Automated Approach To Classification Of Mine-Like Objects Using Multiple-Aspect Sonar Images

Wang, Xiaoguang; Liu, Xuan; Japkowicz, Nathalie; Matwin, Stan

doi:10.1515/jaiscr-2015-0004

Abstract

In this paper, the detection of mines or other objects on the seabed from multiple side-scan sonar views is considered. Two frameworks are provided for this kind of classification. The first framework is based upon the Dempster–Shafer (DS) concept of fusion from a single-view kernel-based classifier and the second framework is based upon the concepts of multi-instance classifiers. Moreover, we consider the class imbalance problem which is always presents in sonar image recognition. Our experimental results show that both of the presented frameworks can be used in mine-like object classification and the presented methods for multi-instance class imbalanced problem are also effective in such classification.

References

[1] B. Zerr, B. Stage. Three-dimensional reconstruction of underwater objects from a sequence of sonar images, Proceedings of the IEEE International Conference on Image Processing, pp. 927–930, (1996).
Search in Google Scholar
[2] B. Zerr, B. Stage and A. Guerrero, Automatic Target Classification Using Multiple Sidescan Sonar Images of Different Orientations, SACLANT CEN Memorandum SM-309 (1997).
Search in Google Scholar
[3] B. Zerr, E. Bovio, B. Stage, Automatic mine classification approach based on AUV manoeuverability and cots side scan sonar, Proceedings of Goats 2001 Conference, La Spezia, Italy, (2001).
Search in Google Scholar
[4] M. Couillard, J. Fawcett, M. Davison and V. Myers, Optimizing time-limited multi-aspect classification, Proceedings of the Institute of Acoustics 29(6), 89-96 (2007).
Search in Google Scholar
[5] J. Fawcett, V. Myers, D. Hopkin, A. Crawford, M. Couillard, B. Zerr. Multiaspect classification of sidescan sonar images: Four different approaches to fusing single-aspect information, Oceanic Engineering, IEEE Journal of 35(4): 863–876 (2010).
Search in Google Scholar
[6] S. Reed, Y. Petillot, J. Bell, Model-based approach to the detection and classification of mines in side scan sonar, Applied Optics 43(2): 237–246. (2004).10.1364/AO.43.00023714735943
Search in Google Scholar
[7] S. Reed, Y. Petillot, J. Bell, Automated approach to classification of mine-like features in sidescan sonar using highlight and shadow information, IEE Proc. Radar, Sonar & Navigation 151 (No.1), 48-56, (2004).10.1049/ip-rsn:20040117
Search in Google Scholar
[8] V. Myers, D. P. Williams, A POMDP for multiview target classification with an autonomous underwater vehicle, OCEANS, pp. 1-5, (2010).10.1109/OCEANS.2010.5664609
Search in Google Scholar
[9] V. Myers, D. P. Williams, Adaptive Multiview Target Classification in Synthetic Aperture Sonar Images Using a Partially Observable Markov Decision Process, Oceanic Engineering, IEEE Journal of, On page(s): 45 - 55, Volume: 37 Issue: 1, Jan. (2012)10.1109/JOE.2011.2175510
Search in Google Scholar
[10] D. Williams, V. Myers, and M. Silvious, ”Mine Classification with Imbalanced Data,” IEEE Geoscience and Remote Sensing Letters, Vol. 6, No. 3, pp. 528-532, July 2009.10.1109/LGRS.2009.2021964
Search in Google Scholar
[11] G. Dobeck, “Fusing sonar images for mine detection and classification,” Proc. SPIE—Int. Soc. Opt. Eng., vol. 3710, 1999, DOI: 10.1117/12.357082.10.1117/12.357082
Search in Google Scholar
[12] J. Tucker, N. Klausner, and M. Azimi-Sadjadi, “Target detection in M-disparate sonar platforms using multichannel hypothesis testing,” in Proc. OCEANS Conf., Quebec City, QC, Canada, 2008, DOI: 10.1109/OCEANS.2008.5151818.10.1109/OCEANS.2008.5151818
