Hyperspectral Image Target Detection Using Deep Ensembles for Robust Uncertainty Quantification.
Abstract not provided.
SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Abstract not provided.
Spectral target detection refers to the process of searching for a specific material with a known spectrum over a large area containing materials with different spectral signatures. Traditional target detection methods in hyperspectral imagery (HSI) require assuming the data fit some statistical or geometric models and based on the model, to estimate parameters for defining a hypothesis test, where one class (i.e., target class) is chosen over the other classes (i.e., background class). Nonlinear manifold learning methods such as Laplacian eigenmaps (LE) have extensively shown their potential use in HSI processing, specifically in classification or segmentation. Recently, Schroedinger eigenmaps (SE), which is built upon LE, has been introduced as a semisupervised classification method. In SE, the former Laplacian operator is replaced by the Schroedinger operator. The Schroedinger operator includes by definition, a potential term V that steers the transformation in certain directions improving the separability between classes. In this regard, we propose a methodology for target detection that is not based on the traditional schemes and that does not need the estimation of statistical or geometric parameters. This method is based on SE, where the potential term V is taken into consideration to include the prior knowledge about the target class and use it to steer the transformation in directions where the target location in the new space is known and the separability between target and background is augmented. An initial study of how SE can be used in a target detection scheme for HSI is shown here. Inscene pixel and spectral signature detection approaches are presented. Finally, the HSI data used comprise various target panels for testing simultaneous detection of multiple objects with different complexities.
In this work, the Schroedinger eigenmaps (SE) algorithm using spatial and spectral information has been applied to supervised classification of hyperspectral imagery (HSI). We have previously introduced the use of SE in spectral target detection problems. The original SE-based target detector was built on the spectral information encoded in the Laplacian and Schroedinger operators. The original SE-based detector is extended such that spatial connectivity of target-like pixels is explored and encoded into the Schroedinger operator using a “knowledge propagation” scheme. The modified SE-based detector is applied to two HSI data sets that share similar target materials. Receiver operating characteristic curves and rates of detection and false alarm at object level are used as quantitative metrics to assess the detector. In addition, the Schroedinger embedding performance in target detection is compared against the performances of principal component embedding and the Laplacian embedding. Finally, results show that the SE-based detector with spatial–spectral features outperforms the other considered approaches.
A necessary input to planet occurrence calculations is an accurate model for the pipeline completeness (Burke et al., 2015). This document describes the use of the Kepler planet occurrence rate products in order to calculate a per-target detection contour for the measured Data Release 25 (DR25) pipeline performance. A per-target detection contour measures for a given combination of orbital period, Porb, and planet radius, Rp, what fraction of transit signals are recoverable by the Kepler pipeline (Twicken et al., 2016; Jenkins et al., 2017). The steps for calculating a detection contour follow the procedure outlined in Burke et al. (2015), but have been updated to provide improved accuracy enabled by the substantially larger database of transit injection and recovery tests that were performed on the final version (i.e., SOC 9.3) of the Kepler pipeline (Christiansen, 2017; Burke Catanzarite, 2017a). In the following sections, we describe the main inputs to the per-target detection contour and provide a worked example of the python software released with this document (Kepler Planet Occurrence Rate Tools KeplerPORTs)1 that illustrates the generation of a detection contour in practice. As background material for this document and its nomenclature, we recommend the reader be familiar with the previous method of calculating a detection contour (Section 2 of Burke et al.,2015), input parameters relevant for describing the data quantity and quality of Kepler targets (Burke Catanzarite, 2017b), and the extensive new transit injection and recovery tests of the Kepler pipeline (Christiansen et al., 2016; Burke Catanzarite, 2017a; Christiansen, 2017).
Abstract not provided.
