These are some of the project lines I am involved in one or other way.

Pedestrian Protection Systems (PPSs)
A PPS detects the presence of both static and moving pedestrians in front of the vehicle in order to warn the driver (acoustially, visually, etc.) and perform active actions on the host vehicle (automatic braking, evasive actions, etc.).

Key ppl: D. Gerónimo, A.D. Sappa, D. Ponsa, A.M. López.
Results: Videos of Seq. 6, Seq. 6 and Seq. 9 from CVC-02-Sys dataset.
Key references: PAMi2009, CVIU2010.


Pedestrian Classification
We basically make use of simple features such as Haar-like features or histograms of oriented gradients, but also research on new features, learning paradigms and new ways to develop better training datasets.

Key ppl: D. Gerónimo, D.Ponsa, D. Vázquez, J. Marín, A.M. López.
Key references: IbPria2007, CVPR2010.


Camera-road pose estimation
The knowledge of the road position is crucial for any vision-based ADAS.
Key ppl: A.D. Sappa, D. Gerónimo, D. Ponsa, A.M. López, F. Dornaika.
Videos: Plane estimation sequence.
Key references: ITS2008, EL2006.