面向靠离泊船只近岸侧外壁的平面提取方法

doi:10.3901/JME.2025.18.050

摘要/Abstract

摘要： 针对散料杂货港口需要检测靠离泊大型散货船以避免事故的需求，考虑到船体方形系数大的特点，将完整船体的检测任务简化为对船只近岸侧外壁的平面特征提取任务，因此，提出了一种基于快速点特征直方图(Fast point feature histogram, FPFH)的模板匹配与改进的M采样估计一致性(M-estimate sample consensus, MSAC)平面拟合的船只近岸侧外壁平面特征提取方法。首先根据现场情况等先验知识设定模板点云，在采集原始点云后进行预处理，获得目标点云；然后估计法向量，计算FPFH特征并进行模板匹配，获得船只近岸侧外壁平面点云；根据船只近岸侧外壁平面点云的法向量方向进行层次密度聚类(Hierarchical density-based spatial clustering of applications with noise, HDBSCAN)，再进行考虑法向量因子的MSAC平面拟合，从而提取出靠离泊船只近岸侧外壁的平面特征。经现场数据验证，该方法比现有方法具有更低的平均相对误差，且处理每帧点云用时的标准差也更低，帧均用时也低于雷达每帧采样用时，可以满足现场实时性需求。

关键词: 稀疏点云, 平面拟合, M采样估计一致性, 聚类, 模板匹配

Abstract: To address the need for detecting bulk carriers during berthing and unberthing at bulk cargo ports to prevent accidents, a planar feature extraction method based on Fast Point Feature Histogram (FPFH) template matching and improved M-estimate Sample Consensus (MSAC) plane fitting was proposed by simplifying the detection of the entire hull, considering the large block coefficient of such carriers. Template point clouds were established using prior knowledge, and the target point cloud was obtained through preprocessing. Normal vectors were estimated and FPFH features were calculated for template matching to extract the shoreward hull point cloud, and hierarchical density-based clustering (HDBSCAN) was applied, followed by MSAC-based plane fitting considering normal vector directions to extract planar features. Validation using on-site data indicated that lower Mean Relative Error (MRE) and reduced standard deviation of processing time per frame were achieved compared to existing methods, with the average processing time per frame found to be shorter than the radar sampling interval, ensuring that real-time operational requirements were met..

Key words: sparse point cloud, plane fitting, M-estimate sample consensus, clustering, template matching

中图分类号:

TP391

周必成, 沈阅, 孔德明. 面向靠离泊船只近岸侧外壁的平面提取方法[J]. 机械工程学报, 2025, 61(18): 50-63.

ZHOU Bicheng, SHEN Yue, KONG Deming. Plane Extraction Method for Berthing and Unberthing Carriers' Shoreward Hull[J]. Journal of Mechanical Engineering, 2025, 61(18): 50-63.

