Distributed multi-hypothesis coding of depth maps using texture motion information and optical flow
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Distributed multi-hypothesis coding of depth maps using texture motion information and optical flow. / Salmistraro, Matteo; Zamarin, Marco; Raket, Lars Lau; Forchhammer, Søren.
2013 IEEE International Conference on Acoustics, Speech and Signal Processing: proceedings. IEEE, 2013. p. 1685-1689.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Distributed multi-hypothesis coding of depth maps using texture motion information and optical flow
AU - Salmistraro, Matteo
AU - Zamarin, Marco
AU - Raket, Lars Lau
AU - Forchhammer, Søren
PY - 2013
Y1 - 2013
N2 - Distributed Video Coding (DVC) is a video coding paradigm allowing a shift of complexity from the encoder to the de- coder. Depth maps are images enabling the calculation of the distance of an object from the camera, which can be used in multiview coding in order to generate virtual views, but also in single view coding for motion detection or image segmen- tation. In this work, we address the problem of depth map video DVC encoding in a single-view scenario. We exploit the motion of the corresponding texture video which is highly correlated with the depth maps. In order to extract the motion information, a block-based and an optical flow-based meth- ods are employed. Finally we fuse the proposed Side Informations using a multi-hypothesis DVC decoder, which allows us to exploit the strengths of all the proposed methods at the same time.
AB - Distributed Video Coding (DVC) is a video coding paradigm allowing a shift of complexity from the encoder to the de- coder. Depth maps are images enabling the calculation of the distance of an object from the camera, which can be used in multiview coding in order to generate virtual views, but also in single view coding for motion detection or image segmen- tation. In this work, we address the problem of depth map video DVC encoding in a single-view scenario. We exploit the motion of the corresponding texture video which is highly correlated with the depth maps. In order to extract the motion information, a block-based and an optical flow-based meth- ods are employed. Finally we fuse the proposed Side Informations using a multi-hypothesis DVC decoder, which allows us to exploit the strengths of all the proposed methods at the same time.
U2 - 10.1109/ICASSP.2013.6637939
DO - 10.1109/ICASSP.2013.6637939
M3 - Article in proceedings
SN - 978-1-4799-0356-6
SP - 1685
EP - 1689
BT - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
PB - IEEE
Y2 - 26 May 2013 through 31 May 2013
ER -
ID: 44837737