General Electric Company

Lockheed Martin Corporation

Ge Aviation Systems Limited

Ge Security, Inc.

Lockheed Martin Company

Thomas Baby Sebastian

Jens Rittscher

Peter Henry Tu

GianFranco Doretto

Eric Daniel Buehler

James Vradenburg Miller

Ravindra Mohan Manjeshwar

Ricardo Scott Avila

Xiaoming Liu

Stefano Angelo Mario Lassini

Ting Yu

Paulo Ricardo Dos Santos Mendonca

Peter Michael Edic

Harry Kirk Mathews, Jr

Samit Kumar Basu

Bruno Kristiaan Bernard De Man

Jeffrey Michael Ashe

Dashan Gao

Harold Woodruff Tomlinson, Jr

Todd Alan Anderson

Alexander Ganin

Kai Erik Thomenius

Yi Xu

Glenn A Forman

Nicholas Thomas

Mauricio Castillo-Effen

Minesh Ashok Shah

Michael Richard Durling

Rahul Bhotika

Deborah Joy Walter

Jilin Tu

Stewart Abbot

Nils Oliver Krahnstoever

Benjamin Thomas Occhipinti

Xiaogang Wang

Konrad Robert Kuczynski

Richard Shawn Kelly

Ana Isabel Del Amo

Stefano Angelo Lassini

Dirk Ryan Padfield

William Macomber Leue

Paulo Ricardo Mendonca

Yi Yao

Colin Craig McCulloch

Floribertus Philippus Martinus Heukensfeldt Jansen

Floribertus Heukensfeldt Jansen

Dinko Eduardo Gonzalez Trotter

John Charles Hill, Jr

Nelson Corby

Nikita Visnevski

Craig Hoover

Harold Woodruff Tomlinson

Matthew James Schafer

Rebecca Jeanne Smith

Steven Richard Hansen

Douglas Stuart Abernathy

Sarah Christine Maas Stotz

Kenneth R Turner

Dinko Gonzalez Trotter

Stewart E Abbot

Amitha Perera

Glenn Alan Forman

Harold Woodruff Tomlinson Jr

Craig Alan Hoover

Dirk R Padfield

A method implemented using a processor based device is disclosed. The method includes receiving a video stream comprising a plurality of image frames having at least one moving object, determining a difference between at least two image frames among the plurality of image frames and generating a difference image comprising a plurality of image blobs corresponding to the at least one moving object. The method further includes generating a plurality of bounding boxes, each bounding box surrounding at least one corresponding image blob among the plurality of image blobs, and determining a subset of bounding boxes among the plurality of bounding boxes, associated with the corresponding moving object, using a fuzzy technique based on a perceptual characterization of the subset of bounding boxes. The method also includes merging the subset of bounding boxes to generate a merged bounding box enclosing the subset of bounding boxes to detect the moving object.

System and method for detection and tracking of moving objects

A method of tracking motion of at least one object of a group of moving objects using hyperspectral imaging includes, among other things, obtaining a series of hyperspectral image frames; comparing each frame in the series to a template to determine changes in the image between frames; identifying a group of pixels in each frame associated with the changes; identifying changes as motion of the moving objects; correlating the pixel groups frame to frame to spatially determine at least one parameter of the motion of the objects; and correlating the pixel groups with a spectral reflectance profile associated with the at least one object wherein the track of the at least one object is distinguishable from the tracks of other moving objects.

Method of tracking objects using hyperspectral imagery

Systems provided herein include a learning environment and an agent. The learning environment includes an avatar and an object. A state signal corresponding to a state of the learning environment includes a location and orientation of the avatar and the object. The agent is adapted to receive the state signal, to issue an action capable of generating at least one change in the state of the learning environment, to produce a set of observations relevant to a task, to hypothesize a set of action models configured to explain the observations, and to vet the set of action models to identify a learned model for the task.

Action-based models to identify learned tasks

A method of referencing an imaged object includes, among other things, obtaining a series of images, observing key characteristics of the object in each of the series of images, associating the observed key characteristics with the object; and assigning a unique identifier to the object based upon the associated key characteristics. The series of images includes spectral and spatial imagery. Some of the key characteristics are in the spectral imagery and some of the key characteristics are in the spatial imagery.

