为解决船舶靠泊过程中视野受限问题，实现靠泊距离的可视化，提出一种无人机辅助视角下的船舶靠泊距离测定方法。首先，利用无人机采集船舶靠泊视频制作数据集，在YOLO v11-seg模型中加入视网膜分割掩膜任务框架，实现对船舶边缘的精细化分割，生成高分辨率掩膜。其次，利用掩膜提取与几何分析方式，提取船舶与泊位多边形坐标，并确定两者边缘线。最后，使用点集距离矩阵以及动态距离匹配技术，计算像素距离并转化为实际距离。实验表明，改进模型平均精度提升5.7%，船舶与泊位间最近距离的误差不大于0.04 m。该方法能够以较高的测量精度实现船舶与泊位间距离的可视化。
To solve the problem of limited field of view during the berthing of ships and realize the visualization of berthing distance, a method for measuring the berthing distance of ships under the assisted perspective of UAV is proposed. Firstly, UAV were used to collect the video of ships berthing to create a dataset. A retinal segmentation mask task framework was added to the YOLO v11-seg model to achieve fine segmentation of the ship's edge and generate a high-resolution mask. Secondly, by using mask extraction and geometric analysis methods, the polygonal coordinates of the ship and the berth are extracted, and the edge lines of the two are determined. Finally, using the point set distance matrix and the dynamic distance matching technology, the pixel distance is calculated and converted into the actual distance. Experiments show that the average accuracy of the improved model has increased by 5.7%, and the error of the shortest distance between the ship and the berth is no more than 0.04 meters. This method can visualize the distance between ships and berths with high measurement accuracy.
2026,48(5): 127-132 收稿日期：2025-7-9
DOI：10.3404/j.issn.1672-7649.2026.05.020
分类号：U691.33
基金项目：国家重点研发计划项目（2023YFB4302300）
作者简介：章文俊(1977-),男,博士,教授,研究方向为交通信息工程及控制
参考文献：
[1] ZHANG H Z, ZHANG Y J, ZHOU Z Y, et al. Research on autonomous berthing control of MASS based on real time kinematic[J]. Ocean Engineering, 2024, 310(1): 118635
[2] SAKAKIBARA S, KUBO M. Ship berthing and mooring monitoring system by pneumatic-type fenders[J]. Ocean Engineering, 2010, 34(8-9): 1174-1181
[3] NOMURA Y, YAMAMOTO S, HASHIMOTO T. Study of 3D measurement of ships using dense stereo vision: towards application in automatic berthing systems[J]. Journal of Marine Science and Technology, 2021, 26(2): 573-581
[4] MIZUCHI Y, OGURA T, HAGIWARAY, et al. Distance measurement system using AStereo camera and radial pattern target for automatic berthing control[J]. Journal of Power System Engineering, 2013, 17(5): 121-127
[5] 甘兴旺, 魏汉迪, 肖龙飞, 等. 基于视觉的船舶环境感知数据融合算法研究[J]. 中国造船, 2021, 62(2): 201-210
GAN X W, WEI H D, XIAO L F, et al. Research on visual-based data fusion algorithm for ship environmental perception[J]. Shipbuilding of China, 2021, 62(2): 201-210
[6] 张山甲, 王建华, 郑翔. 基于视觉伺服的欠驱动无人水面艇自主靠泊方法[J]. 船舶工程, 2020, 42(7): 144-151
ZHANG S J, WANG J H, ZHENG X, et al. Autonomous berthing method of underactuated unmanned surface vehicle based on visual servo[J]. Ship Engineering, 2020, 42(7): 144-151
[7] 费鹏, 李鑫. 无人水面艇的双目视觉应用[J]. 珠江水运, 2019, 27(6): 83-84
FEI P, LI X. The application of binocular vision in unmanned surface vessels[J]. The Pearl River Water Transportation, 2019, 27(6): 83-84
[8] 王昱博, 王建华, 郑翔. 基于泊位水岸线检测的无人艇自主靠泊方法[J]. 船舶工程, 2022, 44(4): 30-37
WANG Y B, WANG J H, ZHENG X. Autonomous berthing method for unmanned surface vessel based on berth shoreline detection[J]. Ship Engineering, 2022, 44(4): 30-37
[9] KIM H, KIM D, PARK B, et al. Artificial intelligence vision-based monitoring system for ship berthing[J]. IEEE Access, 2020, 8: 227014-227023
[10] MIZUCHI Y, OGURA T, KIM Y, et al. Vision-based markerless measurement system for relative vessel positioning[J]. IET Science, Measurement & Technology, 2016, 10(6): 653–658.
[11] 魏宁. 基于无人机视觉的无人船靠泊信息感知研究[D]. 大连海事大学, 2024.
[12] 董瑞恒, 张英俊, 张浩泽. 基于无人机视觉的船舶靠泊距离感知研究[J]. 电子测量技术, 2025, 48(2): 170-177
DONG R H, ZHANG Y J, ZHANG H Z. Research on ship berthing distance perception based on UAV vision[J]. Electronic Measurement Technology, 2025, 48(2): 170-177
[13] 朱婷婷, 滕广, 张亚军, 等. 基于改进YOLO v11的番茄表面缺陷检测方法[J]. 农业机械学报, 2025, 56(6): 546-553
ZHU T T, TENG G, ZHANG Y J, et al. Improved YOLO v11 method for surface defect detection of tomato[J]. Transactions of the Chinese Society for Agricultural Machinery, 2025, 56(6): 546-553
[14] LI L, LU Y, YANG D. Aerial visual data-driven approach for berthing capacity estimation in restricted waters[J]. Ocean & Coastal Management, 2024, 248: 106961.1-106961.12
[15] 周秀珊, 文露婷, 介百飞, 等. 改进YOLO v11的水面膨化饲料颗粒图像实时检测算法[J]. 智慧农业, 2024, 6(6): 155-167
ZHOU X S, WEN L T, JIE B F, et al. Real-time detection algorithm of expanded feed image on the water surface based on improved YOLO v11[J]. Smart Agriculture, 2024, 6(6): 155-167
[16] 张莹莹, 高迪驹, 孙彦琰. 基于图像增强和YOLO的船舶火灾检测方法[J]. 上海海事大学学报, 2024, 45(2): 68-74
ZHANG Y Y, GAO D J, SUN Y Y. A ship fire detection method based on image enhancement and YOLO[J]. Journal of Shanghai Maritime University, 2024, 45(2): 68-74
