Surface Ship-Wake Detection Using Active Sonar and One-Class Support Vector Machine

Jeong, Sungmoon; Ban, Sang-Woo; Choi, Sang-Moon; Lee, Donghun

doi:10.1109/joe.2012.2192344

Cited by 11 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detection of the floating objects and determination of movement parameters is realized mainly by active systems. These are radiolocation systems in the upper hemisphere (radar systems (Loran et al 2023)) and echo ranging systems in the lower hemisphere (sonars and echosounders (Jeong et al, 2012)). Passive systems, which include underwater observation systems, are less used than airborne systems.…”

Section: Introductionmentioning

confidence: 99%

Capabilities to use passive measurement systems to detect objects moving in a water region

Mironiuk,

Buszman

2023

AoT

View full text Add to dashboard Cite

The increase in the use of sea water is the basis for the development of the existing security systems in given areas. Monitoring the navigational situation in a given water area is one of the most important tasks aimed at ensuring the necessary level of safety in maritime traffic. Marine surveillance systems at sea are used for this purpose. As an interesting approach related to the study of the movement of vessels, this paper proposes a method based on the measurement of physical field disturbances generated by objects moving in the sea water. These disturbances can be referred to the upper (air space) and lower (underwater) hemisphere. In the upper hemisphere the motion of the object generates disturbances of the thermal field while in the lower hemisphere disturbances of the acoustic, hydrodynamic, magnetic, electric and seismic fields are generated. Detection of the floating objects and determination of movement parameters is realized mainly by active systems. There are radiolocation systems in the upper hemisphere (radar systems) and echo ranging systems in the lower hemisphere (sonars and echosounders). Monitoring of the upper hemisphere of sea vessels traffic is conducted in a comprehensive manner. The lower hemisphere is in the most cases omitted. Therefore, it is recommended to develop underwater observation systems as a source of additional information about floating objects and thus complement the existing systems used in navigation. However, at present, despite the technological progress, there is a noticeable lack of the comprehensive solutions in the area of monitoring the vessels movement in the underwater space. Therefore, appropriate action should be taken to recognize this technology gap and increasing the safety of vessel traffic. The aim of the article was to present a fully passive, mobile underwater observation system that uses a number of sensors to monitor the underwater environment parameters, the research methodology and analysis of the obtained results. The method of deploying the measurement system at the selected geographical position and the measurement method are described. Based on obtained results, the analysis of sound pressure disturbances caused by passing ships was performed. A feature extraction method was developed to identify a passing vessel based on low frequency signal parameters.

show abstract

Section: Introductionmentioning

confidence: 99%

Capabilities to use passive measurement systems to detect objects moving in a water region

Mironiuk,

Buszman

2023

AoT

View full text Add to dashboard Cite

show abstract

“…For instance, in [16], the OCSVM was used for suppressing clutter arising from ocean waves, more specifically in the context of high frequency ground wave radar. Another example is [17], where OCSVM was used to detect ship wakes using active sonar systems. In [18], another variant of SVM, cost sensitive support vector machine (2C-SVM), was used to handle clutter from multiple models of clutter, in particular the Gaussian and K-distributed clutters, and approximate the Neyman-Pearson detector for a specific false alarm rate.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose two novel techniques for discriminating and classifying the sea and land clutters using two supervised machine learning techniques, namely the regularized randomized neural network (RRNN) and kernel ridge regression (KRR). Although our approaches are supervised learning based, the overall focus here is the classification of clutter as opposed to suppression of clutter or direct target discrimination [2,9,[14][15][16][17][18]20]. As such, we use all possible information towards the classification process rather than discarding useful information in favor of target discrimination.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Sea-Land Clutter Separation Using Regularized Randomized and Kernel Ridge Neural Networks

Thiyagalingam

Xue

et al. 2020

Sensors

View full text Add to dashboard Cite

Classification of clutter, especially in the context of shore based radars, plays a crucial role in several applications. However, the task of distinguishing and classifying the sea clutter from land clutter has been historically performed using clutter models and/or coastal maps. In this paper, we propose two machine learning, particularly neural network, based approaches for sea-land clutter separation, namely the regularized randomized neural network (RRNN) and the kernel ridge regression neural network (KRR). We use a number of features, such as energy variation, discrete signal amplitude change frequency, autocorrelation performance, and other statistical characteristics of the respective clutter distributions, to improve the performance of the classification. Our evaluation based on a unique mixed dataset, which is comprised of partially synthetic clutter data for land and real clutter data from sea, offers improved classification accuracy. More specifically, the RRNN and KRR methods offer 98.50% and 98.75% accuracy, outperforming the conventional support vector machine and extreme learning based solutions.

show abstract

Ship detection and extraction using visual saliency and histogram of oriented gradient

Liu

2016

Optoelectron. Lett.

View full text Add to dashboard Cite

Surface Ship-Wake Detection Using Active Sonar and One-Class Support Vector Machine

Cited by 11 publications

References 16 publications

Capabilities to use passive measurement systems to detect objects moving in a water region

Capabilities to use passive measurement systems to detect objects moving in a water region

A Novel Method for Sea-Land Clutter Separation Using Regularized Randomized and Kernel Ridge Neural Networks

Ship detection and extraction using visual saliency and histogram of oriented gradient

Contact Info

Product

Resources

About