A tactical operations center (tdc) can be modelled by a distributed problem-solving environment. one of the functions of a tdc is the gathering and interpretation of intelligence . the requirements for interpretation of intelligence make severe demands on available personnel during combat situations… More

Research is needed to develop algorithms that are capable of target recognition in real battlefield environments. l.n.k. corporation proposes to investigate an artifical intelligence technique whose inference mechanism is non-directional (both goal-directed and data-confirmed) for recognition of… More

Many clinical settings require waveform analysis and considerable resources are being devoted to the development of specialized programs for analyzing waveform morphology. unlike the generality commonly available in statistical packages, the inability to transfer shape analysis programs across… More

The amount of human effort currently required to assemble datbases for simulators is formidable. advances in automatic scene analysis give rise to the possibility of developing a system that could automatically generate an image database from high altitude imagery. in phase i l.n.k. corporation… More

The process of extraction of industrial terrain features from radar imagery is not automated. currently this feature extraction is done primarily by highly trained photointerpreters. this is expensive and with the increasing amount of radar imagery, automation is becoming important. in recent years… More

Automatic identification of target information using radar cross sections is an extremely difficult problem. a large amount of effort has been devoted to the problem of estimating the radar cross section of various shapes, but the range of possible objects which can be encountered is large, and… More

Current computational approaches are inadequate to perform real time pattern recognition and adaptive resource allocation in order to suitably respond to enemy threats when compared to the dynamically changing military environments. despite decades of effort based upon statistical signal processing… More

The robotic laboratory at nswc is currently using a vision system which differs significantly from those for which most 3-d object recognition algorithms were designed. as a result, the imaging system presents a unique problem in object recognition. lnk proposes to develop algorithms for the… More

Past and current science research are generating enormous amounts of many different kinds of data, that are presently stored primarily on magnetic tape. often, each data set is largely inaccessible to all but the few scientists who designed and built the original instruments, and even for them the… More

Similarity defined through abstraction and generalization is different from similarity under transformation groups. in their early work title "how to know universals", mcculloch and pitts studied neural networks which recognized universals, i.e., features invariant under geometric transformations.… More

Recent soviet advances in acoustic quieting of submarines is placing increased emphasis on the exploitation of passive intermittent and transient emissions. transient signals can be described efficiently in the time--frequency plane using the wigner distribution or in the cyclic spectrum. both of… More

Lnk is proposing to develop algorithms and software for automatic feature extraction of man made and natural features using a variety of image sensors including infrared, visual and radar. the proposed system would be used for both geographic database generation and automatic updating of geographic… More

Lnk proposes to study the application of neural networks to object detection from all-source imagery. in phase i existing artificial neural networks (anns) will be evaluated on object detection problems. the strengths and shortcomings of these techniques will be assesed and new anns will be… More

Lnk is applying a neural architecture target tracking and state estimation system based on motion vision information from a passive 2d sensor. lnk is developing a hybrid 2d silhouette and 3d relative depth model-based target recognition system based on the above motion vision information. the… More

LNK Corp proposes to design a low-cost, domain-independent, knowledge-based, tabletop Intellident Tutoring System (ITS) tool that will enable rapid prototyping and deployment of domain-specific ITS applications. This design will include a Teacher Module thqt can dynamically adapt its teaching… More

The primary objective of this proposal is to design and build a system for fishery and marine mammal stock prediction using nonlinear spatio-temporal neural network theory. while the central engine of the system makes use ofnonlinear neural networks for prediction, several peripheral modules… More

The central focus of this proposal is on building an automatic target recognition system for identifyi-ng relocatable targets by integrating information from multiple sensors using a synergistic framework of neural networks and exprt systems. This frairework is ideally suited for 3..ricorporating… More

Object-oriented methodologies such as model-based vision provide a robust and more intelligent solution to the ATR problem. Because these methodologies exploit a priori knowledge of a limited number of target models, while allowing the targets to be oriented towards the viewer in any arbitrary… More

Wavelet transforms have already proved to be very useful tools in many signal processing applications including digital audio and video compression. Although the wavelet-based representations offer more versatility in time-frequency localization than other Fourier methods, they tend to have poor… More

Virtual reality involves manipulation of massive quantities of three dimensional elevation and imagery data to render a realistic scene as the operator "flies" through. Visualization of the large areas needed in these simulations requires that the data be compressed to very low bit rates to make… More

Wide angle sensors provide a large area of coverage to search for targets, though often non-littoral in nature and offer very little in the way of providing details for Automatic Target Recognition (ATR). On the other hand, narrow angle sensors provide the details on the target for ATR, but… More

The U.S. Navy aims to develop 21st century teaching aids by exploiting the emerging new developments in automated instructional systems, hypermedia, and pedagogical research. In this Phase I we propose to develop a desktop based prototype Intelligent Computer Based Training environment, integrating… More

An autonomous robotic vehicle which needs to move around in an unstructured environment should be able to detect obstacles in its patha and should know its own position at any given time with respect to a global map. Thie requires that the robot detect and recognize certain landmarks and infer its… More

The placement of hyperspectral sensors on future Unmanned Air Vehicles is constrained by a data bottleneck caused by the limited downlink bandwidth. This proposal addresses this problem by developing a lossless compression algorithm that is optimized for hyperspectral imagery. Hyperspectral… More

Not Available The driving force for technology and innovation for next generation aircraft carriers (CVX) is a 50 percent reduction in traditional ship manning. The need exists for a comprehensive methodology to optimize decision making organizations (e.g., carrier CDC/CVIC) to complete complex… More

Optically transparent components for lasers, envelopes for vapor lamps andinfrared transparent domes for missiles require a multi-mode system ofelectromagnetic guidance. In recent years efforts have been concentrated onmaximizing the resolution of optical materials for use in high-energy… More