A hierarchical component model for large parallel interactive applications

Lesage, Jean-Denis; Raffin, Bruno

doi:10.1007/s11227-008-0228-7

Cited by 14 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Modules execute asynchronously on separate threads, and the underlying system transports data between modules transparently. FlowVR focuses on integration of disparate modules that execute at different rates or may themselves encompass parallel code, and a hierarchical component model that facilitates composition of large applications [25]. Unlike in Sprout, latency and parallelization are controlled by hand tuning of module code, execution rates, and placement on compute nodes.…”

Section: Stream Processing Systemsmentioning

confidence: 99%

Exploiting multi-level parallelism for low-latency activity recognition in streaming video

Chen

Mummert

Pillai

et al. 2010

Proceedings of the First Annual ACM SIGMM Conference on Multimedia Systems

View full text Add to dashboard Cite

Video understanding is a computationally challenging task that is critical not only for traditionally throughput-oriented applications such as search but also latency-sensitive interactive applications such as surveillance, gaming, videoconferencing, and vision-based user interfaces. Enabling these types of video processing applications will require not only new algorithms and techniques, but new runtime systems that optimize latency as well as throughput. In this paper, we present a runtime system called Sprout that achieves low latency by exploiting the parallelism inherent in video understanding applications. We demonstrate the utility of our system on an activity recognition application that employs a robust new descriptor called MoSIFT, which explicitly augments appearance features with motion information. MoSIFT outperforms previous recognition techniques, but like other state-of-the-art techniques, it is computationally expensive -a sequential implementation runs 100 times slower than real time. We describe the implementation of the activity recognition application on Sprout, and show that it can accurately recognize activities at full frame rate (25 fps) and low latency on a challenging airport surveillance video corpus.

show abstract

Section: Stream Processing Systemsmentioning

confidence: 99%

Exploiting multi-level parallelism for low-latency activity recognition in streaming video

Chen

Mummert

Pillai

et al. 2010

Proceedings of the First Annual ACM SIGMM Conference on Multimedia Systems

View full text Add to dashboard Cite

show abstract

“…A FlowVR [13], [8]é uma biblioteca projetada para auxiliar o desenvolvimento de aplicações interativas de alto desempenho. Esta biblioteca utiliza o conceito de orientação a fluxo de dados.…”

Section: Trabalhos Relacionadosunclassified

A Tool to Aid the Development of Distributed Virtual Reality Applications

Ferraz

Roque

Belloc

et al. 2014

2014 XVI Symposium on Virtual and Augmented Reality

View full text Add to dashboard Cite

Highly immersive Virtual Reality applications are often complex and demand a lot of computational resources. To meet these demands, it is common to distribute the application execution over multiple computers connected through a data network. Although there are several tools for developing distributed applications, only a few are designed for VR applications. Thus, this paper presents a software tool to aid the development of distributed VR applications. This tool provides flexible features to data exchange and synchronization among processes using simple elements similar to those found in traditional programming languages. This tool uses the publisher/subscriber concept to reduce the coupling among processes and optimize the use of the network. Two applications have been developed using the proposed tool, proving its effectiveness.Resumo-Aplicações de Realidade Virtual de alta imersão geralmente são complexas e demandam muitos recursos computacionais. Para atender estas demandas,é comum distribuir a execução da aplicação em diversos computadores interconectados através de uma rede de dados. Apesar de existirem diversas ferramentas para desenvolvimento de aplicaçães distribuídas, poucas são dedicadas para aplicações de RV. Assim, este trabalho apresenta uma ferramenta de software para facilitar o desenvolvimento de aplicações distribuídas de realidade virtual. Esta ferramenta fornece um meio flexível para troca de dados e sincronização entre processos utilizando elementos simples e análogos aos encontrados nas linguagens de programação tradicionais. Esta ferramentaé baseada no conceito publicador/assinante, reduzindo o acoplamento entre processos e otimizando a utilização do meio físico de comunicação. Duas aplicações foram desenvolvidas utilizando a ferramenta proposta, comprovando sua eficiência. I. INTRODUÇÃOA Realidade Virtual (RV)é umaárea de pesquisa e desenvolvimento multidisciplinar cujo objetivoé criar ambientes não reais através de simulações computacionais e periféricos de interação. Atualmente as tecnologias de RV são empregadas em diversasáreas como treinamento, entretenimento, medicina, engenharia, ensino e artes.A complexidade destas aplicações varia desde programas stand-alone até ambientes multi-usuários compostos por software e hardware de interação. Para as aplicações mais complexasé comum a utilização de um ambiente computacional distribuído, ou seja, um aglomerado de computadores interconectados através de uma rede de dados, no qual cada unidade computacional processa uma parcela específica da aplicação de forma coordenada com as demais unidades [1] [2]. A distribuição do processamento eleva a complexidade da aplicação e geralmenté e um desafio estabelecer a melhor divisão e a melhor arquitetura de troca de dados.A distribuição de uma aplicação de realidade virtual pode ocorrer em diversos níveis, de acordo com a natureza da aplicação. Aplicações multi-usuários, como jogos por exemplo, utilizam a distribuição em um nível mais alto para compartilhar umúnico mundo virtual para diversos usuários...

show abstract

“…To be able to deal with the network design of such applications, FlowVR is based on hierarchical component model [22]. This model introduces a new kind of components called composite.…”

Section: Platform Integrationmentioning

confidence: 99%

“…Another aspect of our contribution is the implementation of the pipeline in a flexible parallel framework. For that purpose, we rely on FlowVR, a middleware dedicated to parallel interactive application [21][22][23]. The application is structured through a hierarchy of components, the leaves being computation tasks.…”

Section: Introductionmentioning

confidence: 99%

Multicamera Real-Time 3D Modeling for Telepresence and Remote Collaboration

Petit

Lesage

Ménier³

et al. 2010

International Journal of Digital Multimedia Broadcasting

Self Cite

View full text Add to dashboard Cite

We present a multicamera real-time 3D modeling system that aims at enabling new immersive and interactive environments. This system, called Grimage, allows to retrieve in real-time a 3D mesh of the observed scene as well as the associated textures. This information enables a strong visual presence of the user into virtual worlds. The 3D shape information is also used to compute collisions and reaction forces with virtual objects, enforcing the mechanical presence of the user in the virtual world. The innovation is a fully integrated system with both immersive and interactive capabilities. It embeds a parallel version of the EPVH modeling algorithm inside a distributed vision pipeline. It also adopts the hierarchical component approach of the FlowVR middleware to enforce software modularity and enable distributed executions. Results show high refresh rates and low latencies obtained by taking advantage of the I/O and computing resources of PC clusters. The applications we have developed demonstrate the quality of the visual and mechanical presence with a single platform and with a dual platform that allows telecollaboration.

show abstract

A hierarchical component model for large parallel interactive applications

Cited by 14 publications

References 19 publications

Exploiting multi-level parallelism for low-latency activity recognition in streaming video

Exploiting multi-level parallelism for low-latency activity recognition in streaming video

A Tool to Aid the Development of Distributed Virtual Reality Applications

Multicamera Real-Time 3D Modeling for Telepresence and Remote Collaboration

Contact Info

Product

Resources

About