Department of Computer Science Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram 522 302, India.
Department of Computing Science and Engineering, B.S.A. Crescent Institute of Science and Technology, Vandalur, Chennai 600 048, India.
Sensors (Basel). 2022 Nov 29;22(23):9307. doi: 10.3390/s22239307.
Recently, there has been an increase in research interest in the seamless streaming of video on top of Hypertext Transfer Protocol (HTTP) in cellular networks (3G/4G). The main challenges involved are the variation in available bit rates on the Internet caused by resource sharing and the dynamic nature of wireless communication channels. State-of-the-art techniques, such as Dynamic Adaptive Streaming over HTTP (DASH), support the streaming of stored video, but they suffer from the challenge of live video content due to fluctuating bit rate in the network. In this work, a novel dynamic bit rate analysis technique is proposed to model client-server architecture using attention-based long short-term memory (A-LSTM) networks for solving the problem of smooth video streaming over HTTP networks. The proposed client system analyzes the bit rate dynamically, and a status report is sent to the server to adjust the ongoing session parameter. The server assesses the dynamics of the bit rate on the fly and calculates the status for each video sequence. The bit rate and buffer length are given as sequential inputs to LSTM to produce feature vectors. These feature vectors are given different weights to produce updated feature vectors. These updated feature vectors are given to multi-layer feed forward neural networks to predict six output class labels (144p, 240p, 360p, 480p, 720p, and 1080p). Finally, the proposed A-LSTM work is evaluated in real-time using a code division multiple access evolution-data optimized network (CDMA20001xEVDO Rev-A) with the help of an Internet dongle. Furthermore, the performance is analyzed with the full reference quality metric of streaming video to validate our proposed work. Experimental results also show an average improvement of 37.53% in peak signal-to-noise ratio (PSNR) and 5.7% in structural similarity (SSIM) index over the commonly used buffer-filling technique during the live streaming of video.
最近，人们对在蜂窝网络（3G/4G）上通过超文本传输协议（HTTP）进行无缝视频流的研究产生了浓厚的兴趣。所涉及的主要挑战是由于资源共享和无线通信信道的动态特性，导致互联网上可用比特率的变化。最先进的技术，如通过 HTTP 的动态自适应流（DASH），支持存储视频的流传输，但由于网络中比特率的波动，它们在实时视频内容方面存在挑战。在这项工作中，提出了一种新的动态比特率分析技术，使用基于注意力的长短时记忆网络（A-LSTM）来模拟客户端-服务器架构，以解决通过 HTTP 网络进行平滑视频流传输的问题。所提出的客户端系统动态地分析比特率，并向服务器发送状态报告以调整正在进行的会话参数。服务器实时评估比特率的动态，并计算每个视频序列的状态。将比特率和缓冲区长度作为顺序输入提供给 LSTM 以生成特征向量。这些特征向量被赋予不同的权重以生成更新的特征向量。这些更新的特征向量被提供给多层前馈神经网络以预测六个输出类标签（144p、240p、360p、480p、720p 和 1080p）。最后，在互联网加密狗的帮助下，使用码分多址演进数据优化网络（CDMA20001xEVDO Rev-A）实时评估所提出的 A-LSTM 工作。此外，还使用流媒体视频的全参考质量指标来分析性能，以验证我们提出的工作。实验结果还表明，在实时视频流传输过程中，与常用的缓冲区填充技术相比，峰值信噪比（PSNR）平均提高了 37.53%，结构相似性（SSIM）指数提高了 5.7%。
