Accelerating wavelet-based video coding on graphics hardware using CUDA

W.J. Laan, van der; J.B.T.M. Roerdink; A.C. Jalba

Accelerating wavelet-based video coding on graphics hardware using CUDA

W.J. Laan, van der, J.B.T.M. Roerdink, A.C. Jalba

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

13 Citations (Scopus)

1 Downloads (Pure)

Abstract

The DiscreteWavelet Transform (DWT) has a wide range of applications from signal processing to video and image compression. This transform, by means of the lifting scheme, can be performed in a memory and computation efficient way on modern, programmable GPUs, which can be regarded as massively parallel co-processors through NVidia’s CUDA compute paradigm. The method is scalable and the fastest GPU implementation among the methods considered. We have integrated our DWT into the Dirac Wavelet Video Codec (DWVC), of which the overlapped block motion compensation compensation and frame arithmetic have been accelerated using CUDA as well.

Original language	English
Title of host publication	Proceedings 6th International Symposium on Image and Signal Processing and Analysis (ISPA 2009, Salzburg, Austria, September 16-18, 2009)
Editors	P. Zinterhof, S. Loncaric, A. Uhl, A. Carini
Pages	608-613
Publication status	Published - 2009

Cite this

@inproceedings{020af19a29a046e990cf6e04c544262b,

title = "Accelerating wavelet-based video coding on graphics hardware using CUDA",

abstract = "The DiscreteWavelet Transform (DWT) has a wide range of applications from signal processing to video and image compression. This transform, by means of the lifting scheme, can be performed in a memory and computation efficient way on modern, programmable GPUs, which can be regarded as massively parallel co-processors through NVidia{\textquoteright}s CUDA compute paradigm. The method is scalable and the fastest GPU implementation among the methods considered. We have integrated our DWT into the Dirac Wavelet Video Codec (DWVC), of which the overlapped block motion compensation compensation and frame arithmetic have been accelerated using CUDA as well.",

author = "{Laan, van der}, W.J. and J.B.T.M. Roerdink and A.C. Jalba",

year = "2009",

language = "English",

isbn = "978-953-184-135-1",

pages = "608--613",

editor = "P. Zinterhof and S. Loncaric and A. Uhl and A. Carini",

booktitle = "Proceedings 6th International Symposium on Image and Signal Processing and Analysis (ISPA 2009, Salzburg, Austria, September 16-18, 2009)",

}

Accelerating wavelet-based video coding on graphics hardware using CUDA. / Laan, van der, W.J.; Roerdink, J.B.T.M.; Jalba, A.C.

Proceedings 6th International Symposium on Image and Signal Processing and Analysis (ISPA 2009, Salzburg, Austria, September 16-18, 2009). ed. / P. Zinterhof; S. Loncaric; A. Uhl; A. Carini. 2009. p. 608-613.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Accelerating wavelet-based video coding on graphics hardware using CUDA

AU - Laan, van der, W.J.

AU - Roerdink, J.B.T.M.

AU - Jalba, A.C.

PY - 2009

Y1 - 2009

N2 - The DiscreteWavelet Transform (DWT) has a wide range of applications from signal processing to video and image compression. This transform, by means of the lifting scheme, can be performed in a memory and computation efficient way on modern, programmable GPUs, which can be regarded as massively parallel co-processors through NVidia’s CUDA compute paradigm. The method is scalable and the fastest GPU implementation among the methods considered. We have integrated our DWT into the Dirac Wavelet Video Codec (DWVC), of which the overlapped block motion compensation compensation and frame arithmetic have been accelerated using CUDA as well.

AB - The DiscreteWavelet Transform (DWT) has a wide range of applications from signal processing to video and image compression. This transform, by means of the lifting scheme, can be performed in a memory and computation efficient way on modern, programmable GPUs, which can be regarded as massively parallel co-processors through NVidia’s CUDA compute paradigm. The method is scalable and the fastest GPU implementation among the methods considered. We have integrated our DWT into the Dirac Wavelet Video Codec (DWVC), of which the overlapped block motion compensation compensation and frame arithmetic have been accelerated using CUDA as well.

M3 - Conference contribution

SN - 978-953-184-135-1

SP - 608

EP - 613

BT - Proceedings 6th International Symposium on Image and Signal Processing and Analysis (ISPA 2009, Salzburg, Austria, September 16-18, 2009)

A2 - Zinterhof, P.

A2 - Loncaric, S.

A2 - Uhl, A.

A2 - Carini, A.

ER -

Accelerating wavelet-based video coding on graphics hardware using CUDA

Abstract

Fingerprint

Cite this