Publication detail

Real-Time Line Detection Using Accelerated High-Resolution Hough Transform

JOŠTH, R. JURÁNKOVÁ, M. HEROUT, A. HAVEL, J.

Original Title

Real-Time Line Detection Using Accelerated High-Resolution Hough Transform

English Title

Real-Time Line Detection Using Accelerated High-Resolution Hough Transform

Type

conference paper

Language

en

Original Abstract

Hough transform is a well-known and popular algorithm for detecting lines in raster images.  The standard Hough transform is rather slow to be usable in real-time, so different accelerated and approximated algorithms exist. This paper proposes a modified accumulation scheme for the Hough transform, which makes it suitable for computer systems with small but fast read-write memory -- such as the today's GPUs.  The proposed algorithm is evaluated both on synthetic binary images and on complex real-world photos of high resolutions.  The results show that using today's commodity graphics chips, the Hough transform can be computed at interactive frame rates even with high resolution of the Hough space and with the Hough transform fully computed.

English abstract

Hough transform is a well-known and popular algorithm for detecting lines in raster images.  The standard Hough transform is rather slow to be usable in real-time, so different accelerated and approximated algorithms exist. This paper proposes a modified accumulation scheme for the Hough transform, which makes it suitable for computer systems with small but fast read-write memory -- such as the today's GPUs.  The proposed algorithm is evaluated both on synthetic binary images and on complex real-world photos of high resolutions.  The results show that using today's commodity graphics chips, the Hough transform can be computed at interactive frame rates even with high resolution of the Hough space and with the Hough transform fully computed.

Keywords

Line Detection, Hough-Transform, Real-Time, GPU, CUDA

RIV year

2011

Released

27.05.2011

Publisher

Springer Verlag

Location

Ystad

ISBN

978-3-642-21226-0

Book

Proceedings of SCIA 2011, LNCS

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

784

Pages to

793

Pages count

9

Documents

BibTex


@inproceedings{BUT76263,
  author="Radovan {Jošth} and Markéta {Juránková} and Adam {Herout} and Jiří {Havel}",
  title="Real-Time Line Detection Using Accelerated High-Resolution Hough Transform",
  annote="Hough transform is a well-known and popular algorithm for detecting lines in
raster images.  The standard Hough transform is rather slow to be usable in
real-time, so different accelerated and approximated algorithms exist.
This paper proposes a modified accumulation scheme for the Hough transform, which
makes it suitable for computer systems with small but fast read-write memory --
such as the today's GPUs.  The proposed algorithm is evaluated both on synthetic
binary images and on complex real-world photos of high resolutions.  The results
show that using today's commodity graphics chips, the Hough transform can be
computed at interactive frame rates even with high resolution of the Hough space
and with the Hough transform fully computed.",
  address="Springer Verlag",
  booktitle="Proceedings of SCIA 2011, LNCS",
  chapter="76263",
  edition="NEUVEDEN",
  howpublished="print",
  institution="Springer Verlag",
  year="2011",
  month="may",
  pages="784--793",
  publisher="Springer Verlag",
  type="conference paper"
}