Northrop Grumman Systems Corporation

Omar Aboutalib

Richard R Ramroth

Walter Dennis Clark

David W Evans

Gregory L Larson

Liya Su

Alex C Fung

Bich M Thai

Annie D Nguyen

Bea Thai

An adaptive navigation system for airborne, ground and dismount applications. The system performs adaptive fusion of all sensed signals, information sources, and databases that may be available on a single or multiple cooperative platforms to provide optimal Positioning, Navigation, and Timing (PNT) state. To reduce error building over time, the system incorporates the concept of geo-registration fusion into the ANAGDA filter. The architecture of the ANAGDA filter consists of user/application configurable functionalities in hierarchical layers. The sensing layer senses the environment and contains the required databases such as surveyed landmarks, and Digital Terrain Elevation Data/Digital Elevation Model (DTED/DEM). The processing layer has a Smart Sensor Resource Manager which is a performance-based sensor/feature selection module. The measurement abstraction layer isolates the filter from hardware specifics. The fusion layer performs the Inertial Measurement Unit (IMU) data integration with sensor measurements, and feature fusion.

Adaptive navigation for airborne, ground and dismount applications (ANAGDA)

A system and method for controlling a swarm of UAVs that are stored on and released from an airborne platform, fly to and destroy a target, where the UAVs download target information from the airborne platform before being released therefrom, do not communicate with each other or the airborne platform while in flight, and do not depend of the presence of GPS. Each UAV includes a vision sensor that provides image data, a navigation module that receives the image data and causes the UAV to navigate and fly towards the target, and a target destruction module that receives the image data and causes the UAV to destroy the target.

Machine vision enabled swarm guidance technology

The invention is a process for identifying an unknown object. In detail, the process includes the steps of: 1) compiling data on selected features on a plurality of segments of a plurality of known objects; 2) illuminating the unknown object with a laser radar system; 3) dividing the unknown object into a plurality segments corresponding to each of the segments of the known objects; 4) sequentially measuring selected features of each of the plurality of segments of the unknown object; and 5) comparing the sequentially measuring selected features of each of the plurality of segments of the unknown object to the selected features on the plurality of segments of the plurality of known objects.

Process for the identification of objects

A method of data fusion comprises the steps of: receiving a plurality of decisions and associated confidences; determining probabilities of a set of the decisions; if the probabilities are not zero, then choosing the decision having a highest likelihood from the plurality of decisions; and if the probabilities are zero, then selecting an algorithm to be used for choosing one of the decisions.

Information fusion predictor

A method comprises the steps of: producing one or more signals representative of a feature of a target or area of interest, statistically processing the signals to produce one or more first hypotheses of the target or area of interest, comparing the first hypotheses to one or more templates in a template library to produce one or more second hypotheses, and comparing the second hypotheses to one or more models in a model library to produce a target decision. An apparatus that performs the method is also provided.

Hybrid architecture for acquisition, recognition, and fusion

The present invention includes a method for analyzing an image wherein elements defining a path within a two-dimensional image are received from a prescreener. A Sobel operator may be applied to the region around each of the elements of the chain to obtain a corresponding array of gradient directions. An angle correction may be applied to any of the gradient directions that goes beyond the highest value (in radian measure; the Pi &#x2212;Pi transition), to obtain an array of gradient directions free of any artificial jumps in value. The gradient direction array (Sobel chaincode) can have its bandwidth taken to determine a single number of straightness so as to identify extremely straight edges, (manmade objects) from less straight edges (natural objects). A similar process can be used to analyze contours for straight sections, which are also parallel. These two and other filters applied to the gradient array can be part of a feature suite, for feature space analysis.

System and method for analyzing a contour of an image by applying a Sobel operator thereto

A system and method for detecting and warning of an impaired operator, such as a drowsy vehicle/machine operator or air traffic controller. The system and method employ an imaging apparatus which produces consecutive digital images including the face and eyes of an operator. There is an eye finding unit which determines the location of the operator's eyes within each digital image, and generates correlation coefficients corresponding to each eye which quantify the degree of correspondence between pixels associated with the location of the operator's eye in an immediately preceding image in comparison to pixels associated with the location of the operator's eye in a current image. An impaired operator detection unit is used to average the first N consecutive correlation coefficients generated to generate a first average correlation coefficient. After the production of each subsequent image by the imaging apparatus, the impaired operator detection unit averages the previous N consecutive correlation coefficients generated to create a next average correlation coefficient. Next, the impaired operator detection unit analyzes the average correlation coefficients associated with each eye to extract at least one parameter attributable to an eyeblink of the operator's eyes. These extracted parameters are compared to an alert operator threshold associated with that parameter. An impaired operator warning unit is used to indicate that the operator may be impaired if any extracted parameters deviate from the associated threshold in a prescribed way.

Impaired operator detection and warning system employing eyeblink

A system and method for finding and tracking the location of a subject's eyes. This system and method employs an imaging apparatus which produces digital image frames including the face and eyes of a subject. An eye position finding and tracking apparatus is also included to average the intensity representing pixel values within respective M.sub.x by M.sub.y pixel blocks of a digitized image frame to create elements of output matrices. Then, elements of the output matrices are compared to various threshold values. These threshold values are chosen so as to identify which matrix elements correspond to a M.sub.x by M.sub.y pixel block potentially representing an image of the subject's pupil and at least the portion of the subject's iris (i.e. a potential eye location). Once the flagged matrix elements have been determined, any M.sub.x by M.sub.y pixel block corresponding to a flagged matrix element can be designated as an actual subject eye location. However, it is preferred that further steps be taken to confirm the actual eye location, as well as to track the changing position of the subject's eye. Accordingly, the preferred system and method include a provision for tracking the location of a center of each M.sub.x by M.sub.y pixel block representing a potential eye location in each subsequent image frame produced from the imaging apparatus. Further, a provision is included to detect a blink at the location. Such a blink confirms the potential eye location is an actual eye location.

Growing community of inventors

Diamond Bar, CA, United States of America

Omar Aboutalib