In this project, we propose a visual analysis method TrajRank to study the travel behaviour of vehicles along one route. For a route, its different road segment costs different time. Besides, travel time can differ greatly from rush hour to non-rush hour. Therefore, we aim to study the spatial-temporal distribution of travel time, i.e., the time spent on each road segment, and the travel time variation in rush/non-rush hours. TrajRank first allows users to interactively select a route, and segment it into several road segments. Then trajectories passing this route are automatically extracted. These trajectories are ranked on each road segment according to travel time, and further clustered according to the rankings on all road segments. Based on the above ranking analysis, we provide a temporal distribution view, showing the temporal distribution of travel time, and a ranking diagram view, showing the spatial variation of travel time. With real taxi GPS data, we present three use cases and a user study to show the effectiveness and usability of our method.
Min Lu, Zuchao Wang, and Xiaoru Yuan.
TrajRank: Exploring Travel Behaviour on a Route by Trajectory Ranking.
In Proceedings of IEEE Pacific Visualization Symposium (PacificVis'15), Hang Zhou, April 14-17, 2015.
Travel behaviour over time and space of 6 selected routes
(left) The rankings of trajectories traveling through the given route; (right) The 8 travel behaviour clusters