A Kinect Based Immersive Video Conferencing System

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents a Kinect Based Immersive Video Conferencing System (KIVC), which aims at improving the quality of user experience (QoE) in the future video conferencing communication. In our KIVC system, we choose Kinect as the camera for capturing the videos, benefiting from the state-of-the-art computer vision toolbox integrated in Kinect. In addition, in order to improve QoE with the constraint on the limited bandwidth, we develop a framework for KIVC system. Then, in our KIVC system, several advanced key technologies are adopted, e.g., fast object-based video coding for real-time data, human-computer interaction, and blurring processing for attracting human visual attention. Extensive experimental results show that our KIVC system has excellent performance and achieves a reliable real-time processing results. As such, the QoE can be enhanced with plenty of user-customized applications by KIVC.

Original languageEnglish
Title of host publicationProceedings of 2015 IEEE 14th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2015
EditorsPhilip Chen, Lotfi A. Zadeh, Ning Ge, Yingxu Wang, Xiaoming Tao, Jianhua Lu, Newton Howard, Bo Zhang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages317-321
Number of pages5
ISBN (Electronic)9781467372893
DOIs
StatePublished - 11 Sep 2015
Event14th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2015 - Beijing, China
Duration: 6 Jul 20158 Jul 2015

Publication series

NameProceedings of 2015 IEEE 14th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2015

Conference

Conference14th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2015
Country/TerritoryChina
CityBeijing
Period6/07/158/07/15

Fingerprint

Dive into the research topics of 'A Kinect Based Immersive Video Conferencing System'. Together they form a unique fingerprint.

Cite this