Transcranial direct current stimulation (tDCS) is a noninvasive form of brain stimulation that involves passing a weak electrical current between electrodes on the scalp to modulate underlying neural tissue. TDCS has been shown to modulate cognition in a variety of domains, including memory, attention, and visual processing. Prior work from our laboratory has shown positive effects of tDCS on learning to detect target objects hidden in complex naturalistic visual scenes and learn rules for categorizing images, though the mechanism for these benefits remains unknown. One possibility is that tDCS optimizes visual search by modulating visual attention or via the reduction in search errors. One method of quantifying visual attention is to use eye tracking to record search patterns to determine if and how visual search is adjusted under verum stimulation conditions. Eye tracking data allows classification of errors into error types, including sampling errors (failing to look in the relevant region), recognition errors (looking at the critical portion of a scene, but failing to recognize it as such as evidenced by visual fixation), and decision-making errors (fixating on the relevant portion of a scene, but making the wrong determination). Our results indicate that the benefit tDCS confers on visual search for targets stems from the reduction in decision-making errors when targets are present (Cohen’s d = 0.86). Also reported is a replication of previous findings showing a tDCS-dependent improvement in learning this task, learning score (Cohen’s d = 0.88); d’ (Cohen’s d = 1.00). This provides support for moving tDCS into the application space by pairing it with analysts who are concerned with the type of search error that is corrected via stimulation.
Abstract not provided.
This report presents new algorithms for target detection, feature extraction, and image formation with the synthetic aperture radar (SAR) technology. For target detection, we consider target detection with SAR and coherent subtraction. We also study how the image false alarm rates are related to the target template false alarm rates when target templates are used for target detection. For feature extraction from SAR images, we present a computationally efficient eigenstructure-based 2D-MODE algorithm for two-dimensional frequency estimation. For SAR image formation, we present a robust parametric data model for estimating high resolution range signatures of radar targets and for forming high resolution SAR images.
Not Available
Not Available
Target detection is one fundamental problem in many sensor network-based applications, which is typically tackled in two separate stages for sensor deployment and data fusion. We propose an integrated solution, referred to as 2C-SSEM,which combines 2-level clustering-based sensor deployment and source strength estimate map-based data fusion for the detection of a single static or moving target. 2C-SSEM conducts the first level of clustering to determine a sensor deployment scheme and the second level of clustering to divide the deployed sensors into several subsets. For each sensor, the source strength is estimated at each grid point of the entire region based on a signal attenuation model, and for each subset of sensors, the target location is estimated using a distribution map-based statistical analysis method. A final detection decision is made by thresholding the clustering degree of the target location estimates computed by all subsets of sensors. Compared with traditional grid-based target detection methods, 2C-SSEM significantly reduces the computation complexity and improves the detection performance through an integrated optimization strategy. Extensive simulation results show the performance superiority of the proposed solution over several well-known methods for target detection.
Overwhelming non-target detections require more representative hypothesis test to target real events. Implicit signal model with convex-cone geometry includes both target waveforms and non-targets. New detector screens target waveforms from convex cone members that correlation detectors return. Proto-type detector returns analyst-equivalent detections, requires minimal modification from correlation detector, and has quantifiable detection performance, and satisfies all solution requirements to reduce false detections for GNDD.
The utility of hyperspectral imaging (HSI) has been well established for a wide array of applications but has generated a need for automated screening of high volumes of large HSI cubes. We report two important automated algorithms for more efficient standoff processing: atmospheric correction and target detection. The atmospheric correction method is based on a fast asymmetric least squares approach that is applied on a pixel-by-pixel basis. Here, the correction can be applied to entire images without manually identifying regions of interest and utilizes only in-scene information, no ancillary modeling of the atmosphere is required. An iterative target detection approach is also introduced which demonstrates faster speeds relative to moving window approaches. The target detection algorithm classifies each pixel as true target detections, near target detections, clutter, and no-calls. The algorithms were tested on forty images of twenty-two solid mineral targets placed at a 14-meter standoff distance allowing general observations on expected detection performance for a variety of minerals. In addition to identifying anomalous pixels, the inclusion of “no-calls” reduced the number of false detections significantly.
