Joseph R Newbrough

US Patent:

20190385338, Dec 19, 2019

Filed:

Dec 18, 2018

Appl. No.:

16/224400

Inventors:

- Herndon VA, US
Christopher Burd - Washington DC, US
Andrew Jenkins - Waterford VA, US
Joseph Newbrough - Springfield VA, US
Scott Szoko - Odenton MD, US
Melanie Vinton - Fairfax Station VA, US

International Classification:

G06T 7/73
G06K 9/62
G06N 3/08
G06N 3/04
G06K 9/00
G06T 5/00
G06T 15/50
G06T 17/05
G06T 7/90

Abstract:

A system for broad area geospatial object recognition, identification, classification, location and quantification, comprising an image manipulation module to create synthetically-generated images to imitate and augment an existing quantity of orthorectified geospatial images; together with a deep learning module and a convolutional neural network serving as an image analysis module, to analyze a large corpus of orthorectified geospatial images, identify and demarcate a searched object of interest from within the corpus, locate and quantify the identified or classified objects from the corpus of geospatial imagery available to the system. The system reports results in a requestor's preferred format.

US Patent:

20180158210, Jun 7, 2018

Filed:

Sep 19, 2017

Appl. No.:

15/709252

Inventors:

- Longmont CO, US
Christopher Burd - Washington DC, US
Andrew Jenkins - Waterford VA, US
Joseph Newbrough - Springfield VA, US
Scott Szoko - Odenton MD, US
Melanie Vinton - Fairfax Station VA, US

International Classification:

G06T 7/73
G06K 9/62
G06N 3/08
G06N 3/04
G06K 9/00
G06T 7/90

Abstract:

A system for broad area geospatial object recognition, identification, classification, location and quantification, comprising an image manipulation module to create synthetically-generated images to imitate and augment an existing quantity of orthorectified geospatial images; together with a deep learning module and a convolutional neural network serving as an image analysis module, to analyze a large corpus of orthorectified geospatial images, identify and demarcate a searched object of interest from within the corpus, locate and quantify the identified or classified objects from the corpus of geospatial imagery available to the system. The system reports results in a requestor's preferred format.

US Patent:

20170061625, Mar 2, 2017

Filed:

Jun 27, 2016

Appl. No.:

15/194541

Inventors:

- Longmont CO, US
Christopher Burd - Washington DC, US
Andrew Jenkins - Waterford VA, US
Joseph Newbrough - Springfield VA, US
Scott Szoko - Odenton MD, US
Melanie Vinton - Fairfax Station VA, US

International Classification:

G06T 7/00
G06N 3/04
G06N 3/08
G06T 7/40
G06K 9/62

Abstract:

A system for broad area geospatial object recognition, identification, classification, location and quantification, comprising an image manipulation module to create synthetically-generated images to imitate and augment an existing quantity of orthorectified geospatial images; together with a deep learning module and a convolutional neural network serving as an image analysis module, to analyze a large corpus of orthorectified geospatial images, identify and demarcate a searched object of interest from within the corpus, locate and quantify the identified or classified objects from the corpus of geospatial imagery available to the system. The system reports results in a requestor's preferred format.