The goal of computer vision is to compute properties of the three-dimensional world from images and video. Problems in this field include indentifying the 3D shape of a scene, determining how things are moving, and recognizing familiar people and objects. This course provides an introduction to computer vision, including such topics as feature detection, image segmentation, motion estimation, object recognition, and 3D shape reconstruction through stereo, photometric stereo, and structure from motion.
This course would form a three course sequence in Artificial Intelligence along with CSE 150 and CSE 151. These two other classes are being redesigned right now, but they will cover core AI topics such as logical inference, heuristic search, planning, probabilistic inference, and learning. CSE152 will focus on machine perception, particularly computer vision. All three courses can be taken independently of each other, in any order. There is no overlap in material coverage. CSE 152 will also serve as part of a potential undergraduate graphics and vision sequence. It will complement the image processing course (CSE166), with very minimal overlap (perhaps 10%). While CSE 166 covers 2-D processing of images (including image enhancement, restoration, and segmentation, stochastic image models, Filter design, sampling, compression Fourier and wavelet transforms), CSE 152 will cover inference of 3-D properties from 2-D images (including motion understanding, stereo, structure from motion, photometric stereo) and object recognition.
Programming assignments in MATlab.
Math 20F, CSE 100 or Math 176, CSE 101 or Math 188. Knowledge of C, C++ or Matlab programming. Please see Prerequisites Page.
One quarter per year, Spring.