Raytheon Company

Raytheon Comopany

Timothy Edward Caber

Thomas K Lo

Todd L Baker

Hien T Dang

Sheldon S Wald

Andrew R Ream

A method for solving the track association problem updates and samples a marginal association likelihood conditioned upon existing track assignments and marginalized over possible sensor biases to assign tracks and build a full association hypothesis. The 'sampling' is repeated multiple times for a given seed track pair and for different seed track pairs to quickly generate hypotheses that approximate the solution space. The probabilistic track association includes a plurality of likely full association hypotheses and a soft association matrix that probabilistically reflects the likelihood of the track association for a pair of sensors. Efficacy can be enhanced by sensing and processing non-metric features (e.g. size, shape, color) to supplement the metric features (e.g. location, velocity). Efficiency may be enhanced by prioritizing the list of seed track pairs in order of decreasing likelihood, saving only full association hypotheses that are both unique and close to the current most likely hypothesis and terminating the search based on a staleness criteria. Probabilistic sampling may be used for such diverse applications as missile defense, autonomous vehicles and package handling.

Probabilistic sampling method for track association

It is often desirable to register a first image to a second image, such as to form a panoramic image. The image registration technique discussed herein forms first and second gradients of the first and second images, respectively, then aligns phase vectors of the first and second gradients by estimating the parameters of a projective (homographic) coordinate transformation that can map the first gradient to the second gradient. The estimated parameters can be used to map the first image to the second image. In some examples, each gradient pixel includes a complex number, such as a unit vector, having a normalized amplitude and a phase vector that indicates the direction of greatest change, at that pixel, for the respective image. Aligning the image gradient phase vectors, rather than image intensity values, can align images produced under different lighting conditions, and/or produced in different wavelength regions of the electromagnetic spectrum.

Image processing system and method for calculating transformation parameters to register a first image to a second image

An exemplary apparatus providing an improved detection system is disclosed as having: a sensor array adapted to detect radiation emanating from a potential target and a missile guidance system for controlling a missile's trajectory. Disclosed features and specifications may be variously controlled, adapted or otherwise optionally modified to improve and/or modify the performance characteristics of the detection system. Exemplary embodiments of the present invention generally provide a detection system for use as, for example, a target detection system for a missile guidance system.

Methods and apparatus for detecting a target

An interceptor-based sensor clusters tracks of objects to generate track clusters based on an uncertainty associated with each track, and generates feature vectors for a cluster under test using the relative placement and the population of other track clusters. The feature vectors may include one or more of a cluster count feature vector (N), a cluster population density feature vector (P), a cluster proximity feature vector (r), a cluster-weighted centroid feature vector (L) and a cluster scattering feature vector (&#x3b8;). The interceptor-based sensor generates belief functions (&#x3bc;) from corresponding feature vectors of clusters of tracks generated from a ground-based sensor and the interceptor-based sensor. The interceptor-based sensor may also associate the tracks with a cluster having a track of interest identified by a ground-based sensor based on the belief functions and may select one of the tracks for intercept of a corresponding object within the threat object cloud.

Pattern classifier and method for associating tracks from different sensors

A fuzzy controller ( ) for use in target detection systems. The fuzzy controller ( ) includes a first circuit ( ) for determining a number of false alarms in a frame of data. A second circuit ( ) determines a desired number of false alarms for the frame of data. A third circuit ( ) computes a threshold multiplier factor based on the number of false alarms, the desired number of false alarms, and one or more fuzzy rules. In a specific embodiment, the first circuit ( ) includes a target detection system for providing addresses of pixels whose values are within a predetermined range relative to a detection threshold. The second circuit ( ) includes an input device ( ) for accepting the desired number of false alarms as input to the fuzzy controller ( ). The third circuit ( ) includes a fuzzifier input calculation circuit ( ) that computes a fuzzifier input value based on the number of false alarms detected in a frame and the desired number of false alarms.

Accurate target detection system

An accurate target detection system. The system includes a sensor (,) that receives electromagnetic signals and provides electrical signals in response thereto. A non-uniformity correction circuit (,) corrects non-uniformities in the sensor (,) based on the electrical signals and provides calibrated electrical signals in response thereto. A third circuit (,) determines if a target signal is present within the calibrated electrical signals and provides a target detection signal in response thereto. A fourth circuit (,) selectively activates or deactivates the non-uniformity correction circuit (,) based on the target detection signal. In a specific embodiment, the sensor (,) is an array of electromagnetic energy detectors (,), each detector providing an electrical detector output signal. The non-uniformity correction circuit (,, and,) includes circuit for compensating for gain, background, and noise non-uniformities (,, and,) in the electromagnetic energy detectors. The non-uniformity correction circuit (,, and,) includes a detector gain term memory (,) for storing detector gain compensation values. The detector gain compensation values are normalized by noise estimates unique to each of the detectors. The third circuit (,, and,) includes a signal enhancement circuit for reducing noise (,) in the calibrated electrical signals. The third circuit (,, and,) includes a noise estimation circuit (,) that estimates noise in each of the detector output signals and provides noise estimates in response thereto. The noise estimation circuit (,) further includes a noise estimator circuit (,) and a recursive background estimator (,).

Growing community of inventors

Tucson, AZ, United States of America

Timothy Edward Caber