Classification performance assessment in side scan sonar image while underwater target object recognition using random forest classifier and support vector machine
Keywords:Underwater mine, SONAR image, side scan sonar image, random forest classifier, mine like object detection, non mine like object detection.
Ocean mine have been a major threat to the safety of vessels and human lives for many years. Identification of mine-like objects is a pressing need for military, and other ocean meets. In mine, countermeasures operations, sonar equipment are utilised to detect and classify mine- like objects if their sonar signatures are similar to known signatures of mines. The classification of underwater mines is an important task, for the safety of ports, harbors and the open sea. Mine detection is needed in military applications because it has been a threat to many lives and vessels. Although the task of finding mine like objects has received recent attention, very little has been published on the problem of discriminating mine-like (target) objects (MLO) and non-mine like (target) objects of similar size and shape. This paper deals with the recognition of mine like and non mine like objects. The recognition is done through robust Random Forest technique.
 Tai F, Kraus D & Zoubir AM, â€œContributions to Automatic Target Recognition Systems for Underwater Mine Classificationâ€, IEEE Transactions on Geo science and Remote Sensing, (2015).
 Bryan DT, Jered C, Mahmood RA & Schock SG, â€œA Multichannel Canonical Correlation Analysis Feature Extraction with Application to Buried Underwater Target Classificationâ€, IEEE International Joint Conference on Neural Network Proceedings, (2006).
 Stewart WK, Min J & Marra M, â€œA neural network approach to classification of sidescan sonar imagery from a midocean ridge areaâ€, IEEE Journal of Oceanic Engineering (1994).
 Castellano AR & Gray BC, â€œAutonomous interpretation of side scan sonar returnsâ€, Symposium on Autonomous Underwater Vehicle Technology, 1990.
 JoEllen W & Robert JM & Jason S, â€œContourlet Detection and Feature Extraction for Automatic Target Recognitionâ€, IEEE International Conference on Systems, Man, and Cybernetics San Antonio, (2009).
 Breiman L, â€œRandom Forestsâ€, Machine Learning, Vol.45, (2001), pp. 5-32.
 Johnson S & Deaett A, â€œThe application of automated recognition techniques to side-scan sonar imageryâ€, IEEE J. Ocean. Eng., Vol.19, No.1, (1994), pp.138â€“144.
 Henriksen L, â€œReal-time underwater object detection based on an electricallyscanned high-resolution sonarâ€, In Proc. Symp. Auton. UnderwaterVeh. Technol., (1994), pp.99â€“104.
 Fandos R. & Zoubir AM, â€œOptimal feature set for automaticdetection and classification of underwater objects in SAS imagesâ€, IEEE J. Sel. Topics Signal Process., Vol.5, No.3, (2011), pp.454â€“468.
 Piper JE, Lim R, Thorsos EI & Williams KL, â€œBuried spheredetection using a synthetic aperture sonarâ€, IEEE J. Ocean. Eng., Vol.34, No.4, (2009), pp.485â€“494.
 Hayes M & Gough P, â€œSynthetic aperture sonar: A review ofcurrent statusâ€, IEEE J. Ocean. Eng., Vol.34, No.3, (2009), pp. 207â€“224.
 Piper J, Commander K, Thorsos E & Williams K, â€œDetection of buried targets using a synthetic aperture sonarâ€, IEEE J. Ocean. Eng., Vol.27, No.3, (2002), pp.495â€“504.
 Fandos R, Zoubir AM & Siantidis K, â€œUnified design of a featurebased ADAC system for mine hunting using synthetic aperturesonarâ€, IEEE Trans. Geosci. Remote Sens., Vol.52, No.5, (2014). pp.2413â€“2426.
 Myers V. & Williams D, â€œAdaptive multiview target classification insynthetic aperture sonar images using a partially observable Markovdecision processâ€, IEEE J. Ocean. Eng., Vol.37, No.1, (2012), pp.45â€“55.
 Fei T. & Kraus D, â€œAn expectation-maximization approach assisted byD empster Shafer theory and its application to sonar image segmentationâ€, in Proc. IEEE ICASSP, (2012), pp.1161â€“1164.
 Fandos R & Zoubir AM, â€œEnhanced initialization scheme for a three region Markovian segmentation algorithm and its application to SAS imagesâ€, Proc. 10th ECUA, Vol.3 (2010), pp.1323â€“ 1331.
 Kumudham R & Rajendran V, â€œObject recognition in underwater sonar images using support vector machineâ€, International Journal of Control Theory and Applications (IJCTA), Vol.10, No. 32, (2017), pp.283-290.
 Reed S, Petillot Y & Bell J, â€œAn automatic approach to the detectionand extraction of mine features in sidescan sonarâ€, IEEE J. Ocean. Eng., Vol.28, No.1, (2003), pp.90â€“105.
 Yang M, Kpalma K & Ronsin J, â€œA Survey of Shape Feature Extraction Techniquesâ€, InTech, Vol.3 (2008), pp.43â€“90.
 Tang Y, Li B, Ma H & Lin J, â€œRing-projection-wavelet-fractal signatures:A novel approach to feature extractionâ€, IEEE Trans. CircuitsSyst. II, Analog Digit. Signal Process., Vol.45, No.8, (1998), pp.1130â€“1134.
 Weszka JS, C. R. Dyer, and A. Rosenfeld, â€œA comparative study of texture measures for terrain classification,â€ IEEE Trans. Syst., Man, Cybern.,vol. SMC-6, No.4, pp. 269â€“285, (1976).
 Kumudham R & Rajendran V, â€œSide scan sonar image denoising and classificationâ€, Journal of Advanced Research in Dynamical & Control Systems, (2017), pp.55-65.
 Kumudham R & Rajendran V, â€œImplementation of various segmentation algorithms on side scan sonar images and analysing its performanceâ€, ARPN, Vol.12, No.8, (2017), pp.2396-2400.
 Kumudham R & Rajendran V, â€œSpeeded up robust feature extraction from underwater sonar imagesâ€, International Journal of Control Theory and Appplications (IJCTA), Vol.10, No.32, (2017), pp.277-282.
 Kumudham R, DhanalakshmiASG, & Rajendran V, â€œComparison of The Performance Metrics of Median Filter and Wavelet Filter when applied on Sonar Images for Denoisingâ€, IEEE sponsored International Conference on Computation of Power Energy Information and Communication, (2016).
View Full Article:
How to Cite
LicenseAuthors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under aÂ Creative Commons Attribution Licensethat allows others to share the work with an acknowledgement of the work''s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal''s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (SeeÂ The Effect of Open Access).