The Multi-sensor Improved Sea Surface Temperatures (MISST) for the Global Ocean Data Assimilation Experiment (GODAE) project intends to produce an improved, high-resolution, global, near-real-time (NRT), sea surface temperature analysis through the combination of satellite observations from complementary infrared (IR) and microwave (MW) sensors and to then demonstrate the impact of these improved sea surface temperatures (SSTs) on operational ocean models, numerical weather prediction (NWP),...
Topics: DTIC Archive, NAVAL RESEARCH LAB MONTEREY CA, *SEA WATER, *SURFACE TEMPERATURE, MULTISENSORS
Multitarget tracking intensity filters are closely related to imaging problems, especially PET imaging. The intensity filter is obtained by three different methods. One is a Bayesian derivation involving target prediction and information updating. The second approach is a simple, compelling, and insightful intuitive argument. The third is a straightforward application of the Shepp-Vardi algorithm. The intensity filter is developed on an augmented target state space. The PHD filter is obtained...
Topics: DTIC Archive, METRON INC RESTON VA, *MULTISENSORS, FILTERS, IMAGES, MULTIPLE TARGETS, NATO
The overall goal of the research and development effort documented in this report is to develop precise (i.e., centimeter to sub-decimeter) geolocation technology that can support detection and discrimination of unexploded ordnance. The detection and remediation of munitions and explosives-of-concern (MEC) on ranges, munitions burning and open detonation areas, and burial pits is one of the US Department of Defense's (DoD) most pressing environmental problems. The MEC characterization and...
Topics: DTIC Archive, OHIO STATE UNIV COLUMBUS, *UNEXPLODED AMMUNITION, DATA ACQUISITION, GEOPHYSICS,...
This paper focuses on multi-sensor fusion for navigation in difficult environments where none of the existing navigation technologies can satisfy requirements for accurate and reliable navigation if used in a stand-alone mode. A generic multi-sensor fusion approach is presented. This approach builds the navigation mechanization around a self-contained inertial navigator, which is used as a core sensor. Other sensors generally derive navigation-related measurements from external signals, such as...
Topics: DTIC Archive, FLORIDA UNIV SHALIMAR RESEARCH AND ENGINEERING EDUCATION FACILITY, *NAVIGATION,...
In the context of this project, we worked on the development of a cross-layer resource management system over single hop and multihop Direct-Sequence Code Division Multiple Access (DS-CDMA) Visual Sensor Networks (VSNs). The target was the optimal determination and allocation of the source and channel coding rates and the power levels among the nodes of the considered network. For the efficient allocation of the nodes' transmission parameters, we applied various distortion-related criteria,...
Topics: DTIC Archive, IOANNINA UNIV (GREECE), *OPTIMIZATION, *VIDEO IMAGES, ALGORITHMS, GAME THEORY,...
The primary objective of the research presented in this report was to develop accurate and reliable geolocation algorithms and tools based on multi-sensor integration, to significantly improve the state-of-the-art in sensor georegistration and to support the collection of geophysical data used to characterize unexploded ordnance (UXO) and munitions and explosives-of-concern (MEC) sites in various environments. The most important tangible outcomes and achievements are: the design and prototype...
Topics: DTIC Archive, OHIO STATE UNIV COLUMBUS, *MULTISENSORS, *AMMUNITION, *EXPLOSIVES, SOFTWARE TOOLS,...
This document describes the work performed as part of the Ananke simulation development. The Ananke simulation tool development is a larger project to provide end-to-end space object simulation and characterization to demonstrate the feasibility of such methods. This document describes the orbit propagation tool, CO-TurboProp, used in the Ananke tool. The document describes the addition of higher-fidelity models in CO-TurboProp and validation of the new tools. The description provided here...
Topics: DTIC Archive, COLORADO UNIV AT BOULDER, *ORBITS, *SIMULATION, *SOFTWARE TOOLS, ALGORITHMS,...
In this paper we present a hidden Markov model (HMM) based framework for situational awareness that utilizes multi-sensor multiple modality data. Situational awareness is a process that comes to a conclusion based on the events that take place over a period of time across a wide area. We show that each state in the HMM is an event that leads to a situation and the transition from one state to another is determined based on the probability of detection of certain events using multiple sensors of...
Topics: DTIC Archive, ARMY RESEARCH LAB ADELPHI MD, *MULTISENSORS, *SITUATIONAL AWARENESS, *MARKOV...
