Publication Details
Real-Time Line Detection Using Accelerated High-Resolution Hough Transform
Dubská Markéta, Ing., Ph.D. (DCGM FIT BUT)
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT)
Havel Jiří, Ing., Ph.D. (DCGM FIT BUT)
Line Detection, Hough-Transform, Real-Time, GPU, CUDA
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.
@INPROCEEDINGS{FITPUB9507, 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 = "https://www.fit.vut.cz/research/publication/9507" }