Téma:Multimodal recognition of objects and victims
Vedoucí:Doc. Ing. Tomáš Svoboda Ph.D.
Vypsáno jako:Diplomová práce,Bakalářská práce,Individuální projekt,Dobrovolná odborná práce,Semestrální projekt
Center for Machine Perception, Department of Cybernetics, contributes to the EU project NIFTi by developing visual algorithms for object/victim detection and robot localization. Among many other sensors, The robot carries an omnidirectional camera, a thermo camera, rotating 3D lidar, and optionally also RGB-Depth sensor on board.

During a search and rescue mission the robot is expected to locate victims and objects and computer their positions in 3D. CMP developed several methods. The goal of this work is mainly robustifying algorithms by combinigng multiple data (thermal, visual, depth, ...)
Pokyny:Contact: Tomáš Svoboda
Recommended courses: Computer Vision Methods, Pattern Recognition and Machine Learning, ...
Literatura:K. Zimmermann, D. Hurych, T. Svoboda. Exploiting Features -- Locally Interleaved Sequential Alignment for Object Detection. In 11th Asian Conference on Computer Vision - ACCV 2012
T. Petricek, T. Svoboda. Area-weighted Surface Normals for 3D Object Recognition. In 21st International Conference on Pattern Recognition - ICPR 2012
E. Derner. Car Detection on a Mobile Robot by Fusing Visual and 3D Lidar Data. BSc Thesis CTU--CMP--2012--10
Realizace:codes C/C++; Python
Vypsáno dne:04.04.2013