Call for Participation

 
 

First ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC-07)

September 25-28, 2007
Vienna, Austria

Plenary Talks:

Feng Zhao, Microsoft Research, USA

Sensing Platforms for World-wide Sensor Web


Abstract
The talk will present challenges and opportunities in wide-area sensor networks that leverage web cams, cell phones, and other sensors to provide unprecedented coverage of real-time events, and will use recent work as examples to illustrate the design and engineering of such systems.

Speaker's Biography
Feng Zhao is a Principal Researcher at Microsoft Research, where he manages the Networked Embedded Computing Group. He received his PhD in Electrical Engineering and Computer Science from MIT and has taught at Stanford University and Ohio State University. Dr. Zhao was a Principal Scientist at Xerox PARC and directed PARC’s sensor network research effort. He serves as the founding Editor-In-Chief of ACM Transactions on Sensor Networks, and has authored or co-authored over 100 technical papers and books, including a recent book published by Morgan Kaufmann - Wireless Sensor Networks: An information processing approach. He has received a number of awards, and his work has been featured in news media such as BBC World News, BusinessWeek, and Technology Review.

Click here for speaker's website.

Mubarak Shah, University of Central Florida, USA

Video Surveillance and Monitoring Using Distributed Cameras


Abstract
The concept of a cooperative multi-camera system, informally a ‘forest’ of sensors, is of great practical relevance. Cameras typically have limited fields of views, but are now available at low costs. Thus, instead of having a single camera that surveys a large area, far greater flexibility and scalability can be achieved by observing a scene ‘through many eyes’, using a multitude of distributed cameras. In this context, multi-camera surveillance and monitoring systems have recently received increasing interest from the research community.

Automatic analysis of videos obtained from distributed cameras involves detection of objects of interest in video (e.g. people, vehicles), tracking of those objects from frame to frame, and recognition of their activities and behavior. In this talk, I will present an overview of our work in these areas.

Speaker's Biography
Dr. Mubarak Shah, Agere Chair Professor of Computer Science, and the founding director of the Computer Visions Lab at the University of Central Florida, is a researcher in a number of computer vision areas. He has worked in several areas including activity and gesture recognition, violence detection, event ontology, object tracking, video segmentation, story and scene segmentation, view morphing, ATR, wide-baseline matching, and video registration. He is a co-author of two books (Motion-Based Recognition (1997) and Video Registration (2003)) both by Kluwer Academic Publisher. Dr. Shah is a fellow of IEEE and IAPR. In 2006, he was awarded a Pegasus Professor award, the highest award at UCF, given to a faculty member who has made a significant impact on the university, has made an extraordinary contribution to the university community, and has demonstrated excellence in teaching, research and service. He was an IEEE Distinguished Visitor speaker for 1997-2000 and received IEEE Outstanding Engineering Educator Award in 1997. He received the Harris Corporation's Engineering Achievement Award in 1999, the TOKTEN awards from UNDP in 1995, 1997, and 2000; Teaching Incentive Program award in 1995 and 2003, Research Incentive Award in 2003, Millionaires' Club awards in 2005 and 2006, University Distinguished Researcher award in 2007, honorable mention for the ICCV 2005 Where Am I? Challenge Problem, and was nominated for the best paper award in ACM Multimedia Conference in 2005. He is an editor of international book series on Video Computing; editor in chief of Machine Vision and Applications journal, and an associate editor of ACM Computing Surveys journal. He was an associate editor of the IEEE Transactions on PAMI, and a guest editor of the special issue of International Journal of Computer Vision on Video Computing.

Click here for speaker's website.

Wilfried Philips, Ghent University, Belgium

Challenges for Single- and Multi-Camera Video Processing


Abstract
The application domain of video surveillance offers a growing number of opportunities for video processing applications, which are inevitably accompanied by technical challenges. The talk will focus on advanced video processing algorithms for video restoration, video segmentation and video augmentation. Interestingly, although these algorithms are quite diverse, they often share a number of underlying concepts related to modeling useful image content and unwanted distortions.

The talk will illustrate the power of state-of-the-art multi-resolution and statistical models for useful image content and unwanted distortions through a number of examples. It will address important topics such as how to incorporate motion information into a multi-resolution framework, how to model imprecise information and how to deal with maximum latency requirements.

In many surveillance applications, multiple cameras are involved. Important improvements in image quality are possible by combining pictures from multiple cameras into a single picture. On the one hand supper-resolution techniques can increase the resolution of the final picture. On the other hand, image fusion of pictures acquired using cameras with different depth of field numbers or different focus depths can result in optimally sharp images of all objects in a scene.

The talk will end with a sneek preview of emerging applications involving smart cameras and minimal information exchange between the cameras and the base station, e.g., to conserve battery power. Novel concepts from information theory can be of help here.

Speaker's Biography
Wilfried Philips was born in Aalst, Belgium, on October 19, 1966. In 1989, he received the Diploma degree in electrical engineering and in 1993 the Ph.D. degree in applied sciences, both from Ghent University, Belgium. From October 1989 until October 1997 he worked at the Department of Electronics and Information Systems of Ghent University for the Flemish Fund for Scientific Research (FWO-Vlaanderen), first as a research assistant and later as a post-doctoral research fellow.

Since November 1997 he is with the Department of Telecommunications and Information Processing of Ghent University, where he is currently a professor and is heading the research group "Image Processing and Interpretation", which has recently become part of the virtual Flemish ICT research institute IBBT.

Some of the recent research activities in his group include image and video restoration and analysis and modeling of image reproduction systems. Important application areas targeted by the group include remote sensing, surveillance, and industrial inspection.

Click here for speaker's website.