Urban Traffic Visual Analysis

Xiaoru Yuan
October 10, 2013 - 12:30 PM
Woodward 130
Abstract: In this talk, we will discuss two visual analysis systems on traffic trajectory. First we introduce TripVista (Triple Perspective Visual Trajectory Analytics) for exploring and analyzing microscopic traffic patterns and abnormal behaviors. In the second interactive system for visual analysis of macroscopic level urban traffic congestion based on GPS trajectories, we developed strategies to extract and derive traffic jam information from taxis trajectories. Traffic jam events are the automatically detected and spatiotemporal related events are concatenated in traffic jam propagation graphs. Case studies with 24 days of taxi GPS trajectories collected in Beijing demonstrate the effectiveness of our system. In addition, we will also discuss how to exploit social media to understand more about the urban traffics. Xiaoru Yuan is a faculty member in the School of Electronics Engineering and Computer Science and vice director of Information Science Center, at Peking University. He received Bachelor degrees in chemistry and law from Peking University, China, in 1997 and 1998, respectively. He received the Ph.D. degree in computer science in 2006, from the University of Minnesota at Twin Cities. His primary research interests are in the field of scientific visualization, information visualization and visual analytics. He has published over 40 co-author papers in IEEE Visualization, IEEE Information Visualization, IEEE TVCG, IEEE EuroVis, IEEE PacificVis and other major international visualization conference and journals. His co-authored work on high dynamic range volume visualization received Best Application Paper Award at the IEEE Visualization 2005 conference. He served on the editorial board of CCF journal of CAD&CG and Springer Journal of Visualization. He served as the chair (2012-13) of CCF YOCSEF. For more information, visit http://vis.pku.edu.cn/wiki