Multi-Feature Extraction and Fusion for the Underwater Moving Targets Classification

Abstract:

The underwater moving targets classfication are important for the underwater surveillance system.This paper presents the classification algrithms based on the multi-feature fusion, including the target echo highlight features,temporal features from the assocition images interframe,and the moving features after tracking.The principal compoment analysis was used to reduce the feature dimension and the k-means algorithm was used for classification. At last,the experiment results of the classification between the divers and underwater vehicles are given, which show that the multifeature fusion can improve the classification performance.And the PCA algorithm can reduce the feature dimension without lower the identification probability.

• Periodical: Applied Mechanics and Materials (Volumes 303-306)
• Pages: 1357-1360
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.303-306.1357
• Online since: February 2013
• Authors: Juan Yang, Feng Xu, Zhi Heng Wei, Jia Liu, Xu Dong An
• Keywords: Classification, Highlight Features, K-Mean, Moving Features, Principal Component Analysis (PCA), Underwater Moving Target

References

[1] Perry, S.W. and G. Ling, Pulse-length-tolerant features and detectors for sector-scan sonar imagery. 2004. 29(1): pp.138-156.

DOI: 10.1109/joe.2003.819312

[2] Chantler, M.J. and J.P. Stoner, Automatic interpretation of sonar image sequences using temporal feature measures. 1997. 22(1): pp.47-56.

DOI: 10.1109/48.557539

[3] Lane, D.M., et al. Tracking and classification of multiple objects in multibeam sector scan sonar image sequences. in Underwater Technology, 1998. Proceedings of the 1998 International Symposium on. (1998).

DOI: 10.1109/ut.1998.670107

[4] Chantler, M.J. and J.P. Stoner. Robust classification of sector-scan sonar image sequences. in OCEANS 94. 'Oceans Engineering for Today's Technology and Tomorrow's Preservation., Proceedings. (1994).

DOI: 10.1109/oceans.1994.364111

[5] Perry, S.W. and G. Ling. Detection of small man-made objects in sector scan imagery usingneural networks. in OCEANS, 2001. MTS/IEEE Conference and Exhibition. (2001).

DOI: 10.1109/oceans.2001.968325

[6] Tena Ruiz, I., D.M. Lane, and M.J. Chantler, A comparison of inter-frame feature measures for robust object classification in sector scan sonar image sequences. 1999. 24(4): pp.458-469.

DOI: 10.1109/48.809266

[7] Jae-Byung Jung, Gerald F. Denny, Broadband Active Sonar Swimmer Detection and Identification. International Joint Conference on Neural Networks. 2006. pp.2600-2605.

DOI: 10.1109/ijcnn.2006.247137