&lt;title&gt;Adaptive time-frequency classification of acoustic backscatter&lt;/title&gt;

Telfer, Brian A.; Szu, Harold; Dobeck, Gerald J.

doi:10.1117/12.205411

Cited by 5 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 1 we report the classification error rates obtained. The error rates at 15 dB are a factor of four lower than previously published results [7,8] …”

Section: Anajysiscontrasting

confidence: 58%

“…These were collected at aspect angles in 5 °increments on three different occasions. A total of 2 17 returns from each object was used, including low SNR returns not used in a previous analysis of this data set [7,8]. Returns from the two classes have similar power, duration and Fourier spectra, but show significant interciass variation in qualitative aspects in the time domain.…”

Section: Datamentioning

confidence: 99%

“…= a "2)(aco). 5 The wavelet transform [3,7] of any L2 function f with respect to the analyzing wavelet is the (complex) function of scale a and position b:…”

Section: The Wavelet Transformmentioning

confidence: 99%

See 2 more Smart Citations

<title>Classification of acoustic backscatter using the generalized target description</title>

Carter

Dobeck

1996

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

A new feature for the classification of echos of a transmitted signal based on the generalized target description is described, and a framework for adaptive classification using it is presented. The generalized target description is a parametric model for the target impulse response. The feature is an order parameter from this model, which can be computed empirically from the growth rate ofpower as a fimction of a scale for a certain wavelet transform ofthe echo. A set of acoustic backscatter data consisting ofretums from a mine and a rock with a linear FM transmit signal was analyzed. Parameters for the wavelet were computed from training sets so that this feature correctly distinguished 94% ofthe returns in test sets at 15 dB. The effectiveness ofthis feature as a classifier was found to degrade reasonably under increasing levels of synthetically generated reverberation noise. The simplest generalized target description model, a single order single center scatterer, was used. This model is not a realistic representation of the target impulse responses of either ofthe two objects, nevertheless it captured enough ofthe difference between the two to provide an effective classification tool.

show abstract

“…In Table 1 we report the classification error rates obtained. The error rates at 15 dB are a factor of four lower than previously published results [7,8] …”

Section: Anajysiscontrasting

confidence: 58%

Section: Datamentioning

confidence: 99%

See 1 more Smart Citation

<title>Classification of acoustic backscatter using the generalized target description</title>

Carter

Dobeck

1996

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…(2) w which gives11: wopt = (yTy)_lyTT (3) The single-aspect classification results of two different realizations based on the even aspect angle data set with different synthesized reverberation realizations were arranged in 3-aspect sequence form, e.g. {O, 30, 60}, .…”

Section: Linear Fusion Schemementioning

confidence: 99%

Underwater target classification using multi-aspect fusion and neural networks

1998

Self Cite

View full text Add to dashboard Cite

This paper presents an extension of the research work on the wavelet-based classification scheme developed to discriminate underwater mine-like from non-mine-like objects using the acoustic backscattered signals.1 Based on the single-aspect classification results, the robustness and discriminatory power of the selected features, and the generalization ability of the trained network are demonstrated on several cases. To further improve the overall classification accuracy, the classification results of multiple aspect angles are fused together. Two different fusion approaches are considered and their performance is tested on ten different realizations. The final results show excellent classification accuracy of 96% for only a 4% false alarm rate.

show abstract

“…They used simple spectral features as the input to the neural-network classifier in order to distinguish a cylindrical target from a rock with similar shape. The method in [11] uses the resonant scattering property of underwater objects that is dependent on the object size, shape, structure, and composition. A signal processing scheme called "G-Transform," which consists of three sequential fast Fourier transform (FFT) of the backscattered signals, was developed [12] to represent the resonance or the modulation on the frequency spectrum of the backscattered signal.…”

Section: Introductionmentioning

confidence: 99%

Underwater target classification using wavelet packets and neural networks

Huang

Azimi-Sadjadi

Tian³

et al.

1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat

View full text Add to dashboard Cite

Abstract-In this paper, a new subband-based classification scheme is developed for classifying underwater mines and mine-like targets from the acoustic backscattered signals. The system consists of a feature extractor using wavelet packets in conjunction with linear predictive coding (LPC), a feature selection scheme, and a backpropagation neural-network classifier. The data set used for this study consists of the backscattered signals from six different objects: two mine-like targets and four nontargets for several aspect angles. Simulation results on ten different noisy realizations and for signal-to-noise ratio (SNR) of 12 dB are presented. The receiver operating characteristic (ROC) curve of the classifier generated based on these results demonstrated excellent classification performance of the system. The generalization ability of the trained network was demonstrated by computing the error and classification rate statistics on a large data set. A multiaspect fusion scheme was also adopted in order to further improve the classification performance.

show abstract

<title>Adaptive time-frequency classification of acoustic backscatter</title>

Cited by 5 publications

References 14 publications

<title>Classification of acoustic backscatter using the generalized target description</title>

<title>Classification of acoustic backscatter using the generalized target description</title>

Underwater target classification using multi-aspect fusion and neural networks

Underwater target classification using wavelet packets and neural networks

Contact Info

Product

Resources

About