• Jun 17] Visual Storytelling Contest videos and materials are updated.
• Apr 14] Workshops (PacificVAST) schedules are updated.
• Mar 7] Conference program and keynote talks are updated.
• Feb] Registration is now available!
• Feb] Accommodation information is updated.

• 2016
  Taipei
  Apr 19 - Apr 22
• 2015
  Hangzhou
  Apr 14 - Apr 17
• 2014
  Yokohama
  Mar 04 - Mar 07
• 2013
  Sydney
  Feb 26 - Mar 01
• 2012
  Songdo
  Feb 28 - Mar 02
• 2011
  Hong Kong
  Mar 01 - Mar 04
• 2010
  Taipei
  Mar 02 - Mar 05
• 2009
  Beijing
  Apr 20 - Apr 23
• 2008
  Kyoto
  Mar 04 - Mar 07

• Facebook Official Facebook Page

• Twitter Official Twitter Account

• WeChat Official WeChat Account (亚太地区可视化会议微信公众号)

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

• Yuri Miyagi
  Ochanomizu University
• Masaki Onishi onishi (at) ni.aist.go.jp
  AIST
• Chiemi Watanabe chiemi (at) cs.tsukuba.ac.jp
  University of Tsukuba
• Takayuki Itoh itot (at) is.ocha.ac.jp
  Ochanomizu University
• Masahiro Takatsuka masa.takatsuka (at) sydney.edu.au
  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.