Dongdaemun
SEOUL | KOREA
APRIL 18-21, 2017
News
Sponsors
Previous Events
Channels

Classification and Visualization for Symbolic People Flow Data Preserving Way Points and Staying Times

  • Yuri Miyagi
    Ochanomizu University
  • Masaki Onishi
    AIST
  • Chiemi Watanabe
    University of Tsukuba
  • Takayuki Itoh
    Ochanomizu University
  • Masahiro Takatsuka
    The University of Sydney

Abstract

People flow information brings us useful knowledge in various industrial and social fields including traffic, disaster prevention and marketing. However, it is still an open problem to develop effective people flow analysis techniques. We suppose compression and data mining techniques are especially important for analysis and visualization of large-scale people flow datasets. This paper presents a visualization tool for large-scale people flow dataset featuring compression and data mining techniques. This tool firstly compresses the people flow datasets using UniversalSAX, an extended method of SAX (Symbolic Aggregate Approximation). Next process is extraction and classification of movement patterns focusing on way points and staying times. Finally, the tool visualize trajectories of people flow and extracted features such as popular walking routes and congestions. We had experiments of classifying and visualizing walking routes using two types of people flow dataset recorded at an exhibition. The results allow us to discover characteristic movements such as stopping at particular places or popular walking routes.