Now showing 1 - 5 of 13
- ItemOverall Quality Prediction for HTTP Adaptive Streaming Using LSTM Network(2021-08) Tran T. T. Huyen; Nguyen V. Duc; Pham Ngoc Nam; Truong Cong ThangHTTP Adaptive Streaming has become a popular solution for multimedia delivery nowadays. However, due to network bandwidth fluctuations, video quality strongly varies during streaming. Therefore, a key challenge in HTTP Adaptive Streaming is how to evaluate the overall quality of a streaming session. In this article, a machine learning approach is proposed for overall quality prediction, where each segment in a streaming session is represented by a set of features. Two options of the feature set are investigated. In the first option, we use four features, namely segment quality, content characteristics, stalling duration, and padding. The second option consists of three features, namely bitstream-level parameters, stalling duration, and padding. The features are fed into a Long Short Term Memory (LSTM) network that is capable of exploring temporal relations between impairment events of quality variations and stalling events. The overall quality is predicted from the outputs of the LSTM network using a linear regression module. Through experimental results, it is shown that the proposed approach achieves a high prediction performance and outperforms seven existing approaches. Especially, the second option is found to be both efficient and effective. The source code of the proposed approach has been made available to the public.
- ItemQoE Models for Adaptive Streaming: A Comprehensive Evaluation(2022-05-13) Nguyen Duc; Pham Ngoc Nam; Truong Cong ThangAdaptive streaming has become a key technology for various multimedia services, such as online learning, mobile streaming, Internet TV, etc. However, because of throughput fluctuations, video quality may be dramatically varying during a streaming session. In addition, stalling events may occur when segments do not reach the user device before their playback deadlines. It is well-known that quality variations and stalling events cause negative impacts on Quality of Experience (QoE). Therefore, a main challenge in adaptive streaming is how to evaluate the QoE of streaming sessions taking into account the influences of these factors. Thus far, many models have been proposed to tackle this issue. In addition, a lot of QoE databases have been publicly available. However, there have been no extensive evaluations of existing models using various databases. To fill this gap, in this study, we conduct an extensive evaluation of thirteen models on twelve databases with different characteristics of viewing devices, codecs, and session durations. Through experiment results, important findings are provided with regard to QoE prediction of streaming sessions. In addition, some suggestions on the effective employment of QoE models are presented. The findings and suggestions are expected to be useful for researchers and service providers to make QoE assessments and improvements of streaming solutions in adaptive streaming.
- ItemQoE-Aware Video Streaming over HTTP and Software Defined Networking(2019) Pham, Hong Thinh; Nguyen, Thanh Dat; Pham, Ngoc Nam; Nguyen, Huu Thanh; Truong, Thu HuongDue to the increase in video streaming traffic over the Internet, more innovative methods are in demand for improving both the Quality of Experience (QoE) of users and the Quality of Service (QoS) of providers. In recent years, HTTP Adaptive Streaming (HAS) has received significant attention from both industry and academia based on its impacts in the enhancement of media streaming services. However, HAS-alone cannot guarantee a seamless viewing experience, since this highly relies on the Network Operators’ infrastructure and evolving network conditions. Along with the development of future Internet infrastructure, SoftwareDefined Networking (SDN) has been researched and newly implemented as a promising solution in improving the services of different Internet layers. In order to enhance the quality of video delivery, we try to combine the above two technologies, which has not been well-studied in academia. In this paper, we present a novel architecture incorporating bitrate adaptation and dynamic route allocation. At the client side, the adaptation logic of VBR videos streaming is built based on the MPEG-DASH standard. On the network side, an SDN controller is implemented with several routing strategies on top of the OpenFlow protocol. Our experimental results show that the proposed solution enhances at least 38% up to 185% in terms of average bitrate in comparison with some existing solutions as well as achieves a smoother viewing experience than the traditional Internet.
- ItemAn LSTM-based Approach for Overall Quality Prediction in HTTP Adaptive Streaming(2019-04) Huyen Tran; Duc Nguyen; Nam Pham; Thang Truong; Duong NguyenHTTP Adaptive Streaming (HAS) has become a popular solution for multimedia delivery nowadays. In HAS, video quality is generally varying in each streaming session. Therefore, a key question in HTTP Adaptive Streaming is how to evaluate the overall quality of a streaming session. In this paper, we propose a machine-learning approach for overall quality prediction in HTTP Adaptive Streaming. In the proposed approach, each segment is represented by four features segment quality, stalling durations, content characteristics, and padding. The features are fed into a Long Short-Term Memory (LSTM) network that is capable of exploring temporal relations between segments. The overall quality of the streaming session is predicted from the outputs of the LSTM network using a linear regression module. Experiment results show that the proposed approach is effective in predicting the overall quality of streaming sessions. Also, it is found that our proposed approach outperforms four existing approaches.
- ItemA Quantitative Analysis of the Effect of Human Detection and Segmentation Quality in Person Re-identification Performance(2019) Binh Nguyen; Quan Nguyen; Lan Le; Thuy Pham; Nam PhamPerson re-identification, a problem of person identity association across camera views at different locations and times, is the second step in two-steps system for automatic video surveillance: person detection, tracking and person reidentification. However, most of the reported person Re-ID methods deal with the human regions of interest (ROIs) which are extracted manually with well-aligned bounding boxes. They mainly focus on designing discriminative feature descriptors and relevant metric learning on these manually-cropped human ROIs. This paper aims to answer two questions: (1) Do human detection and segmentation affect the performance of person reidentification?; (2) How to overcome the effect of human detection and segmentation with the state-of-the-art method for person re-identification? To answer these two questions, quantitative evaluations have been performed for both single-shot and multishot scenarios of person re-identification. Different state-of-the-art methods for human detection and segmentation have been evaluated on two benchmark datasets (VIPeR and PRID2011). The obtained results allow us to give some suggestions for developing fully automatic video surveillance systems.