The course provides an understanding of the processes involved in the formation of images of visual scenes, of how computational approaches for transforming, estimating or recognizing such images are formulated and implemented, and of where these methods can and have been applied. The course will also teach implementation and practical use of a wide variety of vision algorithms.
This course is intended for computer science graduate students, as well as students in allied areas (such as psychology or biomedical engineering) who have interests in computational vision and its applications.
Models of images and image formation (camera models, camera calibration, statistics of images, the geometry of image formation and visual scenes), low-level image processing and feature extraction, features and visual cues of images and scenes (color, texture, shading, stereo, motion), shape and motion estimation, object recognition.
Regular readings and homework assignments, as well as a final project. Midterm and final examinations.