The over-arching objective of the demonstrations described in this report is to gain acceptance of MetalMapper system by the UXO community - including regulators. To achieve this objective, we must show by participating in blind demonstrations that the MetalMapper can indeed be used to reliably prioritize target lists for digging and thus reduce the number of false positive (i.e., non ordnance) items that need to be identified through excavation.
Topics: DTIC Archive, GEOMETRICS INC SAN JOSE CA, *MULTISENSORS, *UNEXPLODED AMMUNITION, CLASSIFICATION,...
A concept of operations for intrusion detection and border security is to put tripwires anywhere--in deserts, borders, or other remote areas where physical terrain does not constrain dismount or vehicle movement--to detect, classify and track intruders.
Topics: DTIC Archive, Arora, Anish, OHIO STATE UNIV COLUMBUS, *INTRUSION DETECTION, *MULTISENSORS,...
The TEMTADS 5x5 Array was demonstrated at two sites, the former Mare Island Naval Shipyard, CA, in 2011, and the former Spencer Artillery Range, TN (fSpAR) in 2012. The MP System was demonstrated at the former Camp Beale, VA, in 2011, and the Central Impact Area of the Massachusetts Military Reservation and fSpAR in 2012. For each site and system, 180 or more target locations were investigated per day with limited rework required. The limited data set of dynamic data collected with the MP...
Topics: DTIC Archive, NAVAL RESEARCH LAB WASHINGTON DC, *UNEXPLODED AMMUNITION, ANOMALIES, CLASSIFICATION,...
The MITRE Corporation recently hosted the first Netted Sensors Community Workshop in McLean, Virginia, on 24 October-26 October 2005. The Workshop was sponsored by the Defense Advanced Research Projects Agency (DARPA), Office of the Secretary of Defense (OSD) Director of Defense Research and Engineering (DDR&E), and the National Science Foundation (NSF). The goal was to establish and sustain an annual Netted Sensors workshop that brings together Government, Industry and Academia to...
Topics: DTIC Archive, Tromp, Laurens D, MITRE CORP BEDFORD MA, *NETWORK ARCHITECTURE, MULTISENSORS, SENSOR...
Sensing techniques are employed in military systems as the primary means to gain knowledge about the external environment, or to update and refine such knowledge. Typically, as a result of their intrinsic shortcomings, single sensor systems have limited capabilities for resolving ambiguities and providing consistent descriptions of the sensed environment. Intelligent military systems thus make use of multiple sensors in order to satisfy the extensive need for precise and timely information....
Topics: DTIC Archive, DEFENCE RESEARCH ESTABLISHMENT VALCARTIER (QUEBEC), *DATA FUSION, *INTEGRATION,...
This report from Japan contains articles on Status, Future trends in Sensor Technology. The topics are Temperature Sensors, Silicon Magnetic Sensors and Optical Sensors.
Topics: DTIC Archive, JOINT PUBLICATIONS RESEARCH SERVICE ARLINGTON VA, *JAPAN, *OPTICAL DETECTORS,...
The objectives of this project were to: 1) Develop mathematical foundations for a unified approach to object (in particular target) detection and recognition. 2) Accommodate multi-sensor data and scenarios with large numbers of objects. 3) Accommodate rigid and non-rigid transformations, variations in lighting conditions, contrast, noise, blur, and clutter. 4) Overcome the massive computational hurdles inherent in the general problem of object detection and recognition.
Topics: DTIC Archive, Grenander, Ulf, BROWN UNIV PROVIDENCE RI, *DETECTION, *RECOGNITION, ILLUMINATION,...
Due to the significance of aerosols in visibility forecasting, transportation, air pollution and global climate change studies, the modeling and successful prediction of aerosol events is of a great interest to both military and civilian users. Recognizing this interest, the Naval Research Laboratory Marine Meteorology Division developed the Navy Aerosol Analysis and Prediction System (NAAPS), the world's only truly operational aerosol prediction model, to provide both aerosol and visibility...
Topics: DTIC Archive, NORTH DAKOTA UNIV GRAND FORKS DEPT OF ATMOSPHERIC SCIENCES, *AEROSOLS, FORECASTING,...
In harsh or dangerous environments, robots can lose function in multiple sensors and effectors over the mission, thus reducing their overall capability. If the capabilities provided by these sensors/effectors are necessary for mission completion, having an adaptive system that can overcome these losses is critical to mission accomplishment. In this paper, we propose a solution using multiple agents, organized as a team, to give robots the ability to adapt and overcome sensor/effector loss. When...
