Conference paper

JOŠTH Radovan, DUBSKÁ Markéta, HEROUT Adam and HAVEL Jiří. Real-Time Line Detection Using Accelerated High-Resolution Hough Transform. In: Proceedings of SCIA 2011, LNCS. Ystad: Springer Verlag, 2011, pp. 784-793. ISBN 978-3-642-21226-0.
Publication language:english
Original title:Real-Time Line Detection Using Accelerated High-Resolution Hough Transform
Title (cs):Detekce čar v reálném čase pomocí akcelerované Houghovy transformace
Pages:784-793
Proceedings:Proceedings of SCIA 2011, LNCS
Conference:Scandinavian Conference on Image Analysis
Place:Ystad, SE
Year:2011
ISBN:978-3-642-21226-0
Publisher:Springer Verlag
Keywords
Line Detection, Hough-Transform, Real-Time, GPU, CUDA
Annotation
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.
BibTeX:
@INPROCEEDINGS{
   author = {Radovan Jo{\v{s}}th and Mark{\'{e}}ta Dubsk{\'{a}} and Adam
	Herout and Ji{\v{r}}{\'{i}} Havel},
   title = {Real-Time Line Detection Using Accelerated High-Resolution
	Hough Transform},
   pages = {784--793},
   booktitle = {Proceedings of SCIA 2011, LNCS},
   year = {2011},
   location = {Ystad, SE},
   publisher = {Springer Verlag},
   ISBN = {978-3-642-21226-0},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=9507}
}

Your IPv4 address: 54.196.201.241
Switch to IPv6 connection

DNSSEC [dnssec]