Segmentation of a trajectory is the problem of subdividing a trajectory into subparts where each part is homogeneous and expresses similar movement characteristics. We formalize trajectory segmentation problem using likelihood of the distance and bearing parameters. Section of a trajectory is considered homogeneous when distance between trajectory points and angular movement between them are within the user specified threshold value. We developed a framework for trajectory segmentation based on calculating distance and bearing between two trajectory points. An algorithmic framework is presented to segment the trajectory into a minimum number of segments based on the distance and bearing parameters. The algorithm has been tested on real data set.

Trajectory segmentation, Bearing based segmentation, Trajectory analysis.

[1] A. Anagnostopoulos, M. Vlachos, M. Hadjieleftheriou, E. Keogh, and P. Yu, “Global distance-based segmentation of trajectories”, Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp. 34–43, 2006.
[2] M. Buchin, A. Driemel, M. van Kreveld, and V. Sacrist´an, “Segmenting trajectories: A framework and algorithms using spatiotemporal criteria”, Journal of Spatial Information Science, volume 3 pp 33–63, 2011.
[3] M. Buchin, H. Kruckenberg, and A. K¨olzsch, “Segmenting trajectories by movement states”, Proc. 15th International Symposium Spatial Data Handling (SDH), pp 15–25. Springer-Verlag, 2012.
[4] J. Gudmundsson, P. Laube, and T. Wolle, “Computational movement analysis”, Springer Handbook of Geographic Information, pp 423–438. Springer, 2012.
[5] J. Shamoun-Baranes ,E. van Loon , R. Purves, B. Speckmann, D. Weiskopf, C. Camphuysen, Analysis and visualization of animal movement, Biol Lett 8(1):6–9, 2012 .
[6] F. Giannotti, M. Nanni, D. Pedreschi and F. Pinelli, ”Trajectory Pattern Mining”, KDD007, San Jose, California, USA, pp. 330-339, August 12-15, 2007.
[7] R. Mann, A. D. Jepson, T. El-Maraghi, “Trajectory segmentation using dynamic programming”, Pattern Recognition, Proceedings 16th International Conference Vol. 1, pp 331 - 334 2002.
[8] E. J. Keogh, S. Chu, D. Hart, M. Pazzani, ” Segmenting Time Series: A Survey and Novel Approach”, Data Mining In Time Series Databases, Vol. 57, pp. 1-22, (2004)
[9] J. Kang and H. Yong ”Mining Trajectory Patterns by Incorporating Temporal Properties”, In Proceedings of the 1st International Conference on Emerging Databases (EDB2009), 2009.
[10] H. Cheng, X. Yan, J. Han, and S. Philip, ”Direct Discriminative Pattern Mining for Effective Classification”, ICDE’ 08 Proceedings of the 2008 IEEE 24th International Conference on Data Engineering, 2008.
[11] Theodoridis, Y. (2003). The R-tree-portal, a collection of moving object databases.
[12] V. Mirge, K. Verma. And S. Gupta, “A Novel Approach for Mining Trajectory Patterns of Moving Vehicles”, International Journal of Computer Applications vol. 104 issue 4 pp 4-8, October 2014.
[13] V. Mirge, K. Verma, & Gupta, S. Dense traffic flow patterns mining in bi-directional road networks using density based trajectory clustering. Advances in Data Analysis and Classification, vol. 11 issue 3 pp 1-15, 2017.
[14] R.S. Walse, G.D. Kurundkar, P. U. Bhalchandra, “
Design and Development of Novel Techniques for Clustering and Classification of Data”, International Journal of Scientific Research in Computer Science and Engineering, Vol.06 , Special Issue.01 , pp.19-22, Jan-2018.