Seletor de Idiomas

Top - Webmail / Login / Trac

Imagem - Destaques

slide interno 8

WMC19 - Technical Session 3 - Multimedia and Edge Computing

Title: Semi-automatic Synchronization of Sensory Effects in Mulsemedia Authoring Tools

Author: Raphael Silva de Abreu


Abstract: Synchronization of sensory effects with multimedia content is a non- trivial and error-prone task that can discourage authoring of mulsemedia applications. Although there are authoring tools that assist in the specification of sensory effect metadata in an automated way, the forms of analysis used by them are not general enough to identify complex components that may be related to sensory effects. In this work, we present an intelligent component, which allows the semi-automatic definition of sensory effects. This component uses a neural network to extract information from video scenes. This information is used to define sensory effects synchronously to related videos. The proposed component was implemented in STEVE~2.0 authoring tool, helping the authoring of sensory effects in a graphical interface.




Title: Automatic Preparation of Media Objects in Multimedia Applications

Author: Marina Ivanov


Abstract: In multimedia applications, spatiotemporal relationships among media

objects should be controlled during the execution phase in order to preserve the quality of presentation. When the content that composes the application is delivered over a communication network, some delays may occur due to network congestion problems. In order to avoid synchronization faults during the presentation of the distributed multimedia applications, this work proposes the automatic preparation of media objects. The automatic preparation of media objects aim to ensure that all media objects are available in the receiver device at their presentation moment. In our proposal, the multimedia presentation engine (formatter) builds a preparation plan based on the network conditions and the presentation behavior learned from the multimedia document that defines the application. As proof of concept, we implemented the automatic creation of the preparation plan in the Ginga-NCL middleware. Furthermore, a use case is presented to demonstrate the automatic preparation for NCL applications. Finally, a brief discussion about garbage collection in multimedia applications containing non-deterministic events is also presented.




Title: V-PRISM: An edge-based architecture to virtualize multimedia sensors in the Internet of Things

Author: Anselmo Luiz Eden Battisti


Abstract: The Internet of Things (IoT) enables the interconnection with the Internet of the most varied physical objects, instrumented by intelligent sensors and actuators. By addressing physical objects and making them part of a global network, the IoT has the potential to provide novel applications to make life easier and healthier for citizens, to increase the productivity of companies and to promote the building of more intelligent and sustainable cities, environments and countries. Several types of sensors compose the IoT ecosystem. Among them, multimedia sensors have recently become a major source of data, giving raise to the Internet of Multimedia Things. With the wide spread of the Internet of Things, and its integration with Cloud platforms, a novel paradigm called Cloud of Things (CoT) has recently emerged. In this context, the cloud works as an intermediary between the sensors/IoT devices and applications. CoT system is strongly based on the concept of virtualization, to help dealing with the complexity raised by the heterogeneity of the sensors. However, multimedia applications usually are latency-sensitive, therefore the data processing in the remote cloud is not always effective. A strategy to minimize the latency is to process the multimedia stream closer to the data sources, exploiting the resources at the edge of the networks. Therefore, in this paper, we propose V-PRISM, an architecture to virtualize multimedia sensors with components deployed and executed at the edge tier of a Cloud of Things ecosystem. The adoption of V-PRISM can reduce the battery and CPU consumption at the IoT devices, reduce the traffic at the IoT network, decrease the end-to-end latency and increase the ROI for infrastructure providers.

Social - Facebook - Twitter - G+