参考文献

[1] SOKUKCU M，SAKAR C. Risk analysis of collision accidents during underway STS berthing maneuver through integrating fault tree analysis (FTA) into Bayesian network (BN)[J]. Applied Ocean Research，2022，126：103290.
[2] 徐广宏，轩少永，朱清华，等. 大型散货船乘潮跟驰进港靠泊[J]. 航海技术，2024(3)：1-4. XU Guanghong，XUAN Shaoyong，ZHU Qinghua，et al. Tidal following and berthing of large bulk carriers [J]. Marine Technology，2024(3)：1-4.
[3] 华培毅.船舶碰撞风险因素分析研究[J]. 珠江水运，2021(7)：17-18. HUA Peiyi. Research on risk factor analysis of ship collisions[J]. Pearl River Water Transport，2021(7)：17-18.
[4] 周正.船舶碰撞码头风险分析[J]. 企业科技与发展，2019(8)：151-152. ZHOU Zheng. Risk analysis of ship collision with wharf[J]. Enterprise Science and Technology and Development，2019(8)：151-152.
[5] 肖建兵. G轮触损码头事故分析及启示[J]. 中国水运，2010，10(4)：37-38. XIAO Jianbing. Analysis and implications of the G-wheel collision with the wharf accident[J]. China Water Transport，2010，10(4)：37-38.
[6] 马勇，胡祖硕，王雯琦，等.船用智能设备与系统的发展现状与展望[J]. 机械工程学报，2024，60(20)：181-192. MA Yong，HU Zushuo，WANG Wenqi，et al. Development status and prospects of intelligent equipment and systems for ships [J]. Journal of Mechanical Engineering，2024，60(20)：181-192.
[7] 王昱博，王建华，郑翔，等. 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 Yubo，WANG Jianhua，ZHENG Xiang，et al. Autonomous berthing method for unmanned surface vehicles based on quay waterline detection[J]. Ship Engineering，2022，44(4)：30-37.
[8] 董亚力，王丹，秦荣明. 基于智能视觉的近海支持船靠泊作业安全监控技术[J]. 现代电子技术，2017，40(24)：88-90. DONG Yali，WANG Dan，QIN Rongming. Safety monitoring technology for berthing operations of nearshore support vessels based on intelligent vision [J]. Modern Electronic Technology，2017，40(24)：88-90.
[9] 王啸雨. 基于深度学习的水面无人艇船舶检测技术研究[D]. 镇江：江苏科技大学，2017. WANG Xiaoyu. Research on ship detection technology for unmanned surface vehicles based on deep learning [D]. Zhenjiang：Jiangsu University of Science and Technology，2017.
[10] 庄加兴，焦侬，殷非. 毫米波雷达与激光雷达在无人船上的应用[J]. 船舶工程，2019，41(11)：79-82，119. ZHUANG Jiaxing，JIAO Nong，YIN Fei. Application of millimeter-wave radar and LiDAR on unmanned surface vehicles[J]. Ship Engineering，2019，41(11)：79-82，119.
[11] 宋浩. 基于点云数据的船舶目标6D位姿估计[D]. 哈尔滨：哈尔滨工程大学，2021. SONG Hao. Vessel target 6D pose estimation based on point cloud data[D]. Harbin：Harbin Engineering University，2021.
[12] 谢涵清，邓乃铭. 基于深度学习的三维感知算法在船舶自主靠泊场景中的应用[J]. 舰船科学技术，2021，43(5)：160-164. XIE Hanqing，DENG Naiming. Application of 3D perception algorithms based on deep learning in autonomous berthing scenarios for ships[J]. Journal of Ship Science and Technology，2021，43(5)：160-164.
[13] 孔德明，张钰，曹帅，等. 面向无人化取料机的毫米波雷达感知技术[J]. 仪器仪表学报，2021，42(7)：189-198. KONG Deming，ZHANG Yu，CAO Shuai，et al. Millimeter-wave radar sensing technology for unmanned reclaimer [J]. Chinese Journal of Scientific Instrument，2021，42(7)：189-198.
[14] 陈晓玉，沈晨，沈阅，等. 基于改进SwiftNet的堆场图像实时分割网络[J]. 计算机工程，2024，50(6)：296-303. CHEN Xiaoyu，SHEN Chen，SHEN Yue，et al. Real-time segmentation network of yard images based on imp-roved SwiftNet [J]. Computer Engineering，2024，50(6)：296-303.
