Hirokatsu KATAOKA, Ph.D.
National Institute of Advanced Industrial Science and Technology (AIST), Japan

[Top] [Research] [Curriculum Vitae] [Publications]

"Big Data Analysis for Trajectory Clustering"
Hirokatsu Kataoka (Keio Univ), Kenji Iwata (AIST), Yutaka Satoh (AIST), Masaki Onishi (AIST), Yoshimitsu Aoki (Keio Univ)

  We're accumulating trajectory data for many services (e.g. crowded analysis and tendency understanding). Now we have more than 50,000,000 trajectories. These data is becoming "Big Trajectory Data". It is necessary to analyze trajectory data and information extraction. In our research, we propose the method for creating main trajectory map and clustering using large-scale trajectory data. We use small and large number of data, in order to show the effectiveness of big data analysis.

  We're accumulating trajectory data for many services (e.g. crowded analysis and tendency understanding). Now we have more than 50,000,000 trajectories. These data is becoming "Big Trajectory Data". It is necessary to analyze trajectory data and information extraction. In our research, we propose the method for creating main trajectory map and clustering using large-scale trajectory data. We use small and large number of data, in order to show the effectiveness of big data analysis.

  We show the main trajectory map and clustering result. The flow of this method is 1. input trajectory files, 2. Creating main trajectory map and 3. trajectory clustering. Each trajectory is divided as a .csv file and input for trajectory analysis. Main trajectory map shows the frequency of direction and IN/OUT in the field. From the values of main trajectory map, we can understand the environment and execute trajectory clustering.




References

- Hirokatsu Kataoka, Kenji Iwata, Yutaka Satoh, Ikushi Yoda, Masaki Onishi, Yoshimitsu Aoki, "Big Trajectory Data Analysis for Clustering and Anomaly Detection", IAPR Conference on Machine Vision Applications (MVA), May 2013. [PDF]   [PPT]




Copyright Hirokatsu Kataoka