Description: M:\public_html\accessories\aau_logo.gif


Readings in Vision, Graphics and Interactive Systems, Fall 2010 (VGIS 9th Semester)

Zheng-Hua Tan, Associate Professor, Ph.D.

+45 9635-8686,

Office: Room A6-319, Niels Jernes Vej 12

Description: M:\public_html\accessories\movline.gif

Course description:

This course aims to give the students a comprehension of the current state-of-the-art in advanced vision, graphics and interactive systems through the presentation and plenum discussion of a number of concepts and systems representative of the field. It will support the concrete topics of the different projects, and the content will therefore change from year to year.


Lecture notes:

·         Lecture 1: Calibration, Persuasion, Optimization  (Morten Aagaard)

o    Time: Monday Oct. 22 at 12.30

o    Slides

o    Readings: 

Mobile gadgets functionality has until now been identified as human-human communication, games and accessories. Psychologists and Rhetoricians identify a new emerging functionality called cognitive support tool. Furthermore a new research field has emerged “Persuasive Technology” in which technology should be designed to influence the users’ behavior. Persuasive Cognitive support tool helps the user to manage their life and improves their social skills.

Signal processing appears to play a crucial role in the core functionality of Cognitive Support tools.
A number of student projects relevant (conceptual level) examples will be given.


·         Lecture 2: Hidden Markov Model (Zheng-Hua)

o    Time: Friday Oct. 29 at 12.30

o    Slides

o    Readings: 

Rabiner, L.R., "A tutorial on hidden Markov models and selected applications in speech recognition", Proceedings of the IEEE, 77 (2), 1989, pp. 257 - 286. (PDF. You have got user name and password to access it via email.)

Steve Young, et al., "The HTK Book" (PDF)

Huang, Acero and Hon, Spoken Language Processing - A Guide to Theory, Algorithm, and System Development, Chapter 8, Prentice Hall PTR, 2001. 

o    Assignment and solution

·         Lecture 3: GPGPU and CUDA (Henrik, Thomas, Francois)

o    Time: Monday Nov. 1 at 12.30

o    Slides

o    Readings: 

John D. Owens, David Luebke, Naga Govindaraju, Mark Harris, Jens Krüger, Aaron Lefohn and Timothy J. Purcell: A Survey of General-Purpose Computation on Graphics Hardware.
Jared Hoberock and David Tarjan, Stanford University:
Introduction to Massively Parallel Computing; GPU History and CUDA Programming Basics.
Nvidia: CUDA Technical Training Volume I:
Introduction to CUDA Programming.
NVIDIA GPU Computing Developer Home Page.

·         Lecture 4: Face detection and tracking (Grazina, Oceane, Alex)

o    Time: Monday Nov. 8 at 12.30

o    Slides

o    Readings: 

Paul Viola & Michael Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” CVPR (1) 2001: 511-518.

Panagiotis Papageorgiou, Nikos Katsarakis, Andreas Stergiou, Aristodemos Pnevmatikakis, “A synergistic detection- and track-level system for monitoring people in smart spaces,” AIT, 2009.

Aristodemos Pnevmatikakis & Fotios Talantzis, “Joint Bayesian Tracking of Head Location and Pose from Low-Resolution Video,” EUSIPCO 2010, Aalborg Denmark. 

·         Lecture 5: Medical imaging (Audrey, Lucie, Antoine)

o    Time: Monday Nov. 15 at 12.30

o    Slides

o    Readings: in slides.  

·         Lecture 6: Color management and display (Thierry, Romain, Florent)

o    Time: Monday Nov. 15 at 14.30

o    Slides

o    Readings: 

·         Lecture 7: Brain computer interfaces (BCI) (Cyril, Julien, Pirerre)

o    Time: Friday Nov. 19 at 12.30

o    Slides

o    Readings:  in slides.

·         Lecture 8: Automatic video indexing (Maite, Itxaso)

o    Time: Monday Nov. 22 at 12.30

o    Slides

o    Readings: 

Gagnon, L., Laliberte, F., Lalonde, M., Beaulieu, M., Toward an Application of Content-Based Video Indexing to Computer-Assisted Descriptive Video , Proc. of Computer and Robot Vision, 2008.

Arun Hampapur, “Semantic Video Indexing: Approach and Issue.” SIGMOD Record 28(1): 32-39 (1999).

Rainer Lienhart. Video OCR: A Survey and Practitioner's Guide. In Video Mining, Kluwer Academic Publisher, pp. 155-184, Oct. 2003.

Cees Snoek, Marcel Worring: Multimodal Video Indexing: A Review of the State-of-the-art. Multimedia Tools Appl. 25(1): 5-35 (2005).



Zheng-Hua Tan, Department of Electronic Systems, Aalborg University