Publication detail

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

PACURA, D. DRAHANSKÝ, M.

Original Title

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

Type

journal article in Scopus

Language

English

Original Abstract

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.

Keywords

digital image stabilization, CUDA, real-time video stabilization

Authors

PACURA, D.; DRAHANSKÝ, M.

Released

27. 6. 2016

ISBN

1738-9984

Periodical

International Journal of Software Engineering and Its Applications

Year of study

10

Number

6

State

Republic of Korea

Pages from

113

Pages to

124

Pages count

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"
}