Modeling and Predicting Future Trajectories of Moving Objects in a Constrained Network

Modeling and Predicting Future Trajectories of Moving Objects in a Constrained Network

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Modeling and Predicting Future Trajectories of Moving Objects in a Constrained Network Jidong Chen Xiaofeng Meng Yanyan Guo Stephane Grumbach Hui Sun Information School, Renmin University of China, Beijing, China { chenjd, xfmeng, guoyy, hsun } @ruc.edu.cn CNRS, LIAMA, Beijing, China grumbach@liama.ia.ac.cn Abstract Advances in wireless sensor networks and positioning technologies enable traffic management (e.g. routing traf- fic) that uses real-time data monitored by GPS-enabled cars. Location management has become an enabling tech- nology in such application. The location modeling and tra- jectory prediction of moving objects are the fundamental components of location management in mobile location- aware applications. In this paper, we model the road network and moving objects in a graph of cellular au- tomata (GCA), which makes full use of the constraints of the network and the stochastic behavior of the traf- fic. A simulation-based method based on graphs of cel- lular automata is proposed to predict future trajectories. Our technique strongly differs from the linear prediction method, which has low prediction accuracy and requires frequent updates when applied to real traffic with veloc- ity changes. The experiments, carried on two different datasets, show that the simulation-based prediction method provides higher accuracy than the linear prediction method. 1 Introduction The continued advances in wireless sensor networks and position technologies enable traffic management and location-based services that track continuously changing positions of moving objects. For example, moving cars on a road network can be monitored and their locations are sam- pled by sensors or GPS periodically, then sent to the server and stored in a database. According to the real-time loca- tions and predicted future trajectories of cars, we can fore- cast traffic jams and route the traffic intelligently. Timely location information is becoming one of the key features in these applications. In this paper, we focus on the the location modeling and future trajectory prediction of mov- ing objects, which are the foundations for efficient location management in mobile location-aware applications. Many models and algorithms have been proposed to han- dle the continuously changing positions of moving objects. Wolfson et al. in [16, 21] firstly proposed a Moving Objects Spatio-Temporal (MOST) model, which represents the lo- cation as a dynamic attribute. Later, the model based on linear constrain [17], abstract data types [9] and Space- Time Grid Storage [4] for moving objects have been pro- posed. However, in most real life applications, objects move within constrained networks, especially the transportation networks (e.g., vehicles move on road networks). These works ignore the interaction between moving objects and the underlying transportation networks....
View Full Document

Page1 / 8

Modeling and Predicting Future Trajectories of Moving Objects in a Constrained Network

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online