Opportunities and Challenges of Implementing P2P Streaming Applications in the Web

P2P applications are increasingly present on the web. We have identified a gap in current proposals when it comes to the use of traditional P2P overlays for real-time multimedia streaming. We analyze the possibilities and challenges to extend WebRTC in order to implement JavaScript APIs for P2P streaming algorithms.

Subjective QoE Analysis of HTTP Adaptive Streaming Applications

Actualmente la optimization de la calidad de experiencia (Quality of Experience- QoE) de HTTP Adaptive Streaming (HAS) de video recibe una atención creciente. Este incremento de interés proviene fundamentalmente de las carencias de las soluciones actuales HAS, que, al no ser QoE-driven, no incluyen la percepción de la calidad de los usuarios finales como una parte integral de la lógica de adaptación. Por lo tanto, la obtención de información de referencia fiable en QoE en HAS presenta retos importantes, ya que las metodologías de evaluación subjetiva de la calidad de vídeo propuestas en las normas actuales no son adecuadas para tratar con la variación temporal de la calidad que es consustancial de HAS. Esta tesis investiga la influencia de la adaptación dinámica en la calidad de la transmisión de vídeo considerando métodos de evaluación subjetiva. Tras un estudio exhaustivo del estado del arte en la evaluación subjetiva de QoE en HAS, se han resaltado los retos asociados y las líneas de investigación abiertas. Como resultado, se han seleccionado dos líneas principales de investigación: el análisis del impacto en la QoE de los parámetros de las técnicas de adaptación y la investigación de las metodologías de prueba subjetiva adecuada para evaluación de QoE en HAS. Se han llevado a cabo un conjunto de experimentos de laboratorio para investigar las cuestiones planteadas mediante la utilización de diferentes metodologáas para pruebas subjetivas. El análisis estadístico muestra que no son robustas todas las suposiciones y reivindicaciones de las referencias analizadas, en particular en lo que respecta al impacto en la QoE de la frecuencia de las variaciones de calidad, de las adaptaciones suaves o abruptas y de las oscilaciones de calidad. Por otra parte, nuestros resultados confirman la influencia de otros parámetros, como la longitud de los segmentos de vídeo y la amplitud de las oscilaciones de calidad. Los resultados también muestran que tomar en consideración las características objetivas de los contenidos puede ser beneficioso para la mejora de la QoE en HAS. Además, todos los resultados han sido validados mediante extensos análisis experimentales que han incluido estudio tanto en otros laboratorios como en crowdsourcing Por último, sobre los aspectos metodológicos de las pruebas subjetivas de QoE, se ha realizado la comparación entre los resultados experimentales obtenidos a partir de un método estandarizado basado en estímulos cortos (ACR) y un método semi continuo (desarrollado para la evaluación de secuencias prolongadas de vídeo). A pesar de algunas diferencias, el resultado de los análisis estadísticos no muestra ningún efecto significativo de la metodología de prueba. Asimismo, aunque se percibe la influencia de la presencia de audio en la evaluación de degradaciones del vídeo, no se han encontrado efectos estadísticamente significativos de dicha presencia. A partir de la ausencia de influencia del método de prueba y de la presencia de audio, se ha realizado un análisis adicional sobre el impacto de realizar comparaciones estadísticas múltiples en niveles estadísticos de importancia que aumentan la probabilidad de los errores de tipo-I (falsos positivos). Nuestros resultados muestran que, para obtener un efectos sólido en el análisis estadístico de los resultados subjetivos, es necesario aumentar el número de sujetos de las pruebas claramente por encima de los tamaños de muestras propuestos por las normas y recomendaciones actuales. ABSTRACT Optimizing the Quality of Experience (QoE) of HTTP adaptive video streaming (HAS) is receiving increasing attention nowadays. The growth of interest is mainly caused by the fact that current HAS solutions are not QoE-driven, i.e. end-user quality perception is not integral part of the adaptation logic. However, obtaining the necessary reliable ground truths on HAS QoE faces substantial challenges, since the subjective video quality assessment methodologies as proposed by current standards are not well-suited for dealing with the time-varying quality properties that are characteristic for HAS. This thesis investigates the influence of dynamic quality adaptation on the QoE of streaming video by means of subjective evaluation approaches. Based on a comprehensive survey of related work on subjective HAS QoE assessment, the related challenges and open research questions are highlighted and discussed. As a result, two main research directions are selected for further investigation: analysis of the QoE impact of different technical adaptation parameters, and investigation of testing methodologies suitable for HAS QoE evaluation. In order to investigate related research issues and questions, a set of laboratory experiments have been conducted using different subjective testing methodologies. Our statistical analysis demonstrates that not all assumptions and claims reported in the literature are robust, particularly as regards the QoE impact of switching frequency, smooth vs. abrupt switching, and quality oscillation. On the other hand, our results confirm the influence of some other parameters such as chunk length and switching amplitude on perceived quality. We also show that taking the objective characteristics of the content into account can be beneficial to improve the adaptation viewing experience. In addition, all aforementioned findings are validated by means of an extensive cross-experimental analysis that involves external laboratory and crowdsourcing studies. Finally, to address the methodological aspects of subjective QoE testing, a comparison between the experimental results obtained from a (short stimuli-based) ACR standardized method and a semi-continuous method (developed for assessment of long video sequences) has been performed. In spite of observation of some differences, the result of statistical analysis does not show any significant effect of testing methodology. Similarly, although the influence of audio presence on evaluation of video-related degradations is perceived, no statistically significant effect of audio presence could be found. Motivating by this finding (no effect of testing method and audio presence), a subsequent analysis has been performed investigating the impact of performing multiple statistical comparisons on statistical levels of significance which increase the likelihood of Type-I errors (false positives). Our results show that in order to obtain a strong effect from the statistical analysis of the subjective results, it is necessary to increase the number of test subjects well beyond the sample sizes proposed by current quality assessment standards and recommendations.

