|
The VIPS laboratory is proud to present a series of advanced lectures on significant topics in Computer Vision, Pattern Recognition, and Image Processing. These courses are particularly addressed to PhD students, but open to all types of researchers. Each course will typically last one week and will be focussed on one specific topic, in order to provide a more productive interaction with the lecturer. The maximum number of participants is limited to 50 persons. In case of a larger number of applications, priority will be given to PhD students. The second school will introduce the area of Immersive Communications and the Computer Vision tecniques used in this field.
Lecture The VIPS Laboratory is proud to announce that: Emanuele TruccoReader at the Dept of Computing and Electrical Engineering, Heriot-Watt University, Edinburgh, will hold a course on: Computer Vision for Immersive CommunicationsThis course will aim to provide:
The program is articulated in 4 sessions of max 5 hours each. SEMINAR 1: COMPUTER VISION FOR IMMERSIVE COMMUNICATIONS. We introduce the advanced, interactive image communications area, its planned development in Europe (as laid out in Research Framework VI), and a spectrum of relevant, specific technologies, incl. videoconferencing (main application considered), immersive interactive environments, and digital TV. We identify the requirements and challenges posed to computer vision and image processing by this scenario. We then run through a brief overview of techniques representing the state-of-the-art of CV solutions adopted, or mature enough to be adopted, by applications. SEMINAR 2: VIDEO TRACKING Tracking is one of the fundamental building blocks for interactive communications. We define the problem in CV terms, and motivate its importance in the overall application scenario. We then propose an overview of basic tracking techniques in increasing order of target complexity, starting from simple window tracking and culminating with model-based tracking of complex 3-D objects. We illustrate reference algorithms, incl. CONDENSATION, active contours, and geometry-based model tracking. SEMINAR 3: LOCATING 3-D OBJECT IN SPACE USING MODELS The ability of locating 3-D object in space even from single images is a well-known problem in computer vision. We assume models of the observed objects are available, which allows us to establish a link with model-based tracking solutions as seen in Seminar 2. We consider two main paradigms, based respectively on a-priori CAD-like models and on appearance models learnt from examples. We illustrate reference algorithms and compare their advantages and disadvantages. SEMINAR 4: HUMAN FIGURE MODELLING FOR COMMUNICATION-ORIENTED COMPUTER VISION Several applications in image communication focus on scenes composed by one or more human figures, for example videoconferencing, videophones, and news programmes. Depth or disparity estimation is often necessary, for instance to support view synthesis, but the complex nature of the human body and the frequent occlusions created by gestures make the problem taxing. Efficient a-priori models of the human figure, partly borrowed from graphics and animation, could be exploited to constrain the problem, for instance to assist the estimation of dense disparity maps in the presence of wide-baseline stereo and strong occlusions. After a presentation of the problem from the computer vision viewpoint, we shall look at some modelling solution oriented mostly to computer graphics (mesh-based models and metaballs), and at their possible application to computer vision systems to be deployed in real-time or near-real-time comms applications. The reference problem will be immersive videoconferencing. Lecture Schedule
Course Fees 150 euro for students, researchers, and other
people working directly for a university. Registration If you are interested, you must send an email to vips_school@sci.univr.it in which you ask for participation. Please state your identity and your status (undergraduate, PhD student, other) and wait for the confirmation email. The ultimate deadline is May 24, 2004. Attached to our confirmation email you will find a registration form to print, compile and send together with a proof of the payment by fax before May 31, 2004, to the following no. +39 045 8027068, to the attention of Prof. V. Murino, 2nd VIPS School on Computer Vision, Pattern Recognition, and Image Processing. The proposed payment method is bank wire transfer (all necessary data are in the form). Important Dates
Accomodations The accomodation costs are not covered by the Course Fee. However, we have made agreements with some convenient hotels and you can find a list of available places here. If you wish to take advantage of these opportunities please remember to notify to the hotel that you are attending our school. At any rate, if you need to reach our department please consult this page. For any other information, please send an email to vips_school@sci.univr.it |
|||||||||||||||||||||||||||||
![]() |
||||||||||||||||||||||||||||||
![]() |
Credits |