Vision is the most important sensing mechanism for humans. Computer vision is related to the extraction of high level information through the analysis of an image or a sequence of images. The goal of this course is to introduce the inherent problems of computer vision and some possible solutions to these problems. Students will have opportunities to apply vision techniques through programming. Since this is an introductory course, more emphasis will be given on practical solutions rather than theoretical ones.

Students need to have some knowledge about mathematics such as linear algebra, probability theory and optimization, Programming skills are also required. (There is no restriction on specific programming languages or computing environment.)

Assignments (40%)
Final exam (60%)
-- The percentages are subject to change.

Computer Vision: A Modern Approach by D. Forsyth and J. Ponce
Computer Vision: Algorithms and Applications by R. Szeliski
Foundations of Computer Vision by A. Torralba, P. Isola, and W. Freeman

Preliminaries (linear algebra, probability)
Image processing
Hand-crafted visual features
Neural networks for vision
Image classification
Object detection
Semantic segmentation
Motion estimation
Video classification
Object tracking
Camera models
Homography and epipolar geometry
Vision and language
Generative models