期刊文献+

基于改进Frechet距离的海上目标航迹相似性度量方法 被引量:1

A Method for Measuring the Similarity of Sea Target Trajectory Based on the Improved Frechet Distance
下载PDF
导出
摘要 轨迹相似性分析是运动目标行为规律分析中的基础。船舶作为一类典型运动目标,其运动特征及行为模式与陆上运动目标有较大差异,直接在船舶轨迹相似性的度量中采用已有方法会面临较多挑战。通过分析船舶运动特征,在考虑运动约束、时空跨度以及定位误差的情况下,提出了基于改进Frechet距离的海上目标航迹相似性度量方法。通过实例验证与对比可得,相较于传统轨迹相似性分析方法,该方法具有更好的尺度不变性与噪声鲁棒性,能够更为准确地刻画不同空间尺度及噪声下的航迹相似程度。 Trajectory similarity is the basis of the behavior analysis of moving targets.As a kind of typical moving target,the ship has movement characteristics and behavior patterns quite different from those of the moving targets on land,so there’re many challenges to overcome if traditional similarity measurement methods are used directly for ships.Therefore,a method is proposed for measuring the similarity of ship track based on the improved Frechet distance by analyzing the ship motion characteristics and considering the ship motion constraints,space and time spans and position errors.Experimental results show that the proposed method has better scale invariance and noise robustness,and can describe the similarity degree of trajectories more accurately under different spatial scales and noises compared with the traditional trajectory similarity analysis methods.
作者 刘敬一 郭琦 陈金勇 楚博策 LIU Jingyi;GUO Qi;CHEN Jinyong;CHU Boce(The 54th Research Institute of CETC,Shijiazhuang 050081,China)
出处 《无线电工程》 北大核心 2022年第6期1080-1085,共6页 Radio Engineering
基金 国家博士后基金(2021M703021) 河北省人才择优资助项目(B2021003031)。
关键词 轨迹相似性 船舶航迹 Frechet距离 自动识别系统数据 trajectory similarity ship track Frechet distance AIS data
  • 相关文献

参考文献2

二级参考文献33

  • 1Hu W M, Tan T N, Wang L, etal. A survey on visual surveillance of object motion and behaviors[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part C: Applications and Reviews, 2004, 34(3) :334-352.
  • 2Vlachos M, Kollios G, Gunopulos D. Discovering similar multidimensional trajectories [C]// Proc 18th Int Conf on Data Engineering. San Jose, CA: IEEE Press, 2002 : 673-684.
  • 3Fatih P. Trajectory distance metric using hidden markov model based representation[EB/OL]. (2004) [ 2008 ]. http://www. merl. com/reports/docs/ TR2004-030. pdf.
  • 4Hervieu A, Bouthemy P, Le Cadre J-P. A HMM- based method for recognizing dynamic video contents from trajectories[C]// Proc IEEE Int Conf on Image Processing. San Antonio, TX: IEEE Press, 2007, 4: Ⅳ-533-Ⅳ-536.
  • 5Fatih P, Tetsuji H. Event detection by eigenvector decomposition using object and frame features[C]// Proc IEEE Computer Society Conf on Computer Vision and Pattern Recognition Workshops. Los Alamitos: IEEE Computer Society Press, 2004: 114-114.
  • 6Li C, Biswas G. A Bayesian approach to temporal data clustering using hidden markov models[C]// Proc 7th Int Conf on Machine Learning. Stanford University: Morgan Kaufmann, 2000: 543-550.
  • 7Levenshtein V I. Binary codes capable of correcting deletions, insertions and reversals[J]. Soviet Physics Doklady, 1966, 10(8):707-710.
  • 8Zheng J B, Feng D D, Zhao R C. Trajectory matching and classification of video moving objects[C]//Proc IEEE 7th Workshop on Multimedia Signal Processing. Shanghai, China: IEEE Press, 2005: 1-4.
  • 9Chen L, Ozsu M T, Oria V. Robust and fast similarity search for moving object trajectories[C]// Proc ACM SIGMOD Int Conf on Management of Data. Baltimore, Maryland, USA: ACM, 2005: 491-502.
  • 10Chen L, Ng R. On the marriage of Lp-norms and edit distance[C]//Proc 30th Int Conf on Very Large Data Bases. Toronto, Canada: Morgan Kaufmann, 2004: 792- 803.

共引文献32

同被引文献20

引证文献1

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