Abstract | ||
---|---|---|
Automatic target recognition (ATR) of objects in side scan sonar imagery typically employs image processing techniques (e.g segmentation, Fourier transform) to extract features describing the objects The features are used to discriminate between sea floor clutter and targets (e.g sea mines) These methods are typically developed for a specific sonar, and are computationally intensive The present work used the Restricted Boltzmann Machine (RBM) to discriminate between images of targets and clutter, achieving a 90% probability of detection and a 15% probability of false alarm, which is comparable to the performance of a Support Vector Machine (SVM) and other state-of-the-art methods on the data The RBM method uses raw image pixels and thus avoids the issue of manually selecting good representations (features) of the data. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-13059-5_47 | Canadian Conference on AI |
Keywords | Field | DocType |
rbm method,support vector machine,image processing technique,restricted boltzmann machine,sea floor clutter,specific sonar,sonar imagery,raw image pixel,g segmentation,g sea mine,mine-like object,boltzmann machine,probability of detection,fourier transform,automatic target recognition | Boltzmann machine,False alarm,Computer science,Image processing,Sonar,Artificial intelligence,Computer vision,Restricted Boltzmann machine,Pattern recognition,Automatic target recognition,Clutter,Support vector machine,Machine learning | Conference |
Volume | ISSN | ISBN |
6085 | 0302-9743 | 3-642-13058-5 |
Citations | PageRank | References |
1 | 0.37 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Warren A. Connors | 1 | 3 | 1.10 |
Patrick C. Connor | 2 | 11 | 1.95 |
Thomas Trappenberg | 3 | 22 | 2.85 |