Skip to main navigation Skip to search Skip to main content

Cloud rendering learning platform technology research for visual analysis of large scale 3D multimedia data

  • Ronghe Wang
  • , Bo Zhang*
  • , Jianning Bi
  • , Xinhai Zhang
  • , Xiaolei Guo
  • , Dong Jiao
  • , Jianghua Lv
  • , Shilong Ma
  • *Corresponding author for this work
  • China Academy of Electronics and Information Technology
  • Beihang University

Research output: Contribution to journalArticlepeer-review

Abstract

This paper designs and implements a cloud rendering system. The system supports application of server cluster load balancing, static extension of rendering machine, and design architecture of parallel task scheduling. At the same time, we put forward a new design idea, and we implement a set of communication rules of multi-task renderer and cloud rendering system. On the system, users could browse 3D scene online by mobile terminal equipments. The task of PC terminal users and mobile terminal users to access remote scenes could be high speed and real-time rendering by this system. In the end of this paper, we analyze the efficiency of our algorithm. Our system can achieve a better effect on the number of concurrent users and the average response delay. The average frame rate of system can reach 30–40 frames per second. Experimental results show that the proposed algorithm performs favorably against the state-of-the-art methods on the public test datasets.

Original languageEnglish
Pages (from-to)5371-5398
Number of pages28
JournalMultimedia Tools and Applications
Volume79
Issue number7-8
DOIs
StatePublished - 1 Feb 2020

Keywords

  • 3D scene
  • Big data
  • Cloud rendering
  • Machine learning
  • Mobile internet

Fingerprint

Dive into the research topics of 'Cloud rendering learning platform technology research for visual analysis of large scale 3D multimedia data'. Together they form a unique fingerprint.

Cite this