Journal of Real-Time Image Processing

, Volume 2, Issue 4, pp 319–329 | Cite as

Real-time image segmentation based on a parallel and pipelined watershed algorithm

  • Dang Ba Khac Trieu
  • Tsutomu MaruyamaEmail author
Special Issue


The watershed transformation is a popular image segmentation technique for gray scale images. This paper describes a real-time image segmentation based on a parallel and pipelined watershed algorithm which is designed for hardware implementation. In our algorithm: (1) pixels in a given image are repeatedly scanned from top-left to bottom-right, and then from bottom-right to top-left, in order to achieve high performance on a pipelined circuit by simplifying memory access sequences, (2) all steps in the algorithm are executed at the same time in the pipelined circuit, (3) the amount of data that are scanned is gradually reduced as the calculation progresses by memorizing which data are modified in the previous scan, and (4) N pixels can be processed in parallel. In our current implementation on an off-the-shelf field-programmable gate array board, up to four pixels can be processed in parallel. The performance for 512 × 512 pixel images is fast enough to be the first step in real-time applications.


Watershed algorithm Segmentation Real time FPGA 


  1. 1.
    Beucher, S., Meyer, F.: The Morphological Approach to Segmentation: the Watershed Transformation. Mathematical Morphology in Image Processing, pp. 433–481. Marcel Dekker, New York (1993)Google Scholar
  2. 2.
    Meyer, F.: Topographic distance and watershed lines. Signal Process. 38(1), 113–125 (1994)zbMATHCrossRefGoogle Scholar
  3. 3.
    Bieniek, A., Moga, A.: An efficient watershed algorithm based on connected components. Pattern Recogn. 33, 907–916 (2000)CrossRefGoogle Scholar
  4. 4.
    Sun, H., Yang, J., Ren, M.: A fast watershed algorithm based on chain code and its application in image segmentation. Pattern Recogn. Lett. 26, 1266–1274 (2005)CrossRefGoogle Scholar
  5. 5.
    Nuguet, D.: A massively parallel implementation of the watershed based on automata. In: IEEE International Conference on Application-Specific Systems, Architectures and Processors, pp. 42–52 (1997)Google Scholar
  6. 6.
    Zahirazami, S., Akil, M.: Implementation of a watershed algorithm on FPGAs. In: Proceedings SPIE Applications of Digital Image Processing, vol. 3460, pp. 98–105 (1999)Google Scholar
  7. 7.
    Kuo, C.J., Odeh, S.F., Huang, M.C.: Image segmentation with improved watershed algorithm and its FPGA implementation. IEEE International Symposium on Circuits and Systems, pp. 753–756 (2001)Google Scholar
  8. 8.
    Rambabu, C., Chakrabarti, I., Mahanta, A.: An efficient architecture for an improved watershed algorithm and its FPGA implementation. International Conference on Field-Programmable Technology, pp. 370–373 (2002)Google Scholar
  9. 9.
    Gupta, K.P., Srinivasan, S.: Reduced memory implementation of modified serial watershed algorithm based ordered queue. In: International Conference on Information Technology: Computers and Communications (ITCC), pp. 514–518 (2003)Google Scholar
  10. 10.
    Rambabu, C., Chakrabarti, I., Mahanta, A.: Flooding-based watershed algorithm and its prototype hardware architecture. Vis. Image Signal Process. IEE 151(3), 224–234 (2004)CrossRefGoogle Scholar
  11. 11.
    Rambabu, C., Chakrabarti, I.: An efficient immersion-based watershed transform method and its prototype architecture. J. Syst. Archit. pp. 210–226 (2007)Google Scholar
  12. 12.
    Trieu, D.B.K., Maruyama, T.: Implementation of a parallel and pipeliend watershed algorithm on FPGA. In: International Conference on Field-Programmable Logic and Applications, pp. 561–566 (2006)Google Scholar

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  1. 1.Systems and Information EngineeringUniversity of TsukubaTsukubaJapan

Personalised recommendations