scholarly journals 4K Real Time Software Solution of Scalable HEVC for Broadcast Video Application

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 46748-46762 ◽  
Author(s):  
Ronan Parois ◽  
Wassim Hamidouche ◽  
Pierre-Loup Cabarat ◽  
Mickael Raulet ◽  
Naty Sidaty ◽  
...  
Author(s):  
J. I. A. Y. Yaqoob ◽  
W. L. Pang ◽  
S. K. Wong ◽  
K. Y. Chan

Nowadays, mobile communication is growing rapidly and become an everyday commodity. The vast deployment of real-time services in Long Term Evolution (LTE) network demands for the scheduling techniques that support the Quality of Service (QoS) requirements. LTE is designed and implemented to fulfill the users’ QoS. However, 3GPP does not define the specific scheduling technique for resource distribution which leads to vast research and development of the scheduling techniques. In this context, a review of the recent scheduling algorithm is reported in the literature. These schedulers in the literature cause high Packet Loss Rate (PLR), low fairness, and high delay. To cope with these disadvantages, we propose an enhanced EXPRULE (eEXPRULE) scheduler to improve the radio resource utilization in the LTE network. Extensive simulation works are carried out and the proposed scheduler provides a significant performance improvement for video application without sacrificing the VoIP performance. The eEXPRULE scheduler increases video throughput, spectrum efficiency, and fairness by 50%, 13%, and 11%, respectively, and reduces the video PLR by 11%.


2021 ◽  
Vol 6 (1) ◽  
pp. 1-4
Author(s):  
Pascale Walters ◽  
David Clausi ◽  
Alexander Wong ◽  
Mehrnaz Fani

A critical step for computer vision-driven hockey ice rink localization from broadcast video is the automatic segmentation of lines on the rink. While the leveraging of segmentation methods for sports field localization has been previously explored, the design of deep neural networks for segmenting ice rink lines has not been well studied. Furthermore, the exploration of efficient architecture designs is very important given the operational requirements of real-time sports analytics. Motivated by this, BenderNet and RingerNet, two highly efficient deep neural network architectures, have been designed specifically for ice rink line segmentation. Experiments on a dataset of annotated NHL broadcast video demonstrate high accuracy while maintaining high model efficiency, thus making the proposed methods well-suited for real-time ice hockey rink localization.


Sign in / Sign up

Export Citation Format

Share Document