Nowadays, big cities are suffering from severe traffic congestion as a result of the continuing increase in vehicles. Taxis equipped with GPS can be viewed as sensors of the traffic situation in city. However, trajectory data generated by taxi's GPS traces are often high-dimensional and contain large spatial and temporal attributes, which pose challenges for analysts. In this paper, based on taxi trajectory data, we present an interactive visual analytics system, T-Watcher, for monitoring and analyzing complex traffic situations in big cities. Users are able to use a carefully designed interface to monitor and inspect data interactively from three levels (region, road and vehicle views). We develop a visualization method to monitor and analyze traffic patterns for abnormal behaviors detection. In the region view of our system, global temporal changes in spatial evolution will be presented to users and can be interactively explored. The road view shows temporal changes to the traffic situations of significant segments of roads. The vehicle view uses a novel visualization method to track individual vehicles. Furthermore, the three views integrate important statistical and historical information related to traffic, which illustrate temporal changes of the traffic. We find that this design can help users explore historical information while monitoring traffic. We test our system on a real-life vehicle dataset collected from thousands of taxis and obtained some interesting findings. The experimental results confirm the effectiveness and efficiency of the proposed visual detection method. The analysis of the results also shows that our system is capable of effectively monitoring traffic and detecting abnormal traffic patterns.
|Original language||English (US)|
|Number of pages||10|
|Journal||Proceedings - IEEE International Conference on Mobile Data Management|
|State||Published - 2013|
|Event||14th International Conference on Mobile Data Management, MDM 2013 - Milan, Italy|
Duration: Jun 3 2013 → Jun 6 2013
All Science Journal Classification (ASJC) codes