Abstract

This paper presents a model-based approach to mine detection and classification by use of sidescan sonar. Advances in autonomous underwater vehicle technology have increased the interest in automatic target recognition systems in an effort to automate a process that is currently carried out by a human operator. Current automated systems generally require training and thus produce poor results when the test data set is different from the training set. This has led to research into unsupervised systems, which are able to cope with the large variability in conditions and terrains seen in sidescan imagery. The system presented in this paper first detects possible minelike objects using a Markov random field model, which operates well on noisy images, such as sidescan, and allows a priori information to be included through the use of priors. The highlight and shadow regions of the object are then extracted with a cooperating statistical snake, which assumes these regions are statistically separate from the background. Finally, a classification decision is made using Dempster-Shafer theory, where the extracted features are compared with synthetic realizations generated with a sidescan sonar simulator model. Results for the entire process are shown on real sidescan sonar data. Similarities between the sidescan sonar and synthetic aperture radar (SAR) imaging processes ensure that the approach outlined here could be made applied to SAR image analysis.

© 2004 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. G. J. Dobeck, J. C. Hyland, L. Smedley, “Automated detection and classification of sea mines in sonar imagery,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds. Proc. SPIE3079, 90–110 (1997).
    [CrossRef]
  2. C. M. Ciany, J. Huang, “Computer aided detection/computer aided classification and data fusion algorithms for automated detection and classification of underwater mines,” in Proceedings of the MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2000), Vol. 1, pp. 277–284.
  3. T. Aridgides, M. Ferdandez, G. Dobeck, “Fusion of adaptive algorithms for the classification of sea mines using high resolution side scan sonar in very shallow water,” in Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2001), Vol. 1, pp. 135–142.
  4. L. M. Linnett, S. J. Clarke, C. St. J. Reid, A. D. Tress, “Monitoring of the seabed using sidescan sonar and fractal processing,” in Conference of Underwater Acoustics Group (Institute of Acoustics, St. Albans, Hertfordshire, UK, 1993) Vol. 15, pp. 49–64.
  5. B. R. Calder, L. M. Linnett, D. R. Carmichael, “Spatial stochastic models for seabed object detection,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds., Proc. SPIE3079, 172–182 (1997).
    [CrossRef]
  6. M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Three class Markovian segmentation of high resolution sonar images,” Comput. Vision Image Understand 76, 191–204 (1999).
    [CrossRef]
  7. S. Reed, Y. Petillot, J. Bell, “An automated approach to the detection and extraction of mine features in sidescan sonar,” IEEE J. Ocean Eng. 28, 90–105 (2003).
    [CrossRef]
  8. S. Reed, J. Bell, Y. Petillot, “Unsupervised segmentation of object shadow and highlight using statistical snakes,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001) pp. 221–236.
  9. B. Zerr, E. Bovio, B. Stage, “Automatic mine classification approach based on AUV manoeuvrability and the COTS side scan sonar,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001), pp. 315–322.
  10. S. LeHegart-Mascle, I. Bloch, D. Vidal-Madjar, “Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing,” IEEE Trans. Geosci. Remote Sens. 35, 1018–1031 (1997).
    [CrossRef]
  11. I. Bloch, “Some aspects of Dempster-Shafer evidence theory for classification of multi-modality medical images taking partial volume effect into account,” Pattern Recog. Lett. 17, 905–919 (1996).
    [CrossRef]
  12. D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge, “Comparing images using the Hausdorff distance,” IEEE Trans. Pattern Anal. Mach. Intell. 15, 850–863 (1993).
    [CrossRef]
  13. J. Besag, “on the statistical analysis of dirty pictures,” J. R. Stat. Soc. Ser. B. Methodol. 48, 259–302 (1986).
  14. M. L. Comer, E. J. Delp, “Segmentation of textured images using a multiresolution Gaussian autoregressive model,” IEEE Trans. Image Process. 8, 408–420 (1999).
    [CrossRef]
  15. S. Geman, D. Geman, “Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images,” IEEE Trans. Pattern Anal. Mach. Intell. 6, 721–741 (1984).
    [CrossRef] [PubMed]
  16. M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Sonar image segmentation using an unsupervised hierarchical MRF model,” IEEE Trans. Image Process. 9, 1216–1231 (2000).
    [CrossRef]
  17. E. Dura, J. Bell, D. Lane, “Superellipse fitting for the classification of mine-like shapes in side-scan sonar images,” Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2002), Vol. 1, pp. 23–28.
  18. C. Chesnaud, P. Refregier, V. Boulet, “Statistical region snake-based segmentation adapted to different physical noise models,” IEEE Trans. Pattern Anal. Mach. Intell. 21, 1145–1157 (1999).
    [CrossRef]
  19. M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Hybrid genetic optimization and statistical model-based approach for the classification of shadow shapes in sonar imagery,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 129–141 (2000).
    [CrossRef]
  20. P. Galerne, K. Yao, G. Burel, “Object classification using neural networks in sonar imagery,” in New Image Processing Techniques and Applications: Algorithms, Methods, and Components II, P. Refregier, R.-J. Ahlers, eds., Proc. SPIE3101, 306–314 (1997).
    [CrossRef]
  21. J. Bell, “A Model for the Simulation of Sidescan Sonar,” Ph.D. dissertation (Heriot-Watt University, Edinburgh, Scotland, 1995).
  22. A. H. S. Solberg, A. K. Jain, T. Taxt, “Multisource classification of remotely sensed data: fusion of landsat TM and SAR images,” IEEE Trans. Geosci. and Remote Sens. 32, 768–778 (1994).
    [CrossRef]
  23. I. Bloch, “Information combination operators for data fusion: a comparative review with classification,” IEEE Trans. Syst. Man Cybern. 26, 52–67 (1996).
    [CrossRef]

