Current Projects

Soon

Past Projects

Forensic Video Mining
Researching computer vision and machine learning techniques to perform image retrieval in surveillance imagery based on visual examples or textual-queries in the context of forensic investigations.

References: ICPR 2014.

Education Project - Traffic Sign Detection
Graduate course on computer vision aimed at detecting and recognizing traffic signs in videos. The ideas, program and materials of the paper were successfully in the 4 months "Project in CV" subject of the term 2011-2012 edition of the Master in CV and AI (UAB).

References: Trans. Education 2013.

Pedestrian Tracking
Multi-person tracking can be exploited in applications such as driver assistance, surveillance, multimedia and human-robot interaction. With the help of human detectors, particle filters offer a robust method able to filter noisy detections and provide temporal coherence.

Results: PETS09 and TUD videos
Key references: ACIVS2012.

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.).

Results: Videos of Seq. 6, Seq. 6 and Seq. 9 from CVC-02-Sys dataset.
Key references: PAMi2010, 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 references: IbPria2007, CVPR2010.

Camera-road pose estimation
The knowledge of the road position is crucial for any vision-based ADAS.

Results: Plane estimation.
Key references: ITS2008, EL2006.