Advertisement

A Single-Scan Algorithm for Connected Components Labelling in a Traffic Monitoring Application

  • Alessandro Bevilacqua
  • Alessandro Lanza
  • Giorgio Baccarani
  • Riccardo Rovatti
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

This paper presents a fast algorithm based on sequential local operations which aims at labelling connected components in binary images. While classical algorithms scan the image twice and utilize an equiv alencetable to store and resolve label redundancies, our method performs just a single scan, relying on the idea of labelling a whole blob at a time. In this way, we avoid label redundancies. As a consequence, the use of both equivalence tables and algorithms to resolve them becomes unnecessary. This leads our labelling algorithm to attain even more significant performances in the case of images characterized by blobs generating a large number of label equivalences. The proposed labelling algorithm has been successfully utilized in our visual surveillance system.

References

  1. 1.
    Bevilacqua, A., Roffilli, M.: Robust denoising and moving shadows detection in traffic scenes. In: Proceedings of the Tech. Sketches of the 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR01). (2001) 1–4Google Scholar
  2. 2.
    Bevilacqua, A.: A novel background initialization method in visual surveillance. In: IAPR Workshop on Machine Vision Applications (MVA02). (2002) 614–617Google Scholar
  3. 3.
    Bevilacqua, A.: Effective shadow detection in traffic monitoring applications. Journal of WSCG 11 (2003) 57–64Google Scholar
  4. 4.
    Bevilacqua, A.: Effective object segmentation in a traffic monitoring application. In: Proceedings of the 3rd Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP02). (2002) 125–130Google Scholar
  5. 5.
    Rosenfeld, A., Pfaltz, J.L.: Sequential operations in digital picture processing. Journal of the ACM 13 (1966) 471–494zbMATHCrossRefGoogle Scholar
  6. 6.
    Rosenfeld, A., Kak, A.C.: Digital Picture Processing. Volume 2. Academic Press (1982)Google Scholar
  7. 7.
    Hattori, T.: A high-speed pipeline processor for regional labeling based on a new algorithm. In: Proceedings of the 10th International Conference on Pattern Recognition (ICPR90). (1990) 494–496Google Scholar
  8. 8.
    Haralick, R.M., Shapiro, G.L.: Computer and Robot Vision. Volume 1. Addison-Wesley (1992)Google Scholar
  9. 9.
    Gonzales, R.C., Woods, R.E.: Digital Image Processing. Addison-Wesley (1992)Google Scholar
  10. 10.
    Klette, R., Zamperoni, P.: Handbook of Image Processing Operators. (1996)Google Scholar
  11. 11.
    Lacassagne, L., Milgram, M., Garda, P.: Motion detection, labeling, data association and tracking, in real-time on RISC computer. In: Proceedings of the l0th International Conference on Image Analysis and Processing (ICIAP99). (1999) 520–525Google Scholar
  12. 12.
    Stefano, L.D., Bulgarelli, A.: A simple and efficient connected components labeling algorithm. In: Proceedings of the 10th International Conference on Image Analysis and Processing (ICIAP99). (1999) 322–327Google Scholar
  13. 13.
    Park, J.M., Looney, G.C., Chen, H.C.: Fast connected-component labeling algorithm using a divide and conquer technique. In: Proceedings of the 15th International Conference on Computers and their Applications (CATA00). (2000) 373–376Google Scholar
  14. 14.
    Suzuki, K., Horiba, I., Sugie, N.: Fast connected-component labeling based on sequential local operations in the course of forward raster scan followed by backward raster scan. In: Proceedings of the 15th International Conference on Pattern Recognition (ICPR00). Volume 2. (2000) 434–437CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Alessandro Bevilacqua
    • 1
  • Alessandro Lanza
    • 1
  • Giorgio Baccarani
    • 1
  • Riccardo Rovatti
    • 1
  1. 1.ARCES - Centre of Excellence, DEIS (Department of Electronics, Computer Science and Systems)University of BolognaBolognaItaly

Personalised recommendations