2003 (1)

S. Reed, Y. Petillot, J. Bell, “An automated approach to the detection and extraction of mine features in sidescan sonar,” IEEE J. Ocean Eng. 28, 90–105 (2003).
[CrossRef]

2000 (2)

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Sonar image segmentation using an unsupervised hierarchical MRF model,” IEEE Trans. Image Process. 9, 1216–1231 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Hybrid genetic optimization and statistical model-based approach for the classification of shadow shapes in sonar imagery,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 129–141 (2000).
[CrossRef]

1999 (3)

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Three class Markovian segmentation of high resolution sonar images,” Comput. Vision Image Understand 76, 191–204 (1999).
[CrossRef]

C. Chesnaud, P. Refregier, V. Boulet, “Statistical region snake-based segmentation adapted to different physical noise models,” IEEE Trans. Pattern Anal. Mach. Intell. 21, 1145–1157 (1999).
[CrossRef]

M. L. Comer, E. J. Delp, “Segmentation of textured images using a multiresolution Gaussian autoregressive model,” IEEE Trans. Image Process. 8, 408–420 (1999).
[CrossRef]

1997 (1)

S. LeHegart-Mascle, I. Bloch, D. Vidal-Madjar, “Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing,” IEEE Trans. Geosci. Remote Sens. 35, 1018–1031 (1997).
[CrossRef]

1996 (2)

I. Bloch, “Some aspects of Dempster-Shafer evidence theory for classification of multi-modality medical images taking partial volume effect into account,” Pattern Recog. Lett. 17, 905–919 (1996).
[CrossRef]

I. Bloch, “Information combination operators for data fusion: a comparative review with classification,” IEEE Trans. Syst. Man Cybern. 26, 52–67 (1996).
[CrossRef]

1994 (1)

A. H. S. Solberg, A. K. Jain, T. Taxt, “Multisource classification of remotely sensed data: fusion of landsat TM and SAR images,” IEEE Trans. Geosci. and Remote Sens. 32, 768–778 (1994).
[CrossRef]

1993 (1)

D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge, “Comparing images using the Hausdorff distance,” IEEE Trans. Pattern Anal. Mach. Intell. 15, 850–863 (1993).
[CrossRef]

1986 (1)

J. Besag, “on the statistical analysis of dirty pictures,” J. R. Stat. Soc. Ser. B. Methodol. 48, 259–302 (1986).

1984 (1)

S. Geman, D. Geman, “Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images,” IEEE Trans. Pattern Anal. Mach. Intell. 6, 721–741 (1984).
[CrossRef] [PubMed]

Aridgides, T.

T. Aridgides, M. Ferdandez, G. Dobeck, “Fusion of adaptive algorithms for the classification of sea mines using high resolution side scan sonar in very shallow water,” in Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2001), Vol. 1, pp. 135–142.

