Results 171 to 180 of about 1,393 (219)

Object classification and acoustic imaging with active sonar

Journal of the Acoustical Society of America, 1992
The theoretical underpinnings of underwater acoustic classification and imaging using high-frequency active sonar are studied. All essential components of practical classification systems are incorporated in a Bayesian theoretic framework. The optimum decision rules and array processing are presented and evaluated.
John A Tague
exaly   +3 more sources

Automatic Object Classification with Active Sonar using Unsupervised Anomaly Detection

2020 28th European Signal Processing Conference (EUSIPCO), 2021
This work describes an unsupervised anomaly detection method for automatic contacts classification of an active sonar system. The proposed method refers to littoral, shallow water environments where there is a significant amount of clutter contacts from the seafloor and coastal reverberation.
Pietro Stinco, Alessandra Tesei, Kevin D Lepage   +2 more
exaly   +2 more sources

Temporal-Feature-Based Classification of Active Sonar Targets in a Deep-Water Environment

IEEE Transactions on Aerospace and Electronic Systems
Do-Hyun Park, Hyoung-Nam Kim, Myoungjun Cheong   +2 more
exaly   +3 more sources

Neural networks for active sonar classification

Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems, 2003
Active sonar classification has been a challenging pattern recognition problem for many years mainly due to the complexity of ocean environment. Improvement of sensors and data acquisition can be very costly and can only provide limited improvement in classification.
C.H. Chen
openaire   +2 more sources

Contrast models and classification of active sonar signals.

The Journal of the Acoustical Society of America, 2008
New features and algorithms are derived from human perception to improve the automation of active sonar signal classification. Data from human subject research on the perceived similarity of sound pairs can be assembled in the form of a dissimilarity matrix. A dissimilarity matrix can be analyzed in many ways, two of which are multidimensional scaling (
Charles F. Gaumond, Colin W. Jemmott, Derek Brock   +2 more
openaire   +2 more sources

Optimum classification with active sonar: new theoretical results

[Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing, 1991
Active underwater acoustic classification is a central sonar signal processing problem. The main thrust of this work is a critical evaluation of several key issues impacting on optimum processor implementation. To this end, the authors have developed systematic methods for evaluating the performance of the overall system.
James G. Kelly, Robert N. Carpenter, John A. Tague, Nicholas K. Haddad   +3 more
openaire   +2 more sources

Pseudo-hybrid PDF estimators for active sonar classification

The Journal of the Acoustical Society of America, 2003
A class of multivariate PDF estimators for use in feature-based target classification in active sonar is presented. The goal is to develop a method that (1) preserves feature identity, (2) captures complex data structures and tails using non-parametric estimates, (3) utilizes parametric models for higher-order inter-feature dependencies, and (4 ...
James M. Gelb, Mark A. Donnell, Brian R. La Cour   +2 more
openaire   +2 more sources

Classification of Underwater Targets with Active Sonar

Proceedings. The First IEEE Regional Conference on Aerospace Control Systems,, 2005
This paper presents an ongoing effort in early classification of underwater targets with active sonar returns. Active sonar will play an important role in future antisubmarine warfare, especially against highly silenced targets. The emphasis of the paper is placed on various aspects and methodologies applicable to the classification problem.
R. Harrison, null Chun Yang, null Ching-Fang Lin, T. Politopoulos, E. Chang   +4 more
openaire   +2 more sources

Applying neural networks to automatic active sonar classification

[1990] Proceedings. 10th International Conference on Pattern Recognition, 2002
The usefulness of applying neural network technology to active sonar classifier development is discussed. The authors offer qualitative results to help those interested in assessing this technology to reach a deeper understanding of its value. At a minimum, the nature of the observations strongly suggest that the best way to evaluate neural network ...
THOMAS B. HALEY
openaire   +2 more sources

A waveguide invariant adaptive matched filter for active sonar target depth classification

Journal of the Acoustical Society of America, 2011
This paper addresses depth discrimination of a water column target from bottom clutter discretes in wideband active sonar. To facilitate classification, the waveguide invariant property is used to derive multiple snapshots by uniformly sub-sampling the short-time Fourier transform (STFT) coefficients of a single ping of wideband active sonar data.
Ryan Goldhahn
exaly   +3 more sources