Topics: DTIC Archive, Matson, Eric, KANSAS STATE UNIV MANHATTAN DEPT OF COMPUTER SCIENCE, *ROBOTICS,...
This paper compares two different approaches for sensor selection for distributed tracking: 1) The Frisbee method, and 2) Global Node Selection (GNS). The Frisbee method is based on the proximity of the nodes to the predicted location of the target; GNS is based on minimizing the unbiased Cramer Rao lower bound (CRLB). Both theoretical and experimental results indicate that the Frisbee method is as effective as GNS. Furthermore, the Frisbee method is attractive due to its very light...
Topics: DTIC Archive, ARMY RESEARCH LAB ADELPHI MD, *MULTISENSORS, *NETWORKS, *TRACKING, *MATHEMATICAL...
This scoring record documents the efforts of the Naval Research Laboratories (NRL) to detect and discriminate unexploded ordnance (UXO) utilizing the APG Standardized UXO Technology Demonstration Site Blind Grid. The scoring record was coordinated by Larry Overbay and by the Standardized UXO Technology Deomostration Site Scoring Committee. Organizations on the committee include the U.S. Army Corps of Engineers, the Environmental Security Technology Certification Program, the Strategic...
Topics: DTIC Archive, Overbay, Larry, ABERDEEN TEST CENTER MD, *FIELD TESTS, *UNEXPLODED AMMUNITION, TOWED...
This project is part of Radiance in a Dynamic Ocean (RaDyO) program which aims at developing a comprehensive understanding of variability in the underwater radiance distribution and its relation to dynamic processes within the ocean-atmosphere boundary layer. The principal objective of this project is to measure and quantitatively characterize the wave-induced fluctuations in underwater radiance under various sea-surface boundary conditions. The specific objectives include the characterization...
Topics: DTIC Archive, SCRIPPS INSTITUTION OF OCEANOGRAPHY LA JOLLA CA MARINE PHYSICAL LAB, *RADIANCE,...
New geolocation methods are needed that will allow accurate location of LPI emitters despite low signal-to-noise ratio (SNR) and multipath propagation. To address this recent work has provided a single-stage localization method called Direct Position Determination (DPD). However, all its computation is concentrated at one computing node. We developed several methods to remedy this problem. To provide even better performance in these challenging real-world scenarios we developed a one-stage...
Topics: DTIC Archive, STATE UNIV OF NEW YORK AT BINGHAMTON, *MULTISENSORS, ELECTRONIC INTELLIGENCE,...
Multi-sensor, multi-target tracking is the process of tracking one or more targets given periodic measurement reports of the target locations from one or more sensors. When there are many targets and/or the target density is high, this can be a complex problem. Because of the complexity, it is useful to measure how well the multi-target tracking system is performing. There are many ways to measure the performance but usually no one single measure can encompass the overall performance. Much work...
Topics: DTIC Archive, NAVAL AIR WARFARE CENTER AIRCRAFT DIV PATUXENT RIVER MD, *TRACKING, *MULTIPLE...
In this paper, we propose a multiple-metric learning algorithm to learn jointly a set of optimal homogenous/ heterogeneous metrics in order to fuse the data collected from multiple sensors for classification. The learned metrics have the potential to perform better than the conventional Euclidean metric for classification. Moreover, in the case of heterogenous sensors, the learned multiple metrics can be quite different, which are adapted to each type of sensor. By learning the multiple metrics...
Topics: DTIC Archive, ILLINOIS UNIV AT URBANA BECKMAN INST, *ALGORITHMS, *LEARNING, *MULTISENSORS,...
Seacoast Science, Inc. and the University of California, San Diego (UCSD) are developing a portable real-time chemical detector system containing multiple sensor technologies. This Phase II STTR final report details our accomplishments during the 2-year program. Scientists at UCSD have modeled the behavior of the metal-phthalocyanine ChemFET, and optimizing both the sensor chemistry and methods to understand the sensor data. Seacoast Science has developed a packed-tube, trap-and-purge...
Topics: DTIC Archive, SEACOAST SCIENCE INC CARLSBAD CA, *CHEMICAL AGENTS, *CHIPS(ELECTRONICS), INTEGRATED...
An algorithm has been developed to initiate tracks of a ballistic missile in initial exoatmospheric phase, using line of sight measurements from one or more moving platforms.
