The interview was recorded only in Czech. Professor Jiří Matas talks about the development of AI in the Peak.cz podcast. “Any artificial intelligence that generates something has to know that it generated it, and it has to be able to answer to me: yes, I generated it,” she says of the AI phenomenon. Artificial intelligence …read more
MRS system for documentation of the interiors of historical monuments by autonomous aerial vehicles has been deployed in the St. Moritz church in Olomouc. The drones can visit places which are not visible to the pilot as they fly autonomously, judging the environment using their onboard sensors and computer technology. They are able to take …read more
Dmytro Mishkin is a Ph.D. student in Computer Vision at the Center for Machine Perception of Department of Cybernetics. Dmytro ´s interests lie in areas like deep learning, metric learning, image matching, local features and so on. Dmytro’s research has been widely successful in many areas of machine learning and computer vision in general. The …read more
D.Rozumnyi and prof. J.Matas were awarded the Honorable Mention for Outstanding Contribution at “German Conference on Pattern Recognition (GCPR)” for the publication R. Rozumnyi, J. Kotera, F. Sroubek J. Matas: Non-Causal Tracking by Deblatting. Gratulujeme!
The work of Tomas Jenicek and Ondra Chum Linking Art trhought Human Poses is discussed in MIT Technology Review article Machine vision can spot unknown links between classic artworks. Congratulations!
Our colleague, Ing. James Brandon Pritts, from the Visual Recognition Group spoke on the topic: Self-driving cars safety. For more information [in Czech], see the article in Hospodarske noviny. Thanks for the representation of our faculty.
In Novinky.cz has been published an interresting article (in Czech language) „Drony z ČVUT pomáhají odkrývat dlouholetá tajemství” (More videos and articles about this topic you can find at the end of this website.) 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
December 16, 2014: Daniel Průša and Tomáš Werner published an article entitled Universality of the Local Marginal Polytope in IEEE Trans. on Pattern Analysis and Machine Intelligence. Congratulations!