Automatic Segmentation of Overlapping Fish Using Shape Priors

  • Sigmund Clausen
  • Katharina Greiner
  • Odd Andersen
  • Knut-Andreas Lie
  • Helene Schulerud
  • Tom Kavli
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)

Abstract

We present results from a study where we segment fish in images captured within fish cages. The ultimate goal is to use this information to extract the weight distribution of the fish within the cages. Statistical shape knowledge is added to a Mumford-Shah functional defining the image energy. The fish shape is represented explicitly by a polygonal curve, and the energy minimization is done by gradient descent. The images represent many challenges with a highly cluttered background, inhomogeneous lighting and several overlapping objects. We obtain good segmentation results for silhouette-like images containing relatively few fish. In this case, the fish appear dark on a light background and the image energy is well behaved. In cases with more difficult lighting conditions the contours evolve slowly and often get trapped in local minima

Keywords

Segmentation Overlapping objects Mumford-Shah Shape priors 

References

  1. 1.
    The AKVA group has developed Vicass – a stereo-based imaging system for size and weight estimation currently used in more than 100 fish farms and distributed and sold in more than eight countries world wide. For more information about an existing stereo system, see: http://www.akvasmart.com
  2. 2.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. Int. J. of Comp. Vis. 1(4), 321–331 (1988)CrossRefGoogle Scholar
  3. 3.
    Mumford, D., Shah, J.: Optimal Approximations by piecewise smooth functions and associated variational problems. Comm. Pure Appl. Math. 42, 577–685 (1989)MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Cremers, D., Tischhäuser, F., Weickert, J., Schnörr, C.: Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah functional. Int. J. of Comp. Vis. 50(3), 295–313 (2002)MATHCrossRefGoogle Scholar
  5. 5.
    Cremers, D.: Statistical Shape Knowledge in Variational Image Segmentation. PhD thesis, University of Mannheim (2002)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Sigmund Clausen
    • 1
  • Katharina Greiner
    • 2
  • Odd Andersen
    • 1
  • Knut-Andreas Lie
    • 1
  • Helene Schulerud
    • 1
  • Tom Kavli
    • 1
  1. 1.SINTEF ICT, OsloNorway
  2. 2.University of Applied Sciences, WiesbadenGermany

Personalised recommendations