Search in Google Scholar
[13] M. Azimi-Sadjadi, A. Jamshidi, and G. Dobeck, “Adaptive underwater target classification with multi-aspect decision feedback,” Proc. SPIE— Int. Soc. Opt. Eng., vol. 4394, 2001, DOI: 10.1117/12.445444.10.1117/12.445444
Search in Google Scholar
[14] X. Xu and E. Frank. Logistic regression and boosting for labeled bags of instances. In Lecture Notes in Computer Science, volume 3056, pages 272–281, April 2004.10.1007/978-3-540-24775-3_35
Search in Google Scholar
[15] Hall, D. L. and Steinberg, A.. Dirty Secrets in Multisensor Data Fusion, http://www.dtic.mil. (2001).10.21236/ADA394631
Search in Google Scholar
[16] Blockeel, H., Page, D., Srinivasan, A.: Multiinstance tree learning. In: ICML (2005).10.1145/1102351.1102359
Search in Google Scholar
[17] Quinlan, J. R. C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, (1993).
Search in Google Scholar
[18] Hosmer, David W.; Lemeshow, Stanley. Applied Logistic Regression (2nd ed.). Wiley. (2000).10.1002/0471722146
Search in Google Scholar
[19] Freund, Y., Schapire,R.E.: Experiments with a new boosting algorithm. In: Machine Learning: Proceedings of the Thirteenth International Conference, pp. 148–156 (1996)
Search in Google Scholar
[20] Kubat, M., & Matwin, S.: Addressing the curse of imbalanced training sets: One-sided selection. In: Proceddings of the Fourteenth International Conference on Machine Learning, 179-186 (1997)
Search in Google Scholar
[21] Dietterich, T., Lathrop, R., Lozano-Perez, T.: Solving the multiple instance problem with the axisparallel rectangles. In: Artificial Intelligence, 89(1-2), 31–71 (1997)10.1016/S0004-3702(96)00034-3
Search in Google Scholar
[22] Maron, O., Lozano-Pz T.: A framework for multiple instance learning. In: Proc. of the 1997 Conf. on Advances in Neural Information Processing Systems 10, p.570-576 (1998)
Search in Google Scholar
[23] Fan, W., Stolfo,S.J., Zhang,J., Chan,P.K.: Ada-Cost: Misclassification Cost-Sensitive Boosting. In: Proc. Int’l Conf. Machine Learning, pp. 97-105 (1999)
Search in Google Scholar
[24] Schapire,R.E., Singer,Y.: Improved boosting algorithms using confidence-rated predictions. In: Machine Learning, 37 (3) 297–336 (1999)10.1023/A:1007614523901
Search in Google Scholar
[25] Ting, K.M.: A Comparative Study of Cost-Sensitive Boosting Algorithms. In: Proc. Int’l Conf. Machine Learning, pp. 983-990 (2000)
Search in Google Scholar
[26] Wang, J., Zucker, J.D.: Solving the multipleinstance problem: A lazy learning approach. In: ICML (2000)
Search in Google Scholar
[27] Japkowicz, N.: Learning from Imbalanced Data Sets: A Comparison of Various Strategies. In: Proc. Am. Assoc. for Artificial Intelligence(AAAI) Workshop Learning from Imbalanced Data Sets, pp. 10-15. (Technical Report WS-00-05) (2000)
Search in Google Scholar
[28] Zhang, Q., Goldman, S. A.: EM-DD: An improved multiple instance learning technique. In: Neural Information Processing Systems 14 (2001)
Search in Google Scholar
[29] Elkan, C.: The Foundations of Cost-Sensitive Learning. In: Proc. Int’l Joint Conf. Artificial Intelligence, pp. 973-978 (2001)
Search in Google Scholar
[30] Ting, K.M.: An Instance-Weighting Method to Induce Cost-Sensitive Trees. In: IEEE Trans. Knowledge and Data Eng., vol. 14, no. 3, pp. 659-665 (2002)10.1109/TKDE.2002.1000348
Search in Google Scholar
[31] Chawla,N. V., Bowyer,K. W., Hall,L. O., Kegelmeyer, W. P.: SMOTE: Synthetic Minority Over-sampling Technique. In: Journal of Artificial Intelligence Research, 16: 321-357 (2002)10.1613/jair.953
Search in Google Scholar
[32] Zhang, M.L., Goldman, S.: Em-dd: An improved multi-instance learning technique. In: NIPS (2002)
Search in Google Scholar
