Introduction to Vision and Robotics
In 2012/2013 The course will be taught in Semester 2
Course Descriptor
10 Minute Introduction
Course Organisers:
| Vittorio Ferrari |
Michael Herrmann |
| Email: vferrari AT staffmail DOT ed DOT ac DOT uk |
Email: mherrman@inf.ed.ac.uk |
| Office: 1.27 Informatics Forum |
Office: 1.42 Informatics Forum |
| Phone: 650 2697 |
Phone: 651 7177 |
Lectures:
Lecturer: Vittorio Ferrari & Michael Herrmann
Lecture times:
Mondays 11:10am and Thursdays 11:10am in AT LT1.
NOTE: the first lecture will be on 14th January, 2013.
Lecture slides and handouts
will be available here before the start of each lecture.
The content will be arranged somewhat differently than
in previous years.
This year the lectures will not be recorded on video. You can still find
audio and videos of previous IVR lectures:
2007/8,
2008/9,
2010/11
and
2011/12.
Tutorial/Practicals:
Demonstrators: Simon Smith (artificialsimon AT ed DOT ac DOT uk) and Davide Modolo (D.Modolo AT sms DOT ed DOT ac DOT uk)
Supervised Lab Times:
From week 2, Monday and Thursday 15:10 to 16:00 at IPAB Robot teaching lab, AT 3.01.
Instructions:
Week 2 - Matlab, webot, khepera introduction
Week 3 - More matlab, webot, khepera skills
Week 4 - Image processing skills
Week 5 - Visual classification skills
Week 6 - Real Khepera control
Assessment:
Coursework (25%)
There will be two pieces of assessed coursework carrying equal weight (12.5% each)
- A vision assignment during weeks 4-7, due 4pm Thursday 7th March.
There will be assessed demonstrations of the assignment in the Robotics Lab from 10:00-16:00 on
Friday 8st March. Details are available here. You will
need these two data sets:
dataset 1 and
dataset 2.
- A robotics assignment during weeks 8-10, with the assignment due 4pm Thursday 28th March. There will be
assessed demonstrations of the assignment in the Robotics Lab from 10:00-16:00 on Thursday 28th of March.
Details are available here
Details will be available after start of term.
The practicals are done in teams of two.
For each assignment a demonstration of the results will be required and a
single, joint report is to be submitted by one of the students in each team.
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.
Exam (75%)
Here is a
sample paper
with
sample answers
The lecture and practical contents define the examinable material.
Reading list:
- Russell & Norvig Chapters 24 & 25 in Artificial Intelligence: A Modern Approach, Prentice Hall, 1995, ISBN 0130803022. Highly recommended
- Solomon & Breckon, "Fundamentals of Digital Image Processing - A Practical Approach with Examples in Matlab", Wiley-Blackwell, 2010, ISBN: 978-0470844731. Highly recommended
- Robin R. Murphy, Introduction to AI Robotics, MIT Press, 2000, ISBN 0262133830. Recommended, supplementary for robotics
- W. Burger, M. Burge; Principles of Digital Image Processing, Springer, 2009, ISBN: 978-1-84800-190-9. Covers some of IVR, AV materials, but maybe less than 50%.
Also online free inside the Univ here.
- R.C. Gonzalez, R.E. Woods, S.L. Eddins; Digital Image Processing Using MATLAB, 2nd edition, Prentice Hall, 2009, ISBN 9780982085400. Excellent but expensive book, covers a lot of IVR, some of AV.
Also a book support site here.
- Introduction to Machine Learning by Ethem Alpaydin, The MIT Press, October 2004, ISBN 0-262-01211-1. Recommended. Chapters 1-5 are a deeper exploration of the Bayesian classification topic
- Phillip J. McKerrow, Introduction to Robotics, Addison Wesley, 1998, ISBN 0 201 18240 8 (now out of print, but some copies can be found on amazon). Supplementary
- Ulrich Nehmzow, Mobile Robotics: A Practical Introduction, Springer; 2nd ed. edition (8 July 2003). Recommended.
See individual lecture handouts for further reference material.
Resources
- MATLAB code for flat part recognition
- Online computer vision resources at University of Edinburgh (and beyond)
- Some YouTube videos of robots in action!
Communications:
This page is maintained by the course lecturer, Michael Herrmann,
mherrman@inf.ed.ac.uk, room IF 1.42, ext 517177.
