Advanced Vision Module
10 Minute Introduction
The goal of this course is provide you with the skills to understand and
sketch out solutions to a variety of computer vision applications. You should
end up with the skills to tackle novel situations and incompletely defined
applications. We will approach this by looking at 6 simplified computer vision
systems that cover a large portion of the range of both applied and research
computer vision.
Lectures:
Lecture times and rooms: Monday 2:10 pm
(AT LT5) and Thursday 2:10 pm (AT LT1).
Lecture plan and presented slides/problems/links
Lecture audio & video recordings from previous years.
Lecture audio & video recordings from 2008/9.
Lecture audio & video recordings from 2009/10.
2010/11 lectures were not recorded, but were very similar to the previous years.
Lecture audio & video recordings from 2011/12.
Lecture audio & video recordings from 2012/13.
Lecturer
Bob Fisher, Informatics Forum 1.26, rbf @ inf.ed.ac.uk, (0131) 651-3441
Demonstrators and Markers
Demonstrators:
Bas Boom - bboom@inf.ed.ac.uk
Steven McDonagh - s0458953@sms.ed.ac.uk
Lab demonstration sessions: Starting week 2, Monday 4-5, 5-6, Thursday 4-5 (just come to 1 hour) in AT 3.01
Before emailing with a question - please check the module FAQ
News
Latest information, class announcements, handouts, etc
Syllabus
This module looks at several approaches to building vision systems.
The order of the topics might change depending on the practicals.
- System 1: Orthographically viewed non-rigid 2D objects
- System 2: Video Tracking (2D)
- System 3: Video based human behaviour understanding
- System 4: Recognising classes of shape
- System 5: 3D objects from stereo vision (recognition)
- System 6: 3D objects from range data (recognition)
In the process of doing this, we will encounter a variety of
topics in low, middle and high level computer vision.
There is also some review material from IVR on recognising
orthographically viewed rigid flat objects.
Activities
- about 15 hours of lectures on the above syllabus are given, depending on the speed of delivery.
- 1 assessed written practical exercise: 10 hours.
- 2 assessed laboratory practical exercises: 30 hours each.
These laboratory exercises are done in teams of 2 to encourage
development of team skills: teamwork exercises skills desired
by employers and improves the learning process by encouraging discussion
of topics.
- Outside reading and exam revision: 15 hours.
- Total: 100 hours
Assessment
A 2 hour examination in the late spring accounts for 70% of the module mark and
the practical work accounts for the other 30%. The practical work is split
into three assessed (of 10% each) exercises.
The three practical exercises are
-
CVonline Entry (10%).
Practical 1 Handout [PDF]
This practical is done individually.
Due: 4 pm Thursday 7 February
-
Intensity Image/Video Analysis (10%).
Practical 2 Handout [PDF]
You must do this practical in teams of 2. Let the lecturer know who your partner is.
Due: 4 pm Thursday 28 Feb
You will have to demonstrate your practical results on Friday 1 March from
9:00-13:00.
-
3D Image Analysis (10%).
Practical 3 Handout [PDF]
You must do this practical in teams of 2 with a different partner from practical 2.
Let the lecturer know who your partner is.
Due: 4 pm Thursday 21 March
You will have to demonstrate your practical results on Friday 22 March from
9:00-13:00.
The plan is to mark and return all practicals within 2 weeks of submission.
Practicals 2 and 3 are done in groups of two.
A single, joint, report is to be submitted.
Maximising your coursework practical score.
All practicals are covered by the
school policy on plagiarism
and students are advised to be fully aware of this when submitting practical work.
Context
This module assumes the students have a secondary school understanding of geometry,
matrix algebra, trigonometry, physics and programming concepts. Knowledge
of elementary optics, signals and photography would be helpful. Students
must be able to program and be able to work in small teams.
Normally, a student will have attended
Introduction to Vision and Robotics (IVR)
before attending this module, but exceptions can be made if you have
the necessary background.
All of the assignments will be in Matlab. This was introduced in IVR,
and some extensions will be introduced here. Please ensure familiarity with
the concepts, techniques and practical aspects of the vision component of the IVR course.
There is a weekly
Institute
of Perception, Action and Behaviour seminar Thursday 11:00 (usually in
IF 4.31) which covers related topics in vision and robotics.
You should check the venue and dates at the IPAB seminars page
Other References, Course Notes and Other Study Materials
- *** Lecture Slides
- Note: that these are not written
module notes. You are still expected to attend lectures and do the required reading.
- *** Recommended course textbooks
-
E.R. Davies - "Machine Vision - Theory, Algorithms and Practice" (Elsevier, 3rd Edition, 2005)
- Solomon & Breckon, "Fundamentals of Digital Image Processing - A Practical Approach with
Examples in Matlab", Wiley-Blackwell, 2010, ISBN: 978-0470844731. (content for about 1/2 of course)
- R. Szeliski, "Computer Vision", Springer, 2011, ISBN: 978-1-84882-934-3. (content for about 1/2 of course)
- ** Optional supplementary textbooks
-
T. Morris - "Computer Vision and Image Processing" (Palgrave, 1st Edition, 2004)
D. A. Forsyth & J. Ponce - "Computer Vision - a modern approach" (Prentice Hall, 1st Edition, 2003)
-
** Online computer vision resources at University of Edinburgh (and beyond)
-
Various Online Resources
This page is maintained by the course lecturer, Bob Fisher,
rbf@inf.ed.ac.uk, room IF 1.26, ext 513441.
