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

Title: Model for mapping settlements

Abstract

A programmable media includes a graphical processing unit in communication with a memory element. The graphical processing unit is configured to detect one or more settlement regions from a high resolution remote sensed image based on the execution of programming code. The graphical processing unit identifies one or more settlements through the execution of the programming code that executes a multi-instance learning algorithm that models portions of the high resolution remote sensed image. The identification is based on spectral bands transmitted by a satellite and on selected designations of the image patches.

Inventors:
; ;
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1260219
Patent Number(s):
9,384,397
Application Number:
13/973,573
Assignee:
UT-Battelle, LLC (Oak Ridge, TN) ORNL
DOE Contract Number:
AC05-00OR22725
Resource Type:
Patent
Resource Relation:
Patent File Date: 2013 Aug 22
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS; 97 MATHEMATICS AND COMPUTING

Citation Formats

Vatsavai, Ranga Raju, Graesser, Jordan B., and Bhaduri, Budhendra L. Model for mapping settlements. United States: N. p., 2016. Web.
Vatsavai, Ranga Raju, Graesser, Jordan B., & Bhaduri, Budhendra L. Model for mapping settlements. United States.
Vatsavai, Ranga Raju, Graesser, Jordan B., and Bhaduri, Budhendra L. Tue . "Model for mapping settlements". United States. doi:. https://www.osti.gov/servlets/purl/1260219.
@article{osti_1260219,
title = {Model for mapping settlements},
author = {Vatsavai, Ranga Raju and Graesser, Jordan B. and Bhaduri, Budhendra L.},
abstractNote = {A programmable media includes a graphical processing unit in communication with a memory element. The graphical processing unit is configured to detect one or more settlement regions from a high resolution remote sensed image based on the execution of programming code. The graphical processing unit identifies one or more settlements through the execution of the programming code that executes a multi-instance learning algorithm that models portions of the high resolution remote sensed image. The identification is based on spectral bands transmitted by a satellite and on selected designations of the image patches.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Jul 05 00:00:00 EDT 2016},
month = {Tue Jul 05 00:00:00 EDT 2016}
}

Patent:

Save / Share:
  • Classifying urban land cover from high-resolution satellite imagery is challenging, and those challenges are compounded when the imagery databases are very large. Accurate land cover data is a crucial component of the population distribution modeling efforts of the Oak Ridge National Laboratory's (ORNL) LandScan Program. Currently, LandScan Program imagery analysts manually interpret high-resolution (1-5 meter) imagery to augment existing satellite-derived medium (30m) and coarse (1km) resolution land cover datasets. At LandScan, the high-resolution image archives that require interpretation are on the order of terabytes. The goal of this research is to automate urban land cover mapping utilizing ORNL's high performancemore » computing capabilities. Our algorithm employs gray-level and local edge-pattern co-occurrence matrices to generate texture and edge patterns. Areas of urban land cover correlate with statistical features derived from these texture and edge patterns. We have parallelized our algorithms for implementation on a 64-node system using a single instruction multiple data programming model (SIMD) with Message Passing Interface (MPI) as the communication mode. Our parallel-configured classifier performs 30-40 times faster than stand-alone alternatives. When compared with manually interpreted IKONOS imagery, the classifier achieves a 91% overall accuracy. These early results are promising, pointing towards future large-scale classification of urban areas.« less
  • Speech processing is obtained that, given a probabilistic mapping between static speech sounds and pseudo-articulator positions, allows sequences of speech sounds to be mapped to smooth sequences of pseudo-articulator positions. In addition, a method for learning a probabilistic mapping between static speech sounds and pseudo-articulator position is described. The method for learning the mapping between static speech sounds and pseudo-articulator position uses a set of training data composed only of speech sounds. The said speech processing can be applied to various speech analysis tasks, including speech recognition, speaker recognition, speech coding, speech synthesis, and voice mimicry.
  • An apparatus is described for detecting radioactive sources on a test specimen, the apparatus comprising: a counter having a gas filled chamber, the chamber being formed by an electrically conductive planar window and a parallel semiconductive surface spaced from the window, and adapted for having an electric field imposed within the chamber by a voltage differential between the window and the semiconductive surface; an encoder surface spaced form the semiconductive surface and having geometrically arrayed elements thereon for receiving an electrical charge induced on the elements by an ion avalanche occurring within the chamber in response to entry of amore » radioactive particle into the chamber; and a dielectric layer between the semiconductive surface and the encoder surface, the semiconductive surface forming a coating on one side of the layer and the arrayed elements forming a coating on the opposite side of the layer.« less
  • A method of detecting selected nuclei within a specimen is described comprising: (a) providing a primary magnetic field having a known field configuration in a three dimensional space having an ''X'', ''Y'', and ''Z'' dimensional frame of reference, the primary magnetic field having a magnetic field orientation in the ''Z'' direction; (b) focusing the magnetic field to produce a resulting magnetic field of known magnetic configuration having a magnetic field orientation in the ''Z'' direction and a selected gradient in the ''Y'' direction and maintaining the resulting field unaltered during the generation of a nuclear magnetic resonance signal; (c) providingmore » a source of oscillating magnetic radiation having a selectable frequency and of limited spacial extent in all directions in the Z-X plane; (d) selecting a frequency ..omega../sub 0/ of the source of oscillating magnetic radiation to satisfy the equation: ..omega../sub 0/= absolute value of H/sub o/..gamma.. where: ..omega../sub 0/ = resonance angular frequency of the selected nuclei; absolute value of H/sub 0/ = magnitude of resulting static magnetic field at a chosen location; ..gamma.. = gyromagnetic ratio for the selected nuclei and is a constant for the selected nuclei. For the selected nuclei within the resulting magnetic field where the field strength is substantially the absolute value of H/sub 0/.« less
  • A prospecting system is described for hydrocarbons using emanoradiation measurements of the neutron, beta, gamma rays, and radon gas emitted at the earth surface and atmosphere from the earth basement complex and, the overlying sedimentary deposits of carbonaceous rocks, shales and sandstone that are impregnated with uranium, thorium and potassium derived from the eroded earth basement complex materials. A number of check points are measured and the radiation levels are plotted to form a georadiograph. A comparison between the background level and the check point levels is used in determining the contour data basically of the earth's stratosphere, altered inmore » its variation by hydrocarbons, radiation active substances, and/or mineral deposits. 2 claims, 10 figures.« less