Journal of Real-Time Image Processing

, Volume 9, Issue 1, pp 205–216 | Cite as

Real-time detection of lines using parallel coordinates and CUDA

  • Jiří Havel
  • Markéta DubskáEmail author
  • Adam Herout
  • Radovan Jošth
Special Issue


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 study 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 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.


Line detection Parallel coordinates CUDA implementation Hough transform Real-time detection 



This research was supported by the EU FP7-ARTEMIS project no. 100230 SMECY, by the research project CEZMSMT, MSM0021630528, and by the CEZMSMT project IT4I - CZ 1.05/1.1.00/02.0070.


  1. 1.
    Atiquzzaman, M.: Pipelined implementation of the multiresolution Hough transform in a pyramid multiprocessor. Pattern Recognit. Lett. 15(9), 841–851 (1994). doi: 10.1016/0167-8655(94)90145-7 CrossRefGoogle Scholar
  2. 2.
    Ballard, D.H.: Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognit. 13(2), 111–122 (1981)CrossRefzbMATHGoogle Scholar
  3. 3.
    Bhattacharya, P., Rosenfeld, A., Weiss, I.: Point-to-line mappings as Hough transforms. Pattern Recognit. Lett. 23(14):1705–1710 (2002). doi: 10.1016/S0167-8655(02)00133-2 CrossRefzbMATHGoogle Scholar
  4. 4.
    d'Ocagne, M.: Coordonnèes parallèles et axiales. Méthode de transformation géométrique et procèdènouveau de calcul graphique dèduits de la considèration des coordonnées parallèlles. Gauthier-Villars (1885)Google Scholar
  5. 5.
    Dubská, M., Havel, J., Herout, A.: Real-time detection of lines using parallel coordinates and OpenGL. In: Proceedings of SCCG (2011)Google Scholar
  6. 6.
    Dubská, M., Herout, A., Havel, J.: PClines—line detection using parallel coordinates. In: Proceedings of the IEEE Conference Computer Vision and Pattern Recognition (CVPR) (2011)Google Scholar
  7. 7.
    Duda, RO., Hart, PE.: Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM 15(1), 11–15 (1972). doi: 10.1145/361237.361242 CrossRefGoogle Scholar
  8. 8.
    Eckhardt, U., Maderlechner, G.: Application of the projected Hough transform in picture processing. In: Proceedings of the 4th International Conference on Pattern Recognition, pp. 370–379. Springer, London (1988)Google Scholar
  9. 9.
    Forman, A.V., Jr.: A modified Hough transform for detecting lines in digital imagery. In: Applications of Artificial Intelligence III, pp. 151–160 (1986). doi: 10.1117/12.964124
  10. 10.
    Harris, M.: GPU Gems 3, Addison-Wesley, chap 39. Parallel Prefix Sum (Scan) with CUDA, pp. 851–876 (2007)Google Scholar
  11. 11.
    Hough, PVC.: Method and means for recognizing complex patterns. US Patent 3,069,654 (1962)Google Scholar
  12. 12.
    Inselberg, A.: Parallel Coordinates: Visual Multidimensional Geometry and Its Applications. Springer, Berlin. ISBN: 978-0-387-21507-5 (2009)Google Scholar
  13. 13.
    Jošth, R., Dubská, M., Herout, A., Havel, J.: Real-time line detection using accelerated high-resolution Hough transform. In: Proceedings of Scandinavian Conference on Image Analysis (SCIA) (2011)Google Scholar
  14. 14.
    Li H, Lavin MA, Le Master RJ. (1986) Fast Hough transform: A hierarchical approach. Comput. Vis. Graph Image Process. 36, 139–161. doi: 10.1016/0734-189X(86)90073-3 CrossRefGoogle Scholar
  15. 15.
    Natterer, F.: The mathematics of computerized tomography. Wiley. ISBN:9780471909590 (1986)Google Scholar
  16. 16.
    O’Gorman, F., Clowes, MB.: Finding picture edges through collinearity of feature points. IEEE Trans. Comput. 25(4), 449–456 (1976)Google Scholar
  17. 17.
    O’Rourke, J.: Dynamically quantized spaces for focusing the Hough transform. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vol. 2, pp. 737–739. Morgan Kaufmann Publ. Inc., San Francisco (1981)Google Scholar
  18. 18.
    O’Rourke, J., Sloan, K.R.: Dynamic quantization: Two adaptive data structures for multidimensional spaces. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 6(3), 266 –280 (1984). doi: 10.1109/TPAMI.1984.4767519 CrossRefGoogle Scholar
  19. 19.
    Pavel, S., Akl, S.: Efficient algorithms for the Hough transform on arrays with reconfigurable optical buses. In: Parallel Processing Symposium, 1996., Proceedings of IPPS ’96, The 10th International, pp. 697–701 (1996). doi: 10.1109/IPPS.1996.508134
  20. 20.
    Princen. J., Illingowrth, J., Kittler, J.: Hypothesis testing: a framework for analyzing and optimizing Hough transform performance. IEEE Trans. Pattern Anal. Mach. Intell.16(4), 329–341 (1994). doi: 10.1109/34.277588 Google Scholar
  21. 21.
    Rau, J.Y., Chen, L.C.: Fast straight lines detection using Hough transform with principal axis analysis. J. Photogramm. Remote Sens. 8, 15–34 (2003)Google Scholar
  22. 22.
    Shapiro, L.G., Stockman, G.C.: Computer Vision. Tom Robbins (2001)Google Scholar
  23. 23.
    Sloan, K.R.: Dynamically quantized pyramids. In: Proceedings of Teh International Joint Conference on Artificial Intelligence (IJCAI), pp. 734–736. Kaufmann (1981)Google Scholar
  24. 24.
    Strzodka, R., Ihrke, I., Magnor, M.: A graphics hardware implementation of the generalized Hough transform for fast object recognition, scale, and 3D pose detection. In: Proceedings of IEEE International Conference on Image Analysis and Processing (ICIAP’03), pp. 188–193 (2003)Google Scholar
  25. 25.
    Underhill, A., Atiquzzaman, M., Ophel, J.: Performance of the Hough transform on a distributed memory multiprocessor. Microprocess. Microsyst. 22(7), 355–362 (1999). doi: 10.1016/S0141-9331(98)00093-3
  26. 26.
    Wallace, R.: A modified Hough transform for lines. In: Proceedings of CVPR, pp. 665–667 (1985)Google Scholar
  27. 27.
    Xu, L., Oja, E., Kultanen, P.: A new curve detection method: Randomized Hough Transform (RHT). Pattern Recognit. Lett. 11, 331–338 (1990). doi: 10.1016/0167-8655(90)90042-Z CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jiří Havel
    • 1
  • Markéta Dubská
    • 1
    Email author
  • Adam Herout
    • 1
  • Radovan Jošth
    • 1
  1. 1.Graph@FIT, Brno University of TechnologyBrnoCzech Republic

Personalised recommendations