&lt;title&gt;Automated detection and classification of sea mines in sonar imagery&lt;/title&gt;

Dobeck, Gerald J.; Hyland, John C.; Smedley, Le'Derick

doi:10.1117/12.280846

Cited by 123 publications

(80 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, such objects will also block the signal from reaching the seabed behind them, thus creating a shadow region. This motivated Dobeck et al to construct a matched filter that comprises a highlight region, dead-zone, and shadow region [4]. Depending on seabed elevation, the shadow length will vary significantly with respect to range.…”

Section: Matched Filtermentioning

confidence: 99%

“…Unlike Dobeck et al [4], our matched filter is constructed as a superposition of rasied cosines rather than their step functions. Our reasoning is motivated by the fact that the sand ripples in our data cannot be well approximated by pure sinusoidal plane waves.…”

Section: Matched Filtermentioning

confidence: 99%

“…Firstly, a detector is applied to eliminate any areas of the image which can be easily distinguished from the targets. A good example of such a detector is the matched filter, first proposed for mine hunting by Dobeck et al [4]. This initial screening or detection stage is designed to accept a large number of false positives (natural background) in order to capture all of the true positives (the mines).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fractal dimension, wavelet shrinkage and anomaly detection for mine hunting

Nelson

Kingsbury

2012

IET Signal Process.

View full text Add to dashboard Cite

An anomaly detection approach is considered for the mine hunting in sonar imagery problem. We exploit previous work that used dual-tree wavelets and fractal dimension to adaptively suppress sand ripples and a matched filter as an initial detector. Here, lacunarity inspired features are extracted from the remaining false positives, again using dual-tree wavelets. A one-class support vector machine is then used to learn a decision boundary, based only on these false positives. The approach exploits the large quantities of 'normal' natural background data available but avoids the difficult requirement of collecting examples of targets in order to train a classifier.

show abstract

Section: Matched Filtermentioning

confidence: 99%

Section: Matched Filtermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fractal dimension, wavelet shrinkage and anomaly detection for mine hunting

Nelson

Kingsbury

2012

IET Signal Process.

View full text Add to dashboard Cite

show abstract

“…The sea-mine images were segmented to three regions: echo, shadow, and sea-bottom reverberation areas, based on different MRF models, estimated for the different classes. Dobeck et al [4] implemented a matched filter, K-nearest neighbor neural network classifier, and a discriminatory filter classifier to detect such mine-like objects in sonar images. The classification process employs up to 45 features for every possible mine-like object.…”

Section: Sea-mine Sonar Imagesmentioning

confidence: 99%

“…The classification process employs up to 45 features for every possible mine-like object. The detection in [4] is based on a large collection of mine-like objects signatures. In the example presented here, no real signature examples are used for defining the signal subspace.…”

Section: Sea-mine Sonar Imagesmentioning

confidence: 99%

Anomaly subspace detection based on a multi-scale Markov random field model

Goldman

Cohen

2005

Signal Processing

View full text Add to dashboard Cite

In this paper we introduce a multi-scale Gaussian Markov random field (GMRF) model and a corresponding anomaly subspace detection algorithm. Natural clutter images, often appear to have several periodical patterns of various period lengths. In such cases, the GMRF model may not sufficiently describe the clutter image. The proposed model is based on a multi-scale wavelet representation of the image, independent component analysis, and modeling each independent component as a GMRF. Anomaly detection is subsequently carried out by applying a matched subspace detector to the innovations process generated by the presumed model. The robustness of the proposed approach is demonstrated with application to automatic target detection in synthetic and real imagery. A quantitative performance analysis and experimental results demonstrate the advantage of the proposed method in comparison to competing methods. r

show abstract

Semisupervised Local Fusion Approach for Mine Detection in SONAR Data

Ismail

Bchir

2015

Int. J. Intell. Syst.

View full text Add to dashboard Cite

In this paper, we propose a novel approach for automatic mine detection in SOund NAvigation and Ranging (SONAR) data. The proposed framework relies on possibilistic‐based fusion method to classify SONAR instances as mine or mine‐like object. The proposed semisupervised algorithm minimizes some objective function, which combines context identification, multi‐algorithm fusion criteria, and a semisupervised learning term. The optimization aims to learn contexts as compact clusters in subspaces of the high‐dimensional feature space via possibilistic semisupervised learning and feature discrimination. The semisupervised clustering component assigns degree of typicality to each data sample to identify and reduce the influence of noise points and outliers. Then, the approach yields optimal fusion parameters for each context. The experiments on synthetic data sets and standard SONAR data set show that our semisupervised local fusion outperforms individual classifiers and unsupervised local fusion.

show abstract

<title>Automated detection and classification of sea mines in sonar imagery</title>

Cited by 123 publications

References 6 publications

Fractal dimension, wavelet shrinkage and anomaly detection for mine hunting

Fractal dimension, wavelet shrinkage and anomaly detection for mine hunting

Anomaly subspace detection based on a multi-scale Markov random field model

Semisupervised Local Fusion Approach for Mine Detection in SONAR Data

Contact Info

Product

Resources

About