SEMINARIOS DE DOCTORADO 2005-2006


Doctorado en Ingeniería Informática y de Telecomunicación
Escuela Politécnica Superior, Universidad Autónoma de Madrid

Escuela Politécnica Superior                        

25 de Mayo de 2006, 12:00

Salón de Grados, Escuela Politécnica Superior, Universidad Autónoma de Madrid

Semantic Video Analysis for Automatic Content Description, Evaluation and Delivery

Andrea Cavallaro

Queen Mary, University of London

     

Abstract

Semantic segmentation is generally associated with second generation video coders, or object-based coders. Object-based coders encode different video objects separately in order to achieve lower bitrates and to enable object-based functionalities. In this seminar, I will describe how the main content message can be extracted from video data through semantic video analysis, an application dependent process that separates relevant information from non relevant information. Semantic analysis and the corresponding content annotation are used under a new perspective: the results of the analysis are exploited for object-based encoders, such as MPEG-4, as well as for frame-based encoders, such as MPEG-1. Moreover, the use of MPEG-7 content descriptors in conjunction with the video is used for improving content visualization for narrow channels and devices with limited capabilities.

A number of applications, such as video indexing, remote monitoring, mobile surveillance, video quality evaluation will be discussed based on this annotation approach. Finally, the impact of semantic video analysis will be evaluated objectively and subjectively, and compared with traditional approaches.


PDF presentation

Andrea Cavallaro

Andrea Cavallaro received his M.Sc. (Summa cum Laude) in Electrical Engineering from the University of Trieste, Italy, in 1996, and the Ph.D. in Electrical Engineering from the Swiss Federal Institute of Technology, Lausanne, Switzerland, in 2002. In 1996 and 1998, he served as a research consultant at the Image Processing Laboratory, University of Trieste, Italy, working on compression algorithms for very low bitrate video coding and on digital image sequence de-interlacing. In 1997 he served the Italian Army as lieutenant at the 33rd Electronic Warfare Battalion in Treviso, Italy. From June 1998 to February 2002 he was a research assistant at the Signal Processing Laboratory of the Swiss Federal Institute of Technology (EPFL). From March 2002 to April 2003, he was a senior researcher at EPFL. Since May 2003, he is lecturer at the Department of Electronic Engineering, Queen Mary, University of London (QMUL).

Dr. Cavallaro was awarded a Research Fellowship with British Telecommunications (BT), a Drapers' Prize for the development of Learning and Teaching in 2004; and an e-learning Fellowship in 2006. He is co-author of the paper ''Hybrid particle filter and mean shift tracker with adaptive transition model'', winner of the student paper contest at the 2005 IEEE ICASSP. Dr. Cavallaro was workpackage leader for the EU projects ACTS Modest and IST art.live and is Principal Investigator in a number of UK Research Council and industry-sponsored projects. Dr. Cavallaro is member of the IEEE Signal Processing Society, Multimedia Signal Processing Technical Committee and has been a member of the organizing/technical committee of several conferences, such as IEEE ICME, IEEE ICIP, SPIE VCIP, ACM Multimedia, IEEE AVSS, ECCV-VS, PETS. He acts as reviewer for several international conferences and journals, and he is author of 45 papers, including 5 book chapters.