Computer Vision

The course begins with an introduction to the goals of computer vision, explores related fields, trends in development and use. It then moves on to image creation, where the basic properties of digital images, the central projection camera model, calibration, distortion correction, photometry and lighting, and the differences between human vision and color perception are discussed. 

In the image analysis section we cover the topics of filtering, histogram operations, edge and vertex detection, the use of the Hough transform, connected component analysis, morphological filtering, active curve models (snakes), shape description, image pyramids, geometric transformations, similarity measures, image registration and RANSAC methods. 

Stereo vision covers the basics of stereo perception, comparison, stereo system modeling and calibration, epipolar geometry and structured illumination. Motion analysis focuses on motion detection, time-to-touch and optical flow, offering students a comprehensive insight into various aspects of computer vision, from image capture and processing to motion interpretation and stereo perception.

The aims of this course are to understand basic concepts, underlying theory, algorithms, and applications of computer vision, especially in intelligent systems for automation and robotics.

The lectures provide a theoretical background on particular subjects together with practical examples in Matlab or C.

Practical work is being performed as the part of laboratory exercises, and is accomplished in the form of multiple assignments, acquainting students with computer vision algorithms. Students work in groups, consisting of two or three students, and the results are in the form of Matlab code. After completing each part, students present their results to the assistant.