Detail publikace

CUDA Accelerated Real-time Digital Image Stabilization in a Video Stream

PACURA, D. DRAHANSKÝ, M.

Originální název

CUDA Accelerated Real-time Digital Image Stabilization in a Video Stream

Typ

článek v časopise ve Scopus, Jsc

Jazyk

angličtina

Originální abstrakt

The most important step for successful video processing in computer vision is its stabilization. Often, it is required to process high resolution video in a real-time. In this paper, a  new method for a  real-time digital image stabilization in a  video stream is presented. This method preserves the intended camera motion and exploits computing power of GPGPU by utilizing CUDA programing interface. In order to reduce required computation power, local search windows are used for the correspondence search of consecutive video frames. These windows are further processed using Local Binary Patterns, which enables fast correlation using bitwise XOR. The experiments on video sequences from both car-mounted and hand-held camera have demonstrated the effectiveness of this method. The speed of stabilization designates this method for video preprocessing in real-time applications.

Klíčová slova

digital image stabilization, CUDA, real-time video stabilization

Autoři

PACURA, D.; DRAHANSKÝ, M.

Vydáno

27. 6. 2016

ISSN

1738-9984

Periodikum

International Journal of Software Engineering and Its Applications

Ročník

10

Číslo

6

Stát

Korejská republika

Strany od

113

Strany do

124

Strany počet

12

URL

BibTex

@article{BUT130986,
  author="Dávid {Pacura} and Martin {Drahanský}",
  title="CUDA Accelerated Real-time Digital Image Stabilization in a Video Stream",
  journal="International Journal of  Software Engineering and Its Applications",
  year="2016",
  volume="10",
  number="6",
  pages="113--124",
  doi="10.14257/ijseia.2016.10.6.10",
  issn="1738-9984",
  url="http://www.sersc.org/journals/IJSEIA/vol10_no6_2016/10.pdf"
}