Real-time detection of lines using parallel coordinates and CUDA

Havel, J., Herout, A., Dubska, M., and Josth, R. Graph@FIT, Brno University of Technology
Corresponding author email: idubska[at]fit.vutbr.cz

Abstract

The 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, using a new parameterization of lines "PClines". This algorithm is suitable for computer systems with a small but fast read-write memory - such as today's graphics processors. The algorithm requires no floating-point computations or goniometric functions. This makes it suitable for special and low-power processors and special-purpose chips. The proposed algorithm is evaluated both on synthetic binary images and on complex real-world photos of high resolutions. The results show that by using today's commodity graphics chips, the Hough transform can be computed at interactive frame rates, even with a high resolution of the Hough space and with the Hough transform fully computed.

Downloads

[full paper], [cite]

Citation

@ARTICLE{havel2014real, author = {Havel, Ji{\v{r}}{\'\i} and Dubsk{\'a}, Mark{\'e}ta and Herout, Adam and Jo{\v{s}}th, Radovan}, title = {Real-time detection of lines using parallel coordinates and CUDA}, journal = {Journal of real-time image processing}, year = {2014}, volume = {9}, pages = {205--216}, number = {1}, publisher = {Springer Berlin Heidelberg} }

Examples of Results

Acknowledgements

This research was supported by the EU FP7-ARTEMIS project no. 100230 SMECY, by the research project CEZMSMT, MSM0021630528, and by the BUT FIT grant FIT-10-S-2.