Bell, J.

S. Reed, Y. Petillot, J. Bell, “An automated approach to the detection and extraction of mine features in sidescan sonar,” IEEE J. Ocean Eng. 28, 90–105 (2003).
[CrossRef]

J. Bell, “A Model for the Simulation of Sidescan Sonar,” Ph.D. dissertation (Heriot-Watt University, Edinburgh, Scotland, 1995).

E. Dura, J. Bell, D. Lane, “Superellipse fitting for the classification of mine-like shapes in side-scan sonar images,” Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2002), Vol. 1, pp. 23–28.

S. Reed, J. Bell, Y. Petillot, “Unsupervised segmentation of object shadow and highlight using statistical snakes,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001) pp. 221–236.

Besag, J.

J. Besag, “on the statistical analysis of dirty pictures,” J. R. Stat. Soc. Ser. B. Methodol. 48, 259–302 (1986).

Bloch, I.

S. LeHegart-Mascle, I. Bloch, D. Vidal-Madjar, “Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing,” IEEE Trans. Geosci. Remote Sens. 35, 1018–1031 (1997).
[CrossRef]

I. Bloch, “Information combination operators for data fusion: a comparative review with classification,” IEEE Trans. Syst. Man Cybern. 26, 52–67 (1996).
[CrossRef]

I. Bloch, “Some aspects of Dempster-Shafer evidence theory for classification of multi-modality medical images taking partial volume effect into account,” Pattern Recog. Lett. 17, 905–919 (1996).
[CrossRef]

Boulet, V.

C. Chesnaud, P. Refregier, V. Boulet, “Statistical region snake-based segmentation adapted to different physical noise models,” IEEE Trans. Pattern Anal. Mach. Intell. 21, 1145–1157 (1999).
[CrossRef]

Bouthemy, P.

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Hybrid genetic optimization and statistical model-based approach for the classification of shadow shapes in sonar imagery,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 129–141 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Sonar image segmentation using an unsupervised hierarchical MRF model,” IEEE Trans. Image Process. 9, 1216–1231 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Three class Markovian segmentation of high resolution sonar images,” Comput. Vision Image Understand 76, 191–204 (1999).
[CrossRef]

Bovio, E.

B. Zerr, E. Bovio, B. Stage, “Automatic mine classification approach based on AUV manoeuvrability and the COTS side scan sonar,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001), pp. 315–322.

Burel, G.

P. Galerne, K. Yao, G. Burel, “Object classification using neural networks in sonar imagery,” in New Image Processing Techniques and Applications: Algorithms, Methods, and Components II, P. Refregier, R.-J. Ahlers, eds., Proc. SPIE3101, 306–314 (1997).
[CrossRef]

Calder, B. R.

B. R. Calder, L. M. Linnett, D. R. Carmichael, “Spatial stochastic models for seabed object detection,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds., Proc. SPIE3079, 172–182 (1997).
[CrossRef]

Carmichael, D. R.

B. R. Calder, L. M. Linnett, D. R. Carmichael, “Spatial stochastic models for seabed object detection,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds., Proc. SPIE3079, 172–182 (1997).
[CrossRef]

Chesnaud, C.

C. Chesnaud, P. Refregier, V. Boulet, “Statistical region snake-based segmentation adapted to different physical noise models,” IEEE Trans. Pattern Anal. Mach. Intell. 21, 1145–1157 (1999).
[CrossRef]

Ciany, C. M.

C. M. Ciany, J. Huang, “Computer aided detection/computer aided classification and data fusion algorithms for automated detection and classification of underwater mines,” in Proceedings of the MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2000), Vol. 1, pp. 277–284.

Clarke, S. J.

L. M. Linnett, S. J. Clarke, C. St. J. Reid, A. D. Tress, “Monitoring of the seabed using sidescan sonar and fractal processing,” in Conference of Underwater Acoustics Group (Institute of Acoustics, St. Albans, Hertfordshire, UK, 1993) Vol. 15, pp. 49–64.

Collet, C.

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Sonar image segmentation using an unsupervised hierarchical MRF model,” IEEE Trans. Image Process. 9, 1216–1231 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Hybrid genetic optimization and statistical model-based approach for the classification of shadow shapes in sonar imagery,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 129–141 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Three class Markovian segmentation of high resolution sonar images,” Comput. Vision Image Understand 76, 191–204 (1999).
[CrossRef]

Comer, M. L.

