Computer Vision Basic Information I070 (2+2+0) - 6 ECTS credits To describe general formation of photography by addressing physical quantities of light, shade and colour and to enumerate different modalities of sensors that convert these quantities into computer representation. To define linear filters, cross-correlation and convolution and apply them in context of image pre-processing and finding of salient regions. Thereafter, to describe more precisely various techniques for detection of features and descriptors. To enumerate different state-of-the-art computer vision problems: classification, semantic segmentation, object detection and their corresponding methods. To define computational geometry in order to reconstruct a scene from photography. To implement all the mentioned topics by using OpenCV and PyTorch. You can access the course content at the following link: PDF Teachers Basic literature D. A. Forsyth, J. Ponce, Computer Vision: A Modern Approach, 2nd edition, Pearson Education, 2012. R. Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010. Additional literature R. Hartley, A. Zisserman, Multiple View Geometry in Computer Vision, 2nd edition, Cambridge University Press, 2003. S. J. D. Prince, Computer Vision: Models, Learning and Inference, Cambridge University Press, 2012. Teaching materials The materials are available on the internal Teams channel of the course, through which all internal communication takes place. Students are required to register on the course’s Teams channel. The channel code for joining the course can be found in the schedule.