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

Title: Rapid Damage eXplorer (RDX): A Probabilistic Framework for Learning Changes From Bitemporal Images

Abstract

Recent decade has witnessed major changes on the Earth, for example, deforestation, varying cropping and human settlement patterns, and crippling damages due to disasters. Accurate damage assessment caused by major natural and anthropogenic disasters is becoming critical due to increases in human and economic loss. This increase in loss of life and severe damages can be attributed to the growing population, as well as human migration to the disaster prone regions of the world. Rapid assessment of these changes and dissemination of accurate information is critical for creating an effective emergency response. Change detection using high-resolution satellite images is a primary tool in assessing damages, monitoring biomass and critical infrastructures, and identifying new settlements. In this demo, we present a novel supervised probabilistic framework for identifying changes using very high-resolution multispectral, and bitemporal remote sensing images. Our demo shows that the rapid damage explorer (RDX) system is resilient to registration errors and differing sensor characteristics.

Authors:
 [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
Work for Others (WFO)
OSTI Identifier:
1067298
DOE Contract Number:
DE-AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: IEEE International Conference on Data Mining, Brussels, Belgium, 20121210, 20121210
Country of Publication:
United States
Language:
English
Subject:
Change detection; gaussian grids; probabilistic distance

Citation Formats

Vatsavai, Raju. Rapid Damage eXplorer (RDX): A Probabilistic Framework for Learning Changes From Bitemporal Images. United States: N. p., 2012. Web.
Vatsavai, Raju. Rapid Damage eXplorer (RDX): A Probabilistic Framework for Learning Changes From Bitemporal Images. United States.
Vatsavai, Raju. 2012. "Rapid Damage eXplorer (RDX): A Probabilistic Framework for Learning Changes From Bitemporal Images". United States. doi:.
@article{osti_1067298,
title = {Rapid Damage eXplorer (RDX): A Probabilistic Framework for Learning Changes From Bitemporal Images},
author = {Vatsavai, Raju},
abstractNote = {Recent decade has witnessed major changes on the Earth, for example, deforestation, varying cropping and human settlement patterns, and crippling damages due to disasters. Accurate damage assessment caused by major natural and anthropogenic disasters is becoming critical due to increases in human and economic loss. This increase in loss of life and severe damages can be attributed to the growing population, as well as human migration to the disaster prone regions of the world. Rapid assessment of these changes and dissemination of accurate information is critical for creating an effective emergency response. Change detection using high-resolution satellite images is a primary tool in assessing damages, monitoring biomass and critical infrastructures, and identifying new settlements. In this demo, we present a novel supervised probabilistic framework for identifying changes using very high-resolution multispectral, and bitemporal remote sensing images. Our demo shows that the rapid damage explorer (RDX) system is resilient to registration errors and differing sensor characteristics.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2012,
month = 1
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • Several series of auroral and geocoronal images from th Dynamics Explorer Mission are presented and analyzed. It is found that the motion of the transpolar arc of a theta aurora is correlated with the y-component of the IMF; the arc motion is in the general direction of the y-component. In addition, a sequence of global images of a small auroral substorm shows the initial development of intense luminosities in a relatively small spatial region or bright spot in the premidnight sector of the auroral oval and a subsequent appearance of an expanding area of lesser intensities at low latitudes andmore » contiguous to the midnight boundary of the bright spot. Finally, a series of images of the geocorona in scattered solar Ly-alpha emissions is used to obtain a best-fit spherical model of atomic hydrogen densities in the earth's exosphere; a Chamberlain model provides an adequate fit to radial distances of 4.5 earth-radii, beyond which an exponential fit is used. The geocoronal tail is detected as an asymmetric increase in scattered Ly-alpha intensities in the antisolar direction. 24 references.« less
  • Traditional content-based image retrieval methods based on learning from examples analyze and attempt to understand high-level semantics of an image as a whole. They typically apply certain case-based reasoning technique to interpret and retrieve images through measuring the semantic similarity or relatedness between example images and search candidate images. The drawback of such a traditional content-based image retrieval paradigm is that the summation of imagery contents in an image tends to lead to tremendous variation from image to image. Hence, semantically related images may only exhibit a small pocket of common elements, if at all. Such variability in image visualmore » composition poses great challenges to content-based image retrieval methods that operate at the granularity of entire images. In this study, we explore a new content-based image retrieval algorithm that mines visual patterns of finer granularities inside a whole image to identify visual instances which can more reliably and generically represent a given search concept. We performed preliminary experiments to validate our new idea for content-based image retrieval and obtained very encouraging results.« less