M. L. Comer, E. J. Delp, “Segmentation of textured images using a multiresolution Gaussian autoregressive model,” IEEE Trans. Image Process. 8, 408–420 (1999).
[CrossRef]

Delp, E. J.

M. L. Comer, E. J. Delp, “Segmentation of textured images using a multiresolution Gaussian autoregressive model,” IEEE Trans. Image Process. 8, 408–420 (1999).
[CrossRef]

Dobeck, G.

T. Aridgides, M. Ferdandez, G. Dobeck, “Fusion of adaptive algorithms for the classification of sea mines using high resolution side scan sonar in very shallow water,” in Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2001), Vol. 1, pp. 135–142.

Dobeck, G. J.

G. J. Dobeck, J. C. Hyland, L. Smedley, “Automated detection and classification of sea mines in sonar imagery,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds. Proc. SPIE3079, 90–110 (1997).
[CrossRef]

Dura, E.

E. Dura, J. Bell, D. Lane, “Superellipse fitting for the classification of mine-like shapes in side-scan sonar images,” Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2002), Vol. 1, pp. 23–28.

Ferdandez, M.

T. Aridgides, M. Ferdandez, G. Dobeck, “Fusion of adaptive algorithms for the classification of sea mines using high resolution side scan sonar in very shallow water,” in Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2001), Vol. 1, pp. 135–142.

Galerne, P.

P. Galerne, K. Yao, G. Burel, “Object classification using neural networks in sonar imagery,” in New Image Processing Techniques and Applications: Algorithms, Methods, and Components II, P. Refregier, R.-J. Ahlers, eds., Proc. SPIE3101, 306–314 (1997).
[CrossRef]

Geman, D.

S. Geman, D. Geman, “Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images,” IEEE Trans. Pattern Anal. Mach. Intell. 6, 721–741 (1984).
[CrossRef] [PubMed]

Geman, S.

S. Geman, D. Geman, “Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images,” IEEE Trans. Pattern Anal. Mach. Intell. 6, 721–741 (1984).
[CrossRef] [PubMed]

Huang, J.

C. M. Ciany, J. Huang, “Computer aided detection/computer aided classification and data fusion algorithms for automated detection and classification of underwater mines,” in Proceedings of the MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2000), Vol. 1, pp. 277–284.

Huttenlocher, D. P.

D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge, “Comparing images using the Hausdorff distance,” IEEE Trans. Pattern Anal. Mach. Intell. 15, 850–863 (1993).
[CrossRef]

Hyland, J. C.

G. J. Dobeck, J. C. Hyland, L. Smedley, “Automated detection and classification of sea mines in sonar imagery,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds. Proc. SPIE3079, 90–110 (1997).
[CrossRef]

Jain, A. K.

A. H. S. Solberg, A. K. Jain, T. Taxt, “Multisource classification of remotely sensed data: fusion of landsat TM and SAR images,” IEEE Trans. Geosci. and Remote Sens. 32, 768–778 (1994).
[CrossRef]

Klanderman, G. A.

D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge, “Comparing images using the Hausdorff distance,” IEEE Trans. Pattern Anal. Mach. Intell. 15, 850–863 (1993).
[CrossRef]

Lane, D.

E. Dura, J. Bell, D. Lane, “Superellipse fitting for the classification of mine-like shapes in side-scan sonar images,” Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2002), Vol. 1, pp. 23–28.

LeHegart-Mascle, S.

S. LeHegart-Mascle, I. Bloch, D. Vidal-Madjar, “Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing,” IEEE Trans. Geosci. Remote Sens. 35, 1018–1031 (1997).
[CrossRef]

Linnett, L. M.

B. R. Calder, L. M. Linnett, D. R. Carmichael, “Spatial stochastic models for seabed object detection,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds., Proc. SPIE3079, 172–182 (1997).
[CrossRef]

L. M. Linnett, S. J. Clarke, C. St. J. Reid, A. D. Tress, “Monitoring of the seabed using sidescan sonar and fractal processing,” in Conference of Underwater Acoustics Group (Institute of Acoustics, St. Albans, Hertfordshire, UK, 1993) Vol. 15, pp. 49–64.

Mignotte, M.

