Monday, November 20, 2017
      CMRE Facebook page  CMRE LinkedIn page  CMRE PAO Youtube page
   
Text Size
CMRE banner

Memorandum Reports

Report that covers interim results during the course of a project. Note: Unless linked to the full text, reports are only available to NATO member nations from designated distribution centres.

Documents

Order by : Name | Date | Hits [ Ascendant ]

Multi-view classification with deep learning for mine countermeasures Multi-view classification with deep learning for mine countermeasures

Date added: 12/23/2015
Date modified: 12/23/2015
Filesize: Unknown

Multi-view classification with deep learning for mine countermeasures. Williams, David P. CMRE-MR-2015-012. December 2015.

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 deep learning algorithm so that the sonar data from multiple views can be combined and exploited at the (earliest) image level. The method utilizes single-view imagery and, whenever available, multi-view fused imagery, in the same unified classification framework. The promise of the proposed approach is demonstrated in the context of a mine classification task with real synthetic aperture sonar imagery collected at sea.

Developing performance-based planning and evaluation for phased MCM using modern systems Developing performance-based planning and evaluation for phased MCM using modern systems

Date added: 12/23/2015
Date modified: 12/23/2015
Filesize: Unknown

Developing performance-based planning and evaluation for phased MCM using modern systems. Connors, Warren. CMRE-MR-2015-013. December 2015.

The emergence of robust, reliable robotic platforms equipped with advanced sensing and logging capabilities has resulted in the need for a reconsideration of both the tools and tactics for NATO MCM. This need encompasses not only the methods of employment, but also the metrics and data products which are available from these platforms. Traditional NATO MCM is based on a set of tactics and tools which define the standards for interoperability. Previous work has shown the inability for these algorithms and tactics to integrate modern systems and sensors, resulting in an inability to fully exploit of the capabilities of these systems in the context of NATO MCM. This report considers recent work performed at CMRE in collaboration with the NATO nations to advance interoperable planning and evaluation using through-the-sensor techniques for evaluation, advanced data products, and methods for performance prediction. This work includes the consideration of the metrics of mine warfare, the fidelity of these metrics, and advanced visualization techniques for MCM performance. As a result of experimentation, recommended enhancements for current experimental tactics are presented, as well as a method for predicting sensor performance in previously unseen environments. This ability to quantify performance in new environments is the primary requirement for effective mission planning at the tactical level. This work will also introduce a collaborative effort between the operational and scientific communities to develop interoperable planning and evaluation for NATO MCM. The goal of this work is to provide guidance on the tactics, algorithms, metrics and data products for future interoperable MCM.

Assessment of the impact of ocean data collection from heterogeneous networks on sonar performance prediction Assessment of the impact of ocean data collection from heterogeneous networks on sonar performance prediction

Date added: 10/21/2015
Date modified: 10/21/2015
Filesize: Unknown

Assessment of the impact of ocean data collection from heterogeneous networks on sonar performance prediction. Jiang, Yong Min; Alvarez, Alberto; Falchetti, Silvia. CMRE-MR-2015-010. September 2015.

The fidelity of sonar performance predictions depends on the model used and the quantity and quality of the environmental information that is imputed and that will determine the sound transmission loss. To investigate the impact of the oceanographic information collected by a heterogeneous and near-real time adaptive network of robots in a simulated access denied area, a field experiment (REP13-MED) was conducted by CMRE during August 2013 in an area (70 X 81 km) located off-shore La Spezia (Italy), in the Ligurian Sea. The sonar performance assessment assumes fixed target strength, detection threshold and ambient noise levels, and makes use of acoustic data recorded by a vertical line array at source ? receiver ranges from 0.5 to 30 km to benchmark active transmission losses. Continuous wave pulses at multiple frequencies (300 ? 600 Hz) were transmitted at two source depths, 25 and 60 metres, at each range. At least 60 pings were collected for each source depth to build up the statistics of the acoustic received level and quantify the measurement uncertainty. A comparison of the acoustic transmission loss measured and predicted using an ocean prediction model (ROMS) assimilating the observed oceanographic data is presented, and the performance of the observational network is evaluated.

Technological requirements for intelligent passive acoustics surveillance and reconnaissance with gliders Technological requirements for intelligent passive acoustics surveillance and reconnaissance with gliders

Date added: 10/14/2015
Date modified: 10/14/2015
Filesize: Unknown

Technological requirements for intelligent passive acoustics surveillance and reconnaissance with gliders.  Pennucci, Giuliana; Cardeira, Bruno; Garau, Bartolome; Alvarez, Alberto; Jiang, Yong Min. CMRE-MR-2015-009. September 2015.

This report defines the main requirements needed to conduct cost-effective and discreet passive acoustic monitoring of background ambient noise using fleets of low cost and intelligent unmanned underwater vehicles (UUVs). Recently, the NATO-STO Centre for Maritime Research and Experimentation (CMRE) has proposed different approaches, based on cutting edge technology, of extending the capabilities of Slocum gliders using passive acoustic payloads. The goal of the present study is to explore to what extend Commercial, cost effective and off-the-shelf (COTS) devices can be employed to design an acquisition/processing unit to monitor underwater ambient noise without significantly jeopardizing UUV endurance. The study has been conducted considering a Slocum glider to facilitate the portability of the results to other users.

The digital communications stack: the NEMO source code distribution The digital communications stack: the NEMO source code distribution

Date added: 10/07/2015
Date modified: 10/07/2015
Filesize: Unknown

The digital communications stack: the NEMO source code distribution.  Vermeij, Arjan. CMRE-MR-2015-008. June 2015.

NEMO has been developed at CMRE as a building block of the CASW Project 1, as an effort to merge multiple sets of requirements and efforts from both CASW Project 1 and 2. NEMO has become sufficiently stable for others to use in their own underwater communication projects. During the REP15 Atlantic trial NEMO will, for the first time, be deployed on non-CMRE owned underwater vehicles, when the University of Porto will deploy NEMO on their Light Autonomous Underwater Vehicle (LAUV), and do joint experimentation with CMRE. This report is the companion to the NEMO source code distribution. This report describes how to install NEMO on a Ubuntu 14.04 Linux system, as well as how to test NEMO to verify that it works correctly. It provides detailed documentation on all NEMO and non-NEMO components that are part of this source code distribution.

User Login