Enhancing IEEE 802.11 Energy Efficiency for Continuous Media Applications

This paper proposes the Optimized Power save Algorithm for continuous Media Applications (OPAMA) to improve end-user device energy efficiency. OPAMA enhances the standard legacy Power Save Mode (PSM) of IEEE 802.11 by taking into consideration application specific requirements combined with data aggregation techniques. By establishing a balanced cost/benefit tradeoff between performance and energy consumption, OPAMA is able to improve energy efficiency, while keeping the end-user experience at a desired level. OPAMA was assessed in the OMNeT++ simulator using real traces of variable bitrate video streaming applications. The results showed the capability to enhance energy efficiency, achieving savings up to 44% when compared with the IEEE 802.11 legacy PSM.

An IEEE 802.11 energy efficient mechanism for continuous media applications

The widespread deployment of wireless mobile communications enables an almost permanent usage of portable devices, which imposes high demands on the battery of these devices. Indeed, battery lifetime is becoming one the most critical factors on the end-users satisfaction when using wireless communications. In this work, the optimized power save algorithm for continuous media applications (OPAMA) is proposed, aiming at enhancing the energy efficiency on end-users devices. By combining the application specific requirements with data aggregation techniques, {OPAMA} improves the standard {IEEE} 802.11 legacy Power Save Mode (PSM) performance. The algorithm uses the feedback on the end-user expected quality to establish a proper tradeoff between energy consumption and application performance. {OPAMA} was assessed in the OMNeT++ simulator, using real traces of variable bitrate video streaming applications, and in a real testbed employing a novel methodology intended to perform an accurate evaluation concerning video Quality of Experience (QoE) perceived by the end-users. The results revealed the {OPAMA} capability to enhance energy efficiency without degrading the end-user observed QoE, achieving savings up to 44 when compared with the {IEEE} 802.11 legacy PSM.

Mode-Controlled Data-Flow Modeling of Real-Time Memory Controllers

Accepted in 13th IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia 2015), Amsterdam, Netherlands.

Security in multicast communication

Multicast is one method to transfer information in IPv4 based communication. Other methods are unicast and broadcast. Multicast is based on the group concept where data is sent from one point to a group of receivers and this remarkably saves bandwidth. Group members express an interest to receive data by using Internet Group Management Protocol and traffic is received by only those receivers who want it. The most common multicast applications are media streaming applications, surveillance applications and data collection applications. There are many data security methods to protect unicast communication that is the most common transfer method in Internet. Popular data security methods are encryption, authentication, access control and firewalls. The characteristics of multicast such as dynamic membership cause that all these data security mechanisms can not be used to protect multicast traffic. Nowadays the protection of multicast traffic is possible via traffic restrictions where traffic is allowed to propagate only to certain areas. One way to implement this is packet filters. Methods tested in this thesis are MVR, IGMP Filtering and access control lists which worked as supposed. These methods restrict the propagation of multicast but are laborious to configure in a large scale. There are also a few manufacturerspecific products that make possible to encrypt multicast traffic. These separate products are expensive and mainly intended to protect video transmissions via satellite. Investigation of multicast security has taken place for several years and the security methods that will be the results of the investigation are getting ready. An IETF working group called MSEC is standardizing these security methods. The target of this working group is to standardize data security protocols for multicast during 2004.

INDICIa: a new distributed clustering protocol

Many data streaming applications produces massive amounts of data that must be processed in a distributed fashion due to the resource limitation of a single machine. We propose a distributed data stream clustering protocol. Theoretical analysis shows preliminary results about the quality of discovered clustering. In addition, we present results about the ability to reduce the time complexity respect to the centralized approach.

Energy Management and Optimization for Video Decoders based on Functional-oriented Reconfiguration

In recent years, the increasing sophistication of embedded multimedia systems and wireless communication technologies has promoted a widespread utilization of video streaming applications. It has been reported in 2013 that youngsters, aged between 13 and 24, spend around 16.7 hours a week watching online video through social media, business websites, and video streaming sites. Video applications have already been blended into people daily life. Traditionally, video streaming research has focused on performance improvement, namely throughput increase and response time reduction. However, most mobile devices are battery-powered, a technology that grows at a much slower pace than either multimedia or hardware developments. Since battery developments cannot satisfy expanding power demand of mobile devices, research interests on video applications technology has attracted more attention to achieve energy-efficient designs. How to efficiently use the limited battery energy budget becomes a major research challenge. In addition, next generation video standards impel to diversification and personalization. Therefore, it is desirable to have mechanisms to implement energy optimizations with greater flexibility and scalability. In this context, the main goal of this dissertation is to find an energy management and optimization mechanism to reduce the energy consumption of video decoders based on the idea of functional-oriented reconfiguration. System battery life is prolonged as the result of a trade-off between energy consumption and video quality. Functional-oriented reconfiguration takes advantage of the similarities among standards to build video decoders reconnecting existing functional units. If a feedback channel from the decoder to the encoder is available, the former can signal the latter changes in either the encoding parameters or the encoding algorithms for energy-saving adaption. The proposed energy optimization and management mechanism is carried out at the decoder end. This mechanism consists of an energy-aware manager, implemented as an additional block of the reconfiguration engine, an energy estimator, integrated into the decoder, and, if available, a feedback channel connected to the encoder end. The energy-aware manager checks the battery level, selects the new decoder description and signals to build a new decoder to the reconfiguration engine. It is worth noting that the analysis of the energy consumption is fundamental for the success of the energy management and optimization mechanism. In this thesis, an energy estimation method driven by platform event monitoring is proposed. In addition, an event filter is suggested to automate the selection of the most appropriate events that affect the energy consumption. At last, a detailed study on the influence of the training data on the model accuracy is presented. The modeling methodology of the energy estimator has been evaluated on different underlying platforms, single-core and multi-core, with different characteristics of workload. All the results show a good accuracy and low on-line computation overhead. The required modifications on the reconfiguration engine to implement the energy-aware manager have been assessed under different scenarios. The results indicate a possibility to lengthen the battery lifetime of the system in two different use-cases.

A parallel pattern for iterative stencil + reduce

We advocate the Loop-of-stencil-reduce pattern as a means of simplifying the implementation of data-parallel programs on heterogeneous multi-core platforms. Loop-of-stencil-reduce is general enough to subsume map, reduce, map-reduce, stencil, stencil-reduce, and, crucially, their usage in a loop in both data-parallel and streaming applications, or a combination of both. The pattern makes it possible to deploy a single stencil computation kernel on different GPUs. We discuss the implementation of Loop-of-stencil-reduce in FastFlow, a framework for the implementation of applications based on the parallel patterns. Experiments are presented to illustrate the use of Loop-of-stencil-reduce in developing data-parallel kernels running on heterogeneous systems.

Underwater acoustic modem with streaming video capabilities

Oceans have shown tremendous importance and impact on our lives. Thus the need for monitoring and protecting the oceans has grown exponentially in recent years. On the other hand, oceans have economical and industrial potential in areas such as pharmaceutical, oil, minerals and biodiversity. This demand is increasing and the need for high data rate and near real-time communications between submerged agents became of paramount importance. Among the needs for underwater communications, streaming video (e.g. for inspecting risers or hydrothermal vents) can be seen as the top challenge, which when solved will make all the other applications possible. Presently, the only reliable approach for underwater video streaming relies on wired connections or tethers (e.g. from ROVs to the surface) which presents severe operational constraints that makes acoustic links together with AUVs and sensor networks strongly appealing. Using new polymer-based acoustic transducers, which in very recent works have shown to have bandwidth and power efficiency much higher than the usual ceramics, this article proposes the development of a reprogrammable acoustic modem for operating in underwater communications with video streaming capabilities. The results have shown a maximum data-rate of 1Mbps with a simple modulation scheme such as OOK, at a distance of 20 m.

