CONEX - Robust and Adaptive Approaches to Scene and Object Recognition

The goal of this joint project is to investigate new robust and adaptive approaches in the area of object and scene recognition. This is a necessary requirement for developing truly cognitive systems as well as advanced and novel multimodal interfaces leading to ambient intelligence. Having a robust object and scene recognition system the following applications will greatly benefit: novel user interfaces which understand human activities, intelligent surveillance, indexing multi-media databases and content analysis of images, autonomous mobile systems and robotics, industrial inspection and robotics, etc. The goal is to develop computer vision based systems that can recognize objects, and in the context of environment perform localization and navigation. The major challenge is to develop systems and methods that can work under realistic unconstrained conditions (i.e., outside the lab). The three partners proposing this project (Czech Technical University Prague, University of Ljubljana, and Institute for Computer Graphics and Vision, TU Graz) have considerable expertise in this area and developed complementary methods and techniques. The goal of the proposed project is to join the efforts, combine the expertise and thereby, improve the cooperation in the light of possible joint participation in the 6th FP. In particular, we propose the following activities: * Organization of Joint workshops and colloquia * Exchange of PhD. students * Joint research/joint papers