[15] 占金锋，程红蓉，张黎，等. 35000吨散货船船体线型优化及设计研究[J]. 船舶工程，2011，33(5)：10-13，26. ZHAN Jinfeng，CHENG Hongrong，ZHANG Li，et al. Research on hull form optimization and design of 35，000 DWT bulk carrier[J]. Ship Engineering，2011，33(5)：10-13，26.
[16] ZHOU J，ZHAO Y，ZHANG Y，et al. An analytical method for evaluating the structural resistance of plate structures under in-plane impact load in ship-side collision scenarios[J]. Ocean Engineering，2023，288：115961.
[17] 李颖，卢晓东，陈晨. 靠泊船舶的多点离岸距离提取技术[J]. 哈尔滨工程大学学报，2022，43(3)：365-370. LI Ying，LU Xiaodong，CHEN Chen. Multi-point offshore distance extraction technology for berthing ships[J]. Journal of Harbin Engineering University，2022，43(3)：365-370.
[18] 闫晓飞，刘泽西，李颖，等. 基于激光三维视觉的船舶靠泊动态监测技术[J]. 激光与红外，2016，46(12)：1452-1458. YAN Xiaofei，LIU Zexi，LI Ying，et al. Dynamic monitoring technology for ship berthing based on laser three-dimensional vision[J]. Laser & Infrared，2016，46(12)：1452-1458.
[19] GUO H，DU L，LI G. An investigation of geometric feature recognition in 3D ship data[J]. International Journal of Naval Architecture and Ocean Engineering，2024，16：100597
[20] LI Y，LI Z，YANG Y，et al. A fast recognition algorithm of ship hatch in bulk cargo terminal based on point cloud contour extraction[J]. Measurement and Control，2023，56(1-2)：228-236.
[21] WEI S，XIAO Y，YANG X，et al. Attitude estimation method for target ships based on LiDAR point clouds via an improved RANSAC[J]. Journal of Marine Science and Engineering，2023，11(9)：1755.
[22] LINDSTAD H，SANDAAS I，STEEN S. Assessment of profit，cost，and emissions for slender bulk vessel designs[J]. Transportation Research Part D：Transport and Environment，2014，29：32-39.
[23] MENTJES J，WIARDS H，FEUERSTACK S. Berthing assistant system using reference points[J]. Journal of Marine Science and Engineering，2022，10(3)：385.
[24] FISCHLER M A，BOLLES R C. Random sample consensus：a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM，1981，24(6)：381-395.
[25] 雷经发，何玉，张淼，等.平面拟合算法抗干扰能力对比研究[J]. 安徽建筑大学学报，2020，28(4)：28-32. LEI Jingfa，HE Yu，ZHANG Miao，et al. Comparative study of anti-interference capability of plane fitting algorithms[J]. Journal of Anhui Jianzhu University，2020，28(4)：28-32.
[26] TORR P H S，ZISSERMAN A. MLESAC：A new robust estimator with application to estimating image geometry[J]. Computer vision and image understanding，2000，78(1)：138-156.
[27] 苏云龙，平雪良，李楠. 基于RANSAC三维点云的平面提取算法[J]. 激光与红外，2019，49(6)：780-784. SU Yunlong，PING Xueliang，LI Nan. Plane extraction algorithm based on RANSAC 3D point cloud [J]. Laser & Infrared，2019，49(6)：780-784.
[28] 王洋，王俊元，杜文华，等. 基于最小平方中值的点云平面拟合算法[J]. 激光与光电子学进展，2023，60(4)：247-254. WANG Yang，WANG Junyuan，DU Wenhua，et al. Point cloud plane fitting algorithm based on least median squares [J]. Laser and Optoelectronics Progress，2023，60(4)：247-254.
[29] 吴颖，彭警，刘小生. 融合法向信息和尺度自适应的稳健点云平面拟合方法[J/OL].大地测量与地球动力学，2024. http：//10.14075/j.jgg.2024.03.110. Wu Ying，Peng Jing，Liu Xiaosheng. Robust point cloud plane fitting method integrating normal information and scale adaptation[J/OL]. Journal of Geodesy and Geodynamics，2024.http：//10.14075/j.jgg.2024.03.110.
[30] XU X，LUO M，TAN Z，et al. Plane segmentation and fitting method of point clouds based on improved density clustering algorithm for laser radar[J]. Infrared Physics & Technology，2019，96：133-140.
