TY - JOUR
T1 - A collaborative client participant fusion system for realistic remote conferences
AU - Song, Wei
AU - Wen, Mingyun
AU - Xi, Yulong
AU - Chu, Phuong Minh
AU - Vu, Hoang
AU - Kayumiy, Shokh Jakhon
AU - Cho, Kyungeun
N1 - Publisher Copyright:
© 2015, Springer Science+Business Media New York.
PY - 2016/7/1
Y1 - 2016/7/1
N2 - Remote conferencing systems provide a shared environment where people in different locations can communicate and collaborate in real time. Currently, remote video conferencing systems present separate video images of the individual participants. To achieve a more realistic conference experience, we enhance video conferencing by integrating the remote images into a shared virtual environment. This paper proposes a collaborative client participant fusion system using a real-time foreground segmentation method. In each client system, the foreground pixels are extracted from the participant images using a feedback background modeling method. Because the segmentation results often contain noise and holes caused by adverse environmental lighting conditions and substandard camera resolution, a Markov Random Field model is applied in the morphological operations of dilation and erosion. This foreground segmentation refining process is implemented using graphics processing unit programming, to facilitate real-time image processing. Subsequently, segmented foreground pixels are transmitted to a server, which fuses the remote images of the participants into a shared virtual environment. The fused conference scene is represented by a realistic holographic projection.
AB - Remote conferencing systems provide a shared environment where people in different locations can communicate and collaborate in real time. Currently, remote video conferencing systems present separate video images of the individual participants. To achieve a more realistic conference experience, we enhance video conferencing by integrating the remote images into a shared virtual environment. This paper proposes a collaborative client participant fusion system using a real-time foreground segmentation method. In each client system, the foreground pixels are extracted from the participant images using a feedback background modeling method. Because the segmentation results often contain noise and holes caused by adverse environmental lighting conditions and substandard camera resolution, a Markov Random Field model is applied in the morphological operations of dilation and erosion. This foreground segmentation refining process is implemented using graphics processing unit programming, to facilitate real-time image processing. Subsequently, segmented foreground pixels are transmitted to a server, which fuses the remote images of the participants into a shared virtual environment. The fused conference scene is represented by a realistic holographic projection.
KW - Foreground segmentation
KW - GPU
KW - Human-centric communication
KW - Mixed reality
KW - Remote conferencing systems
UR - http://www.scopus.com/inward/record.url?scp=84948679227&partnerID=8YFLogxK
U2 - 10.1007/s11227-015-1580-z
DO - 10.1007/s11227-015-1580-z
M3 - Article
AN - SCOPUS:84948679227
SN - 0920-8542
VL - 72
SP - 2720
EP - 2733
JO - Journal of Supercomputing
JF - Journal of Supercomputing
IS - 7
ER -