Volume 46 Issue 5
Jun.  2017
Turn off MathJax
Article Contents
Article Navigation >  Infrared and Laser Engineering  > 2017  >  46(5): 528001-0528001(8)

Zhou Peipei, Ding Qinghai, Luo Haibo, Hou Xinglin. Trajectory outlier detection based on DBSCAN clustering algorithm[J]. Infrared and Laser Engineering, 2017, 46(5): 528001-0528001(8). doi: 10.3788/IRLA201746.0528001
Citation: Zhou Peipei, Ding Qinghai, Luo Haibo, Hou Xinglin. Trajectory outlier detection based on DBSCAN clustering algorithm[J]. Infrared and Laser Engineering, 2017, 46(5): 528001-0528001(8). doi: 10.3788/IRLA201746.0528001
shu

Trajectory outlier detection based on DBSCAN clustering algorithm

doi: 10.3788/IRLA201746.0528001
  • 1.

    Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;

  • 2.

    University of Chinese Academy of Sciences,Beijing 100049,China;

  • 3.

    Space Star Technology Co.,Ltd.,Beijing 100086,China;

  • 4.

    Key Laboratory of Opt-Electronic Information Processing,Chinese Academy of Sciences,Shenyang 110016,China

  • Received Date: 2016-09-11
  • Rev Recd Date: 2016-10-20
  • Publish Date: 2017-05-25
  • Existing traditional trajectory outlier detection algorithms always focus on spatial outliers and ignore temporal outliers, and the accuracy is relatively low. To solve these problems, a simple and effective approach based on enhanced clustering algorithm was proposed to detect spatio-temporal trajectory outliers. Firstly, each original trajectory was simplified into a set of sequential line segments with the velocity-based minimum description length (VMDL) partition principle. Secondly, the distance formula between line segments was improved to enhance the clustering performance. Using DBSCAN algorithm, the line segments were classified into different groups which could represent local normal behaviors. Thirdly, outliers were detected using two-level detection algorithm which first detected spatial outliers and then detected temporal outliers. Experimental results on multiple trajectory data sets demonstrate that the proposed algorithm could successfully detect three kinds of spatio-temporal outliers, position, angle and velocity. Compared with other methods, the precision and accuracy make great improvement.
  • [1] Bamnett V, Lewis T. Outliers in Statistical Data[M]. Chichester:John Wiley, 1995:584.
    [2] Cui Xiongwen, Wu Qinzhang, Jiang Ping, et al. Affine-invariant target tracking based on subspace representation[J]. Infrared and Laser Engineering, 2015, 44(2):769-774. (in Chinese)崔雄文, 吴钦章, 蒋平, 等. 子空间模型下的仿射不变目标跟踪[J]. 红外与激光工程, 2015, 44(2):769-774.
    [3] Hi H, Ling H, Wu Y,, et al. Real time robust l1 tracker using accelerated proximal gradient approach[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012, 157(10):1830-1837.
    [4] Milan A, Leal-Taix L, Schindler K, et al. Joint tracking and segmentation of multiple targets[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015:5397-5406.
    [5] Lee J G, Han J, Li X. Trajectory outlier detection:A partition-and-detect framework[C]//IEEE 24th International Conference on Data Engineering, 2008:140-149.
    [6] Yuan G, Xia S, Zhang L, et al. Trajectory outlier detection algorithm based on structural features[J]. Journal of Computational Information Systems, 2011, 11(7):4137-4144.
    [7] Aquino A R de, Alvares L O, Renso C, et al. Towards semantic trajectory outlier detection[C]//Proceedings of GeoInfo, 2013:115-126.
    [8] Liu Z, Pi D, Jiang J. Density-based trajectory outlier detection algorithm[J]. Journal of Systems Engineering and Electronics, 2013, 24(2):335-340.
    [9] Hu H Y, Li Z H. Multi-level trajectory learning for traffic behavior detection and analysis[J]. Journal of the Chinese Institute of Engineers, 2014, 37(8):995-1006.
    [10] Zhang L, Hu Z, Yang G. Trajectory outlier detection based on multi-factors[J]. IEICE Transactions on Information and Systems, 2014, E97.D(8):2170-2173.
    [11] Lee J G, Han J, Whang K Y. Trajectory clustering:a partition-and-group framework[C]//Proceedings of the 2007 ACM SIGMOD International Conference on Management of Data, 2007:593-604.
    [12] Kut A, Birant D. Spatio-temporal outlier detection in large databases[J]. CIT Journal of Computing and Information Technology, 2006, 14(4):291-297.
    [13] Alvar M, Torsello A, Sanchez-Miralles A, et al. Abnormal behavior detection using dominant sets[J]. Machine Vision and Applications, 2014, 25(5):1351-1368.
    [14] Wang Y, Wang D, Chen F. Abnormal behavior detection using trajectory analysis in camera sensor networks[J]. International Journal of Distributed Sensor Networks, 2014, 2014(1):1-9.
    [15] Jeong H, Chang H J, Choi J Y. Modeling of moving object trajectory by spatio-temporal learning for abnormal behavior detection[C]//20118th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), 2011:119-123.
    [16] Lee J G, Han J, Li X, et al. TraClass:trajectory classification using hierarchical region-based and trajectory-based clustering[J]. Proceedings of the VLDB Endowment, 2008, 1(1):1081-1094.
    [17] Fontes V C, Alencar L A de, Renso C, et al. Discovering trajectory outliers between regions of interest[C]//Proceedings of GeoInfo, 2013:49-60.
    [18] Ester M, Kriegel H P, Sander J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Proceedings of Kdd Location, 1996:226-231.
    [19] Chen J, Leung M K, Gao Y. Noisy logo recognition using line segment Hausdorff distance[J]. Pattern Recognition, 2003, 36(4):943-955.
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索
Get Citation
PDF
XML

Article Metrics

Article views(736) PDF downloads(166) Cited by()

Related
Proportional views

Trajectory outlier detection based on DBSCAN clustering algorithm

doi: 10.3788/IRLA201746.0528001
  • 1. Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;
  • 2. University of Chinese Academy of Sciences,Beijing 100049,China;
  • 3. Space Star Technology Co.,Ltd.,Beijing 100086,China;
  • 4. Key Laboratory of Opt-Electronic Information Processing,Chinese Academy of Sciences,Shenyang 110016,China
  • Received Date: 2016-09-11
  • Rev Recd Date: 2016-10-20
  • Publish Date: 2017-05-25

Abstract: Existing traditional trajectory outlier detection algorithms always focus on spatial outliers and ignore temporal outliers, and the accuracy is relatively low. To solve these problems, a simple and effective approach based on enhanced clustering algorithm was proposed to detect spatio-temporal trajectory outliers. Firstly, each original trajectory was simplified into a set of sequential line segments with the velocity-based minimum description length (VMDL) partition principle. Secondly, the distance formula between line segments was improved to enhance the clustering performance. Using DBSCAN algorithm, the line segments were classified into different groups which could represent local normal behaviors. Thirdly, outliers were detected using two-level detection algorithm which first detected spatial outliers and then detected temporal outliers. Experimental results on multiple trajectory data sets demonstrate that the proposed algorithm could successfully detect three kinds of spatio-temporal outliers, position, angle and velocity. Compared with other methods, the precision and accuracy make great improvement.

    HTML

Reference (19)

Catalog

    版权所有 © 2019 《红外与激光工程》编辑部｜ Address: 58 Zhonghuan West Road, Tianjin Airport Economic Zone｜ Post Code: 300308

    津ICP备19007885号-1

    Supported by: Beijing Renhe Information Technology Co. Ltd  

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return