skip to main content
DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding

Abstract

An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detect geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.

Inventors:
;
Issue Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1415441
Patent Number(s):
9858502
Application Number:
15/134,437
Assignee:
Los Alamos National Security, LLC (Los Alamos, NM)
Patent Classifications (CPCs):
H - ELECTRICITY H03 - BASIC ELECTRONIC CIRCUITRY H03M - CODING
G - PHYSICS G06 - COMPUTING G06K - RECOGNITION OF DATA
DOE Contract Number:  
AC52-06NA25396
Resource Type:
Patent
Resource Relation:
Patent File Date: 2016 Apr 21
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; 47 OTHER INSTRUMENTATION

Citation Formats

Moody, Daniela, and Wohlberg, Brendt. Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding. United States: N. p., 2018. Web.
Moody, Daniela, & Wohlberg, Brendt. Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding. United States.
Moody, Daniela, and Wohlberg, Brendt. Tue . "Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding". United States. https://www.osti.gov/servlets/purl/1415441.
@article{osti_1415441,
title = {Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding},
author = {Moody, Daniela and Wohlberg, Brendt},
abstractNote = {An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detect geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2018},
month = {1}
}

Patent:

Save / Share:

Works referenced in this record:

Dictionary Learning with Large Step Gradient Descent for Sparse Representations
book, January 2012


Updating the Inverse of a Matrix
journal, June 1989


Method of optimal directions for frame design
conference, January 1999


Fast Image Recovery Using Variable Splitting and Constrained Optimization
journal, September 2010


Learning mid-level features for recognition
conference, June 2010


Alternating Direction Method with Self-Adaptive Penalty Parameters for Monotone Variational Inequalities
journal, August 2000


On Shift-Invariant Sparse Coding
book, January 2004


Image compression using learned dictionaries by RLS-DLA and compared with K-SVD
conference, May 2011


Fast Convolutional Sparse Coding
conference, June 2013


Non-local sparse models for image restoration
conference, September 2009


A Sherman–Morrison approach to the solution of linear systems
journal, May 2006


From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
journal, February 2009


Unsupervised learning of sparse and shift-invariant decompositions of polyphonic music
conference, January 2004


Supervised translation-invariant sparse coding
conference, June 2010


General design algorithm for sparse frame expansions
journal, January 2006


Deconvolutional networks
conference, June 2010


Sparse and shift-Invariant representations of music
journal, January 2006


Task-Driven Dictionary Learning
journal, April 2012


Adaptive deconvolutional networks for mid and high level feature learning
conference, November 2011


An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems
journal, March 2011


Atomic Decomposition by Basis Pursuit
journal, January 1998


A fast proximal method for convolutional sparse coding
conference, August 2013

  • Chalasani, Rakesh; Principe, Jose C.; Ramakrishnan, Naveen
  • 2013 International Joint Conference on Neural Networks (IJCNN 2013 - Dallas), The 2013 International Joint Conference on Neural Networks (IJCNN)
  • https://doi.org/10.1109/IJCNN.2013.6706854

Explicit Shift-Invariant Dictionary Learning
journal, January 2014


Multi-Scale Dictionary Learning Using Wavelets
journal, September 2011