期刊文献+

面向港口停留区域识别的船舶停留轨迹提取方法 被引量:10

Ship trajectory extraction method for port parking area identification
下载PDF
导出
摘要 针对港口停留区域识别时船舶轨迹大数据的精度低、稀疏、漂移等问题,提出了一种多约束条件下的船舶停留轨迹提取(MPTSSE)方法。首先,结合船舶轨迹数据特点,给出了用于停留区域识别与提取的停留段概念的定义;其次,建立了基于速度、时间差、停留时长、距离等多约束的轨迹停留段提取模型和并行化轨迹停留段提取算法;最后,基于Hadoop框架给出了船舶轨迹大数据集上的轨迹停留段提取算法实现。基于真实船舶轨迹数据的实验结果表明,与基于Stop/Move模型的轨迹停留提取方法相比,MPTSSE方法在三个港口泊位的提取中准确率提高了22%。MPTSSE方法能有效避免轨迹停留段误分割情况,同时在大规模船舶轨迹数据下具有较高的执行效率。 Ship trajectory data shows the characteristics of low precision, sparseness and trajectory drift for the port parking area recognition. To improve the accuracy of port parking area recognition based on ship trajectory big data, a Multiconstrained and Parallel Track Stay Segment Extraction( MPTSSE) method was proposed. Firstly, the definition of stay segment based on ship trajectory data was given as a basic concept for parking area identification. Secondly, a stay segment extraction model based on multiple constraints, such as speed, time difference, dwell time and distance, was introduced.Furthermore, a parallel trajectory stay segment extraction algorithm was proposed. Finally, Hadoop framework was adopted to implement the proposed algorithm. In comparison experiments with the trajectory stay segment extraction method based on Stop/Move model based on real ship trajectory big dataset, the accuracy of MPTSSE is increased by 22% in berth recognition of three ports. The MPTSSE method can effectively avoid misdivision of track stay segment and has better execution efficiency under large-scale ship trajectory dataset.
作者 郑振涛 赵卓峰 王桂玲 徐垚 ZHENG Zhentao;ZHAO Zhuofeng;WANG Guiling;XU Yao(Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data (North China University of Technology),Beijing 100144,China;Shore-based Information System Department,Ocean Information Technology Research Institute Co.,Ltd,China Electronics Technology Group Corporation (CETC Ocean Corp.),Beijing 100041,China)
出处 《计算机应用》 CSCD 北大核心 2019年第1期113-117,共5页 journal of Computer Applications
基金 北京市自然科学基金资助项目(4172018 4162021) 中电科海洋信息技术研究院有限公司高校合作课题项目(402054841879) 北方工业大学毓优团队培养计划项目(107051360018XN012/020)~~
关键词 港口停留区域 船舶轨迹数据 停留轨迹 多约束提取 Hadoop框架 port stay area ship trajectory data trajectory stay trajectory multi-constrained extraction Hadoop framework
  • 相关文献

参考文献6

二级参考文献128

  • 1桂智明,向宇,李玉鉴.基于出租车轨迹的并行城市热点区域发现[J].华中科技大学学报(自然科学版),2012,40(S1):187-190. 被引量:22
  • 2郭庆胜,刘小利,陈宇箭.线与线之间的空间拓扑关系组合推理[J].武汉大学学报(信息科学版),2006,31(1):39-42. 被引量:12
  • 3高勇,张晶,朱晓禧,刘瑜.移动对象时空拓扑关系模型[J].北京大学学报(自然科学版),2007,43(4):468-473. 被引量:14
  • 4IALA. IALA-NET Web Statisti[EB/OL], www. ial athree, org/ialanet. 被引量:1
  • 5Ristic, B , B. L. Scala, et al. Statistical analysis of Motion Patterns in AIS Data: Anomaly Detection and Motion Prediction[C]. l lth International Conference on Information Fusion, 2008. 被引量:1
  • 6Vries, G d. and M. v. Someren . Unsupervised Ship Trajectory Modeling and Prediction Using Compres sion and Clustering[C]. Proceedings of the 18th An- nual Belgian Dutch Conference on Maehine Learning, 2009. 被引量:1
  • 7Vries, G d. and M. v. Someren. Clustering Vessel Trajectories with Alignment Kernels under Trajectory Compression[C]. Machine Learning and Knowledge Discovery in Databases, 2010. 被引量:1
  • 8Laxhammar, R. Artificial Intelligence for Situation Assessment[D]. Master Thesis , KTH Computer Sci . Communication, 2007. 被引量:1
  • 9Laxhammar, R, G. Falkman, et al. Anomaly Detec- tion in Sea Traffic-a Comparison of the Gaussian Mix ture Model and the Kernel Density Estimator[C]. 12th International Conference on Information Fusion, 2009. 被引量:1
  • 10Riveiro, M. Visual Analytics for Maritime Anomaly Detection [D]. Ph. D Thesis, Skovde University, 2011. 被引量:1

共引文献248

同被引文献75

引证文献10

二级引证文献39

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部