Document Type
Conference Proceeding
Publication Date
10-2014
Abstract
Nuclear explosion yield estimation equations based on a 3D model of the explosion volume will have a lower uncertainty than radius based estimation. To accurately collect data for a volume model of atmospheric explosions requires building a 3D representation from 2D images. The majority of 3D reconstruction algorithms use the SIFT (scale-invariant feature transform) feature detection algorithm which works best on feature-rich objects with continuous angular collections. These assumptions are different from the archive of nuclear explosions that have only 3 points of view. This paper reduces 300 dimensions derived from an image based on Fourier analysis and five edge detection algorithms to a manageable number to detect hotspots that may be used to correlate videos of different viewpoints for 3D reconstruction. Furthermore, experiments test whether histogram equalization improves detection of these features using four kernel sizes passed over these features. Dimension reduction using principal components analysis (PCA), forward subset selection, ReliefF, and FCBF (Fast Correlation-Based Filter) are combined with a Mahalanobis distance classifiers to find the best combination of dimensions, kernel size, and filtering to detect the hotspots. Results indicate that hotspots can be detected with hit rates of 90% and false alarms ¡ 1%.
Source Publication
2014 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)
Recommended Citation
Schmitt, D. T., & Peterson, G. L. (2014). Machine learning nuclear detonation features. 2014 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 1–7. https://doi.org/10.1109/AIPR.2014.7041936
Comments
© 2014 IEEE.Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
AFIT Scholar furnishes the accepted version of this conference paper. The published version of record is available from IEEE via subscription at the DOI link in the citation below.