Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing.

doi:10.14358/PERS.72.5.531

Title: Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing.

Full Record
Other Related Research

Abstract

We describe a method for indexing and retrieving high-resolution image regions in large geospatial data libraries. An automated feature extraction method is used that generates a unique and specific structural description of each segment of a tessellated input image file. These tessellated regions are then merged into similar groups, or sub-regions, and indexed to provide flexible and varied retrieval in a query-by-example environment. The methods of tessellation, feature extraction, sub-region clustering, indexing, and retrieval are described and demonstrated using a geospatial library representing a 153 km2 region of land in East Tennessee at 0.5 m per pixel resolution.

Authors:

Tobin Jr, Kenneth William ^[1]; Bhaduri, Budhendra L ^[1]; Bright, Eddie A ^[1]; Cheriydat, Anil ^[2]; Karnowski, Thomas Paul ^[1]; Palathingal, Paul J ^[1]; Potok, Thomas E ^[1]; Price, Jeffery R ^[1]

ORNL
Oak Ridge National Laboratory (ORNL)

Publication Date:: Mon May 01 00:00:00 EDT 2006

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE Laboratory Directed Research and Development (LDRD) Program

OSTI Identifier:: 931591

DOE Contract Number:: DE-AC05-00OR22725

Resource Type:: Journal Article

Resource Relation:: Journal Name: Photogrammetric Engineering & Remote Sensing; Journal Volume: 72; Journal Issue: 5

Country of Publication:: United States

Language:: English

Subject:: 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; INFORMATION RETRIEVAL; IMAGES; AUTOMATION; TENNESSEE; GEOGRAPHIC INFORMATION SYSTEMS

Citation Formats


                    Tobin Jr, Kenneth William, Bhaduri, Budhendra L, Bright, Eddie A, Cheriydat, Anil, Karnowski, Thomas Paul, Palathingal, Paul J, Potok, Thomas E, and Price, Jeffery R. Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing..  United States: N. p., 2006. 
        Web.  doi:10.14358/PERS.72.5.531.

Copy to clipboard


                    Tobin Jr, Kenneth William, Bhaduri, Budhendra L, Bright, Eddie A, Cheriydat, Anil, Karnowski, Thomas Paul, Palathingal, Paul J, Potok, Thomas E, & Price, Jeffery R. Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing..  United States.  doi:10.14358/PERS.72.5.531.

Copy to clipboard


                    Tobin Jr, Kenneth William, Bhaduri, Budhendra L, Bright, Eddie A, Cheriydat, Anil, Karnowski, Thomas Paul, Palathingal, Paul J, Potok, Thomas E, and Price, Jeffery R. Mon .  
        "Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing.".  United States.  
        doi:10.14358/PERS.72.5.531.

Copy to clipboard


                    
@article{osti_931591,

  title        = {Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing.},

  author       = {Tobin Jr, Kenneth William and Bhaduri, Budhendra L and Bright, Eddie A and Cheriydat, Anil and Karnowski, Thomas Paul and Palathingal, Paul J and Potok, Thomas E and Price, Jeffery R},

  abstractNote = {We describe a method for indexing and retrieving high-resolution image regions in large geospatial data libraries. An automated feature extraction method is used that generates a unique and specific structural description of each segment of a tessellated input image file. These tessellated regions are then merged into similar groups, or sub-regions, and indexed to provide flexible and varied retrieval in a query-by-example environment. The methods of tessellation, feature extraction, sub-region clustering, indexing, and retrieval are described and demonstrated using a geospatial library representing a 153 km2 region of land in East Tennessee at 0.5 m per pixel resolution.},

  doi          = {10.14358/PERS.72.5.531},

  journal      = {Photogrammetric Engineering & Remote Sensing},

  number       = 5,

  volume       = 72,

  place        = {United States},

  year         = {Mon May 01 00:00:00 EDT 2006},

  month        = {Mon May 01 00:00:00 EDT 2006}

}

Copy to clipboard

Journal Article:

DOI: 10.14358/PERS.72.5.531

Other availability

Find in Google Scholar

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Large-Scale Geospatial Indexing for Image-Based Retrieval and Analysis

Book Tobin Jr, Kenneth William ; Bhaduri, Budhendra L ; Bright, Eddie A ; ...

