Classification and Localization of Naval Mines With Superellipse Active Contours

Köhntopp, Daniel; Lehmann, Benjamin; Kraus, Dieter; Birk, Andreas

doi:10.1109/joe.2018.2835218

Cited by 12 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, with very dynamic development of autonomous systems, we can discover new possibilities of detecting, classifying and identifying possible threat [28][29][30][31][32][33][34]. The use of autonomous vehicles for harbour and seaway traffic lines monitoring is one of the most effective solutions for maintaining security awareness.…”

Section: Discussionmentioning

confidence: 99%

Bulletin of the Polish Academy of Sciences: Technical Sciences

Wawrzyński

Zieja

Żokowski³

et al. 2022

View full text Add to dashboard Cite

This article presents the information concerning aspects of the autonomous underwater vehicle (AUV) mission planning process, emphasizing maritime security monitoring and surveillance, and using side-looking sonars as a primary data source. The paper describes characteristic mission plan phases and gives suggestions for the operators, mainly concerning the safety and effectiveness of the AUV mission. The article describes the coverage path planning algorithm, which could be used to create an effective AUV mission plan, considering AUV manoeuvrability, sonar characteristics, and environmental factors. The results of the algorithms have been verified during the real mission of the AUV vehicle.

show abstract

Section: Discussionmentioning

confidence: 99%

Bulletin of the Polish Academy of Sciences: Technical Sciences

Wawrzyński

Zieja

Żokowski³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…They showed that their method is applicable to sonar image segmentation, but its use in high-noise scenarios is limited because it is a frequency domain operation. Kohntopp et al [ 25 ] segmented specific objects in sonar images using an active contour algorithm, and their method can adapt to the intensity distribution characteristics of sonar images. Li et al [ 26 ] proposed a new active contour model for image segmentation.…”

Section: Introductionmentioning

confidence: 99%

Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images

Zhao

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

Forward-looking sonar is a technique widely used for underwater detection. However, most sonar images have underwater noise and low resolution due to their acoustic properties. In recent years, the semantic segmentation model U-Net has shown excellent segmentation performance, and it has great potential in forward-looking sonar image segmentation. However, forward-looking sonar images are affected by noise, which prevents the existing U-Net model from segmenting small objects effectively. Therefore, this study presents a forward-looking sonar semantic segmentation model called Feature Pyramid U-Net with Attention (FPUA). This model uses residual blocks to improve the training depth of the network. To improve the segmentation accuracy of the network for small objects, a feature pyramid module combined with an attention structure is introduced. This improves the model’s ability to learn deep semantic and shallow detail information. First, the proposed model is compared against other deep learning models and on two datasets, of which one was collected in a tank environment and the other was collected in a real marine environment. To further test the validity of the model, a real forward-looking sonar system was devised and employed in the lake trials. The results show that the proposed model performs better than the other models for small-object and few-sample classes and that it is competitive in semantic segmentation of forward-looking sonar images.

show abstract

“…Among these, underwater SONAR has become prominent in the contemporary use of such arrays, providing surveillance for maritime safety and security against threats such as sea mines [ 4 , 5 , 6 , 7 , 8 ]. Many recent studies are dedicated to naval mine detection, mine-like object classification, and mine countermeasures [ 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Versatile Approach for Underwater Conformal Volumetric Array Design

Yusuf

Pyo

Roh

2021

Sensors

View full text Add to dashboard Cite

In this study, we present a novel approach to the design of a conformal volumetric array composed of M × N convex subarrays in two orthogonal curvilinear directions for underwater acoustic imaging for mine detection. Our design targets require that the proposed array transducer has three-dimensional half-power beamwidths of 85° and 25° in either of its convex subarray parts, while also reaching a peak transmitting voltage response above 147 dB. The radiated sound pressure of the subarrays was independently derived as a function of their geometrical parameters. The resulting directional factors were then combined to analyze the beam profile of the entire array. The design was finally optimized to minimize the ripple level. To validate this theoretical design, the structure was modeled and analyzed using the finite element method. The comparison between the resulting beam pattern from the finite element analysis and the analytical computation showed an excellent compliance. The method advanced is a simple and systematic analytical model to facilitate the development of new conformal volumetric arrays for underwater mine detection.

show abstract

Classification and Localization of Naval Mines With Superellipse Active Contours

Cited by 12 publications

References 19 publications

Bulletin of the Polish Academy of Sciences: Technical Sciences

Bulletin of the Polish Academy of Sciences: Technical Sciences

Feature Pyramid U-Net with Attention for Semantic Segmentation of Forward-Looking Sonar Images

A Novel Versatile Approach for Underwater Conformal Volumetric Array Design

Contact Info

Product

Resources

About