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

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

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:
 [1];  [1];  [1];  [2];  [1];  [1];  [1];  [1]
  1. ORNL
  2. Oak Ridge National Laboratory (ORNL)
Publication Date:
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.
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.
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.
@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}
}
  • 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.
  • 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 » present in a combinatorial library. We demonstrated the applicability of the technology towards selection of peptides with predetermined affinity for bacterial lipopolysaccharide (LPS, endotoxin). We expect that this technology will have broad applications for high throughput screening of chemical libraries or natural product extracts. 21 refs., 4 figs.« less
  • Purpose: The availability of corresponding landmarks in IGRT image series allows quantifying the inter and intrafractional motion of internal organs. In this study, an approach for the automatic localization of anatomical landmarks is presented, with the aim of describing the nonrigid motion of anatomo-pathological structures in radiotherapy treatments according to local image contrast.Methods: An adaptive scale invariant feature transform (SIFT) was developed from the integration of a standard 3D SIFT approach with a local image-based contrast definition. The robustness and invariance of the proposed method to shape-preserving and deformable transforms were analyzed in a CT phantom study. The application ofmore » contrast transforms to the phantom images was also tested, in order to verify the variation of the local adaptive measure in relation to the modification of image contrast. The method was also applied to a lung 4D CT dataset, relying on manual feature identification by an expert user as ground truth. The 3D residual distance between matches obtained in adaptive-SIFT was then computed to verify the internal motion quantification with respect to the expert user. Extracted corresponding features in the lungs were used as regularization landmarks in a multistage deformable image registration (DIR) mapping the inhale vs exhale phase. The residual distances between the warped manual landmarks and their reference position in the inhale phase were evaluated, in order to provide a quantitative indication of the registration performed with the three different point sets.Results: The phantom study confirmed the method invariance and robustness properties to shape-preserving and deformable transforms, showing residual matching errors below the voxel dimension. The adapted SIFT algorithm on the 4D CT dataset provided automated and accurate motion detection of peak to peak breathing motion. The proposed method resulted in reduced residual errors with respect to standard SIFT, providing a motion description comparable to expert manual identification, as confirmed by DIR.Conclusions: The application of the method to a 4D lung CT patient dataset demonstrated adaptive-SIFT potential as an automatic tool to detect landmarks for DIR regularization and internal motion quantification. Future works should include the optimization of the computational cost and the application of the method to other anatomical sites and image modalities.« less