[31] YANG Lina，LI Yuchen，LI Xichun，et al. Efficient plane extraction using normal estimation and RANSAC from 3D point cloud[J]. Computer Standards & Interfaces，2022，82：103608.
[32] VARGA D，SZALAI-GINDL J M，FORMANEK B，et al. Template matching for 3D objects in large point clouds using dbms[J]. IEEE Access，2021，9：76894-76907.
[33] DU G，ZHOU M，YIN C，et al. Classifying fragments of terracotta warriors using template-based partial matching[J]. Multimedia Tools & Applications，2018，77：19171-19191.
[34] RUSU R B，BLODOW N，MARTON Z C，et al. Aligning point cloud views using persistent feature histograms[C]//2008 IEEE/RSJ International Conference on Intelligent Robots and Systems，IEEE，2008：3384-3391.
[35] RUSU R B，BLODOW N，BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//2009 IEEE International Conference on Robotics and Automation，IEEE，2009：3212-3217.
[36] HOPPE H，DEROSE T，DUCHAMP T，et al. Surface reconstruction from unorganized points[C]//Proceedings of the 19th Annual Conference on Computer Graphics and Interactive Techniques，1992：71-78.
[37] 马大贺，刘国柱. 改进的基于FPFH特征配准点云的方法[J]. 计算机与现代化，2017(11)：46-50. MA Dahe，LIU Guozhu Improved method of point cloud registration based on FPFH feature [J]. Computer and Modernization，2017(11)：46-50.
[38] 李海鹏，徐丹，付宇婷，等. 基于FPFH特征提取的散乱点云精简算法[J]. 图学学报，2022，43(4)：599-607. LI Haipeng，XU Dan，FU Yuting，et al. Simplification algorithm for unorganized point clouds based on FPFH feature extraction[J]. Journal of Graphics，2022，43(4)：599-607.
[39] CANTRELL C D. Modern mathematical methods for physicists and engineers[J]. Measurement Science and Technology，2001，12(12)：2211-2211.
[40] FISCHLER M A，BOLLES R C. Random sample consensus：a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM，1981，24(6)：381-395.
[41] CAMPELLO R J G B，MOULAVI D，SANDER J. Density-based clustering based on hierarchical density estimates[C]//Pacific-Asia conference on knowledge discovery and data mining. Berlin，Heidelberg：Springer Berlin Heidelberg，2013：160-172.
[42] 王述红，魏崴，陈浩，等. 基于HDBSCAN算法的岩体结构面产状识别及分组方法[J]. 东北大学学报，2022，43(6)：888-896. WANG Shuhong，WEI Wei，CHEN Hao，et al. Identification and grouping method of strike information of rock mass based on the HDBSCAN algorithm[J]. Journal of Northeastern University，2022，43(6)：888-896.
[43] LUXBURG U. A tutorial on spectral clustering[J]. Statistics and Computing，2007，17：395-416.
[44] 陈立媛，杨神化，索永峰，等. 不同船舶目标电磁散射仿真[J]. 集美大学学报，2021，26(6)：519-526. CHEN Liyuan，YANG Shenhua，SUO Yongfeng，et al. Electromagnetic scattering simulation of different ship targets[J]. Journal of Jimei University，2021，26(6)：519-526.
[45] CARDILLO E，FERRO L. Multi-frequency analysis of microwave and millimeter-wave radars for ship collision avoidance[C]//2022 Microwave Mediterranean Symposium (MMS). IEEE，2022：1-4.
[46] 王伟伟，庞勇，杜黎明，等. 超体素约简和谱聚类结合的机载LiDAR点云单木分割[J]. 遥感学报，2022，26(8)：1650-1661. WANG Weiwei，PANG Yong，DU Liming，et al. Individual tree segmentation for airborne Li DAR point cloud data using spectral clustering and supervoxel-based algorithm[J]. Journal of Remote Sensing，2022，26(8)：1650-1661.