General Electric Company

Brown University

Other

Joseph Leagrand Mundy

Benjamin Kimia

Matthew William Turek

Kongbin Kang

Philip Nathan Klein

Reuben E Joynson

Huseyin Can Aras

Peter Henry Tu

James Vradenburg Miller

Robert August Kaucic

Van-Duc Nguyen

Thomas M Cipolla

Kevin George Harding

Xiaoye Wu

Glen William Brooksby

William E Lorensen

Ricardo Scott Avila

William D Barber

Bryce Zachary Porter

Joseph Benjamin Ross

Paulo Ricardo Dos Santos Mendonca

Ryan Mark Justus

Colin Craig McCulloch

Charles Vernon Stewart

Donald Wagner Hamilton

Francisco Rivas

Victor Nzomigni

Roderic Greene Collins

Thomas Watkins Lloyd

Gilbert B Porter, Iii

Tony Chi-shao Pan

Shannon Lee Hastings

Ranan Banerji

A system for modeling a roof structure comprising an aerial imagery database and a processor in communication with the aerial imagery database. The aerial imagery database stores a plurality of stereoscopic image pairs and the processor selects at least one stereoscopic image pair among the plurality of stereoscopic image pairs and related metadata from the aerial imagery database based on a geospatial region of interest. The processor identifies a target image and a reference image from the at least one stereoscopic pair and calculates a disparity value for each pixel of the identified target image to generate a disparity map. The processor generates a three dimensional point cloud based on the disparity map, the identified target image and the identified reference image. The processor optionally generates a texture map indicative of a three-dimensional representation of the roof structure based on the generated three dimensional point cloud.

Systems and methods for modeling structures using point clouds derived from stereoscopic image pairs

In one aspect, a method and apparatus for detecting subject matter of interest in view data obtained by scanning an object including generating a filter adapted to respond to the subject matter of interest, splatting the filter onto a portion of the view data to provide a filter splat, and performing at least one operation on the portion of the view data using the filter splat to facilitate determining whether the subject matter of interest is present in the portion of the view data.

Methods and apparatus for identifying subject matter in view data

In one aspect, a method and apparatus for determining a value for at least one parameter of a configuration of a model associated with structure of which view data has been obtained including detecting at least one feature in the view data, and determining the value for the at least one parameter of the configuration of the model based at least in part on the at least one feature. In another aspect, a method and apparatus for detecting at least one blood vessel from object view data obtained from a scan of the at least one blood vessel including generating a model of the at least one blood vessel, the model having a plurality of parameters describing a model configuration, determining a hypothesis for the model configuration based, at least in part, on at least one feature detected in the object view data, and updating the model configuration according to a comparison with the object view data to arrive at a final model configuration, so that the final model configuration represents the at least one blood vessel.

Methods and apparatus for model-based detection of structure in view data

A method for detecting, quantifying, staging, reporting, and/or tracking of a disease includes providing analysis software configured to detect, quantify, stage, report, and/or track a disease utilizing images of a patient. The analysis software is executable on a personal computer of a patient. Patients are then imaged utilizing a medical imaging apparatus and medical images of the patient produced by the imaging apparatus are downloaded to the personal computer of the patient. The imaging and downloading are repeated a plurality of times at intervals selected to provide the analysis software with sufficient images to detect, quantify, stage, report, and/or track the disease in the patient.

Methods and apparatus for processing image data to aid in detecting disease

A method for measuring tubular anatomical structures, for example lung airways, comprises isolating by at least one segmentation process a given tubular anatomical structure of interest and measuring at least one attribute of the structure of interest. A system for measuring lung airways using acquired image data is provided. The system comprises an imaging device for acquiring the image data and an image processing device coupled to the imaging device. The imaging processing device is configured for isolating by at least one segmentation process a given airway of interest, fitting an inner ellipse to an inner boundary of the given airway and an outer ellipse to an outer boundary of the airway structure using statistical techniques at a given point in the airway, and further configured for generating measurements of the given airway using the inner and outer ellipses.

