Professor
Carsten Griwodz
Head of Department
griff@simula.no
+47 926 84 380

The Media department addresses resource utilization and  performance challenges to support a wide range of interactive multimedia  services to the large user masses in the Internet. The goals are to reduce the  costs, increase the number of users and optimize the perceived service quality. MPG's activities branch into several areas of multimedia systems to maintain and improve our ability to evaluate the performance of complete multimedia systems. This goal ties research branches together that are as diverse as multicore programming and user perception. Any level of a system may constitute a performance bottleneck, and the critical bottlenecks are known to move from component to component as the state of the art develops. Therefore, MPG's research keeps a global scope, while its research activities target the critical performance question.


MPG on the Web

For recent news from MPG, look at our blog:

Media Crew Mar 2014
 

A list of academic publications by members of the group can be found here.

MPG is a department at Simula, but also part of the research group Networks and Distributed Systems at the University of Oslo. To see the researchers of MPG, follow the link to our people page.


Current projects


Brief Overview of Activities

Video Delivery Systems

MPG covers a range of video delivery systems ranging from traditional video streaming, video search to 3D representation of content and delivery of free-view video. In a fairly mature part of the field, we address questions of efficient delivery and best user experience when using the adaptive segmented HTTP streaming that is currently favoured by industry. In a very young part of the field, we investigate means of combining video streams from sparse camera arrays that monitor large space to generate 3D scenes in real-time and deliver them to viewers.

Perceptual Video Quality Assessments

To make the right decision in video coding, adaptation during transport and rendering on users' screens, it is necessary to understand how these decisions affect the people who watch the result. The delivery of perfect quality is always inhibited by limited resources, such as recording devices, computing power, network bandwidth and display devices. Adapting to available resources involves a choice of, for example, compression method, target bandwidth, quantization factor, resolution or frame rates of videos. Whether decisions are good is known to depend on external conditions as well as content and user intent, but how to make good decisions is a wide-open research field, and one that MPG pursues.

Distributed Data Processing

Multimedia data, and especially the current trend towards 3D scene creation and rendering, generates large data volumes that must be processed in a timely manner. With growing complexity and an increased user expectation to use complex media, the computational demand for multimedia data processing grows. The latest hardware architectures use an increasing number of heterogenous multi-core processors to cope with the demand for computing power. Developers find it much harder to develop application for such architecture than for homogeneous sequential ones, and MPG investigates how multimedia applications, which differ from other workloads by their need for deadline-driven scheduling, their ability to trade speed for quality and their cyclic nature, can be developed for and deployed on such architectures.

  • P2G - The P2G framework is a distributed execution system for processing of continuous multimedia wordloads on heterogeneous architectures.

Data Communication

Existing data communication protocols are designed for best-effort networks, and transport protocols today are optimized for high-bandwidth applications like plain file transfers and web-browsing. Interactive distributed multimedia applications however have a different requirement, the delivery of usually small amounts of data within consistently short times. Even though interactive applications that have this requirement comprise a large number of connections in the current Internet, they are hardly researched at all and existing solutions fail. MPG investigates new protocols and mechanisms that address this challenge and that realistically deployable in the Internet.

 

Personal tools