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Hybrid genetic optimization and statistical model-based approach for the classification of shadow shapes in sonar imagery,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 129–141 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Sonar image segmentation using an unsupervised hierarchical MRF model,” IEEE Trans. Image Process. 9, 1216–1231 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Three class Markovian segmentation of high resolution sonar images,” Comput. Vision Image Understand 76, 191–204 (1999).
[CrossRef]

Perez, P.

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Hybrid genetic optimization and statistical model-based approach for the classification of shadow shapes in sonar imagery,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 129–141 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Sonar image segmentation using an unsupervised hierarchical MRF model,” IEEE Trans. Image Process. 9, 1216–1231 (2000).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Three class Markovian segmentation of high resolution sonar images,” Comput. Vision Image Understand 76, 191–204 (1999).
[CrossRef]

Petillot, Y.

S. Reed, Y. Petillot, J. Bell, “An automated approach to the detection and extraction of mine features in sidescan sonar,” IEEE J. Ocean Eng. 28, 90–105 (2003).
[CrossRef]

S. Reed, J. Bell, Y. Petillot, “Unsupervised segmentation of object shadow and highlight using statistical snakes,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001) pp. 221–236.

Reed, S.

S. Reed, Y. Petillot, J. Bell, “An automated approach to the detection and extraction of mine features in sidescan sonar,” IEEE J. Ocean Eng. 28, 90–105 (2003).
[CrossRef]

S. Reed, J. Bell, Y. Petillot, “Unsupervised segmentation of object shadow and highlight using statistical snakes,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001) pp. 221–236.

Refregier, P.

C. Chesnaud, P. Refregier, V. Boulet, “Statistical region snake-based segmentation adapted to different physical noise models,” IEEE Trans. Pattern Anal. Mach. Intell. 21, 1145–1157 (1999).
[CrossRef]

Reid, C. St. J.

L. M. Linnett, S. J. Clarke, C. St. J. Reid, A. D. Tress, “Monitoring of the seabed using sidescan sonar and fractal processing,” in Conference of Underwater Acoustics Group (Institute of Acoustics, St. Albans, Hertfordshire, UK, 1993) Vol. 15, pp. 49–64.

Rucklidge, W. J.

D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge, “Comparing images using the Hausdorff distance,” IEEE Trans. Pattern Anal. Mach. Intell. 15, 850–863 (1993).
[CrossRef]

Smedley, L.

G. J. Dobeck, J. C. Hyland, L. Smedley, “Automated detection and classification of sea mines in sonar imagery,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds. Proc. SPIE3079, 90–110 (1997).
[CrossRef]

Solberg, A. H. S.

A. H. S. Solberg, A. K. Jain, T. Taxt, “Multisource classification of remotely sensed data: fusion of landsat TM and SAR images,” IEEE Trans. Geosci. and Remote Sens. 32, 768–778 (1994).
[CrossRef]

Stage, B.

B. Zerr, E. Bovio, B. Stage, “Automatic mine classification approach based on AUV manoeuvrability and the COTS side scan sonar,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001), pp. 315–322.

Taxt, T.

A. H. S. Solberg, A. K. Jain, T. Taxt, “Multisource classification of remotely sensed data: fusion of landsat TM and SAR images,” IEEE Trans. Geosci. and Remote Sens. 32, 768–778 (1994).
[CrossRef]

Tress, A. D.

L. M. Linnett, S. J. Clarke, C. St. J. Reid, A. D. Tress, “Monitoring of the seabed using sidescan sonar and fractal processing,” in Conference of Underwater Acoustics Group (Institute of Acoustics, St. Albans, Hertfordshire, UK, 1993) Vol. 15, pp. 49–64.

Vidal-Madjar, D.

S. LeHegart-Mascle, I. Bloch, D. Vidal-Madjar, “Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing,” IEEE Trans. Geosci. Remote Sens. 35, 1018–1031 (1997).
[CrossRef]

Yao, K.

P. Galerne, K. Yao, G. Burel, “Object classification using neural networks in sonar imagery,” in New Image Processing Techniques and Applications: Algorithms, Methods, and Components II, P. Refregier, R.-J. Ahlers, eds., Proc. SPIE3101, 306–314 (1997).
[CrossRef]

Zerr, B.

