Percorrer por autor "Marinheiro, Rui"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- A flexible monitor for assessing 3D video QoE in real-timePublication . João, Ricardo; Marinheiro, Rui; Assunção, Pedro; Cruz, LuisWith the evolution of 3D technology, 3D IPTV services may prove to be a common service widely distributed by operators. So it is important that they have the necessary means to easily and inexpensively monitor the Quality of Experience (QoE) of this new service. Deployment of 3D video QoE monitors anywhere in the network will enable operators to adapt their service and network infrastructure in order to guarantee a desired QoE level, e.g., in scenarios where 3D IPTV streaming is offered to users with multi-homed equipment and simultaneous access to the network by means of heterogeneous smartcells in the customer premises. This paper presents a prototype developed for monitoring 3D video QoE in multiple use-case scenarios. A novel aspect is that this monitor may inspect video using several inputs, allowing different coding standards and encapsulation schemes. It can either analyze offline captures or perform real-time monitoring, and operate either using a graphical user interface or in command line mode. The latter allows its integration in network embedded devices like smartcells. The prototype puts in practice a flexible architecture that allows easy integration of modules new QoE evaluation models.. To demonstrate the monitor applicability and validate its performance in a real use-case scenario, a video-plus-depth QoE assessment model was implemented and extensive tests were performed with real traffic data, using the ITU-T G.1050 recommendation to simulate network impairments. It has been demonstrated that inferred quality results have a very high correlation with the measured quality values
- Objective quality prediction model for lost frames in 3D video over TSPublication . Feitor, Bruno; Assunção, Pedro; Soares, João; Cruz, Luís; Marinheiro, RuiThis paper proposes an objective model to predict the quality of lost frames in 3D video streams. The model is based only on header information from three different packet-layer levels: Network Abstraction Layer (NAL), Packetised Elementary Streams (PES) and Transport Stream (TS). Transmission errors leading to undecodable TS packets are assumed to result in frame loss. The proposed method estimates the size of the lost frames, which is used as a model parameter to predict their objective quality measured as the Structural Similarity Index Metric (SSIM). The results show that SSIM of missing stereoscopic frames in 3D coded video can be predicted with Root Mean Square Error (RMSE) accuracy of about 0.1 and Pearson correlation coefficient of 0.8, taking the SSIM of uncorrupted frames as reference. It is concluded that the proposed model is capable of estimating the SSIM quite accurately using only the lost frames estimated sizes.