Stopping behavior recognition and classification of ship based on trajectory characteristics
-
摘要: 为准确评估大规模轨迹数据中的船舶停留活动，构建了两阶段船舶轨迹停留点提取策略，提出了特征驱动的船舶停留行为识别与自动分类方法；以距离、时间和轨迹点数量为约束条件构建了规则模型，检测了原始轨迹中的停留候选轨迹，引入孤立森林算法检测和去除异常离群点，提取了高聚集度的船舶停留轨迹集合；基于船舶靠泊和锚泊的时空特征，定义了轨迹点重复率、相邻点平均距离和最远点对距离3个指标，构建了新的轨迹相似性度量模型，量化了船舶停留轨迹点的分布特征和聚合程度，并利用K近邻算法完成了船舶锚泊行为与靠泊行为的自动分类；采用提出的方法处理了3个不同水域的船舶轨迹数据，准确获取了船舶停留行为的分类结果，并验证了船舶锚泊与靠泊在轨迹时空特征上的差异性，以人工标注结果为参考依据评估了船舶停留行为识别与分类的准确性。研究结果表明：船舶靠泊的轨迹点重复率在80%以上，最远点对距离和相邻点平均距离分别为6~11和1~2 m，船舶锚泊的轨迹点重复率在10%以下，最远点对距离和相邻点平均距离分别为150~250和8~10 m，说明轨迹点重复率、相邻点平均距离和最远点对距离这3个时空特征对船舶靠泊和锚泊具有显著的区分能力；提出的方法对船舶停留识别分类的正确率在98%以上，充分证明了其有效性；采用提出的方法可更新已有码头和锚地的空间位置，自动识别规则水域外的船舶异常停留和规则水域内的超长时间船舶异常停留，掌握在港船舶停留分布情况，识别不同季节、不同时段的热点码头和锚地，从而辅助优化港口规划布局和交通组织。Abstract: To estimate stopping activities of ships from massive trajectory data accurately, a two-stage strategy was established to extract stop points from ship trajectories, and an automatic characteristic-based ship stopping behavior recognition and classification method was also proposed. By taking the distance, time and number of points as the constraint conditions, a rule model was constructed to detect the candidate stop trajectories from the raw trajectories. The isolation forest algorithm was applied for the abnormal outliers detection and elimination. A set of highly clustered ship stop trajectories was extracted. Based on the spatio-temporal characteristics of ship berthing and anchoring. Three indices, including the repetition rate of trajectory point, mean distance between neighboring points, and distance between the farthest point pair, were defined to establish a new trajectory similarity measurement model. Then, the distribution characteristics and aggregation degree of ship stop trajectory points were quantitatively evaluated, and the K-nearest neighbor algorithm was then used to automatically classify the berthing and anchoring behaviors of ships. The proposed method was applied to the ship trajectory data collected from three different waters. The classification results of ship stopping behaviors were obtained accurately. The differences in spatio-temporal characteristics of ship anchoring and berthing were verified. The accuracies of recognition and classification of ship stopping behaviors were assessed with the help of manually annotated results. Research results indicate that the repetition rate of trajectory points for ship berthing is more than 80%. The distance between the furthest point pair and the mean distance between neighboring points are 6-11 and 1-2 m, respectively. The repetition rate of trajectory points for ship anchoring is less than 10%. The distance between the furthest point pair and the mean distance between neighboring points are 150-250 and 8-10 m, respectively. Thus, the three spatio-temporal characteristics, including the repetition rate of trajectory point, mean distance between neighboring points, and distance between the farthest point pair have a significant ability to distinguish the ship berthing and anchoring. The recognition and classification accuracy of the proposed method reaches up to 98%. Therefore, its effectiveness is fully proved. With the help of the proposed model, the spatial positions of existing docks and anchorages can be updated. Abnormal ship stops outside the regular waters or abnormal ship stops for prolonged periods inside the regular waters can be recognized automatically. The stopping distribution in ports can be monitored, and the popular docks and anchorages in different times and seasons can be known. In this way, the port planning layout and traffic organization can be optimized. 3 tabs, 7 figs, 31 refs.
