Postgraduate Course: Advanced Vision (Level 11) (INFR11031)
||School of Informatics
||College of Science and Engineering
||Not available to visiting students
|Credit level (Normal year taken)
||SCQF Level 11 (Postgraduate)
|Home subject area
||Other subject area
||Taught in Gaelic?
||This module aims to build on the introductory computer vision material taught in Introduction to Vision and Robotics. The main aim is to give students an understanding of main concepts in visual processing by constructing several vision systems during the course of the lecture series and practicals.
|| It is RECOMMENDED that students have passed
Introduction to Vision and Robotics (INFR09019)
|| Students MUST NOT also be taking
Advanced Vision (Level 10) (INFR10001)
|| For Informatics PG and final year MInf students only, or by special permission of the School. This course assumes an ability to program in MATLAB and the following mathematical knowledge: Eigenvectors, Basic matrix algebra: multiply, inverse, Basic 3D geometry: rotations, translations, Covariance matrices, Principal Component Analysis, Basics of surfaces in 3D, Least Square Error estimation.
Course Delivery Information
|Delivery period: 2011/12 Semester 2, Not available to visiting students (SS1)
||WebCT enabled: No
|No Classes have been defined for this Course|
||First class information not currently available|
||M-F 0900-1700 as arranged.
|Main Exam Diet S2 (April/May)||2:00|
Summary of Intended Learning Outcomes
|1 - understand machine vision principles (assessed by exam).
2 - be able to acquire and process raw image data (assessed practical).
3 - be able to relate image data to 3D scene structures (assessed practical).
4 - know the concepts behind and how to use several model-based object representations, and to critically compare them (assessed by exam).
5 - know many of the most popularly used current computer vision techniques (assessed by exam).
6 - undertake computer vision work in MATLAB (assessed practical).
7 - be able to review and critique current research work (literature review).
|Written Examination 70
Assessed Assignments 30
Oral Presentations 0
There are 2 lab-based practicals at 10% each, plus a 3rd assignment for 10% more. The lab exercise is done in teams of 2. These exercises usually involve: 1) basic image processing and 2) 3D scene or video analysis. Any programming language can be used, but Matlab is the language used in the lecture materials. The 3rd assignment will be to create a web page summarising a topic in CVonline for which no material exists at present. There will be a small set of alternative topics suitable for level 11 students available for the web page construction.
||In the course of constructing six vision systems, students will learn about: image noise reduction, region growing, boundary segmentation, Canny edge detector, Hough transform, RANSAC, 2D and 3D coordinate systems, interpretation tree matching, rigid 2D object modeling, 2D position estimation, point distribution models, 3D range sensors, range data segmentation, 3D position estimation, stereo sensors, motion tracking and various approaches to object recognition.
The activities of the module are designed to further develop intellectual skills in the areas of: laboratory, writing (lab reports and short essays), teamwork, critical analysis, programming and laboratory skills.
Relevant QAA Computing Curriculum Sections: Computer Vision and Image Processing
||* R. Jain, R. Kasturi, B. G. Schunck, Machine Vision, McGraw Hill International Editions, 1995
* T. Morris - "Computer Vision and Image Processing" (Palgrave, 1st Edition, 2004)
* E. Trucco and A. Verri, "Introductory Techniques for 3-D Computer Vision", Prentice Hall, 1998
* E.R. Davis - "Machine Vision - Theory, Algorithms and Practice" (Elsevier, 3rd Edition, 2005)
Timetabled Laboratories 0
Non-timetabled assessed assignments 36
Private Study/Other 44
||Dr Michael Rovatsos
Tel: (0131 6)51 3263
||Miss Kate Weston
Tel: (0131 6)50 2701
copyright 2011 The University of Edinburgh -
3 April 2011 11:21 am