[33] Andrews, S., Tsochandaridis, I., Hofman, T.: Support vector machines for multiple instance learning. In: Adv. Neural. Inf. Process. Syst. 15, 561–568 (2003)
Search in Google Scholar
[34] Batista, G.E.A.P.A., Prati,R.C., Monard,M.C.: A Study of the Behavior of Several Methods for Balancing Machine Learning Training Data. In: ACM SIGKDD Explorations Newsletter, vol. 6, no. 1, pp. 20-29 (2004)10.1145/1007730.1007735
Search in Google Scholar
[35] Blockeel, H., Page, D., Srinivasan, A.: Multiinstance tree learning. In: ICML (2005)10.1145/1102351.1102359
Search in Google Scholar
[36] Sun,Y., Kamel,M.S., Wong, A.K.C., Wang, Y.: Cost-Sensitive Boosting for Classification of Imbalanced Data. In: Pattern Recognition, vol. 40, no. 12, pp. 3358-3378 (2007)10.1016/j.patcog.2007.04.009
Search in Google Scholar
[37] Foulds, J., Frank, E.: Revisiting multiple-instance learning via embedded instance selection. In: W. Wobcke & M. Zhang(Eds), 21st Australasian Joint Conference on Artificial Intelligence Auckland, New Zealand, (pp. 300-310) (2008)10.1007/978-3-540-89378-3_29
Search in Google Scholar
[38] Leistner, C., Saffari, A., and Bischof, H.: MIForests: Multiple Instance Learning with Randomized Trees. In: Proc. ECCV (2010)10.1007/978-3-642-15567-3_3
Search in Google Scholar
[39] Bjerring, L., Frank, E.: Beyond trees: Adopting MITI to learn rules and ensemble classifiers for multi-instance data. In: D. Wang & M. Reynolds (Eds.), AI 2011, LNAI 7106 (pp. 41-50) (2011)10.1007/978-3-642-25832-9_5
Search in Google Scholar
[40] Japkowicz, N., Shah, M.: Evaluating Learning Algorithms: A Classification Perspective. Cambridge University Press (2011)10.1017/CBO9780511921803
Search in Google Scholar
[41] Shawe-Taylor, J. and Cristianini, N.: Further results on the margin distribution. In: Proceedings of the 12th Conference on Computational Learning Theory, 278-285 (1999)10.1145/307400.307470
Search in Google Scholar
[42] Morik, K., Brockhausen, P., Joachims, T.: Combining Statistical Learning with a Knowledge-Based Approach - A Case Study in Intensive Care Monitoring. In: ICML: 268-277 (1999)
Search in Google Scholar
[43] Veropoulos, K., Campbell, C., & Cristianini, N.: Controlling the sensitivity of support vector machines. In: Proceedings of the International Joint Conference on Artificial Intelligence, 55–60. (1999)
Search in Google Scholar
[44] Chih-Chung Chang and Chih-Jen Lin.: LIBSVM : a library for support vector machines. In: ACM Transactions on Intelligent Systems and Technology, 2:27:1–27:27, (2011)10.1145/1961189.1961199
Search in Google Scholar
[45] Chin-Wei Hsu, Chih-Chung Chang and Chih-Jen Lin.: A practical guide to support vector classification. In: Technical Report, National Taiwan University. (2010)
Search in Google Scholar
[46] Bergstra, James; Bengio, Yoshua. :Random Search for Hyper-Parameter Optimization. In: J. Machine Learning Research 13: 281-305. (2012)
Search in Google Scholar
[47] Wang, X., Shao, H., Japkowicz, N., Matwin, S., Liu, X., Bourque, A., Nguyen, B.: Using SVM with Adaptively Asymmetric Misclassification Costs for Mine-Like Objects Detection. In: ICMLA (2012)10.1109/ICMLA.2012.227
Search in Google Scholar
[48] Wang, X., Matwin, S., Japkowicz, N., Liu, X.: Cost-Sensitive Boosting Algorithms for Imbalanced Multi-instance Datasets. In: Canadian Conference on AI (2013)10.1007/978-3-642-38457-8_15
Search in Google Scholar
[49] Hosmer, David W. Lemeshow, Stanley: Applied Logistic Regression. Wiley. ISBN 0-471-35632-8.200010.1002/0471722146
Search in Google Scholar

Automated Approach To Classification Of Mine-Like Objects Using Multiple-Aspect Sonar Images

Abstract

Paradigm

My account