The problem of classification of underwater targets from the acoustic backscattered signals is considered. A wavelet packet-based feature extraction scheme is used in conjunction with the linear prediction coding scheme as the front-end processor. Selected features with higher discriminatory power are then fed to a neural network classifier. Several different classification systems are benchmarked in this paper. These include: an ellipsoidal K-nearest neighbor classifier, probabilistic neural networks and support vector machines. The performance of these classifiers are examined on a wideband 80 kHz acoustic backscattered data set collected for six different objects. These systems are then benchmarked with the previously used backpropagation neural network in terms of their receiver operating characteristic and robustness with respect to reverberation.
Comparison of confidence level of different classification paradigms for underwater target discrimination
2001
12 Seiten, 14 Quellen
Conference paper
English
akustische Signalverarbeitung , Rückwärtsstreuung , Bayes-Verfahren , Clutter , Fehlerstatistik , Merkmalextraktionsverfahren , Lernen , lernender Automat , Maximum-Likelihood-Schätzung , Bildklassifikation , Strahlennetz , Unterwasserschall , Wavelet-Transformation , Vertrauensbereich , neuronales Netz , Klassifizierung , Rückwärtsausbreitung , ROC-Kurve , Robustheit , Nachhall , Kreuzkorrelation , Kovarianzmatrix
Underwater Image Processing and Target Classification
British Library Conference Proceedings | 1995
|An adaptive underwater target classification system
Tema Archive | 1999
|Underwater target classification using wavelet packets and neural networks
Tema Archive | 1998
|UNDERWATER TARGET DETECTION SYSTEM AND UNDERWATER TARGET DETECTION METHOD THEREOF
European Patent Office | 2021
|