, 梁秀梅. 海雾下的视频图像去雾算法研究[J]. 计算机应用研究, 2014, 31(9): 2836–2840
[12] 赵凝霞, 刘维亭, 朱志宇. 基于水天线检测的数字图像处理算法研究[J]. 江苏科技大学学报(自然科学版), 2005, 19(1): 54–58
[13] 张冰, 赵凝霞, 刘维亭, 等. 基于小波变换的水天线提取算法研究[J]. 激光与红外, 2005, 35(4): 297–299
[14] 魏俊杰. 水岸图像的中值滤波和分割算法的研究及实现[D]. 吉林：吉林大学, 2011.
[15] 裴立力, 史泽林, 罗海波. 一种基于小波多尺度分析的水天线检测方法[J]. 沈阳工业大学学报, 2003, 25(2): 125–128
[16] 王博, 苏玉民, 万磊, 等. 基于梯度显著性的水面无人艇的海天线检测方法[J]. 光学学报, 2016(5): 58–67
[17] RAN G, MOSHE Y, BAREL A, et al. Distance estimation for marine vehicles using a monocular video camera[C]// Signal Processing Conference. IEEE, 2016: 2405-2409.
[18] GUO H, ZHANG Y M, ZHOU J, et al. A fast and robust vision-based horizon tracking method[C]// International Computer Conference on Wavelet Active Media Technology and Information Processing. IEEE, 2016: 71–74.
[19] 万磊, 曾文静, 张铁栋, 等. 近海岸目标快速提取[J]. 哈尔滨工程大学学报, 2012, 33(9): 1158–1163
[20] LI C, CAO Z, XIAO Y, et al. Fast object detection from unmanned surface vehicles via objectness and saliency[C]// Chinese Automation Congress. IEEE, 2016: 500–505.
[21] 李畅. 水面目标检测与识别算法研究[D]. 武汉: 华中科技大学, 2016.
[22] MOU X, WANG H. Image-Based Maritime Obstacle Detection Using Global Sparsity Potentials[J]. Journal of Information & Communication Convergence Engineering, 2016, 14(2): 129–135
[23] WANG H, WEI Z, OW C S, et al. Improvement in real-time obstacle detection system for USV[C]// International Conference on Control Automation Robotics & Vision. IEEE, 2012: 1317–1322.
[24] SHIN B S, MOU X, MOU W, et al. Vision-based navigation of an unmanned surface vehicle with object detection and tracking abilities[J]. Machine Vision and Applications, 2017
[25] YANG Jian, XIAO Yang, FANG Zhiwen, et al. An object detection and tracking system for unmanned surface vehicles [C]// Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, 2017: 10–31.
[26] PARK J, CHO Y, YOO B, et al. Autonomous collision avoidance for unmanned surface ships using onboard monocular vision[C]// Oceans. IEEE, 2016.
[27] HUNTSBERGER T, AGHAZARIAN H, HOWARD A, et al. Stereo vision–based navigation for autonomous surface vessels[J]. Journal of Field Robotics, 2011, 28(1): 3–18
[28] SINISTERRA A J, DHANAK M R, ELLENRIEDER K V. Stereovision-based target tracking system for USV operations[J]. Ocean Engineering, 2017, 133: 197–214
[29] RAN G, MOSHE Y, BAREL A, et al. Distance Estimation for Marine Vehicles Using a Monocular Video Camera[C]//gnalProcessingConference, 2016: 2405–2409.
[30] MOU X, WANG H, et al. Wide-baseline stereo-based obstacle mapping for unmanned surface vehicles[J]. Sensors, 2018, 18(4)
[31] HERMANN D, GALEAZZI R, ANDERSEN J C, et al. Smart sensor based obstacle detection for high-speed unmanned surface vehicle[C]// Ifac Conference on Manoeuvring and Control of Marine Craft, 2015.
