This course provides a comprehensive introduction to
computer vision, starting from digital Image analysis
(filtering, image pyramids, frequency based processing,
Hough transform and invariant feature extraction),
advancing to geometry based computer vision (2D
transforms, homographies, camera models and stereo),
and ending with the presentation of state-of-the-art deep
learning based computer vision techniques
(convolutional networks, vision transformers, object
detection and semantic segmentation).
|