Schedule: 09.09.2019 - 13.12.2019
Teaching Period (valid 01.08.2018-31.07.2020):
I - II (Autumn)
Learning Outcomes (valid 01.08.2018-31.07.2020):
After the course, the student is familiar with basic concepts and methods of computer vision. The student understands the basic principles of image-based 3D reconstruction and is familiar with techniques used for automatic object recognition from images. The student can design and implement common computer vision methods and apply them to practical problems with real-world image data.
Content (valid 01.08.2018-31.07.2020):
Image formation and processing, feature detection and matching, motion estimation, structure-from-motion, object recognition, image-based 3D reconstruction. The course gives an overview of algorithms, models and methods, which are used in automatic analysis of visual data.
Assessment Methods and Criteria (valid 01.08.2018-31.07.2020):
Combination of exercises, project and exam (details are provided on the first lecture).
Workload (valid 01.08.2018-31.07.2020):
24 + 24 (2 + 2) and project work
Study Material (valid 01.08.2018-31.07.2020):
Lecture material is partially based on the following books:
R. Szeliski. Computer Vision: Algorithms and Applications (http://szeliski.org/Book/)
Hartley & Zisserman: Multiple View Geometry in Computer Vision (http://www.robots.ox.ac.uk/~vgg/hzbook/)
Substitutes for Courses (valid 01.08.2018-31.07.2020):
T-61.5070 Computer Vision
Prerequisites (valid 01.08.2018-31.07.2020):
Programming skills and basic knowledge of data structures and mathematics (linear algebra, probability) are necessary. Matlab is used in the programming exercises and therefore previous experience with Matlab is beneficial.
Grading Scale (valid 01.08.2018-31.07.2020):