Virtual Scenarios for Pedestrian Detection

Most promising object detectors rely on classifiers trained with annotated samples. However, the required annotation step represents an intensive and subjective task when it has to be done by persons. Therefore, it is worth to minimize the human intervention in such a task by using automatically generated synthetic data. Nevertheless, the use of this kind of data comes with the following question: can an object model learnt with synthetic data work successfully for object detection in real-world scenarios?More info

Domain Adaptation

When training and testing data comes from different domains the classifiers can suffer the so called dataset shift problem. Accordingly, it can be used domain adaptation techniques to face this problem. The state of the art results in this field points out a new methodology that would allow the systems to adapt to different situations, which may provide the foundations for future research in this unexplored area. More info

Color in Human Detection 

In this project we evaluate the opponent colors (OPP) space as a biologically inspired alternative for human detection. In particular, by feeding OPP space in the baseline framework of Dalal et al. for human detection (based on RGB, HOG and linear SVM), we will obtain better detection performance than by using RGB space. More info

eCo-DRIVERS: Ecologic Cooperative Driver and Road Intelligent Visual Exploration for Route Safety

The aim of this project is to research technologies for bringing ADAS to urban oriented electric vehicles. The major distinctive features of this proposal are: (1) the use of vision as “eco”-sensor; and (2) to follow a  driver-centric approach. Both things together build the concept of eco-driver.More info

Scene Understanding

More info