We describe a method for indexing and retrieving high-resolution image regions in large geospatial data libraries. An automated feature extraction method is used that generates a unique and specific structural description of each segment of a tessellated input image file. These tessellated regions are then merged into similar groups and indexed to provide flexible and varied retrieval in a query-by-example environment.
DOI: 10.1007/11595755_66
Affinity-based screening of combinatorial libraries using automated, serial-column chromatography

Journal Article Evans, D.M. ; Williams, K.P. ; McGuinness, B. - Nature Biotechnology

The authors have developed an automated serial chromatographic technique for screening a library of compounds based upon their relative affinity for a target molecule. A {open_quotes}target{close_quotes} column containing the immobilized target molecule is set in tandem with a reversed-phase column. A combinatorial peptide library is injected onto the target column. The target-bound peptides are eluted from the first column and transferred automatically to the reversed-phase column. The target-specific peptide peaks from the reversed-phase column are identified and sequenced. Using a monoclonal antibody (3E-7) against {beta}-endorphin as a target, we selected a single peptide with sequence YGGFL from approximately 5800 peptidesmore »« less
DOI: 10.1038/nbt0496-504
Variability in large-scale wind power generation: Variability in large-scale wind power generation

Journal Article Kiviluoma, Juha ; Holttinen, Hannele ; Weir, David ; ... - Wind Energy

The paper demonstrates the characteristics of wind power variability and net load variability in multiple power systems based on real data from multiple years. Demonstrated characteristics include probability distribution for different ramp durations, seasonal and diurnal variability and low net load events. The comparison shows regions with low variability (Sweden, Spain and Germany), medium variability (Portugal, Ireland, Finland and Denmark) and regions with higher variability (Quebec, Bonneville Power Administration and Electric Reliability Council of Texas in North America; Gansu, Jilin and Liaoning in China; and Norway and offshore wind power in Denmark). For regions with low variability, the maximum 1more »« less
DOI: 10.1002/we.1942
Molecular dynamics-based ion-surface interaction models for ionized physical vapor deposition feature scale simulations

Journal Article Coronell, D.G. ; Hansen, D.E. ; Voter, A.F. ; ... - Applied Physics Letters

A procedure is presented for incorporating the results of atomistic simulations of ion{endash}surface interactions into integrated circuit topographic simulations of ionized physical vapor deposition (PVD). Energy and angular dependent sticking probabilities for energetic Cu atoms impacting a {l_brace}111{r_brace} Cu surface, obtained from molecular dynamics simulations, were implemented in a simple Monte Carlo flux model. The resulting flux-averaged Cu sticking probability was found to vary significantly with position within submicron features and with the feature geometry. This illustrates the shortcomings of a constant (energy and angle independent) sticking probability model for ionized PVD. {copyright} {ital 1998 American Institute of Physics.}
DOI: 10.1063/1.122917
Feature-scale fluid-based erosion modeling for chemical-mechanical polishing

Journal Article Runnels, S.R. - Journal of the Electrochemical Society; (United States)

A physics-based feature-scale erosion model is critical to forming a cohesive understanding of chemical-mechanical polishing because it can link chemical effects modeled on the particle scale to process conditions modeled at the wafer scale. Such a model is described here for polishing processes utilizing a hydrodynamic slurry layer. The stresses induced by the flowing slurry on feature surfaces are computed and used in erosion models that incorporate fracture mechanics and chemistry empirically. Good agreement with experimental erosion profile data is demonstrated and the effect of hydrodynamic layer thickness and feature pattern density on planarization rate is investigated.
DOI: 10.1149/1.2055024

Similar Records