Tomas Werner has successfully defended his habilitation thesis (reviewed by V. Kolmogorov, M. Loebl, and M.I. Schlesinger). Congratulation!
Our colleague, dr. Tomáš Pajdla (Geometry of Vision and Robotics Group), was invited to the Studio Leonardo of the Czech Radio. He discussed (in Czech language) the topic „About the robots and computer vision“. Many thanks for the representation of our department!
In the Czech Science Foundation grant competition for 2015, three members of our department succeeded and obtained grants for 2016 – 2018: Ing. Tomas Werner, Ph.D. – coordinator, Ing. Petr Kremen, Ph.D. – grant with Faculty of Mathematics and Physics, Charles University in Prague, Ing. Daniel Novak, Ph.D. – grant with the 1st Faculty of …read more
Jiří Matas obtained a prestigious project in Finland Distinguished Professor programme. For details, see the announcement of new FiDiPro professors. Congratulations!
Paper Efficient Scene Text Localization and Recognition with Local Character Refinement by Jiří Matas and Lukáš Neumann received Best Paper prize at ICDAR 2015. Congratulations!
Tomáš Svoboda discussed on DVTV with Martin Veselovský the future of transportation systems and autonomous vehicles (in Czech). Many thanks for successful representation of our department!
Former member of our departmant, Zuzana Kúkelová, recieved The Cor Baayen Award of ERCIM which is given each year to a promising young researcher in computer science and applied mathematics. Zuzana received this award mostly for her work done at our department under the supervision of Dr. Tomáš Pajdla. Zuzana currently works as a postdoctoral …read more
Andrej Mikulík successfully defended his Ph.D. thesis entitled Large-Scale Content-Based Sub-Image Search (supervisor: Prof. Jiří Matas). Congratulations!
Our colleague, Assoc. Prof. Tomáš Svoboda (Center for Machine Perception, Center for Robotics and Autonomous Systems, was invited to the Magazine Leonardo (in Czech) of the Czech Radio Plus channel. He discussed (in Czech) about a rescue robot called TRADR. Many thanks for the representation of our department!
The successively evaluated features used in a sliding window detection process to decide about object presence/absence also contain knowledge about object deformation. We exploit these detection features to estimate the object deformation. Estimated deformation is then immediately applied to not yet evaluated features to align them with the observed image data. In our approach, the …read more