Advertisement

Trajectory Pattern Identification and Anomaly Detection of Pedestrian Flows Based on Visual Clustering

  • Li LiEmail author
  • Christopher Leckie
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 486)

Abstract

Extracting pedestrian movement patterns and determining anomalous regions/time periods is a major challenge in data mining of massive trajectory datasets. In this paper, we apply contour map and visual clustering algorithms to visually identify and analyse areas/time periods with anomalous distributions of pedestrian flows. Contour maps are adopted as the visualization method of the origin-destination flow matrix to describe the distribution of pedestrian movement in terms of entry/exit areas. By transforming the origin-destination flow matrix into a dissimilarity matrix, the iVAT visual clustering algorithm is applied to visually cluster the most popular and related areas. A novel method based on the iVAT algorithm is proposed to detect normal/abnormal time periods with similar/anomalous pedestrian flow patterns. Synthetic and large, real-life datasets are used to validate the effectiveness of our proposed algorithms.

Keywords

Data mining Pedestrian trajectory pattern Visualization Clustering iVAT algorithm 

Notes

Acknowledgments

This work is partially supported by China Scholarship Council. The authors want to acknowledge Mr. Xiaoting Wang for his suggestions on our works and the anonymous reviewers for their constructive suggestions and feedback.

References

  1. 1.
    Bezdek, J.C., Hathaway, R.J.: VAT: a tool for visual assessment of (cluster) tendency. In: IJCNN 2002, pp. 2225–2230 (2002)Google Scholar
  2. 2.
    Chawla, S., Yu, Z., Jiafeng, H.: Inferring the root cause in road traffic anomalies. In: IEEE ICDM 2012, pp. 141–150 (2012)Google Scholar
  3. 3.
    Giannotti, F., Mirco, N., Fabio, P., Dino, P.: Trajectory pattern mining. In: KDD 2007, pp. 330–339 (2007)Google Scholar
  4. 4.
    Liu, L., Assaf, B., Carlo, R.: Urban mobility landscape: real time monitoring of urban mobility patterns. In: Proceedings of the 11th International Conference on Computers in Urban Planning and Urban Management, pp. 1–16 (2009)Google Scholar
  5. 5.
    Liu, W., Xinyi, C., Pengfei, H., Norman, I.B.: Learning motion patterns in unstructured scene based on latent structural information. J. Vis. Lang. Comput. 25(1), 43–53 (2014)CrossRefGoogle Scholar
  6. 6.
    Lu, X., Caixia, W., Nader, K., Arie, C., Anthony, S.: Deriving implicit indoor scene structure with path analysis. In: Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Indoor Spatial Awareness, pp. 43–50 (2011)Google Scholar
  7. 7.
    Majecka, B.: Statistical models of pedestrian behaviour in the forum. Master’s thesis, School of Informatics, University of Edinburgh (2009)Google Scholar
  8. 8.
    Pang, L.X., Sanjay, C., Wei, L., Yu, Z.: On detection of emerging anomalous traffic patterns using GPS data. Data Knowl. Eng. 87, 357–373 (2013)CrossRefGoogle Scholar
  9. 9.
    Wang, L., Uyen, T.N., James, C.B., Christopher, A.L., Kotagiri, R.: iVAT and aVAT: enhanced visual analysis for cluster tendency assessment. In: PAKDD 2010, pp. 16–27 (2010)Google Scholar
  10. 10.
    Witayangkurn, A., Teerayut, H., Yoshihide, S., Ryosuke, S.: Anomalous event detection on large-scale GPS data from mobile phones using hidden Markov model and cloud platform. In: UbiComp. 2013, pp. 1219–1228 (2013)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2016

Authors and Affiliations

  1. 1.Department of Computing and Information SystemsThe University of MelbourneMelbourneAustralia

Personalised recommendations