DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Object detection approach using generative sparse, hierarchical networks with top-down and lateral connections for combining texture/color detection and shape/contour detection

Abstract

An approach to detecting objects in an image dataset may combine texture/color detection, shape/contour detection, and/or motion detection using sparse, generative, hierarchical models with lateral and top-down connections. A first independent representation of objects in an image dataset may be produced using a color/texture detection algorithm. A second independent representation of objects in the image dataset may be produced using a shape/contour detection algorithm. A third independent representation of objects in the image dataset may be produced using a motion detection algorithm. The first, second, and third independent representations may then be combined into a single coherent output using a combinatorial algorithm.

Inventors:
; ; ; ;
Issue Date:
Research Org.:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1330321
Patent Number(s):
9477901
Application Number:
14/805,540
Assignee:
Los Alamos National Security, LLC (Los Alamos, NM)
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
DOE Contract Number:  
AC52-06NA25396
Resource Type:
Patent
Resource Relation:
Patent File Date: 2015 Jul 22
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS; 97 MATHEMATICS AND COMPUTING

Citation Formats

Paiton, Dylan M., Kenyon, Garrett T., Brumby, Steven P., Schultz, Peter F., and George, John S. Object detection approach using generative sparse, hierarchical networks with top-down and lateral connections for combining texture/color detection and shape/contour detection. United States: N. p., 2016. Web.
Paiton, Dylan M., Kenyon, Garrett T., Brumby, Steven P., Schultz, Peter F., & George, John S. Object detection approach using generative sparse, hierarchical networks with top-down and lateral connections for combining texture/color detection and shape/contour detection. United States.
Paiton, Dylan M., Kenyon, Garrett T., Brumby, Steven P., Schultz, Peter F., and George, John S. Tue . "Object detection approach using generative sparse, hierarchical networks with top-down and lateral connections for combining texture/color detection and shape/contour detection". United States. https://www.osti.gov/servlets/purl/1330321.
@article{osti_1330321,
title = {Object detection approach using generative sparse, hierarchical networks with top-down and lateral connections for combining texture/color detection and shape/contour detection},
author = {Paiton, Dylan M. and Kenyon, Garrett T. and Brumby, Steven P. and Schultz, Peter F. and George, John S.},
abstractNote = {An approach to detecting objects in an image dataset may combine texture/color detection, shape/contour detection, and/or motion detection using sparse, generative, hierarchical models with lateral and top-down connections. A first independent representation of objects in an image dataset may be produced using a color/texture detection algorithm. A second independent representation of objects in the image dataset may be produced using a shape/contour detection algorithm. A third independent representation of objects in the image dataset may be produced using a motion detection algorithm. The first, second, and third independent representations may then be combined into a single coherent output using a combinatorial algorithm.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Oct 25 00:00:00 EDT 2016},
month = {Tue Oct 25 00:00:00 EDT 2016}
}

Works referenced in this record:

Image editing apparatus and method
patent, June 2006


Feature selection method using support vector machine classifier
patent, June 2009


Detecting objects in images with covariance matrices
patent, June 2010


System for object recognition in colorized point clouds
patent, July 2013


Methods of fabricating nanostructures and nanowires and devices fabricated therefrom
patent-application, November 2002


Alternatives to a table of criterion values in signal detection theory
journal, May 1986


Support-vector networks
journal, September 1995


ART neural networks for remote sensing: vegetation classification from Landsat TM and terrain data
journal, March 1997


LIBSVM: A library for support vector machines
journal, April 2011


Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization
journal, February 2003


Classification of transient signals using sparse representations over adaptive dictionaries
conference, June 2011


Receptive fields and functional architecture of monkey striate cortex
journal, March 1968


Task-Driven Dictionary Learning
journal, April 2012


Sparse Representation for Color Image Restoration
journal, January 2008


A model of saliency-based visual attention for rapid scene analysis
journal, January 1998


Simplified neuron model as a principal component analyzer
journal, November 1982


Emergence of simple-cell receptive field properties by learning a sparse code for natural images
journal, June 1996


Trailblazing with Roadrunner
journal, July 2009


Spatial frequency selectivity of cells in macaque visual cortex
journal, January 1982


The orientation and direction selectivity of cells in macaque visual cortex
journal, January 1982


Hierarchical models of object recognition in cortex
journal, November 1999


Matching pursuits with time-frequency dictionaries
journal, January 1993


Large-scale functional models of visual cortex for remote sensing
conference, October 2009


A feedforward architecture accounts for rapid categorization
journal, April 2007


Robust Object Recognition with Cortex-Like Mechanisms
journal, March 2007