Lockheed Martin Corporation

Lockhead Martin Corp.

Lockheed Martin Missiles & Fire Control

Hai-Wen Chen

Teresa Olson

Gene D Tener

Timothy Alderson

Barry G Mattox

Jennifer K Park

James P Kane, Iii

David J Huber

John Cowan

William R Herzog

Surachai Sutha

Felix M Fontan

Steven R Frey, Jr

Methods and systems for image processing are provided. A method for processing images of a scene includes receiving image data of a reference and a current frame; generating N motion vectors that describe motion of the image data within the scene by computing a correlation function on the reference and current frames at each of N registration points; registering the current frame based on the N motion vectors to produce a registered current frame; and updating the image data of the scene based on the registered current frame. Optionally, registered frames may be oversampled. Techniques for generating the N motion vectors according to roll, zoom, shift and optical flow calculations, updating image data of the scene according to switched and intermediate integration approaches, re-introducing smoothed motion into image data of the scene, re-initializing the process, and processing images of a scene and moving target within the scene are provided.

Continuous extended range image processing

A method for identifying potential targets as far away as possible is disclosed. In a simple background scene such as a blue sky, a target may be recognized from a relatively long distance, but for some high clutter situations such as mountains and cities, the detection range is severely reduced. The background clutter may also be non-stationary further complicating the detection of a target. To solve these problems, target detection (recognition) of the present invention is based upon temporal fusion (integration) of sensor data using pre-detection or post-detection integration techniques, instead of using the prior art technique of fusing data from only a single time frame. Also disclosed are double-thresholding and reversed-thresholding techniques which further enhance target detection and avoid the shortcomings of the traditional constant false alarm rate (CFAR) thresholding technique. The present invention further discloses improved spatial fusion techniques for target detection (recognition) employing multiple sensors instead of employing the more conventional single sensor techniques. If spatial fusion is implemented with more than three sensors, then target detection can be enhanced by also using post-detection techniques. Moreover, since the pre-detection and the post-detection technique are complementary to each other, a combination of these two integration techniques will further improve target detection (recognition) performance.

Target detection improvements using temporal integrations and spatial fusion

A method and system, for detecting closely spaced objects with data from an imaging sensor. A CFAR detector performs detection on the image data at a threshold level. A processor runs a first algorithm on exceedances above the CFAR threshold. The first algorithm is for single target detection and includes a local-max algorithm that identifies multiple exceedances within a 2&#xd7;2 matrix of image data and only keeps exceedance with the maximum value. All other exceedances in image are single target detections. The processor runs a second algorithm that identifies multiple exceedances (single target detections) within a local regional area across the whole image. The regional area size may be a 3&#xd7;3, 4&#xd7;4, or 5&#xd7;5 matrix depending on the specified CSO separations. This algorithm may use a regional moving window across the whole image. An alternative method using the indices of all the exceedances' (x,y) coordinates is also disclosed.

Closely-spaced multiple targets detection using a regional window as a discriminant function

A method and system provide a multi-sensor data fusion system capable of adaptively weighting the contributions from each one of a plurality of sensors using a plurality of data fusion methods. During a predetermined tracking period, the system receives data from each individual sensor and each data fusion method is performed to determine a plurality of reliability functions for the system based on combining each sensor reliability function which are individually weighted based on the S/N (signal-to-noise) ratio for the received data from each sensor, and a comparison of predetermined sensor operation characteristics for each sensor and a best performing (most reliable) sensor. The system may dynamically select to use one or a predetermined combination of the generated reliability functions as the current (best) reliability function which provides a confidence level for the multi-sensor system relating to the correct classification (recognition) of targets and decoys.

Method and system for data fusion using spatial and temporal diversity between sensors

A method and apparatus for detecting and tracking objects using infrared sensors are disclosed. The system is preferably an IRST (infrared, search and tracking) system, and it includes at least one or more infrared sensors, a receiver and a processor. The receiver receives image data from the infrared sensors having a predetermined field of view. The image data includes a reference image, which is preferably a current frame, and a search image, which is preferably a previous frame. The image data is classified to determine whether the image data includes relatively low clutter or relatively high clutter. When the image data includes relatively high clutter of the type typically found in an urban area, the processor performs spot time-difference processing on multiple frames of the image data. The processor detects a moving object from the multiple frames of image data, and it is also capable of detecting stationary objects and random objects.

Method and system for improved unresolved target detection using multiple frame association

A system and method for estimating noise using measurement based parametric fitting non-uniformity correction is disclosed. Fixed pattern noise ('FPN') is estimating from an overall noise component within a detection system to enhance candidate target detection and tracking. A sensor in the detection system receives energy, such as radiant flux, that is converted to a digital image. A non-uniformity correction device generates an estimated FPN according to an applicable temperate range and integration time. A memory storing an array of coefficients is accessed to determine the estimated FPN. The valves within the array of coefficients are based on actual FPN measurements that are parametrically fitted.

System and method for estimating noise using measurement based parametric fitting non-uniformity correction

A method and system for detecting a point source target using multiple matched filters are disclosed. A sensor, which is preferably an infrared focal plane array, includes a plurality of pixels for providing image data. A processor processes the image data from a selected pixel corresponding to a potential point source target and from a plurality of neighboring pixels. The system includes multiple filters having a plurality of different phases, including at least a center phase and four corner phases. The multiple filters filter the image data to obtain different filtered spatial images. A detector, which is preferably a CFAR detector, detects a target based upon the spatially filtered images from the multiple matched filters.

Unresolved target detection improvement by use of multiple matched filters approach at different spatial phases

A multi-sensor data fusion system and method provides adaptive weighting of the contributions from a plurality of sensors in the system using an additive calculation of a sensor reliability function for each sensor. During a predetermined tracking period, data is received from each individual sensor in the system and a sensor reliability function is determined for each sensor based on the SNR (signal-to-noise ratio) for the received data from each sensor. Each sensor reliability function is individually weighted based on the SNR for each sensor and a comparison of predetermined sensor operation characteristics for each sensor and a best performing (most reliable) sensor. Additive calculations are performed on the sensor reliability functions to produce both an absolute and a relative reliability function which provide a confidence level for the multi-sensor system relating to the correct classification (recognition) of targets and decoys.

Method and system for multi-sensor data fusion

A multi-sensor data fusion system and method provide an additive fusion technique including a modified belief function (algorithm) to adaptively weight the contributions from a plurality of sensors in the system and to produce multiple reliability terms including reliability terms associated with noise for low SNR situations. During a predetermined tracking period, data is received from each individual sensor in the system and a predetermined algorithm is performed to generate sensor reliability functions for each sensor based on each sensor SNR using at least one additional reliability factor associated with noise. Each sensor reliability function may be individually weighted based on the SNR for each sensor and other factors. Additive calculations are performed on the reliability functions to produce at least one system reliability function which provides a confidence level for the multi-sensor system relating to the correct classification (recognition) of desired objects (e.g., targets and decoys).

Method and system for multi-sensor data fusion using a modified dempster-shafer theory

A target detection and tracking system provides dynamic changing of the integration time (IT) for the system IR sensor within a discrete set of values to maintain a high sensor sensitivity. The system changes the integration time to the same or a different sensor integration time within the discrete set based on the image data output from the sensor satisfying pre-determined system parameter thresholds. The system includes an IT-related saturation prediction function allowing the system to avoid unnecessary system saturation when determining whether an IT change should be made. The tracking portion of the system provides tracking feedback allowing target objects with a low sensor signature to be detected without being obscured by nearby uninterested objects that produce system saturation.

Growing community of inventors

Orlando, FL, United States of America

Hai-Wen Chen