期刊名称:International Journal of Soft Computing & Engineering
电子版ISSN:2231-2307
出版年度:2011
卷号:1
期号:5
页码:150-157
出版社:International Journal of Soft Computing & Engineering
摘要:Mine detection and classification using side scan sonar imagery is a challenging problem. As opposed to the majority of techniques, several Neural-network-based methods for the detection and classification of mines and mine like objects have been proposed. Detection and classification of underwater objects in sonar imagery is a complicated problem, due to various factors such as variations in operating and environmental conditions, presence of spatially varying clutter, variations in target shapes, compositions and orientation. Moreover, bottom features such as coral reefs, sand formations, and the attenuation of the sonar signal in the water column can totally obscure a mine-like object. Side scan sonar is a proven tool for detection of underwater objects. In order to overcome such complicated problems detection and classification system is needed. This method is able to extrapolate beyond the training data and successfully classify mine-like objects (MLOs). Five basic components of detection and classification techniques are considered namely data preprocessing, segmentation, feature extraction, detection and classification. In this paper nearly fifteen research papers of neural network techniques have been reviewed.