Detection of Fishes in Underwater Videos Based on Signature Invariant to Scale and Rotation

Authors

  • Puneeth Kumar B. S  Department of Computer Science, Kuvempu University, Shivamogga, Karnataka, India
  • Suresha M.  Department of Computer Science, Kuvempu University, Shivamogga, Karnataka, India

Keywords:

Cross-Correlation, Detection, Fish, Rotation, Scale, Signature.

Abstract

This paper introduces a novel shape descriptor approach for the automatic detection of fish in underwater video environment. The detection process is applied on isolated fish objects in underwater video and it requires segmentation of objects in video, segmentation is done by background subtraction method followed by extraction of representative shape signature and the similarity estimation of pairs of objects. In order to achieve an efficient object representation, a novel boundary-based shape descriptor invariant to rotation is introduced particularly for fish, formed by a set of one dimensional signals referred to as shape signature. During detection, the cross correlation metric is used to measure the degree of similarity between objects. The proposed method is invariance to scaling is performed when correlating shape signature. The proposed vision system is robust to scaling, rotation, translation. The detection performance has been examined using the Fish4Knowledge dataset.

References

  1. Zivkovic, Z. Improved adaptive Gaussian mixture model for background subtraction, International Conference on Pattern Recognition (ICPR-2004), 17th International Conference, vol. 2, page 28-31, 2004
  2. Palazzo, S., Kavasidis, I. and Spampinato, C., Covariance based modeling of underwater scenes for fish detection. Proceedings of 20th IEEE International Conference on Image Processing, 1481-1485, 2013.
  3. Fiona H Evans. Detecting fish in underwater video using the em algorithm. In Proceedings of the 2003 International Conference on Image Processing (ICIP) , volume 3, pages III-1029. IEEE, 2003.
  4. C. Spampinato, D. Giordano, R. Di Salvo, Y.-H. J. Chen-Burger, R. B. Fisher, and G. Nadarajan. Automatic fish classification for underwater species behavior understanding. ARTEMIS ’10, pages 45-50, 2010
  5. Porikli F  Achieving real-time object detection and tracking under extreme conditions. JReal Time Image Process 1 (1):33-40,2006.
  6. Harvey, E. S., Cappo, M., Shortis, M. R., Robson, S., Buchanan, J. and Speare, P. The accuracy and precision of underwater measurements of length and maximum body depth of southern bluefin tuna (Thunnus maccoyii) with a stereo-video camera system. Fisheries Research, vol.63: page 315-326.2003.
  7. P. Huang, B. Boom, R. Fisher. Underwater live fish recognition using a balance-guaranteed optimized tree Asian Conference on Computer Vision (2012).
  8. Paris S, Halkias X, Glotin H Sparse coding for histograms of local binary patterns applied for image categorization: Toward a bag-of-scenes analysis. In: 21st International Conference on Pattern Recognition (ICPR), pp 2817-2820.2012.
  9. T. Blank K,Lingrand D,Precioso F.Fish Species recognition from video using SVM classifier In: working Notes CLEF 2014 conference 2014.
  10. K. Blanc, D. Lingrand, F. Precioso, "Fish species recognition from video using svm classifier", Proceedings of the 3rd ACM International Workshop on Multimedia Analysis for Ecological Data, ACM, pp. 1-6, 2014.
  11. Pienaar, L.V. and Thomson, J. A. Allometric weight-length regression model. Journal of the Fisheries Research Board of Canada,vol. 26:page.123-131. 1969.
  12. Shieh, A. C. R. and Petrell, R. J.  Measurement of fish size in Atlantic salmon (salmo salar l.) cages using stereographic video techniques. Aquacultural Engineering, 17(1):pp. 29-43,1998
  13. AQ1 Systems. http://www.aq1systems.com/products (accessed March 14, 2013)
  14. C. Stauffer, W. Grimson. Adaptive background mixture models for real-time tracking. Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, 1999.
  15. T. Bouwmans, F. El Baf and B. Vachon. Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey. Recent Patents on Computer Science 1, 3, pp. 219-237, 2008.
  16. Sobel, I., Feldman, G., "A 3x3 Isotropic Gradient Operator for Image Processing", presented at the Stanford Artificial Intelligence Project (SAIL) in 1968.
  17. Haralick, R., Shapiro, L.G. (eds.): Computer and Robot Vision, vol. I, pp. 28-48. Addison Wesley, London, UK (1992)
  18. Carter, J.R.: Boundary tracing method and system. European Patent Application EP341819-A3 (1989)

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2018-02-28

Issue

Volume 3, Issue 1, January-February-2018

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Puneeth Kumar B. S, Suresha M., " Detection of Fishes in Underwater Videos Based on Signature Invariant to Scale and Rotation , IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 3, Issue 1, pp.1881-1889 , January-February-2018.