Instructors
Lectures:
Martin Jagersand
Labs:
Allie Luo luo3@ualberta.ca, and
Justin Valentine jvalenti@ualberta.ca
Communication
Course material, due dates etc:
http://ugweb.cs.ualberta.ca/~vis/courses/CompVis/
Course instructors available for meetings Tue after class.
eClass is for questions and on-line discussion in the Q and A forum
eClass link
Calendar Description
Introduction to the geometry and photometry of the 3D to 2D image formation process for the purpose of computing scene properties from camera images. Computing and analyzing motion in image sequences. Recognition of spatial relationships and 3D geometry from images and tracking these in video sequences.
Course Outline
- Image representation
- Optic flow and visual motion.
- Video tracking.
- 2D geometry and homogeneous transforms.
- Physical cameras, construction, lenses, properties.
- Pinhole perspective and affine mathematical camera models.
- 3D and multiple view geometry.
- Stereo reconstruction and 3D modeling.
- Photometric properties, image constancy and disparity computation.
- Computer vision systems and applications in surveillance, automatic inspection, robotics and image-based rendering.
Schedule
Lectures: Tuesday, Thursday 2:00-3:20, ETLC E1-008, potentially we will move to CSC1-05 if the class fits
Lab CSC 1-05 Sessions Tue, Wed 5-8pm
Grading
Written exams:
40% Two midterms 20%+20% See calendar page
40% Assignments throughout the term (Graduate students 30%), see on-line schedule
20% Project, computer vision topic and implementation related to class
Graduate students will do research readings and a presentation 5%.
Graduate students expected to do a research-oriented project 25%.
A grade of "satisfactory" requires a working knowledge of how to solve real world computer vision problems. For higher grades additionally an understanding of the derivation of methods, their properties and context will be required.
Literature
A message from the university administration:
The University of Alberta is committed to the highest standards of academic integrity and honesty. Students are expected to be familiar with these standards regarding academic honesty and to uphold the policies of the University in this respect. Students are particularly urged to familiarize themselves with the provisions of the Code of Student Behavior (online at www.ualberta.ca/secretariat/appeals.htm) and avoid any behavior which could potentially result in suspicions of cheating, plagiarism, misrepresentation of facts and/or participation in an offence. Academic dishonesty is a serious offence and can result in suspension or expulsion from the University. Policy can be found in ยง23.4(2) of the University Calendar.