B. Zerr, E. Bovio, B. Stage, “Automatic mine classification approach based on AUV manoeuvrability and the COTS side scan sonar,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001), pp. 315–322.

Comput. Vision Image Understand (1)

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Three class Markovian segmentation of high resolution sonar images,” Comput. Vision Image Understand 76, 191–204 (1999).
[CrossRef]

IEEE J. Ocean Eng. (1)

S. Reed, Y. Petillot, J. Bell, “An automated approach to the detection and extraction of mine features in sidescan sonar,” IEEE J. Ocean Eng. 28, 90–105 (2003).
[CrossRef]

IEEE Trans. Geosci. and Remote Sens. (1)

A. H. S. Solberg, A. K. Jain, T. Taxt, “Multisource classification of remotely sensed data: fusion of landsat TM and SAR images,” IEEE Trans. Geosci. and Remote Sens. 32, 768–778 (1994).
[CrossRef]

IEEE Trans. Geosci. Remote Sens. (1)

S. LeHegart-Mascle, I. Bloch, D. Vidal-Madjar, “Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing,” IEEE Trans. Geosci. Remote Sens. 35, 1018–1031 (1997).
[CrossRef]

IEEE Trans. Image Process. (2)

M. L. Comer, E. J. Delp, “Segmentation of textured images using a multiresolution Gaussian autoregressive model,” IEEE Trans. Image Process. 8, 408–420 (1999).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Sonar image segmentation using an unsupervised hierarchical MRF model,” IEEE Trans. Image Process. 9, 1216–1231 (2000).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell. (4)

S. Geman, D. Geman, “Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images,” IEEE Trans. Pattern Anal. Mach. Intell. 6, 721–741 (1984).
[CrossRef] [PubMed]

D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge, “Comparing images using the Hausdorff distance,” IEEE Trans. Pattern Anal. Mach. Intell. 15, 850–863 (1993).
[CrossRef]

C. Chesnaud, P. Refregier, V. Boulet, “Statistical region snake-based segmentation adapted to different physical noise models,” IEEE Trans. Pattern Anal. Mach. Intell. 21, 1145–1157 (1999).
[CrossRef]

M. Mignotte, C. Collet, P. Perez, P. Bouthemy, “Hybrid genetic optimization and statistical model-based approach for the classification of shadow shapes in sonar imagery,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 129–141 (2000).
[CrossRef]

IEEE Trans. Syst. Man Cybern. (1)

I. Bloch, “Information combination operators for data fusion: a comparative review with classification,” IEEE Trans. Syst. Man Cybern. 26, 52–67 (1996).
[CrossRef]

J. R. Stat. Soc. Ser. B. Methodol. (1)

J. Besag, “on the statistical analysis of dirty pictures,” J. R. Stat. Soc. Ser. B. Methodol. 48, 259–302 (1986).

Pattern Recog. Lett. (1)

I. Bloch, “Some aspects of Dempster-Shafer evidence theory for classification of multi-modality medical images taking partial volume effect into account,” Pattern Recog. Lett. 17, 905–919 (1996).
[CrossRef]

Other (10)

E. Dura, J. Bell, D. Lane, “Superellipse fitting for the classification of mine-like shapes in side-scan sonar images,” Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2002), Vol. 1, pp. 23–28.

S. Reed, J. Bell, Y. Petillot, “Unsupervised segmentation of object shadow and highlight using statistical snakes,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001) pp. 221–236.

B. Zerr, E. Bovio, B. Stage, “Automatic mine classification approach based on AUV manoeuvrability and the COTS side scan sonar,” in Autonomous Underwater Vehicle and Ocean Modelling Networks: GOATS 2000 Conference Proceedings CP-46, (NATO Saclant Undersea Research Centre, La Spezia, Italy, 2001), pp. 315–322.

G. J. Dobeck, J. C. Hyland, L. Smedley, “Automated detection and classification of sea mines in sonar imagery,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds. Proc. SPIE3079, 90–110 (1997).
[CrossRef]

C. M. Ciany, J. Huang, “Computer aided detection/computer aided classification and data fusion algorithms for automated detection and classification of underwater mines,” in Proceedings of the MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2000), Vol. 1, pp. 277–284.

T. Aridgides, M. Ferdandez, G. Dobeck, “Fusion of adaptive algorithms for the classification of sea mines using high resolution side scan sonar in very shallow water,” in Proceedings of MTS/IEEE Oceans Conference and Exhibition, (Institute of Electrical and Electronics Engineers, New York, 2001), Vol. 1, pp. 135–142.

