2014 Poster Sessions : Map Reconstruction from GPS Trajectories

Student Name : Chen Chen
Advisor : Leo Guibas
Research Areas: Graphics/HCI
Abstract:
Road network is a dynamic object which is changing constantly due to various reasons, such as accidents, closures, new constructions, etc. Consequently, constructing and maintaining accurate, up-to-date road maps are challenging tasks. Recently, large collections of GPS trajectories are becoming widely available due to the fast deployment of GPS devices in mobile platforms. A single trajectory provides a noisy partial observation of the underlying road network, and a large collection of trajectories can be leveraged to build and maintain high-quality, up-to-date road maps. We look at the problem of map reconstruction from large collection of GPS trajectories. We show that prior knowledge of the road network is useful in reconstructing the geometry of the road network, and high ordered information in trajectories can be used to correct the topology of the road network.

Bio:
Chen Chen received his B.E. degree in Electrical Engineering from Peking University, Beijing, China, in 2008, and M.S. degree in Electrical Engineering from Stanford University, Stanford, CA, in 2011. Currently, he is a Ph.D. candidate in the department of Electrical Engineering at Stanford University. His primary research interests include network reconstruction and pattern mining from large collections of trajectory data.