Topics: DTIC Archive, Bar-Shalom, Y., CONNECTICUT UNIV STORRS, *GUIDED MISSILES, *MULTISENSORS, ALGORITHMS,...
Today many tracking and surveillance systems show multi sensor configurations, which are used to enhance the breadth of measurement and likewise to increase the capability of the system to survive if any individual sensor fails. Currently, multi sensor systems rely on a central processor where global data fusion takes place, or a central communication medium through which all messages between sensors must be transferred. Such centralized architectures give rise to problems with communication...
Topics: DTIC Archive, FRAUNHOFER SOCIETY WACHTBERG (GERMANY) FRAUNHOFER INST FOR HIGH FREQUENCY PHYSICS AND...
The overall objective of this project is to develop reliable techniques for discriminating between buried UXO and clutter using multisensors electromagnetic induction sensor array data. The basic idea is to build on existing research which exploits differences in shape between ordnance and clutter to include the effects of other distinctive properties of ordnance items (fuze bodies, driving bands, fin assemblies, etc.). During the course of this project, we will clearly elucidate the underlying...
Topics: DTIC Archive, Miller, J, AETC INC ARLINGTON VA, *MINE DETECTORS, *UNEXPLODED AMMUNITION,...
For many applications of radar and sensor based filtering, simulations can not represent the sole estimate of performance, provide points where threats become engageable, or determine when to use weaponsplatform based sensors effectively in an engagement, etc... No signicant advances have been proposed to analytically characterize performance or at least bound performance of the Kalman filter other than the use of simple two or three state constant gain filters. This paper suggests methods for...
Topics: DTIC Archive, NAVAL SURFACE WARFARE CENTER DAHLGREN DIV VA, *RADAR TRACKING, SYMPOSIA, DETECTORS,...
A multi-sensor correlation processor with an alpha, beta and gamma tracker is introduced as the multi-sensor fusion track model to address the multi-target and maneuvering targets. The new system requires no algorithmic matrix inversion and can be proven to be mathematically equivalent to the popular multi-sensor fusion track model in accuracy. The new multi-sensor fusion track model consists of the sensors, I/O parameter transformation processor, multi-sensor correlation processor, the alph,...
Topics: DTIC Archive, Jeun, Buddy H, LOCKHEED MARTIN AERONAUTICAL SYSTEMS MARIETTA GA, *KALMAN FILTERING,...
The Final Report for the Multi-Sensor Characterization and Data Correlation (MSCDC) test has been completed and submitted. This completes all efforts on the MSCDC contract. In addition, the final report for Phase One of the Multi-Spectral Shipboard Surveillance System (M4S) contract has also been submitted. All work on these contracts is completed and no further activity is anticipated. This monthly report is the last to be submitted.
Topics: DTIC Archive, Capron, Bruce, LITTON SYSTEMS INC SAN JOSE CA APPLIED TECHNOLOGY DIV, *SHIPBOARD,...
The Maximum Likelihood Probabilistic Data Association (ML-PDA) tracker and the Maximum Likelihood Probabilistic Multi-Hypothesis (ML-PMHT) tracker are tested in their capacity as algorithms for very low observable targets (VLO, meaning 6 dB post-signal-processing or even less) and are then applied to five synthetic benchmark multistatic active sonar scenarios featuring multiple targets, multiple sources and multiple receivers. Both methods end up performing well in situations where there is a...
Topics: DTIC Archive, NAVAL UNDERSEA WARFARE CENTER DIV NEWPORT RI, *PROBABILITY, ALGORITHMS, MAXIMUM...
Swarm Intelligence (SI) is a relatively new paradigm being applied in a host of research settings to improve the management and control of large numbers of interacting entities such as communication, computer and sensor networks, satellite constellations and more. Attempts to take advantage of this paradigm and mimic the behavior of insect swarms however often lead to many different implementations of SI. The rather vague notions of what constitutes self-organized behavior lead to rather ad hoc...
Topics: DTIC Archive, Fleischer, Mark, MARYLAND UNIV COLLEGE PARK INST FOR SYSTEMS RESEARCH, *COMPUTER...
The usage of non-collocated sources and receivers in multistatic sonar networks (MSNs) has emerged as a promising area of opportunity in sonar systems. This thesis addresses point coverage sensing problems in MSNs, where a number of points of interest (targets) must be monitored. For detection we assume cookie-cutter sensors and a two-dimensional homogenous environment. Based on current algorithms and the theory of detection discs, we develop the new preprocessing algorithm LOC-GEN-II to...
