SemanticTraj: A New Approach to Interacting with Massive Taxi Trajectories

Massive taxi trajectory data is exploited for knowledge discovery in transportation and urban planning. Existing tools typically require users to select and brush geospatial regions on a map when retrieving and exploring taxi trajectories and passenger trips. To answer seemingly simple questions such as “What were the taxi trips starting from Main Street and ending at Wall Street in the morning?” or “Where are the taxis arriving at the Art Museum at noon typically coming from?”, tedious and time consuming interactions are usually needed since the numeric GPS points of trajectories are not directly linked to the keywords such as “Main Street”, “Wall Street”, and “Art Museum”. In this paper, we present SemanticTraj, a new method for managing and visualizing taxi trajectory data in an intuitive, semantic rich, and efficient means. With SemanticTraj, domain and public users can find answers to the aforementioned questions easily through direct queries based on the terms. They can also interactively explore the retrieved data in visualizations enhanced by semantic information of the trajectories and trips. In particular, taxi trajectories are converted into taxi documents through a textualization transformation process. This process maps GPS points into a series of street/POI names and pick-up/drop-off locations. It also converts vehicle speeds into user-defined descriptive terms. Then, a corpus of taxi documents is formed and indexed to enable flexible semantic queries over a text search engine. Semantic labels and meta-summaries of the results are integrated with a set of visualizations in a SemanticTraj prototype, which helps users study taxi trajectories quickly and easily. A set of usage scenarios are presented to show the usability of the system. We also collected feedback from domain experts and conducted a preliminary user study to evaluate the visual system.

1 Introduction

Advanced sensing technologies and computing infrastructures have produced a variety of trajectory data of humans and vehicles in urban spaces. Taxi trajectory data records realtime moving paths sampled as a series of positions associated with vehicle attributes over urban road networks. Massive trajectory data contains abundant knowledge about a city and its citizens which has been widely used in urban computing [40]. Exploratory visualization systems are demanded to study taxi trajectories with efficient user interaction and instant visual feedback. However, users often need to select, brush, and filter regions on maps to interact with GPS points and trajectory paths. Complex operations are needed to complete some straightforward tasks. We give two scenarios as examples: •

Scenario 1: A shopping mall has a plan to open shuttle buses for their customers. Its manager wants to investigate where and when visitors take taxis to the mall.

Task 1: “For the taxi trips arriving at the shopping mall, what are their major pick-up locations? “

•

Scenario 2: Two witnesses reported a criminal suspect taking a taxi passing South Street and North Street between 3pm and 3:20pm. A policeman wants to find suspicious taxi paths. Task 2: “What are the taxi trips passing South Street and North Street between 3pm and 3:20pm? What are the other streets/POIs they visited?”