Browsing by Subject "Target classification"
Now showing items 1-20 of 20
-
3D target shape from SAS images based on a deformable mesh
(NURC, 2009/12)The seafloor can nowadays be scanned with side-looking sonar that provides a very high resolution over a large swath, which has proved beneficial for underwater target detection and classification. For systems operated at ... -
A classification technique combining aspect dependence and elastic properties of target scattering
(NATO. SACLANTCEN, 1999/04)Discrimination between man-made and natural underwater objects and between man-made objects of different characteristics are the key objectives of target classication. The current approach is mainly based on the analysis ... -
A data-driven control strategy in synergy with continuous active sonar for littoral underwater surveillance
(CMRE, 2017/11)In this work, we describe a data-driven Mission Management Layer (MML) running on-board AUVs which manages the phases of a littoral surveillance mission and exploits the characteristics of Continuous Active Sonar (CAS) ... -
Active contours for synthetic aperture sonar snippet registration
(CMRE, 2019/06)In mine-hunting operations, there is currently a strong focus on using autonomous systems in order to remove personnel and ships from the minefield. These systems must perform their missions effectively, and the collected ... -
Ambiguity reduction of underwater targets in framework of topic modeling
(CMRE, 2019/06)An unsupervised track classification approach based on appropriate discriminative and aggregative features derived from beamformed and normalized matched-filtered data is applied to sonar multistatic tracking and extended ... -
Analysis of a signal starting time estimator based on the Page test statistic
(NATO. SACLANTCEN, 1995/12)The time of the most recent reset to zero of the Page test statistic is proposed as an estimator of the starting time of a signal. The probability mass function of the estimator is determined analytically subject to a ... -
Automatic target classification using multiple sidescan sonar images of different orientations
(NATO. SACLANTCEN, 1997/09)In this report, the target classification performance of a multiple view sidescan sonar is investigated. The classification statistics are estimated using model based automatic classifiers. The guidelines to the design of ... -
Autonomous networked anti-submarine warfare research and development at CMRE
(CMRE, 2019/06)CMRE has been evaluating the potential of autonomous networked ASW using underwater vehicles through a program of sonar signal processing, underwater communications, navigation and robotic behavior developments and at-sea ... -
Demystifying deep convolutional neural networks for sonar image classification
(CMRE, 2019/06)Deep convolutional neural networks (CNNs) are developed to perform underwater target classification in synthetic aperture sonar (SAS) imagery. The deep networks are trained using a huge database of sonar data collected at ... -
Exploiting phase information in synthetic aperture sonar images for target classification
(CMRE, 2019/05)It is demonstrated that the phase information present in complex high-frequency synthetic aperture sonar (SAS) imagery can be exploited for successful object classification. That is, without using the amplitude content of ... -
Forward looking sonar mosaicing for mine countermeasures
(CMRE, 2019/06)Forward looking sonars (FLS) are nowadays popular for many different applications. In particular, they can be used for Automatic Target Recognition (ATR) in the context of Mine Countermeasures. Currently, ATR techniques ... -
Micro-bathymetry data acquisition for 3D reconstruction of objects on the sea floor
(CMRE, 2019/06)This paper describes an effort to capture micro-bathymetry data for the end purpose of 3D object reconstruction, using an AUV-borne multibeam echo sounder. Due to the combination of relatively narrow across-track coverage ... -
Multi-view SAS image classification using deep learning
(CMRE, 2017/11)A new approach is proposed for multi-view classification when sonar data is in the form of imagery and each object has been viewed an arbitrary number of times. An image-fusion technique is employed in conjunction with a ... -
Multi-view target classification in synthetic aperture sonar imagery
(NURC, 2009/12)This work proposes an elegantly simple solution to the general task of classifying the shape of an object that has been viewed multiple times. Specifically, this problem is addressed in the context of underwater mine ... -
Multiple view sidescan sonar
(NATO. SACLANTCEN, 1995/12)The classification of objects on the seafloor by means of a sonar can be -
Probability of false alarm estimation in oversampled active sonar systems
(NATO. SACLANTCEN, 1998/08)The probability of false alarm (Pfa)in active sonar systems is an -
Real-and synthetic-array signal processing of buried targets
(NATO. SACLANTCEN, 2002/01)Results from two field experiments aimed at investigating the detection and classification of buried targets are presented. In both experiments a 2-16 kHz parametric source was used. In the first experiment the source was ... -
The propagation and reception of transient electromagnetic signals in the presence of a conducting half-space
(NATO. SACLANTCEN, 1961/05)In this paper a theoretical treatment is given of the short-distance propagation and reception of a step-function in the presence of a conducting half-space. The step-function is generated by a horizontal electric dipole ... -
Underwater target classification in synthetic aperture sonar imagery using deep convolutional neural networks
(CMRE, 2019/06)Deep convolutional neural networks are used to perform underwater target classification in synthetic aperture sonar (SAS) imagery. The deep networks are learned using a massive database of real, measured sonar data collected ... -
Wavelet analysis of side scan sonar imagery for classification
(NATO. SACLANTCEN, 1997)Wavelet-based techniques are presented for compressing side scan sonar images communicated from UUV's through band limited communication channels. Testing with an automatrc classifier on reconstructed images demonstrates ...