-
图 1 两阶段船舶停留轨迹点提取策略
Figure 1. Two-stage strategy of stop points extraction from ship trajectory
图 4 试验区域地理范围和船舶轨迹数据可视化
Figure 4. Geographical scope and visualization of ship trajectory data of test regions
图 6 三个区域船舶停留轨迹特征和分类结果
Figure 6. Characteristics and classification results of ship stop trajectories in three regions
图 7 三个区域船舶停留分类结果可视化
Figure 7. Visualization of classification result of ship stops in three regions
表 1 试验区域船舶和轨迹总数
Table 1. Total numbers of ships and trajectories in test regions
数据属性 区域1 区域2 区域3 轨迹总数 316 831 845 358 2 672 613 船舶数 77 326 460 时间范围 2017-01 2017-01 2017-01 
下载: 导出CSV
表 2 船舶停留K近邻分类结果
Table 2. K-nearest neighbor classification results of ship stops
试验位置 停留次数 锚泊次数 靠泊次数 区域1 349 121 228 区域2 1 914 1 300 614 区域3 3 512 1 903 1 609
下载: 导出CSV
表 3 算法分类结果的人工验证
Table 3. Manual verification of classification results of algorithm
试验位置 停留次数 人工验证错误数 识别正确率/% A组 B组 C组 平均 区域1 349 4 4 4 4 98.85 区域2 1 914 19 21 20 20 98.95 区域3 3 512 39 43 50 44 98.75
下载: 导出CSV
-
[1] 陈金海, 陆锋, 彭国均. 海洋运输船舶轨迹分析研究进展[J]. 中国航海, 2012, 35(3): 53-57. doi: 10.3969/j.issn.1000-4653.2012.03.012CHEN Jin-hai, LU Feng, PENG Guo-jun. The progress of research in maritime vessel trajectory analysis[J]. Navigation of China, 2012, 35(3): 53-57. (in Chinese) doi: 10.3969/j.issn.1000-4653.2012.03.012 [2] 黄亮, 刘益, 文元桥, 等. 内河渡船异常行为识别[J]. 大连海事大学学报, 2017, 43(1): 8-13. https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201701002.htmHUANG Liang, LIU Yi, WEN Yuan-qiao, et al. Abnormal behavior recognition of inland river ferryboat[J]. Journal of Dalian Maritime University, 2017, 43(1): 8-13. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201701002.htm [3] HUANG Liang, WEN Yuan-qiao, GUO Wei, et al. Mobility pattern analysis of ship trajectories based on semantic transformation and topic model[J]. Ocean Engineering, 2020, 201: 107092. doi: 10.1016/j.oceaneng.2020.107092 [4] SHENG Pan, YIN Jing-bo. Extracting shipping route patterns by trajectory clustering model based on automatic identification system data[J]. Sustainability, 2018, 10(7): 2327. doi: 10.3390/su10072327 [5] GAO Miao, SHI Guo-you, LI Shuang. Online prediction of ship behavior with automatic identification system sensor data using bidirectional long short-term memory recurrent neural network[J]. Sensors, 2018, 18(12): 4211. doi: 10.3390/s18124211 [6] YANG Dong, WU Ling-xiao, WANG Shuai-an, et al. How big data enriches maritime research—a critical review of automatic identification system (AIS) data applications[J]. Transport Reviews, 2019, 39(6): 755-773. doi: 10.1080/01441647.2019.1649315 [7] SHENG Kai, LIU Zhong, ZHOU De-chao, et al. Research on ship classification based on trajectory features[J]. Journal of Navigation, 2018, 71(1): 100-116. doi: 10.1017/S0373463317000546 [8] HÖRTEBORN A, RINGSBERG J W, SVANBERG M, et al. A revisit of the definition of the ship domain based on AIS analysis[J]. Journal of Navigation, 2019, 72(3): 777-794. doi: 10.1017/S0373463318000978 [9] GAO Miao, SHI Guo-you. Ship spatiotemporal key feature point online extraction based on AIS multi-sensor data using