L. M. Linnett, S. J. Clarke, C. St. J. Reid, A. D. Tress, “Monitoring of the seabed using sidescan sonar and fractal processing,” in Conference of Underwater Acoustics Group (Institute of Acoustics, St. Albans, Hertfordshire, UK, 1993) Vol. 15, pp. 49–64.

B. R. Calder, L. M. Linnett, D. R. Carmichael, “Spatial stochastic models for seabed object detection,” in Detection and Remediation Technologies for Mines and Minelike Targets II, A. C. Dubey, R. L. Barnard, eds., Proc. SPIE3079, 172–182 (1997).
[CrossRef]

P. Galerne, K. Yao, G. Burel, “Object classification using neural networks in sonar imagery,” in New Image Processing Techniques and Applications: Algorithms, Methods, and Components II, P. Refregier, R.-J. Ahlers, eds., Proc. SPIE3101, 306–314 (1997).
[CrossRef]

J. Bell, “A Model for the Simulation of Sidescan Sonar,” Ph.D. dissertation (Heriot-Watt University, Edinburgh, Scotland, 1995).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (6)

Fig. 1
Fig. 1

As in radar, the wave (here it is sound) is blocked by objects and a shadow is generated. Given the relative position of the sonar fish, an estimate of the object’s height and size can therefore be obtained. This information can then be used to remove obvious false alarms.

Fig. 2
Fig. 2

Detection CSS model result for an image containing objects hidden within the sand ripple seafloor. The first image is the raw sidescan image. The second image contains the MRF detection result before the post-processing or CSS stages. The third image shows the detection result obtained. Accurate shadow segmentation results for all objects have been obtained due to the constrained movement of the CSS model.

Fig. 3
Fig. 3

Description of the shadow formation process. Individual pings are added together to form an overall sonar image (bottom left-hand side). Synthetic shadow representations from the three considered classes are also shown on the right-hand side: cylinder (top), sphere (middle), and truncated cone (bottom). These can be compared with the real sonar shadow to find a match.

Fig. 4
Fig. 4

Examples of (a) cylinder, (b) sphere, (c) truncated cone, and (d) clutter objects used to test the classification model.

Fig. 5
Fig. 5

Percentage of correctly classified mine objects plotted against the percentage incorrectly classified clutter objects.

Fig. 6
Fig. 6

(a) Four different views of the same cylinder. (b) Four different views of the same truncated cone. These views are taken from different directions, fish heights, and slant ranges.

Tables (2)

Tables Icon

Table 1 Belief Functions for Different Classes for the Individual Images and the Overall Fused Result for a Cylindrical Objecta

Tables Icon

Table 2 Belief Functions for Different Classes for the Individual Images and the Overall Fused Result for a Truncated Cone Objecta

Equations (15)

Equations on this page are rendered with MathJax. Learn more.

PX,O|Yx, o|y  PXxPO|Xo|xPY|Xy|x.
Ux, y, o=sS Φsxs, ys+s,t βst1-δxs, xt-sS δxs, e2lnΨXs-sS χsxs, os.
lgaussy, w=-Nh logθh-Np logθp-Nb logθb,
θu=1Nuwi,jΩu yi, j2-1Nuwi,jΩu yi, j2
logPmeanw=μ tanh12 αmΔ-β+c,
logPpositionw=C-t1U|Δmax|-ζ|Δmax|2-t2U|Δmin|-ζ|Δmin|2,
Jy, w=λ0 logPregw+1-λ0×λ1 logPpositionw+λ2ly, w+1.0-λ1-λ2logPmeanw,
HA, B=maxhA, B, hB, A
ha, b=maxaA minbB a-b
ωjfinalHj, Θjb, α=ωjhausHjωjparΘjbωjelongα.
ωjhausHj=1  if Hjm¯j=exp- Hj-m¯j22σj2 if Hj>m¯j,
m=0, A2D mA=1.
Bel=0, BelA=BA mB,  AD, A,
Pls=0, PlsA=BA mB,  AD, A.
m1  m2  mnA=B1Bn=A m1B1m2B2mnBn1-B1Bn= m1B1m2B2mnBn

Metrics