Harris Geospatial Solutions, Inc.

Exelis Inc.

Eagle Technology, LLC

Digitalglobe, Incorporated

Michael Paul Deskevich

Christopher Padwick

Robert A Simon

Christopher R Lees

An image processing system may include a processor and an associated memory configured to store training data that includes training geospatial images. Each training geospatial image may include pixels. The processor may be configured to operate a training model to identify a given feature from each of the training geospatial images, and to iteratively generate a probability distribution function based upon a number of pixels corresponding to the given feature and also based upon a bias factor being reduced with each iteration.

Image processing system including iteratively biased training model probability distribution function and related methods

Methods and systems in accordance with the present invention automatically subdivide an area having an arbitrary shape into multiple sub-regions that have approximately equal area under a threshold, with compact shapes having minimal perimeter length. These systems input an arbitrarily shaped zone and recursively bisect it until all of the new sub-zones are smaller than a particular threshold. A data processing system subdivides a two-dimensional region, such as a digital image of a landmass. The data processing system loads the region into memory, determines a minor axis of the region, and splits the region along the minor axis into a first sub-region and a second sub-region. The sub-regions are evaluated to determine if they are under the threshold area. The steps of the process are repeated until all resulting sub-regions are under the threshold area. Consistently compact sub-regions with minimal perimeter are achieved by splitting along the minor axis.

Method and system for fast approximate region bisection

An image processing system may include a processor and an associated memory configured to store training data that includes training geospatial images. The processor may be configured to operate a training model to identify a given feature from each of the training geospatial images, and to iteratively apply a bias factor to a loss function based upon a number of incorrectly identified pixels for the given feature. The bias factor may be reduced with each iteration.

Image processing system including training model based upon iteratively biased loss function and related methods

An image processing system may include a processor and an associated memory configured to store training data that includes training geospatial images. The processor may be configured to blur each of the training geospatial images. The processor may also be configured to iteratively operate a training model to identify a given feature from each of the blurred training geospatial images so that the blurring is reduced with each iteration.

Image processing system including training model based upon iterative blurring of geospatial images and related methods

An image processing system combines higher-resolution panchromatic images and lower resolution multispectral images using a hyperspherical color space pan-sharpening technique. By converting the multispectral images into a hyperspherical color space, the intensities of the multispectral images can be intensity matched to the intensities of the panchromatic image and then retransformed back to the original color space. The intensity matching can utilize a number of techniques, including, but not limited to, direct substitution of the intensities of the panchromatic image for the intensities of the multispectral images, modification of the intensities of the multispectral images based on predefined statistical models and modification of the intensities of the multispectral images based on dynamically generated statistical models and a selected sharpening parameter &#x3b2;.

System and method for combining color information with spatial information in multispectral images

An image processing system using hyperspherical pan-sharpening. The image processing system of the present invention includes circuitry for converting the multispectral image into a hyperspherical color space, matching the intensities of the multispectral image to the intensities of the corresponding panchromatic image and then retransforming the color space back the original multispectral image. The intensity matching of the present invention includes modification of the intensities of the multispectral images based on dynamically generated statistical models and a selected sharpening parameter &#x3b2;.

Hyperspherical pan sharpening

A method of converting a raster scan image to a vector-based image including (a) reading a scanline of a raster scan image containing n pixels per scanline; (b) classifying n+1 groupings of four adjacent pixels within the scanline using only the four adjacent pixel values; (c) assigning to each grouping (x,y), for all groupings in the scanline, plural vectors based on (1) the classification of the grouping (x,y) and (2) vectors assigned to a grouping (x&#x2212;1,y) and vectors assigned to a grouping (x, y&#x2212;1); (d) adding a point (x,y) to at least one vector assigned to the grouping (x,y) when the classification of grouping (x,y) indicates that the point (x,y) corresponds to a corner; (e) determining whether the points added to any vector form a closed loop; (f) writing out the points added to any vector that form a closed loop; and (g) repeating steps (a)-(f) for all of the scanlines of the raster scan image.

Growing community of inventors

Boulder, CO, United States of America

Michael Paul Deskevich