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
10 Minute Introduction
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.
Dimitris Papadopoulos - email@example.com
Semester 2 full class meeting times and rooms: Monday and Thursday 2:10 pm
(Venue: Room G.06 at 50 George Square).
Lab demonstration sessions: Starting week 2, Monday 4-5, 5-6 or Thurs 4-5 (just come to 1 hour) in FH ga11.
IMPORTANT INFORMATION: This course is not taught by the traditional lectures. Instead, AV uses an Inverted Classroom method. This means that you will have about 15 hours of video to watch in your own time. This material is assessible. There are still 2 full class meetings each week. Normally, at the first meeting each week we will be discussing any questions that you either suggest in advance or raise in class on the day. The second meeting will normally be a guest lecture teaching you some advanced vision technology and applications (these talks are not assessed).
Here is the link to the lecture videos, associated readings and associated Matlab in the University's LEARN system. You will need an EASE account to access this materials. Here is an Introduction to how the course is intended to be followed.
Here is a proposed schedule of video watching and guest lectures:
|Jan 11||Introduction parts 1-3>, Flat parts System 1, modules 1-2||Course Intro + Fisher: bats & fish||Q&A|
|Jan 18||Flat parts : System 1, modules 3-6||Q&A||???|
|Jan 25||Detection and tracking : System 2, modules 1-7||Q&A||???|
|Feb 1||Detection and tracking : System 2, modules 8-13, Deforming flat part recognition : System 3, modules 1-2||Q&A||???|
|Feb 8||Deforming flat part recognition : System 3, modules 3-8||Q&A||???|
|Feb 15||Innovative Learning Week|
|Feb 22||Range Image Analysis : System 4, modules 1-8||Q&A||???|
|Mar 1||Persistent tracking and behavior recognition : System 5, modules 1-6||Q&A||???|
|Mar 8||Stereo based 3D part recognition : System 5, modules 1-5||Q&A||???|
|Mar 15||Stereo based 3D part recognition : System 5, modules 6-11 + Course Summary||Q&A||Previous Exam Review|
The two practical exercises are:
Practicals 1 and 2 are done in groups of two. A single, joint, PDF report is to be submitted. For distance learning students: you still have to work in teams of two. If you're not in the same city, then communicate by skype and jointly work on the practical. Decide how to split the work. You should be able to use matlab on the university computers, to which you will have an account. However, it may be difficult to display images remotely, so it is probably better and easier for you to buy a Matlab student license.
All practicals are covered by the school policy on plagiarism and students are advised to be fully aware of this when submitting practical work.
firstname.lastname@example.org, room IF 1.26, ext 513441.
Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail: email@example.com
Please contact our webadmin with any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh