Maria Torres Vega

When does lower bitrate give higher quality in modern video services

Due to the difficulties on approximating the human perception with algorithms, increasing the users Quality of Experience (QoE) in modern video services is a challenging task. But more than that, prior to estimating QoE, it is important to know how different types of network impairments actually affect the video quality. This paper takes a closer look at the relation between the network quality of service (QoS) and the video QoE degradation. Using a sophisticated network emulation environment, we benchmark a range of video types and video quality levels under controlled network conditions. Our analysis shows that, along with a number of expected situations come also some counterintuitive QoS-to-QoE conditions. We discuss ways in which a better understanding of the mutual influence between networks and video streams could lead to more efficient utilization of the Internet.

End-to-end performance evaluation in high-speed wireless networks

When dealing with lossy networks, performance management through conventional Quality of Service (QoS) based methods becomes difficult and is often ineffective. We find, in fact, that in this case quality emerges as an end-to-end factor, for it is particularly sensitive to the end-user perception of the overall service. To better explore the value of assessing Quality of Experience (QoE) alongside QoS in high-speed, lossy networks, this paper investigates the case of video streaming services in Radio-over-Fiber (RoF) networks, a prominent example in which network performance is critically related to the application. By means of a pilot RoF test-environment, we study the sensitivity of QoE to the most critical network parameters for different test case scenarios. The outcome is a QoE-based method to assess networks performance, which allows to underpin the network criticalities and non-linear relationships between service and network planes.

Cognitive no-reference video quality assessment for mobile streaming services

The evaluation of mobile streaming services, particularly in terms of delivered Quality of Experience (QoE), entails the use of automated methods (which excludes subjective QoE) that can be executed in real-time (i.e. without delaying the streaming process). This calls for lightweight algorithms that provide accurate results under considerable constraints. Starting from a low complexity no-reference objective algorithm for still images, in this work we contribute a new version that not only works for videos but, is general enough to adjust to a diverse range of video types while not significantly increasing the computational complexity. To achieve the necessary level of flexibility and computational efficiency, our method relies merely on information available at the client side and is equipped with a lightweight Artificial Neural Network which makes the algorithm independent from type of network or video. Its resource efficiency and generality make our method fit to be used in mobile streaming services. To prove the viability of our approach, we show a high level of correlation with the well-known full-reference method SSIM.

An experimental survey of no-reference video quality assessment methods

Purpose The Video Quality Metric (VQM) is one of the most used objective methods to assess video quality, because of its high correlation with the human visual system (HVS). VQM is, however, not viable in real-time deployments such as mobile streaming, not only due to its high computational demands but also because, as a Full Reference (FR) metric, it requires both the original video and its impaired counterpart. In contrast, No Reference (NR) objective algorithms operate directly on the impaired video and are considerably faster but loose out in accuracy. The purpose of this paper is to study how differently NR metrics perform in the presence of network impairments. Design/methodology/approach The authors assess eight NR metrics, alongside a lightweight FR metric, using VQM as benchmark in a self-developed network-impaired video data set. This paper covers a range of methods, a diverse set of video types and encoding conditions and a variety of network impairment test-cases. Findings The authors show the extent by which packet loss affects different video types, correlating the accuracy of NR metrics to the FR benchmark. This paper helps identifying the conditions under which simple metrics may be used effectively and indicates an avenue to control the quality of streaming systems. Originality/value Most studies in literature have focused on assessing streams that are either unaffected by the network (e.g. looking at the effects of video compression algorithms) or are affected by synthetic network impairments (i.e. via simulated network conditions). The authors show that when streams are affected by real network conditions, assessing Quality of Experience becomes even harder, as the existing metrics perform poorly.

Cognitive streaming on android devices

As the number of mobile devices increases, so do the complexity of wireless networks and the users requirements. This tendency makes necessary for Multimedia Services to take the needed actions to adapt to the upcoming technology. A prominent example of this type of services is HTTP Adaptive Video Streaming Applications. In this research, we have studied how the latest HTTP Adaptive Streaming techniques, mainly developed for standard computers, could be adapted and used in mobile wireless devices. Furthermore, inspired by these solutions, which usually make use of Reinforcement Learning (RL) algorithms to find the suitable streaming rate, we have conceived a novel smart video player client in Java for Android platform using the Dynamic Adaptive Streaming over HTTP (DASH) protocol. We have assessed the performance of our proposed solution in a self-developed wireless test-bed under different network conditions. Thus, we have seen that by including in the reward function contributions regarding the download speed of the video segments, especially needed due to the fluctuating nature of the wireless networks, and the segments already buffered, improves drastically the overall performance of the video client. Besides that, we have discovered that, in a cognitive adaptive approach, bandwidth constraints affect the users experience more substantially, while impairments such as packet loss can be prevented.

Predictive no-reference assessment of video quality

Among the various means to evaluate the quality of video streams, light-weight No-Reference (NR) methods have low computation and may be executed on thin clients. Thus, these methods would be perfect candidates in cases of real-time quality assessment, automated quality control and in adaptive mobile streaming. Yet, existing real-time, NR approaches are not typically designed to tackle network distorted streams, thus performing poorly when compared to Full-Reference (FR) algorithms. In this work, we present a generic NR method whereby machine learning (ML) may be used to construct a quality metric trained on simplistic NR metrics. Testing our method on nine, representative ML algorithms allows us to show the generality of our approach, whilst finding the best-performing algorithms. We use an extensive video dataset (960 video samples), generated under a variety of lossy network conditions, thus verifying that our NR metric remains accurate under realistic streaming scenarios. In this way, we achieve a quality index that is comparably as computationally efficient as typical NR metrics and as accurate as the FR algorithm Video Quality Metric (97% correlation). A generic NR method for real-time quality assessment of streaming video is proposed.It uses supervised learning techniques for achieving high accuracy and adaptivity.It is evaluated in a broad set of videos streamed over lossy networks.To prove its generality, nine representative supervised learning models are employed.Our method obtains a 97% correlation to the Video Quality Metric.

Accuracy of No-Reference Quality Metrics in Network-impaired Video Streams

The Video Quality Metric (VQM) is nowadays one of the most used objective methods to assess video quality, thanks to its high correlation with both the human visual system (HVS) and subjective methods. VQM is, however, not viable in real-time deployments such as mobile streaming, not only due to its high computational demands but, specifically, because it is a Full-Reference (FR) metric, which requires as input both the original video and its impaired counterpart. On the other hand, No-Reference (NR) objective algorithms operate directly on the impaired video and are considerably faster, but loose out when it comes to accuracy. In this research, we assess a range of NR metrics, alongside a lightweight FR metric, using VQM as benchmark. Our study covers a range of methods, a diverse set of video types and encoding conditions, and a range of network impairment test-cases. We show the extent by which packet loss affects different video types, correlating the accuracy of NR metrics to the FR benchmark. Our study helps identifying the conditions under which simple metrics may be used effectively and indicates an avenue to control the quality of streaming systems in line with human perception.

Redundancy Reduction in Wireless Sensor Networks via Centrality Metrics

The advances in wireless communications, together with the need of sensing and controlling various nature or human made systems in a large number of points (e.g. smart traffic control, environmental monitoring), lead to the emergence of Wireless Sensor Networks (WSN) as a powerful tool to fulfill the above requirements. Due to the large amount of wireless devices needed and cost constraints, such networks are usually made by low-cost devices with limited energy and computational capabilities, these further on being subject to easy communication or hardware fails. At the same time, the deployment of such devices in harsh environments (e.g. in the ocean) may lead to uncontrollable redundant topologies which have to be often refined during the exploitation phase of these networks in an automated manner. In the scope of these arguments, in this paper, we take advantage of the latest theoretical advances in complex networks and we propose an automated solution to refine the topology of WSNs by using centrality metrics to detect the redundant nodes and links in a network, and further on to shut down them safely. Our solution may work in both ways, centralized or decentralized, by choosing a centralized or a decentralized centrality metric, this choice being driven by the application goal. The experiments performed on a wide variety of network topologies with different sizes (e.g. number of nodes and links), using different centrality metrics, validate our approach and recommend it as a solution for the automatic control of WSNs topologies during the exploitation phase of such networks to optimize, for instance, their life time.

Unsupervised deep learning for real-time assessment of video streaming services

Evaluating quality of experience in video streaming services requires a quality metric that works in real time and for a broad range of video types and network conditions. This means that, subjective video quality assessment studies, or complex objective video quality assessment metrics, which would be best suited from the accuracy perspective, cannot be used for this tasks (due to their high requirements in terms of time and complexity, in addition to their lack of scalability). In this paper we propose a light-weight No Reference (NR) method that, by means of unsupervised machine learning techniques and measurements on the client side is able to assess quality in real-time, accurately and in an adaptable and scalable manner. Our method makes use of the excellent density estimation capabilities of the unsupervised deep learning techniques, the restricted Boltzmann machines, and light-weight video features computed just on the impaired video to provide a delta of quality degradation. We have tested our approach in two network impaired video sets, the LIMP and the ReTRiEVED video quality databases, benchmarking the results of our method against the well-known full reference metric VQM. We have obtained levels of accuracy of at least 85% in both datasets using all possible cases.

Resilience of Video Streaming Services to Network Impairments

When dealing with networks, performance management through conventional quality of service (QoS)-based methods becomes difficult and is often ineffective. In fact, quality emerges as an end-to-end factor, for it is particularly sensitive to the end-user perception of the overall service, i.e., the user’s quality of experience (QoE). However, the two are not independent from each other and their relationship has to be studied through metrics that go beyond the typical network parameters. To better explore the value of assessing QoE alongside QoS in high-speed, lossy networks, this paper presents an experimental methodology to understand the relation between network QoS onto service QoE, with the aim to perform a combined network-service assessment. Using video streaming services as the test-case (given their extended usage nowadays), in this paper, we provide studies on three network-impaired video-sets with the aim to provide a comprehensive evaluation of the effects of networks on video quality. First, the ReTRIeVED video set provides the means to understand the most impairing effects on networks. Furthermore, it triggered the idea to create our own sets, specialized in the most impairing conditions for 2-D and 3-D: the LIMP Video Quality Database and the 3-D-HEVC-Net Video Quality Database. Our study and methodology are meant to provide service providers with the means to pinpoint the working boundaries of their video-sets in face of different network conditions. At the same time, network operators may use our findings to predict how network control policies affect the user’s perception of the service.