an improved sliding window algorithm[J]. Sensors, 2019, 19(12): 2706. doi: 10.3390/s19122706 [10] ZHANG Shu-kai, SHI Guo-you, LIU Zheng-jiang, et al. Data-driven based automatic maritime routing from massive AIS trajectories in the face of disparity[J]. Ocean Engineering, 2018, 155: 240-250. doi: 10.1016/j.oceaneng.2018.02.060 [11] KIM J S, JEONG J S. Extraction of reference seaway through machine learning of ship navigational data and trajectory[J]. International Journal of Fuzzy Logic and Intelligent Systems, 2017, 17(2): 82-90. doi: 10.5391/IJFIS.2017.17.2.82 [12] ZHOU Yang, DAAMEN W, VELLINGA T, et al. Ship classification based on ship behavior clustering from AIS data[J]. Ocean Engineering, 2019, 175: 176-187. doi: 10.1016/j.oceaneng.2019.02.005 [13] JIN Liang, LUO Zheng-yi, GAO Shu. Visual analytics approach to vessel behaviour analysis[J]. The Journal of Navigation, 2018, 71(5): 1195-1209. doi: 10.1017/S0373463318000085 [14] 文元桥, 张义萌, 黄亮, 等. 基于语义的船舶行为动态推理机制[J]. 中国航海, 2019, 42(3): 34-39, 50. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGHH201903008.htmWEN Yuan-qiao, ZHANG Yi-meng, HUANG Liang, et al. Mechanism of ship behavior dynamic reasoning based on semantics[J]. Navigation of China, 2019, 42(3): 34-39, 50. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGHH201903008.htm [15] ALESSANDRINI A, MAZZARELLA F, VESPE M. Estimated time of arrival using historical vessel tracking data[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 20(1): 7-15. [16] WEN Yuan-qiao, ZHANG Yi-meng, HUANG Liang, et al. Semantic modelling of ship behavior in harbor based on ontology and dynamic Bayesian network[J]. ISPRS International Journal of Geo-Information, 2019, 8(3): 107. doi: 10.3390/ijgi8030107 [17] HUANG Ya-min, CHEN Lin-ying, VAN GELDER P H A J M. Generalized velocity obstacle algorithm for preventing ship collisions at sea[J]. Ocean Engineering, 2019, 173: 142-156. doi: 10.1016/j.oceaneng.2018.12.053 [18] WANG Jiang, ZHU Cheng, ZHOU Yun, et al. Vessel spatio-temporal knowledge discovery with AIS trajectories using co-clustering[J]. Journal of Navigation, 2017, 70(6): 1383-1400. doi: 10.1017/S0373463317000406 [19] PATROUMPAS K, ALEVIZOS E, ARTIKIS A, et al. Online event recognition from moving vessel trajectories[J]. GeoInformatica, 2017, 21(2): 389-427. doi: 10.1007/s10707-016-0266-x [20] PALLOTTA G, VESPE M, BRYAN K. Vessel pattern knowledge discovery from AIS data: a framework for anomaly detection and route prediction[J]. Entropy, 2013, 15(6): 2218-2245. [21] 丁兆颖, 姚迪, 吴琳, 等. 一种基于改进的DBSCAN的面向海量船舶位置数据码头挖掘算法[J]. 计算机工程与科学, 2015, 37(11): 2061-2067. doi: 10.3969/j.issn.1007-130X.2015.11.011DING Zhao-ying, YAO Di, WU Lin, et al. A dock mining algorithm for massive vessel location data based on improved DBSCAN[J]. Computer Engineering and Science, 2015, 37(11): 2061-2067. (in Chinese) doi: 10.3969/j.issn.1007-130X.2015.11.011 [22] 叶仁道, 姜玲, 张瑜. 大数据背景下全球船舶停泊点的数据挖掘分析[J]. 杭州电子科技大学学报(社会科学版), 2018, 14(1): 13-17. https://www.cnki.com.cn/Article/CJFDTOTAL-HZDS201801003.htmYE Ren-dao, JIANG Ling, ZHANG Yu. A data mining analysis of global moorages under big data background[J]. Journal of Hangzhou Dianzi University (Social Sciences), 2018, 14(1): 13-17. