闽江口水域船舶锚泊行为识别与挖掘方法  

Identification and Excavation Method of Ship Anchoring Behavior in Minjiang Estuary Waters

作　　者：刘宗杨 周春辉[1,2] 孙业峰 谭林旭 赵俊男 肖进丽 LIU Zongyang;ZHOU Chunhui;SUN Yefeng;TAN Linxu;ZHAO Junnan;XIAO Jinli(School of Navigation, Wuhan University of Technology, Wuhan 430063, China;Hubei Key Laboratory of Inland Shipping Technology, Wuhan 430063, China)

机构地区：[1]武汉理工大学航运学院,武汉430063 [2]内河航运技术湖北省重点实验室,武汉430063

出　　处：《武汉理工大学学报（交通科学与工程版）》2021年第4期805-810,共6页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家重点研发计划(2018YFC1407405);国家自然科学基金(41801375)。

摘　　要：针对沿海船舶海上随意锚泊难以被识别和监管的情况,提出一种基于聚类算法船舶锚泊行为识别与锚泊聚集区挖掘方法.基于船舶锚泊行为特征构建船舶锚泊行为识别方法,结合DBSCAN与K-medoide算法得到单船锚泊代表点,并进一步挖掘得到船舶锚泊聚集区.以闽江口水域为例进行验证,得到不同月份闽江口水域内的锚泊船识别结果和锚泊聚集区分布,挖掘出闽江口水域锚泊热点区域,并结合数据对主要聚集区时空变化进行分析,验证了提出方法和流程的可行性.In view of the fact that it is difficult to identify and supervise the random anchoring of coastal ships at sea,a clustering algorithm-based method for ship anchoring behavior identification and anchoring gathering area mining was proposed.The method of ship anchoring behavior recognition was constructed based on the characteristics of ship anchoring behavior.The representative points of single ship anchoring were obtained by combining DBSCAN and K-Medode algorithm,and the ship anchoring gathering area was further excavated.Taking the Minjiang Estuary waters as an example,the identification results of anchor boats and the distribution of anchor gathering areas in different months were obtained,and the anchor hot spots in the Minjiang Estuary waters were excavated.Combined with the data,the temporal and spatial changes of the main gathering areas were analyzed,and the feasibility of the proposed method and process was verified.

关 键 词：聚类算法 锚泊行为识别 聚集区挖掘 闽江口水域 时空变化 

分 类 号：U698[交通运输工程—港口、海岸及近海工程]