Method of identification from a spatial and spectral object model

A trajectory-based sense-and-avoid system for use on an aircraft is provided that utilizes 4-D constructs, such as 4-D trajectories or 4-D polytopes, to maintain separation from other aircraft and/or to avoid collisions with other aircraft. In certain embodiments the trajectory-based sense-and-avoid system utilizes 4-D trajectories provided from an external source and/or 4-D trajectories estimated based on a variety of data sources during operation.

Trajectory based sense and avoid

A multispectral staring array comprises, amongst other things, at least two sensors where each sensor is adapted to detect an image in a different predetermined spectral sensitivity; a first lens to focus capture spectral bands; a spectral filter between the lens and the sensors to subdivide the incident spectral bands; and a second lens to direct and focus the subdivided incident spectral bands on each of the sensors.

Mixed-material multispectral staring array sensor

A method of removing a hyperspectral signature from at least one hyperspectral image, includes among other things, selecting a hyperspectral signature and determining a dissimilarity value between each pixel in the at least one hyperspectral image and the selected at least one hyperspectral signature. If the dissimilarity value between the signature of a given pixel in the at least one hyperspectral image and the selected at least one hyperspectral signature is less than a predetermined threshold value then the value of the signature for the given pixel is set to zero to create a signature-subtracted hyperspectral image.

Substance subtraction in a scene based on hyperspectral characteristics

A device and method for processing an image to create appearance and shape labeled images of a person or object captured within the image. The appearance and shape labeled images are unique properties of the person or object and can be used to re-identify the person or object in subsequent images. The appearance labeled image is an aggregate of pre-stored appearance labels that are assigned to image segments of the image based on calculated appearance attributes of each image segment. The shape labeled image is an aggregate of pre-stored shape labels that are assigned to image segments of the image based on calculated shape attributes of each image segment. An identifying descriptor of the person or object can be computed based on both the appearance labeled image and the shape labeled image. The descriptor can be compared with other descriptors of later captured images to re-identify a person or object.

Identifying descriptor for person and object in an image

Identifying descriptor for person or object in an image

A system and method for vehicle-centric infrastructure monitoring system includes an inspection system mountable on a vehicle configured to travel over an expanse of rail track having a plurality of track blocks. The inspection system acquires track data for at least some track blocks along the expanse of rail track. The monitoring system also includes a positioning system to determine a location of the vehicle and generate location data indicative of an associated track block location, a communications device to transmit the track/location data to a remote location, and a centralized computing system positioned at the remote location to receive the transmitted track/location data. The centralized computing system is programmed to determine a current probability of a track condition for a track block and combine the current track condition probability with a previously determined cumulative track condition probability to provide an updated track condition probability for the track block.

Apparatus and method for monitoring of infrastructure condition

Aspects of the disclosure provide a method for crowd segmentation that can globally optimize crowd segmentation of an input image based on local information of the input image. The method can include receiving an input image of a site, initializing a plurality of hypothesis based on the input image, dividing the input image into a plurality of patches, calculating an affinity measure of one or more patches to a hypothesis based on a partial response of the patches to a whole body classifier of the hypothesis that includes a combination of weak classifiers, and optimizing assignments of the plurality of patches to the plurality of hypothesis based on the affinity measures of the plurality of patches to the plurality of hypothesis.

Method and system for crowd segmentation

The present invention aims at providing a method for detecting a color of a signal light from a moving vehicle such as railroad train. The method includes capturing an image from a camera mounted on the moving vehicle and extracting candidate regions in the image that contain light region. The method further includes classifying the candidate regions as a signal light region or a non-signal light region and identifying the color of the signal light region.

Method and system for detecting signal color from a moving video platform

The present invention aims at providing a method for detecting a signal structure from a moving vehicle. The method for detecting signal structure includes capturing an image from a camera mounted on the moving vehicle. The method further includes restricting a search space by predefining candidate regions in the image, extracting a set of features of the image within each candidate region and detecting the signal structure accordingly.

Method and system for detecting a signal structure from a moving video platform

A device and method for efficient computation of statistical information, such as a mean, co-variance, or histogram of the image pixels, over discrete image regions. The computation employs integral computations to determine the statistical information over image regions of arbitrary shape, including irregular polygonal shaped regions. The integral computations are simplified by categorizing corner points of boundaries of image regions. The computation can be applied to calculate descriptors or signatures of persons or objects within an image. The computation also has a low computational cost enabling fast calculation of image statistics.

Device and method for fast computation of region based image features

Growing community of inventors

Flemington, NJ, United States of America

Thomas Baby Sebastian