Publications

Abstract not provided.

We present a deep learning image reconstruction method called AirNet-SNL for sparse view computed tomography. It combines iterative reconstruction and convolutional neural networks with end-to-end training. Our model reduces streak artifacts from filtered back-projection with limited data, and it trains on randomly generated shapes. This work shows promise to generalize learning image reconstruction.

Abstract not provided.

Abstract not provided.

We propose a technique for reconstruction from incomplete compressive measurements. Our approach combines compressive sensing and matrix completion using the consensus equilibrium framework. Consensus equilibrium breaks the reconstruction problem into subproblems to solve for the high-dimensional tensor. This framework allows us to apply two constraints on the statistical inversion problem. First, matrix completion enforces a low rank constraint on the compressed data. Second, the compressed tensor should be consistent with the uncompressed tensor when it is projected onto the low-dimensional subspace. We validate our method on the Indian Pines hyperspectral dataset with varying amounts of missing data. This work opens up new possibilities for data reduction, compression, and reconstruction.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

We investigate deep neural networks to reconstruct and classify hyperspectral images from compressive sensing measurements. Hyperspectral sensors provide detailed spectral information to differentiate materials. However, traditional imagers require scanning to acquire spatial and spectral information, which increases collection time. Compressive sensing is a technique to encode signals into fewer measurements. It can speed acquisition time, but the reconstruction can be computationally intensive. First we describe multilayer perceptrons to reconstruct compressive hyperspectral images. Then we compare two different inputs to machine learning classifiers: compressive sensing measurements and the reconstructed hyperspectral image. The classifiers include support vector machines, K nearest neighbors, and three neural networks (3D convolutional neural networks and recurrent neural networks). The results show that deep neural networks can speed up the time for the acquisition, reconstruction, and classification of compressive hyperspectral images.

This paper will present an overview of compressive sensing for channeled polarimetry. We frame the reconstruction of the Stokes parameters as an underdetermined problem, where we solve for 3N unknowns from N measurements. We discuss two types of polarimeters: channeled spectropolarimeters and channeled linear imaging polarimeters. The polarimeters may differ in a few aspects: the output may be signals or images, the optical elements may vary, and the dimensions may be spatial or spectral. Our algorithms work with existing polarimeters and require no change in optical elements or measurement procedure. The purpose of this work is to present this framework and describe how it applies across different types of polarimeters. Both simulations and experiments show that our algorithms produce more accurate reconstructions with less artifacts than frequency domain filtering

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Hyperspectral and multispectral imagers have been developed and deployed on satellite and manned aerial platforms for decades and have been used to produce spectrally resolved reflectance and other radiometric products. Similarly, light detection and ranging, or LIDAR, systems are regularly deployed from manned aerial platforms to produce a variety of products, including digital elevation models. While both types of systems have demonstrated impressive capabilities from these conventional platforms, for some applications it is desirable to have higher spatial resolution and more deployment flexibility than satellite or manned aerial platforms can offer. Commercially available unmanned aerial systems, or UAS, have recently emerged as an alternative platform for deploying optical imaging and detection systems, including spectral imagers and high resolution cameras. By enabling deployments in rugged terrain, collections at low altitudes, and flight durations of several hours, UAS offer the opportunity to obtain high spatial resolution products over multiple square kilometers in remote locations. Taking advantage of this emerging capability, our team recently deployed a commercial UAS to collect hyperspectral imagery, RGB imagery, and photogrammetry products at a legacy underground nuclear explosion test site and its surrounds. Ground based point spectrometer data collected over the same area serves as ground truth for the airborne results. The collected data is being used to map the site and evaluate the utility of optical remote sensing techniques for measuring signatures of interest, such as the mineralogy, anthropogenic objects, and vegetative health. This work will overview our test campaign, our results to date, and our plans for future work.

Compressive sensing shows promise for sensors that collect fewer samples than required by traditional Shannon-Nyquist sampling theory. Recent sensor designs for hyperspectral imaging encode light using spectral modulators such as spatial light modulators, liquid crystal phase retarders, and Fabry-Perot resonators. The hyperspectral imager consists of a filter array followed by a detector array. It encodes spectra with less measurements than the number of bands in the signal, making reconstruction an underdetermined problem. We propose a reconstruction algorithm for hyperspectral images encoded through spectral modulators. Our approach constrains pixels to be similar to their neighbors in space and wavelength, as natural images tend to vary smoothly, and it increases robustness to noise. It combines L1 minimization in the wavelet domain to enforce sparsity and total variation in the image domain for smoothness. The alternating direction method of multipliers (ADMM) simplifies the optimization procedure. Our algorithm constrains encoded, compressed hyperspectral images to be smooth in their reconstruction, and we present simulation results to illustrate our technique. This work improves the reconstruction of hyperspectral images from encoded, multiplexed, and sparse measurements.

Channeled spectropolarimetry measures the spectrally resolved Stokes parameters. A key aspect of this technique is to accurately reconstruct the Stokes parameters from a modulated measurement of the channeled spectropolarimeter. The state-of-the-art reconstruction algorithm uses the Fourier transform to extract the Stokes parameters from channels in the Fourier domain. While this approach is straightforward, it can be sensitive to noise and channel cross-talk, and it imposes bandwidth limitations that cut o high frequency details. To overcome these drawbacks, we present a reconstruction method called compressed channeled spectropolarimetry. In our proposed framework, reconstruction in channeled spectropolarimetry is an underdetermined problem, where we take N measurements and solve for 3N unknown Stokes parameters. We formulate an optimization problem by creating a mathematical model of the channeled spectropolarimeter with inspiration from compressed sensing. We show that our approach o ers greater noise robustness and reconstruction accuracy compared with the Fourier transform technique in simulations and experimental measurements. By demonstrating more accurate reconstructions, we push performance to the native resolution of the sensor, allowing more information to be recovered from a single measurement of a channeled spectropolarimeter.

Abstract not provided.

Abstract not provided.

Channeled linear imaging polarimeters measure the two-dimensional distribution of the linear Stokes parameters. A key aspect of this technique is to accurately reconstruct the Stokes parameters from a snapshot, modulated measurement of the channeled linear imaging polarimeter. The state-of-The-Art reconstruction takes the Fourier transform of the measurement to separate the Stokes parameters into channels. While straightforward, this approach is sensitive to channel cross-Talk and imposes bandwidth limitations that cut off high frequency details. To overcome these drawbacks, we present a reconstruction method called compressed channeled linear imaging polarimetry. In this framework, reconstruction in channeled linear imaging polarimetry is an underdetermined problem, where we measure N pixels and recover 3N Stokes parameters. We formulate an optimization problem by creating a mathematical model of the channeled linear imaging polarimeter with inspiration from compressed sensing. Through simulations, we show that our approach mitigates artifacts seen in Fourier reconstruction, including image blurring and degradation and ringing artifacts caused by windowing and channel cross-Talk. By demonstrating more accurate reconstructions, we push performance to the native resolution of the sensor, allowing more information to be recovered from a single measurement of a channeled linear imaging polarimeter.

Abstract not provided.