John F. Gibbon

A digital on-demand video service supporting content-based queries

Video-on-demand represents a key demonstrative application for enabling multimedia technology in communication, database, and interface research. This application requires solving a number of diverse technical problems including the data synchronization problem for time-dependent data delivery. In this paper we describe the general requirements of video-on-demand and introduce a system supporting content-based retrieval and playback for the structure and content of digital motion pictures. In our model we capture domain-specific information for motion pictures and provide access to individual scenes of movies through queries on a temporal database. We describe our implementation of this service using existing workstation and storage technology.

The use of network delay estimation for multimedia data retrieval

Multimedia data have specific temporal presentation requirements. For example in video conferencing applications the voice and images of the participants must be delivered and presented synchronously. These requirements can be achieved by scheduling or managing system resources. We present a technique called limited a priori scheduling (LAP) to manage the delivery channel from source to destination for digital multimedia data. By using delay estimation a LAP scheduler can retrieve stored digital media spanning arbitrary networks with unspecified delays. The use of delay estimation also facilitates selective degradation of service in bandwidth and buffer limited situations. Such degradation enables the continuous real-time playout and synchronization of various media arriving from different sources. The performance of the LAP scheduler is described based on implementation and experimentation using Ethernet.

SELECTION AND DISSEMINATION OF DIGITAL VIDEO VIA THE VIRTUAL VIDEO BROWSER

The Virtual Video Browser (VVB) is a manifestation of our mechanisms for the location, identification, and delivery of digital audio and video in a distributed system which can be extended to several application domains including multimedia-based home entertainment, catalog shopping, and distance learning. In the following sections we describe the VVB software application designed to allow the interactive browsing and content-based query of a video database and to facilitate the subsequent playout of selected titles.

Real-time data delivery for multimedia networks

A coherent computer-based multimedia presentation requires the use of real-time scheduling theory applied to system resources including storage devices, the bus, and network. In this paper we present a scheduling technique which is essentially static in nature during periods of network quiescence, but becomes dynamic in response to detection of network load changes of users interaction. This mechanism, called the limited a priori (LAP) scheduler, is an extension of earlier work on scheduling which assumed guaranteed system loading characteristics. The LAP schedules determines network load changes and estimates packet delay using a dynamic filtering algorithm. We show the bounds of accuracy for this technique and describe its suitability with respect to multi-media traffic across an FDDI network.

Real-time scheduling for multimedia services

High-speed networks and high-performance workstations are necessary but not sufficient to support distributed multimedia applications. A real-time scheduling system designed for multimedia data types is also required to orchestrate communications channels, disk storage units, output devices, and the CPU. These subsystems are coordinated to accommodate the special requirements of multimedia data: timely retrieval, transmission, and delivery with permissible levels of data loss and corruption. In this paper we present our framework for the use of real-time scheduling disciplines to support time-dependent multimedia data in a distributed-data environment. Within this framework we propose the application of a statistical resource reservation mechanism and a real-time session scheduler. Furthermore, we relate scheduling and quality of service in a summary of the objectives of multimedia service provision and negotiation.

Management of time-dependent multimedia data

A number of approaches have been proposed for supporting high-bandwidth time-dependent multimedia data in a general purpose computing environment. Much of this work assumes the availability of ample resources such as CPU performance, bus, I/O, and communication bandwidth. However, many multimedia applications have large variations in instantaneous data presentation requirements (e.g., a dynamic range of order 100,000). By using a statistical scheduling approach these variations are effectively smoothed and, therefore, more applications are made viable. The result is a more efficient use of available bandwidth and the enabling of applications that have large short-term bandwidth requirements such as simultaneous video and still image retrieval. Statistical scheduling of multimedia traffic relies on accurate characterization or guarantee of channel bandwidth and delay. If guaranteed channel characteristics are not upheld due to spurious channel overload, buffer overflow and underflow can occur at the destination. The result is the loss of established source-destination synchronization and the introduction of intermedia skew. In this paper we present an overview of a proposed synchronization mechanism to limit the effects of such anomalous behavior. The proposed mechanism monitors buffer levels to detect impending low and high levels on frame basis and regulates the destination playout rate. Intermedia skew is controlled by a similar control algorithm. This mechanism is used in conjunction with a statistical source scheduling approach to provide an overall multimedia transmission and resynchronization system supporting graceful service degradation.

Multimedia data delivery using network delay modeling

Most multimedia systems are by nature distributed. Stored digital media applications such as video-on-demand involve many separate clients and servers; communication applications such as videoconferencing involve users in distinct geographic locations. The retrieval of multimedia data for these applications across computer networks must be done in a timely fashion to accommodate end-to-end delay constraints, buffer space limitations, and inter-media synchronization. In this paper, we present a mechanism called thelimited a priori (LAP) scheduler which manages the retrieval of distributed multimedia data using network delay modeling. The LAP scheduler determines network load changes and estimates packet delay using a dynamic filtering algorithm. We show the bounds of accuracy for this technique and describe its suitability with respect to digital media traffic across a general-purpose network.