Dr. Michael D. DeVore Profile

Dr. Michael D. DeVore

Senior Research Scientist at Barron Associates Inc

SPIE Involvement:

Author

Publications (13)

Proceedings Article | 13 May 2010 Paper

Polynomial chaos theory for performance evaluation of ATR systems

Michael DeVore, Alec Bateman

Proceedings Volume 7696, 76960R (2010) https://doi.org/10.1117/12.853747

KEYWORDS: Automatic target recognition, Sensors, Probability theory, Detection and tracking algorithms, Filtering (signal processing), Chaos, Error analysis, Chaos theory, Complex systems, Systems modeling

Read Abstract +

Proceedings Article | 13 May 2010 Paper

A probability of error-constrained sequential decision algorithm for data-rich automatic target recognition

Irwin Reyes, Michael DeVore, Peter Beling, Barry Horowitz

Proceedings Volume 7696, 769615 (2010) https://doi.org/10.1117/12.858293

KEYWORDS: Detection and tracking algorithms, Data processing, Target recognition, Data modeling, Automatic target recognition, Clouds, Sensors, LIDAR, 3D modeling, 3D metrology

Read Abstract +

Proceedings Article | 7 May 2007 Paper

Statistical models for target detection in infrared imagery

Samuel Huddleston, Xin Zhou, William Evans, Alice Chan, Michael DeVore

Proceedings Volume 6566, 65661A (2007) https://doi.org/10.1117/12.747148

KEYWORDS: Target detection, Data modeling, Statistical analysis, Infrared imaging, Infrared radiation, Infrared detectors, Automatic target recognition, Algorithm development, Long wavelength infrared, Process modeling

Read Abstract +

Proceedings Article | 18 May 2006 Paper

Minimum probability of error recognition of three-dimensional laser-scanned targets

Michael DeVore, Xin Zhou

Proceedings Volume 6234, 623407 (2006) https://doi.org/10.1117/12.668685

KEYWORDS: Data modeling, Imaging systems, 3D metrology, Detection and tracking algorithms, 3D acquisition, LIDAR, 3D modeling, Target recognition, Radar imaging, Object recognition

Read Abstract +

SPIE Journal Paper | 1 December 2005

Shape recognition from three-dimensional point measurements with range and direction uncertainty

Xin Zhou, Michael DeVore

OE, Vol. 44, Issue 12, 127202, (December 2005) https://doi.org/10.1117/12.10.1117/1.2138067

KEYWORDS: Optical spheres, Detection and tracking algorithms, Error analysis, 3D modeling, Optical engineering, Algorithm development, Data modeling, Monte Carlo methods, Shape analysis, LIDAR

Read Abstract +

Proceedings Article | 2 September 2004 Paper

Analytical performance evaluation of SAR ATR with inaccurate or estimated models

Michael DeVore

Proceedings Volume 5427, (2004) https://doi.org/10.1117/12.548352

KEYWORDS: Error analysis, Statistical analysis, Automatic target recognition, Synthetic aperture radar, Systems modeling, Performance modeling, Radar, Solids, Target recognition, Monte Carlo methods

Read Abstract +

Proceedings Article | 12 September 2003 Paper

Azimuth correlation models for radar imaging

Michael DeVore, Joseph O'Sullivan, Lee Montagnino

Proceedings Volume 5095, (2003) https://doi.org/10.1117/12.488642

KEYWORDS: Reflectivity, Data modeling, Radar, Synthetic aperture radar, Expectation maximization algorithms, Detection and tracking algorithms, Image processing, Data processing, Target recognition, Statistical analysis

Read Abstract +

Proceedings Article | 1 August 2002 Paper

Conditionally gamma- and k-distribution models for SAR ATR

Michael DeVore, Joseph O'Sullivan, Lee Montagnino

Proceedings Volume 4727, (2002) https://doi.org/10.1117/12.478690

KEYWORDS: Data modeling, Synthetic aperture radar, Statistical modeling, Automatic target recognition, Statistical analysis, Algorithm development, Expectation maximization algorithms, Radar, Model-based design, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 22 October 2001 Paper