Controle de qualidade para 3D-vídeo streaming em redes em malha sem fio

Redes em Malha sem Fio ( do inglês Wireless Mesh Networks - WMNs) são previstas serem uma das mais importantes tecnologias sem fio no que se refere ao fornecimento do acesso de última milha em redes multimídia futuras. Elas vão permitir que milhares de usuários fixos e móveis acessem, produzam e compartilhem conteúdo multimídia de forma onipresente. Neste contexto, vídeo 3D está previsto atrair mais e mais o mercado multimídia com a perspectiva de reforçar as aplicações (vídeos de vigilância, controle demissões críticas, entretenimento, etc). No entanto, o desafio de lidar com a largura de banda optante, escassez de recursos e taxas de erros variantes com o tempo destas redes, ilustra a necessidade da transmissão de vídeos 3D mais resistentes a erros. Dessa forma, alternativas como abordagens de Correção Antecipada de Erros (FEC) se tornam necessárias para fornecer a distribuição de aplicações de vídeo para usuários sem fio com garantia de melhor qualidade de serviço (QoS) e Qualidade de Experiência (QoE). Esta dissertação apresenta um mecanismo baseado em FEC com Proteção Desigual de Erros (UEP) para melhorar a transmissão de vídeo 3D em WMNs, aumentando a satisfação do usuário e permitindo uma melhoria do uso dos recursos sem fio. Os benefícios e impactos do mecanismo proposto serão demonstrados usando simulação e a avaliação será realizada através de métricas de QoE objetivas e subjetivas.

Reliable Broadcasting and Streaming of Multimedia Content

This thesis is focused on the study of techniques that allow to have reliable transmission of multimedia content in streaming and broadcasting applications, targeting in particular video content. The design of efficient error-control mechanisms, to enhance video transmission systems reliability, has been addressed considering cross-layer and multi-layer/multi-dimensional channel coding techniques to cope with bit errors as well as packet erasures. Mechanisms for unequal time interleaving have been designed as a viable solution to reduce the impact of errors and erasures by acting on the time diversity of the data flow, thus enhancing robustness against correlated channel impairments. In order to account for the nature of the factors which affect the physical layer channel in the evaluation of FEC schemes performances, an ad-hoc error-event modeling has been devised. In addition, the impact of error correction/protection techniques on the quality perceived by the consumers of video services applications and techniques for objective/subjective quality evaluation have been studied. The applicability and value of the proposed techniques have been tested by considering practical constraints and requirements of real system implementations.

Interactive Ray Tracing for Virtual TV Studio Applications

In the last years, the well known ray tracing algorithm gained new popularity with the introduction of interactive ray tracing methods. The high modularity and the ability to produce highly realistic images make ray tracing an attractive alternative to raster graphics hardware. Interactive ray tracing also proved its potential in the field of Mixed Reality rendering and provides novel methods for seamless integration of real and virtual content. Actor insertion methods, a subdomain of Mixed Reality and closely related to virtual television studio techniques, can use ray tracing for achieving high output quality in conjunction with appropriate visual cues like shadows and reflections at interactive frame rates. In this paper, we show how interactive ray tracing techniques can provide new ways of implementing virtual studio applications.

Interactive free viewpoint video streaming using prioritized network coding

In free viewpoint applications, the images are captured by an array of cameras that acquire a scene of interest from different perspectives. Any intermediate viewpoint not included in the camera array can be virtually synthesized by the decoder, at a quality that depends on the distance between the virtual view and the camera views available at decoder. Hence, it is beneficial for any user to receive camera views that are close to each other for synthesis. This is however not always feasible in bandwidth-limited overlay networks, where every node may ask for different camera views. In this work, we propose an optimized delivery strategy for free viewpoint streaming over overlay networks. We introduce the concept of layered quality-of-experience (QoE), which describes the level of interactivity offered to clients. Based on these levels of QoE, camera views are organized into layered subsets. These subsets are then delivered to clients through a prioritized network coding streaming scheme, which accommodates for the network and clients heterogeneity and effectively exploit the resources of the overlay network. Simulation results show that, in a scenario with limited bandwidth or channel reliability, the proposed method outperforms baseline network coding approaches, where the different levels of QoE are not taken into account in the delivery strategy optimization.

StreamCloud: An elastic and scalable data streaming system

Many applications in several domains such as telecommunications, network security, large scale sensor networks, require online processing of continuous data lows. They produce very high loads that requires aggregating the processing capacity of many nodes. Current Stream Processing Engines do not scale with the input load due to single-node bottlenecks. Additionally, they are based on static con?gurations that lead to either under or over-provisioning. In this paper, we present StreamCloud, a scalable and elastic stream processing engine for processing large data stream volumes. StreamCloud uses a novel parallelization technique that splits queries into subqueries that are allocated to independent sets of nodes in a way that minimizes the distribution overhead. Its elastic protocols exhibit low intrusiveness, enabling effective adjustment of resources to the incoming load. Elasticity is combined with dynamic load balancing to minimize the computational resources used. The paper presents the system design, implementation and a thorough evaluation of the scalability and elasticity of the fully implemented system.