Most existing video-based target detection systems employ state-space models to keep track of an explicit number of individual targets. We introduce a framework for enhancing target detection in video by applying probabilistic models to the soft information in correlation outputs before thresholding. We show how to efficiently compute arrays of posterior target probabilities for every position in the scene conditioned on all current and past frames of a video sequence. These arrays can then be thresholded in the typical manner to yield more reliable target detections. Because the framework avoids the formation of explicit tracks, it is well suited for handling scenes with unknown numbers of targets at unknown positions. Simulation results on forward-looking infrared (FLIR) video sequences show that our proposed framework can significantly reduce the false-alarm rate of a bank of correlation filters while requiring only a marginal increase in computation.
Quantum illumination (QI) provides entanglement-enabled target-detection enhancement, despite operating in an entanglement-breaking environment. Existing experimental studies of QI have utilized a Bayesian approach, assuming that the target is equally likely to be present or absent before detection, to demonstrate an advantage over classical target detection. However, such a premise breaks down in practical operational scenarios in which the prior probability is unknown, thereby hindering QI's applicability to real-world target-detection scenarios. In this work, we adopt the Neyman-Pearson criterion in lieu of the error probability for equally likely target absence or presence as our figure of merit for QI. We demonstrate an unconditional quantum advantage over the optimal classical-illumination protocol as benchmarked by the receiver operating characteristic, which examines detection probability versus false-alarm probability without resorting to known prior probabilities. Our work represents a critical advancement in adapting quantum-enhanced sensing to practical operational settings.
Imagery collected from satellites and airborne platforms provides an important tool for remotely analyzing the content of a scene. In particular, the ability to remotely detect a specific material within a scene is of critical importance in nonproliferation and other applications. The sensor systems that process hyperspectral images collect the high-dimensional spectral information necessary to perform these detection analyses. For a d-dimensional hyperspectral image, however, where d is the number of spectral bands, it is common for the data to inherently occupy an m-dimensional space with m << d. In the remote sensing community, this has led to recent interest in the use of manifold learning, which seeks to characterize the embedded lower-dimensional, nonlinear manifold that the data discretely approximate. The research presented in this paper focuses on a graph theory and manifold learning approach to target detection, using an adaptive version of locally linear embedding that is biased to separate target pixels from background pixels. Finally, this approach incorporates multiple target signatures for a particular material, accounting for the spectral variability that is often present within a solid material of interest.
Multispectral imaging can offer many benefits in cost, complexity, resolution, size, weight, and power, relative to hyperspectral imaging. When designing a multispectral system, spectral bandpasses can be selected using optimization algorithms configured to maximally separate target detection scores between target and background regions. A hyperspectral image (HSI) can serve as the source of data from which band groupings can be tested for optimality. The output of an adaptive cosine estimator target detection algorithm is used in an objective function. Three optimization algorithms are compared: particle swarm, dual annealing, and differential evolution. A global optimum is also found using a brute force approach on the Livermore Computing Syrah supercomputer. Three materials are investigated: calcite, gypsum, and limestone. This is done for 3-, 4-, and 5-band systems. The data originate from a longwave infrared HSI of a material display board. The optimization algorithms were run 30 times for every scenario. Performance statistics (maximum, minimum, mean, standard deviation, and median) based on the separation values are given. Additional characterization was performed using receiver operator characteristic (ROC) curves and the area under the ROC curve. While good performance was obtained for the three optimization algorithms, the dual annealing algorithm produced the highest and most consistent detection separation scores on average.
We propose to design a peak-to-average power ratio (PAPR) constrained transmit waveform that achieves the optimal performance (following the Neyman Pearson lemma) in detecting a target in the presence of signal-dependent interference. The direct time-domain approach allows straightforward characterizations of the correlation and PAPR properties of the designed signals, which are critically important to analyze the system performance in the presence of multiple targets and to assess the transmitter power-utilization, respectively. Therefore, instead of designing a transmit signal only for the optimal detection performance, we solve a biobjective Pareto-optimization problem, subjecting to the PAPR and total energy constraints, in order to simultaneously optimize the detection and cross-correlation performances. With extensive numerical examples, we demonstrate that PAPR-constrained signals produce nearly optimum detection performance even with a strict PAPR requirement, and also highlight the conflicting behavior of the detection and correlation performances.