Friday, February 15, 2008

Keynotes at WIAMIS 2008

WIAMIS 2008 is pleased the following keynote speaker:

  • Horst Bischof, TU Graz, Austria: Robust Person Detection for Surveillance using Online learning
  • John R. Smith, IBM T. J. Watson Research Center, USA: Unleashing Video Search
  • Jens-Rainer Ohm, RWTH Aachen, Germany: Recent, current and future developments in video coding
Robust Person Detection for Surveillance using Online learning

Recently, there has been considerable amount of research in methods for person detection. This talk will focus on methods for person detection in a surveillance setting (known environment). We will demonstrate that in this setting one can build robust and highly reliable person detectors by using on-line learning methods. In particular, I will first discuss "conservative learning"
which is able to learn a person detector without any hand labelling effort. As a second example I will discuss a recently developed grid based person detector.

The basic idea is to considerably simplify the detection problem by considering individual image locations separately. Therefore, we can use simple adaptive classifiers which are trained on-line. Due to the reduced complexity we can use a simple update strategy that requires only a few positive samples and is stable by design. This is an essential property for real world applications which require operation for 24 hours a day, 7 days a week. During the talk we will illustrate our results on video sequences and standard benchmark databases.

Unleashed Video Search

Video is rapidly becoming a regular part of our digital lives. However, its tremendous growth is increasing users’ expectations that video will be as easy to search as text. Unfortunately, users are still finding it difficult to find relevant content. And today’s solutions are not keeping pace on problems ranging from video search to content classification to automatic filtering. In this talk we describe recent techniques that leverage the computer’s ability to effectively analyze visual features of video and apply statistical machine learning techniques to classify video scenes automatically. We examine related efforts on the modeling of large video semantic spaces and review public evaluations such as TRECVID, which are greatly facilitating research and development on video retrieval. We discuss the role of MPEG-7 as a way to store metadata generated for video in a fully standards-based searchable representation. Overall, we show how these approaches together go a long way to truly unleash video search.

Recent, current and future developments in video coding

Most recent attention in development of video coding algorithms has been devoted to the ITU-T Rec.H.264 | ISO/IEC 14496-10 Advanced Video Coding standard. Recent and current extensions to this standard include developments for professional applications, highly-efficient scalable video coding and multi-view video coding. Finally, digital video over various networks, going for higher and higher resolutions, is becoming reality.

While this technology is progressing and further optimizations are sought, new challenges appear at the horizon. New types of displays include 3D capabilities, requiring for generation of additional view perspectives beyond available camera positions. Cameras and displays are coming up with permanently increasing frame rates and sizes. The tremendous amount of different applications for digital video requires additional flexibility and reconfigurability of devices. And last not least, increased compression efficiency (meaning rate reduction versus processing cost) is again becoming more important with ever increasing numbers of pixels to be transmitted. The talk will focus on possible solutions to these challenges and discuss the maturity they currently have.

No comments: