TCP-Oriented Raptor Coding for High-Frame-Rate Video Transmission Over Wireless Networks

• Published in: IEEE journal on selected areas in communications Vol. 34; no. 8; pp. 2231 - 2246
• Main Authors: Wu, Jiyan, Yuen, Chau, Wang, Ming, Chen, Junliang, Chen, Chang Wen
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Coding; Digital video; Distortion; Encoding; Forward error correction; High-frame-rate video; Mathematical models; raptor codes; Real time; Real-time systems; Streaming media; TCP; TCP (protocol); unequal error protection; Video communication; Video transmission; Wireless networks; wireless video transmission
• ISSN: 0733-8716; 1558-0008
• DOI: 10.1109/JSAC.2016.2577178

High-frame-rate (HFR) video technology is becoming widely implemented in popular multimedia applications (e.g., Youtube and cloud gaming) to provide a smooth viewing experience, while transmission control protocol (TCP) is pervasively adopted as the transport-layer solution for video communications to achieve firewall traversal and network friendliness. However, it is severely challenging to effectively deliver real-time HFR video over TCP: 1) HFR video streaming features high transmission rate, enhanced frame density, and stringent delay constraint and 2) the packet retransmission and congestion control mechanisms in TCP may cause frequent throughput fluctuations and deadline violations. Motivated by addressing these critical issues, this research presents an application-layer forward error correction (FEC) framework dubbed Raptor coded HFR video over TCP (ROCHET). First, we develop a mathematical model to analyze the frame-level distortion of systematic Raptor code-based HFR video communication over TCP in wireless networks. Second, we propose a joint approximate distortion estimation and Raptor coding adaption solution to minimize the sum of total distortion. The proposed ROCHET is able to effectively leverage unequal error protection and TCP state analysis to enhance streaming video quality. We conduct the performance evaluation through extensive emulations in Exata involving real-time HFR video encoded with H.264 codec. Compared with the existing FEC coding schemes, ROCHET achieves appreciable improvements in terms of video peak signal-to-noise ratio, goodput, and frame success rate. Thus, ROCHET is recommended for TCP-based HFR video transmission over wireless networks.