Relationships between computational system performance and recognition system performance

Michael DeVore, Joseph O'Sullivan, Roger Chamberlain, Mark Franklin

Proceedings Volume 4379, (2001) https://doi.org/10.1117/12.445384

KEYWORDS: Image processing, Synthetic aperture radar, Computing systems, Data modeling, Automatic target recognition, Telecommunications, Performance modeling, Radar, Microelectromechanical systems, Target recognition

Read Abstract +

Proceedings Article | 27 August 2001 Paper

Statistical assessment of model fit for synthetic aperture radar data

Michael DeVore, Joseph O'Sullivan

Proceedings Volume 4382, (2001) https://doi.org/10.1117/12.438231

KEYWORDS: Data modeling, Synthetic aperture radar, Statistical modeling, Statistical analysis, Performance modeling, Data acquisition, Algorithm development, Radar, Sensors, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 27 August 2001 Paper

Probabilistic approach to model extraction from training data

Michael DeVore, Joseph O'Sullivan, Sushil Anand, Natalia Schmid

Proceedings Volume 4382, (2001) https://doi.org/10.1117/12.438229

KEYWORDS: Data modeling, Automatic target recognition, Target recognition, Model-based design, Statistical modeling, Synthetic aperture radar, Radar, Solid modeling, Image segmentation, Systems modeling

Read Abstract +

Many of the approaches to automatic target recognition (ATR) for synthetic aperture radar (SAR) images that have been proposed in the literature fall into one of two broad classes, those based on prediction of images from models (CAD or otherwise) of the targets and those based on templates describing typical received images which are often estimated from sample data. Systems utilizing model-based prediction typically synthesize an expected SAR image given some target class and pose and then search for the combination of class and pose which maximizes some match metric between the synthesized and observed images. This approach has the advantage of being robust with respect to target pose and articulation not previously encountered but does require detailed models of the targets of interest. On the other hand, template-based systems typically do not require detailed target models but instead store expected images for a range of targets and poses based on previous observations (training data) and then search for the template which most closely represents the observed image. We consider the design and use of probabilistic models for targets developed from training data which do not require CAD models of the targets but which can be used in a hypothesize-and-predict manner similar to other model-based approaches. The construction of such models requires the extraction from training data of functions which characterize the target radar cross section in terms of target class, pose, articulation, and other sources of variability. We demonstrate this approach using a conditionally Gaussian model for SAR image data and under that model develop the tools required to determine target models and to use those models to solve inference problems from an image of an unknown target. The conditionally Gaussian model is applied in a target-centered reference frame resulting in a probabilistic model on the surface of the target. The model is segmented based on the information content in regions of the target space. Modeling radar power variability and target positional uncertainty results in improved accuracy. Performance results are presented for both target classification and orientation estimation using the publicly available MSTAR dataset.

Proceedings Article | 24 August 2000 Paper

Performance-complexity tradeoffs for several approaches to ATR from SAR images

Joseph O'Sullivan, Michael DeVore

Proceedings Volume 4053, (2000) https://doi.org/10.1117/12.396370

KEYWORDS: Synthetic aperture radar, Detection and tracking algorithms, Databases, Automatic target recognition, Error analysis, Data modeling, Performance modeling, Image classification, Target recognition, Radar

Read Abstract +

Proceedings Article | 17 August 2000 Paper

ATR performance of a Rician model for SAR images

Michael DeVore, Aaron Lanterman, Joseph O'Sullivan

Proceedings Volume 4050, (2000) https://doi.org/10.1117/12.395589

KEYWORDS: Synthetic aperture radar, Data modeling, Detection and tracking algorithms, Performance modeling, Automatic target recognition, Error analysis, Expectation maximization algorithms, Databases, Target recognition, System on a chip

Read Abstract +

Showing 5 of 13 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years