Topics: DTIC Archive, NAVAL POSTGRADUATE SCHOOL MONTEREY CA, *OPTIMIZATION, *POSITION(LOCATION), *SONAR...
LONG-TERM GOALS: [To] Ensure that Navy capabilities for a new generation of sea surface temperature products are coordinated with and benefitting from international research and development embodied by the Group for High Resolution Sea Surface Temperature (SST; GHRSST) and domestic capabilities demonstrated in the U.S. Integrated Ocean Observing System (IOOS) regions and applicable to regions around the world. This project is the Navy component of a broad national NOPP/IOOS/NASA MISST for IOOS...
Topics: DTIC Archive, NAVAL RESEARCH LAB STENNIS DETACHMENT STENNIS SPACE CENTER MS, *OCEAN SURFACE,...
Poor individual sensor performance as well as a large number of sensor scans per time interval are two challenges for multi-target tracking is large sensor networks. We introduce a two-stage processing scheme (ML-MHT) to address the former issue, and another to address the latter issue (MHT2). We consider as well the combination of these two techniques (ML-MHT2). Simulation results are encouraging. Future work will include application of these techniques to more challenging multi-sensor...
Topics: DTIC Archive, NATO UNDERSEA RESEARCH CENTRE LA SPEZIA (ITALY), *COMPUTER ARCHITECTURE, ITALY,...
The current investigation explores the use of a biological technique, known as Stigmergy, to coordinate semi-autonomous surveillance platforms during search operations such as in the case of Unmanned Aerial Vehicles (UAVs). Stigmergy was recognized and named by French biologist P.P. Grasse in 1959 while studying nest building of termites. He observed that indirect coordination among termites was accomplished through sensing and modification of their environment. The chemicals secreted by each...
Topics: DTIC Archive, Richey, Barrett F, BTG INC FAIRFAX VA, *PLATFORMS, *MULTISENSORS, SYMPOSIA, ROBOTICS,...
Briefing charts of presentation on French UAV programs, including SIDM CONOPS, French Air Force imagery architecture, and future French MALE UAV program.
Topics: DTIC Archive, MINISTRY OF DEFENCE PARIS (FRANCE), *SURVEILLANCE DRONES, MILITARY INTELLIGENCE, AIR...
Passive Hydrogen Maser (PHM) and Rubidium Atomic Frequency Standard (RAFS) are the two baseline on-board clock technologies for Galileo, the European Global Navigation Satellite System (GNSS), which are currently being validated on-board two experimental spacecrafts, GIOVE-A and GIOVE-B. These two spacecraft are orbiting in a Galileo-representative orbit and transmit Galileo-representative signals that are tracked and collected by a network of evenly distributed sensor stations (the Galileo...
Topics: DTIC Archive, EUROPEAN SPACE AGENCY NOORDWIJK (NETHERLANDS), *NAVIGATION SATELLITES, FREQUENCY...
This interdisciplinary research program is focused on designing and implementing robust controllers on smart structures. The primary research objectives are: (1) structural modeling of smart structures incorporating both material and geometric nonlinearities, (2) development of controllers using conventional and neural network based algorithms, and (3) distributed control techniques using spatially distributed sensors and actuators. We have investigated modeling techniques for structures that...
Topics: DTIC Archive, Rao, Vittal S., MISSOURI UNIV-ROLLA, *NEURAL NETS, *ARTIFICIAL INTELLIGENCE,...
The objective of this multi-year research funding is to devise new and novel methods to suppress interferers impinging on a multi-sensor GPS receiver. The research has considered chirp-like jammers as well as wideband interference. A self-coherence anti-jamming scheme is introduced which relies on the unique structure 0 the coarse/acquisition (C/A) code of the satellite signals. Because of the repetition of the CIA-code within each navigation symbol, the satellite signals exhibit strong...
Topics: DTIC Archive, Amin, Moeness G, VILLANOVA UNIV PA, *SIGNAL PROCESSING, *GLOBAL POSITIONING SYSTEM,...
Layered sensing provides a hierarchical netcentric architecture for universal situational awareness with global coverage and persistent surveillance. Sensors in the layered hierarchy provide spatial, temporal, spectral, and polarization diversity with different scales and resolutions over different time horizons. Cooperative management of netted sensors is a successful strategy to achieve targeting performance and overall measures of merit (MOM) goals. After a brief introduction to issues in...
