Computer Vision teaches computers to perceive and understand the visual world of humans through one or multiple cameras. How is your smartphone able to detect faces or automatically create panoramic images? This course introduces the fundamental concepts of computer vision as well as its modern applications. Topics include image processing, object detection, scene recognition, stereo vision and motion analysis.
This course requires programming experience as well as basic knowledge of linear algebra, calculus, and probability theory.
We will use Computer Vision: Algorithms and Applications by Richard Szeliski as the main textbook. The book is available online.
Other good textbooks are Computer Vision: A Modern Approach by David Forsyth and Digital Image Processing by Rafael Gonzalez and Richard Woods.
Assignments & Grading
This course will consist of three programming assignments that involve practical realizations of computer vision algorithms presented in the lecture. At the end of this course, there will be a written final exam. You will need to successfully complete all programming assignments (more than 50% of the total points per assignment) to be allowed to take the written final exam.