Advanced Topics in
Computer Vision and Robotics
Time/Location: Tuesday 4:30-7:10pm,
Innovation Hall 208
Instructor: Jana Kosecka
Office hours: 2-3pm Wednesday
Contact: Office 4444 Engineering Build., e-mail:
Course web page: http://www.cs.gmu.edu/~kosecka/cs884/
This course will cover computer vision techniques for object and category recognition,
recognition of human activities from video streams and ego-centric
vision. Recognition of objects instances (my cup, cereal box) or generic
categories (any cup, bottle) is an essential capability for a variety of robotics and
multimedia applications. This course will provide a comprehensive
survey of the existing methods and discuss the performance of reviewed
methods on several benchmark datasets. We will also consider the techniques needed for real-time
interactive applications on robots or mobile devices, e.g. domesticservice robots or mobile
phones that can retrieve information about objects in the environment based on visual observation.
The class will consist of lectures by the instructor and weekly reading
of the assigned papers.The students will be responsible for presentation of the
selected paper and implementation of some methods as part of
homeworks. The papers will be selected from the recent proceedings
of Computer Vision and Robotics Conferences and journals.
The grade will be based on paper presentations, homeworks and final presentation of the project.
Prerequisites: Students should have one (ideally two) of the following as
CS 682 Computer Vision, CS 685
Autonomous Robotics, CS 687 Advanced Artificial Intelligence, 688 Patter
Recognition or Advanced Data Mining Class or ask for a
permission of an instructor.
Students taking the class should be comfortable some image
processing in Matlab (introduction to feature computation
will be provided) and basic machine learning techniques;
such as Support Vector Machines, Decision Trees, Boosting, Hidden
Markov Models, LDA, Logistic Regression, Gaussian Mixture Models etc.
Homeworks, Presentations 60% and Project 40%
The homeworks should be handed in on time. Late submissions are
accepted but will incur late submission penalty.
The integrity of the University community is affected by the
individual choices made by each of us. GMU has an Honor Code
with clear guidelines regarding academic integrity. Three
fundamental and rather simple principles to follow at all times
are that: (1) all work submitted be your own; (2) when using the
work or ideas of others, including fellow students, give full
credit through accurate citations; and (3) if you are uncertain
about the ground rules on a particular assignment, ask for
clarification. No grade is important enough to justify academic
misconduct. Plagiarism means using the exact words, opinions, or
factual information from another person without giving the
person credit. Writers give credit through accepted
documentation styles, such as parenthetical citation, footnotes,
or endnotes. Paraphrased material must also be cited, using MLA
or APA format. A simple listing of books or articles is not
sufficient. Plagiarism is the equivalent of intellectual robbery
and cannot be tolerated in the academic setting. If you have any
doubts about what constitutes plagiarism, please see me.
CS department Honor Code can be found here.