Campuses:

Matched-pair machine learning for hyperspectral target detection

Thursday, October 25, 2018 - 3:05pm - 3:55pm
Keller 3-180
Amanda Ziemann (Los Alamos National Laboratory)
Many materials that are of civilian and military interest are difficult to distinguish using traditional cameras, as those cameras are designed to recreate what we see visually. These materials, however, often possess rich information in narrow visible and non-visible channels of the electromagnetic spectrum, which can be captured by hyperspectral cameras. When deployed on airborne or spaceborne platforms, the high spectral resolution of hyperspectral imagery enables remote discrimination of these materials. In the target detection regime, we exploit this spectral resolution for the detection of image pixels that are likely to contain the target material. Traditional hyperspectral target detection algorithms begin with specific models of the target, of the background, and of the interaction between the two. While closed-form solutions are desirable, more sophisticated (and physically-realistic) models often lead to detectors that are not analytically tractable. Here, we investigate the development of a broader machine learning framework for target detection that enables us to use more sophisticated physicsbased and data-driven models to produce detection algorithms that are not confined to simplistic assumptions. In this, matched pairs of data samples are created: for each pixel in the original hyperspectral image, a corresponding pixel is generated by implanting the target into the original pixel. These matched pairs are used as training data for a machine learning algorithm to classify pixels as either non-target or target. Here we use a support vector machine, but the matched pair machine learning (MPML) framework does not restrict the choice of classifier type. Detectors using both approaches are applied both to simulated data (with Gaussian and with multivariate fit distributed backgrounds) and to real hyperspectral data with known, referenced targets.