  • The authors have developed a method for the rapid pixel-by-pixel estimation of glucose metabolic rate from a dynamic sequence of PCT images acquired over 40 minutes following venous bolus injection of 2-deoxy-2-fluoro-D-glucose (2-FDG). The calculations are based on the conventional four parameter model. The dephosphorylation rate (k/sub 4/) cannot be reliably estimated from only 40 minutes of data; however, neglecting dephosphorylation can nonetheless introduce significant biases into the parameter estimation processes. In the authors' method, the rate is constrained to fall within a small range about a presumed value. Computer simulation studies show that this constraint greatly reduces the systematicmore » biases in the other three fitted parameters and in the metabolic rate that arise from the assumption of no dephosphorylation. The parameter estimation scheme used is formally identical to one originally developed for dynamic methods of cerebral blood flow estimation. Estimation of metabolic rate and the individual model rate parameters k/sub 1/, k/sub 2/, and k/sub 3/, can be carried out for each pixel sequence of a 100 x 100 pixel image in less than two minutes on our PDP 11/60 minicomputer with floating point processor. While the maps of k/sub 2/ amd k/sub 3/ are quite noisy, accurate estimates of average values can be attained for regions of a few cm/sup 2/. The maps of metabolic rate offer many advantages in addition to that of direct visualization. These include improved statistical precision and the avoidance of averaging failure in the fitting of heterogeneous regions.« less
  • Interest in producing high damage threshold KH{sub 2}PO{sub 4} (KDP) and (D{sub x}H{sub 1-x}){sub 2}PO{sub 4} (KD*P, DKDP) for optical switching and frequency conversion applications is being driven by the system requirements for the National Ignition Facility (NIF) at Lawrence Livermore National Lab (LLNL). Historically, the path to achieving higher damage thresholds has been to improve the purity of crystal growth solutions. Application of advanced filtration technology has increased the damage threshold, but gives little insight into the actual mechanisms of laser damage. We have developed a laser scatter diagnostic to better study bulk defects and laser damage mechanisms inmore » KDP and KD*P crystals. This diagnostic consists of a cavity doubled, kilohertz class, Nd:YLF laser (527 nm) and high dynamic range CCD camera which allows imaging of bulk scatter signals. With it, we have performed damage tests at 355 nm on four different {open_quotes}vintages{close_quotes} of KDP crystals, concentrating on crystals produced via fast growth methods. We compare the diagnostic`s resolution to LLNL`s standard damage detection method of 100X darkfield microscopy and discuss its impact on damage threshold determination. We have observed the disappearance of scatter sites upon exposure to subthreshold irradiation. In contrast, we have seen scatterers appear where none previously existed. This includes isolated, large (high signal) sites as well as multiple small scatter sites which appear at fluences above 7 J/cm{sup 2} (fine tracking). However, we have not observed a strong correlation of preexisting scatter sites and laser damage sites. We speculate on the connection between the laser-induced disappearance of scatter sites and the observed increase in damage threshold with laser conditioning.« less
  • Interest in producing high damage threshold KH{sub 2}PO{sub 4} (KDP) and (D{sub x}H{sub 1{minus}x}){sub 2}PO{sub 4} (KDP*, DKDP) for optical switching and frequency conversion applications is being driven by the system requirements for the National Ignition Facility (NIF) at Lawrence Livermore National Lab (LLNL). Historically, the path to achieving higher damage thresholds has been to improve the purity of crystal growth solutions. Application of advanced filtration technology has increased the damage threshold, but gives little insight into the actual mechanisms of laser damage. The authors have developed a laser scatter diagnostic to better study bulk defects and laser damage mechanismsmore » in KDP and KD*P crystals. This diagnostic consists of a cavity doubled, kilohertz class, Nd:YLF laser (527 nm) and high dynamic range CCD camera which allows imaging of bulk scatter signals. With it, they have performed damage tests at 355 nm on four different {open_quotes}vintages{close_quotes} of KDP crystals, concentrating on crystals produced via fast growth methods. The authors compare the diagnostic`s resolution to LLNL`s standard damage detection method of 100X darkfield microscopy and discuss its impact on damage threshold determination. They have observed the disappearance of scatter sites upon exposure to subthreshold irradiation. In contrast, they have seen scatterers appear where none previously existed. This includes isolated, large (high signal) sites as well as multiple small scatter sites which appear at fluences above 7 J/cm{sup 2} (fine tracking). However, they have not observed a strong correlation of preexisting scatter sites and laser damage sites. The authors speculate on the connection between the laser-induced disappearance of scatter sites and the observed increase in damage threshold with laser conditioning.« less