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HZDS201801003.htm [23] 郑海林, 胡勤友, 杨春, 等. 上海外高桥港区停泊船聚类分析与异常检测[J]. 地球信息科学学报, 2018, 20(5): 640-646. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201805012.htmZHENG Hai-lin, HU Qin-you, YANG Chun, et al. Clustering analysis and anomaly detection of berthing ships at Waigaoqiao Harbour District of Shanghai[J]. Journal of Geo-information Science, 2018, 20(5): 640-646. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201805012.htm [24] 郑振涛, 赵卓峰, 王桂玲, 等. 面向港口停留区域识别的船舶停留轨迹提取方法[J]. 计算机应用, 2019, 39(1): 113-117. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201901022.htmZHENG Zhen-tao, ZHAO Zhuo-feng, WANG Gui-ling, et al. Ship trajectory extraction method for port parking area identification[J]. Journal of Computer Applications, 2019, 39(1): 113-117. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201901022.htm [25] LIU F T, TING K M, ZHOU Zhi-hua. Isolation-based anomaly detection[J]. ACM Transactions on Knowledge Discovery from Data, 2012, 6(1): 1-39. [26] 向琛. 基于孤立森林算法的船舶异常行为集成检测[D]. 大连: 大连海事大学, 2020.XIANG Chen. Integrated detection of ship abnormal behavior based on isolation forest algorithm[D]. Dalian: Dalian Maritime University, 2020. (in Chinese) [27] 陈家义, 李福武, 何小阳. AIS系统在大型船舶锚泊半径及船间距的应用[J]. 舰船科学技术, 2017, 39(5): 67-69. https://www.cnki.com.cn/Article/CJFDTOTAL-JCKX201710024.htmCHEN Jia-yi, LI Fu-wu, HE Xiao-yang. The application of AIS system in the large ship's mooring radius and ship spacing[J]. Ship Science and Technology, 2017, 39(5): 67-69. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JCKX201710024.htm [28] 刘磊, 初秀民, 蒋仲廉, 等. 基于KNN的船舶轨迹分类算法[J]. 大连海事大学学报, 2018, 44(3): 15-21. https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201803005.htmLIU Lei, CHU Xiu-min, JIANG Zhong-lian, et al. Ship trajectory classification algorithm based on KNN[J]. Journal of Dalian Maritime University, 2018, 44(3): 15-21. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201803005.htm [29] LUO Xiang-long, LI Dan-yang, YANG Yu, et al. Spatiotemporal traffic flow prediction with KNN and LSTM[J]. Journal of Advanced Transportation, 2019, 2019: 4145353. [30] 霍豪, 沈金星, 郑长江. 基于KNN算法的公交到站时间预测[J]. 交通运输工程与信息学报, 2020, 18(4): 76-82, 102. https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC202004010.htmHUO Hao, SHEN Jin-xing, ZHENG Chang-jiang. Bus arrival time prediction based on KNN algorithm[J]. Journal of Transportation Engineering and Information, 2020, 18(4): 76-82, 102. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC202004010.htm [31] 吕荣. 基于大数据处理技术的AIS应用研究[J]. 海军工程大学学报, 2017, 29(4): 98-102, 112. https://www.cnki.com.cn/Article/CJFDTOTAL-HJGX201704020.htmLYU Rong. Applications for AIS by bigdata processing technology[J]. Journal of Naval University of Engineering, 2017, 29(4): 98-102, 112. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HJGX201704020.htm -
点击查看大图
图(7) / 表(3)
计量
- 文章访问数: 1324
- HTML全文浏览量: 321
- PDF下载量: 203
- 被引次数: 0
