Visual Analysis of Metropolitan-Scale Sparse Trajectories





Image: UrbanMotion user interface: (a) movement visualization showing five major regions in Beijing during commute time; (b) time/date selection panel, the morning (7AM-10AM) of July 12th is selected; (c) algorithm configuration menu for flow generation; (d) visualization control panel.




1. Propose effective methods to extract and aggregate population movements from dense parts of the trajectories leveraging their long-tailed sparsity

2. Extend the original wind map design by supporting map-matched local movements, multi-directional population flows, and population distributions

3. Prototype and evaluate the above techniques



·        Lei Shi, Congcong Huang and Meijun Liu,,UrbanMotion: Visual Analysis of Metropolitan-Scale Sparse Trajectories, IEEE Transactions on Visualization and Computer Graphics, accepted (selected for presentation at IEEE VIS'20). [paper] [code]