Machine-learning-based perceptual video coding in wireless multimedia communications

Author(s):  
Shengxi Li ◽  
Mai Xu ◽  
Yufan Liu ◽  
Zhiguo Ding
2017 ◽  
Vol 77 (4) ◽  
pp. 4453-4475 ◽  
Author(s):  
Hong Yang ◽  
Linbo Qing ◽  
Xiaohai He ◽  
Xianfeng Ou ◽  
Xiaojuan Liu

2020 ◽  
Author(s):  
Md Jalil Piran

The stringent requirements of wireless multimedia<br>transmission lead to very high radio spectrum solicitation. Although the radio spectrum is considered as a scarce resource, the<br>issue with spectrum availability is not scarcity, but the inefficient<br>utilization. Unique characteristics of cognitive radio (CR) such<br>as flexibility, adaptability, and interoperability, particularly have<br>contributed to it being the optimum technological candidate to<br>alleviate the issue of spectrum scarcity for multimedia communications. However, multimedia communications over CR<br>networks (MCRNs) as a bandwidth-hungry, delay-sensitive, and<br>loss-tolerant service, exposes several severe challenges specially<br>to guarantee quality of service (QoS) and quality of experience<br>(QoE). As a result, to date, different schemes based on source and<br>channel coding, multicast, and distributed streaming, have been<br>examined to improve the QoS/QoE in MCRNs. In this paper,<br>we survey QoS/QoE provisioning schemes in MCRNs. We first<br>discuss the basic concepts of multimedia communication, CRNs,<br>QoS and QoE. Then, we present the advantages of utilizing CR<br>for multimedia services and outline the stringent QoS and QoE<br>requirements in MCRNs. Next, we classify the critical challenges<br>for QoS/QoE provisioning in MCRNs including spectrum sensing,<br>resource allocation management, network fluctuations management, latency management, and energy consumption management. Then, we survey the corresponding feasible solutions for<br>each challenge highlighting performance issues, strengths, and<br>weaknesses. Furthermore, we discuss several important open<br>research problems and provide some avenues for future research. <br>


Author(s):  
Diego Jesus Serrano-Carrasco ◽  
Antonio Jesus Diaz-Honrubia ◽  
Pedro Cuenca

AbstractWith the advent of smartphones and tablets, video traffic on the Internet has increased enormously. With this in mind, in 2013 the High Efficiency Video Coding (HEVC) standard was released with the aim of reducing the bit rate (at the same quality) by 50% with respect to its predecessor. However, new contents with greater resolutions and requirements appear every day, making it necessary to further reduce the bit rate. Perceptual video coding has recently been recognized as a promising approach to achieving high-performance video compression and eye tracking data can be used to create and verify these models. In this paper, we present a new algorithm for the bit rate reduction of screen recorded sequences based on the visual perception of videos. An eye tracking system is used during the recording to locate the fixation point of the viewer. Then, the area around that point is encoded with the base quantization parameter (QP) value, which increases when moving away from it. The results show that up to 31.3% of the bit rate may be saved when compared with the original HEVC-encoded sequence, without a significant impact on the perceived quality.


Sign in / Sign up

Export Citation Format

Share Document