Topics: DTIC Archive, AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH, *HIERARCHIES, *MULTISENSORS,...
This work deals with worst case geometric scenarios of a system of satellite mounted sensors in determining the location of a signal source on the earth's surface. This is an Interim Report.
Topics: DTIC Archive, Russak, I. B., NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF MATHEMATICS, *SIGNAL...
As the number of sensors, platforms, exploitation sites, and command and control nodes continues to grow in response to Joint Vision 2010 information dominance requirements, Commanders and analysts will have an ever increasing need to collect and process vast amounts of data over wide areas using a large number of disparate sensors and information gathering sources.
Topics: DTIC Archive, Kessler, Otto, DEFENSE ADVANCED RESEARCH PROJECTS AGENCY ARLINGTON VA, *DATA BASES,...
This paper presents a game theoretic approach for the management of multiple mobile sensors. Our approach can maintain tracks of smart targets under possibly adversarial environments. To ensure computational tractability, sensor management is divided into sensor assignment and sensor scheduling. In sensor assignment, covariance control and information theoretic sensor assignment are combined logically. In sensor scheduling, the targets are modeled as entities with different levels of...
Topics: DTIC Archive, DCM RESEARCH RESOURCES GERMANTOWN MD, *MULTISENSORS, *GAME THEORY, *TARGET...
A framework and analysis for a distributed sensor network based surveillance system is presented here. In a previous effort we have presented methodologies for coordination and decision-making amongst sensors for tracking targets while in [2] we presented the results of endowing the sensor network with autonomy. Sensors monitor targets that crisscross a rectangular surveillance zone. When a sensor pursuits a target it leaves areas unguarded through which other targets can get past undetected....
Topics: DTIC Archive, ARKANSAS UNIV FAYETTEVILLE DEPT OF COMPUTER SCIENCE AND ENGINEERING, *MULTISENSORS,...
The primary objective of this research is to develop the theory and operation of heterogeneous sensor networks that can provide a desired quality of sensor fusion for creating actionable situation awareness. This goal is being achieved by developing (i) Mathematically rigorous and novel language theoretic sensor data representation and multi-level heterogeneous sensor fusion techniques that require substantially less sensing and communication resources as compared to conventional techniques,...
Topics: DTIC Archive, PENNSYLVANIA STATE UNIV STATE COLLEGE, *MULTISENSORS, *NETWORK ARCHITECTURE,...
A fundamental challenge in securing sensor networks is that sensor nodes can be physically compromised. Most of the security mechanisms relies on the secrecy of some important data that is stored on sensor nodes. For example, for encryption, the security depends on the secrecy of keys. Because of the lack of physical security and memory protection, sensors can be captured by adversaries, and secret keys stored in memories can be compromised. Once those secrets are disclosed, a sensor is...
Topics: DTIC Archive, Du, Wenliang, SYRACUSE UNIV NY DEPT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE,...
This paper presents a statistical-mechanics-inspired procedure for optimization of the sensor field configuration to detect mobile targets. The key idea is to capture the low-dimensional behavior of the sensor field configurations across the Pareto front in a multiobjective scenario for optimal sensor deployment where the nondominated points are concentrated within a small region of the large-dimensional decision space. The sensor distribution is constructed using location-dependent energy-like...
Topics: DTIC Archive, NAVAL UNDERSEA WARFARE CENTER DIV NEWPORT RI, *MOVING TARGETS, *MULTISENSORS, *TARGET...
In this paper, we propose a novel multi-task multivariate (MTMV) sparse representation method for multi-sensor classification, which takes into account correlations between sensors simultaneously while considering joint sparsity within each sensor's observations. This approach can be seen as the generalized model of multi-task and multivariate Lasso, where all the multi-sensor data are jointly represented by a sparse linear combination of training data. We further modify our MTMV model by...
Topics: DTIC Archive, JOHNS HOPKINS UNIV BALTIMORE MD DEPT OF ELECTRICAL AND COMPUTER ENGINEERING,...
We propose a self-organising map (SOM) algorithm has a solution to a new multi-goal path planning problem for active perception and data collection tasks. We optimise paths for a multi-robot team that aims to maximally observe a set of nodes in the environment.
Topics: DTIC Archive, Best,Graeme, University of Sydney Sydney Australia, robots, algorithms, multisensors,...