Method and system for airway measurement

A method for processing medical images for use in the detection and diagnosis of disease comprises classifying regions of interest within the medical images based on a hierarchy of anatomical models and signal models of signal information of an image acquisition device used to acquire the medical images. The anatomical models are derived to be representative of anatomical information indicative of a given disease. A computer-aided system for use in the diagnosis and detection of disease comprises an image acquisition device for acquiring a plurality of image data sets and a processor adapted to process the image data sets. The processor is adapted to classify selected tissue types within the image data sets based on a hierarchy of signal and anatomical models and the processor is further adapted to differentiate anatomical context of the classified tissue types for use in the diagnosis and detection of disease.

Method and system for lung disease detection

A method for increasing the dynamic light intensity range of an image by combining pixel data from multiple images collected at different levels of illumination intensity to create a single floating-point image representation of an observed scene.

Method for high dynamic range image construction based on multiple images with multiple illumination intensities

The present invention is directed to an imaging apparatus for examining an object having smooth surfaces to determine shape deformations in the surface of object. The imaging apparatus includes an imaging device for obtaining a scanned image of the object to be examined. A reference image of the object is stored in a memory. An image register is coupled to the imaging device and to the memory containing the reference image of the object. The image register stores patch information corresponding to both the reference image and the scanned image. A transformation estimator is coupled to the image register, and provides a transform for registering the scanned image to the reference image. A deformation estimator is coupled to the transformation estimator and to the image register. The deformation estimator is configured to utilize the transform and the patch information to determine shape deformations of the object.

Method and apparatus for finding shape deformations in objects having smooth surfaces

A method for optical part shape measurement of a bare metal part to determine acceptability of the manufactured part. A variable level light source illuminates the part which is mounted on positioning equipment that allows the part to be moved from one position to another. Localized variations in light level are first determined and are compared with a reflectivity model of the part to determine optimization of the setup. Light level and viewing orientation of the part are adjusted to optimize the quality of test data obtained. Data quality is reviewed to ascertain a confidence factor for each location on the part's surface. Using both the reflectivity model and quality test results, data acquired for specified areas of the part is either accepted or rejected. Light level and part orientation are changed based upon how a reflectivity map of the part changes with each adjustment. New and acceptable data are now acquired for those areas of the part where data was previously discarded. This new acceptable data is combined with the previously acceptable data to obtain a complete set of data upon which acceptability of the part is determined.

Method of measuring a part with a wide range of surface reflectivities

A method of detecting abnormalities including a learning phase and an inspection phase. In the learning phase, a first statistical quantity and a second statistical quantity are determined based on a first set of n-dimensional data. A second set of n-dimensional data is obtained and a bimodal distribution for a plurality of n-dimensional points in each of the second set of n-dimensional data is determined. A reference template is generated in response to the first statistical quantity, second statistical quantity and bimodal distribution. In the inspection phase, n-dimensional test data to be inspected for abnormalities is obtained and compared to the reference template to detect abnormalities.

Method for automatic screening of abnormalities

A parallax method of wavelength labeling is based on optical triangulation. A complementary color pattern projected onto the surface is characterized by a continuous variation of the power ratio of two wavelength bands, and the profile can be measured at all points in the field of view. Shifts of the wavelength bands on separate detector arrays correspond to profile deviations. A signal processor calculates a normalized signal that is independent of surface reflectivity and roughness variations; the phase shift of this signal yields depth data from which the surface profile can be mapped.

Non-contact measurement of surface profile

High contrast image data is acquired from metal and other hard surfaces with varying roughness and reflectivity on which characters are impressed by vibrapeening or laser marking. The optical scanner applies normal illumination and a linear photodiode array detects light reflected normal to the surface and within a narrow acceptance angle, so that characters appear dark and the background light. The detector signal is preprocessed to remove nonuniform background variations and yield image data which can be fed to conventional character recognition equipment.

Optical character recognition

Line and edge features on the peripheral segments of a two dimensional data scene are classified by data manipulations in the Hadamard transform domain. One dimensional transform coefficients which uniquely determine the classifications are extracted through weighting by submatrices characteristic of the peripheral segments.

Growing community of inventors

Barrington, RI, United States of America

Joseph Leagrand Mundy