Michael Pieper

Detection Algorithms in Hyperspectral Imaging Systems: An Overview of Practical Algorithms

Hyperspectral imaging applications are many and span civil, environmental, and military needs. Typical examples include the detection of specific terrain features and vegetation, mineral, or soil types for resource management; detecting and characterizing materials, surfaces, or paints; the detection of man-made materials in natural backgrounds for the purpose of search and rescue; the detection of specific plant species for the purposes of counter narcotics; and the detection of military vehicles for the purpose of defense and intelligence. The objective of this article is to provide a tutorial overview of detection algorithms used in current hyperspectral imaging systems that operate in the reflective part of the spectrum (0.4 - 24 μm.) The same algorithms might be used in the long-wave infrared spectrum; however, the phenomenology is quite different. The covered topics and the presentation style have been chosen to illustrate the strong couplings among the underlying phenomenology, the theoretical framework for algorithm development and analysis, and the requirements of practical applications.

The remarkable success of adaptive cosine estimator in hyperspectral target detection

A challenging problem of major importance in hyperspectral imaging applications is the detection of subpixel targets of military and civilian interest. The background clutter surrounding the target, acts as an interference source that simultaneously distorts the target spectrum and reduces its strength. Two additional limiting factors are the spectral variability of the background clutter and the spectral variability of the target. Since a result in applied statistics is only as reliable as the assumptions from which it is derived, it is important to investigate whether the basic assumptions used for the derivation of matched filter and adaptive cosine estimator algorithms are a reasonable description of the physical situation. Careful examination of the linear signal model used to derive these algorithms and the replacement signal model, which is a more realistic model for subpixel targets, reveals a serious discrepancy between modeling assumptions and the physical world. Despite this discrepancy and additional mismatches between assumed and actual signal and clutter models, the adaptive cosine estimator shows an amazing effectiveness in practical target detection applications. The objective of this paper is an attempt to explain this unbelievable effectiveness using a combination of classical statistical detection theory, geometrical interpretations, and a novel realistic performance prediction model for the adaptive cosine estimator.

Neural Network Estimation of Atmospheric Profiles Using AIRS/IASI/AMSU Data in the Presence of Clouds

A novel statistical method for the retrieval of atmospheric temperature and water vapor profiles has been developed and evaluated with sounding data from the Atmospheric InfraRed Sounder (AIRS) and the Advanced Microwave Sounding Unit (AMSU) on the NASA Aqua satellite and the Infrared Atmospheric Sounding Interferometer (IASI) and AMSU on the EUMETSAT MetOp-A satellite. The present work focuses on the cloud impact on the AIRS and IASI radiances and explores the use of the stochastic cloud clearing methodology together with neural network estimation. A stand-alone statistical algorithm will be presented that operates directly on cloud-impacted AIRS/AMSU and IASI/AMSU data, with no need for a physical cloud clearing process. The performance of this method was evaluated using global (ascending and descending) EOS-Aqua orbits collocated with ECMWF fields for a variety of days throughout 2003, 2004, 2005, and 2006. Over 1,000,000 fields of regard (3×3 arrays of footprints) over ocean and land were used in the study. The method requires significantly less computation than traditional variational retrieval methods, while achieving comparable performance. Retrieval accuracy will be evaluated using ECMWF atmospheric fields as ground truth. The accuracy of the neural network retrieval method will be compared to the accuracy of the AIRS Level 2 (Version 5) retrieval method.

Hyperspectral detection and discrimination using the ACE algorithm

One of the fundamental challenges for a hyperspectral imaging system is the detection and discrimination of subpixel objects in background clutter. The background surrounding the object, which acts as interference, provides the major obstacle to successful detection and discrimination. In many applications we look for a single signature and discrimination among different signatures is not required. However, there are important applications where we are interested for multiple signatures. In these cases, the use of spectral discrimination algorithms is both necessary and valuable. In this paper, we develop an approach to spectral discrimination based on the adaptive cosine estimation (ACE) algorithm. The basic idea is to jointly exploit the detection statistics from the various signatures and set a common threshold that ensures larger separation between signatures of interest and background. The operation of the proposed detection-discrimination approach is illustrated using real-world hyperspectral imaging data.

Performance Prediction of Matched Filter and Adaptive Cosine Estimator Hyperspectral Target Detectors

Many applications of hyperspectral remote sensing involve the detection of subpixel targets for search and rescue or defense and intelligence operations. The design and potential capabilities of these systems depends on their target detection performance. Therefore, it is important to have tools that reliably predict the performance of target detection systems under different realistic situations. The purpose of this paper is to present a hyperspectral target performance prediction model for the widely used matched filter (MF) and adaptive cosine estimator (ACE) detectors. We use a replacement signal model for resolved and subpixel targets and a finite probability mixture of t-elliptically contoured distributions ( t-ECDs) for the background. A major contribution of this paper is the development of a robust analytical and numerical approach to determine the output distribution of ACE for mixtures of t-ECDs. The proposed technique can be a very useful tool for evaluating target detection performance for highly complex backgrounds.

Neural network estimation of atmospheric profiles using AIRS/IASI/AMSU data in the presence of clouds

As the forthcoming launch of the NPOESS Preparatory Project (NPP) nears, pre-launch predictions of onorbit performance are of critical importance to illuminate possible emphasis areas for the intensive calibration/ validation (cal/val) period to follow launch. During this period of intensive cal/val (ICV), quick-look performance assessment tools that can analyze global data over a variety of observing conditions will also play an important role in verifying and potentially improving environmental data record (EDR) quality. In this paper, we present recent work on a fast and accurate sounding algorithm based on neural networks for use with the Cross-track Infrared Sounder (CrIS) and the Advanced Technology Microwave Sounder (ATMS) to be flown on the NPP satellite. The algorithm is being used to assess pre-launch sounding performance using proxy data (where observations from current satellite sensors are transformed spectrally and spatially to resemble CrIS and ATMS) from the Atmospheric InfraRed Sounder (AIRS) and the Advanced Microwave Sounding Unit (AMSU) on the NASA Aqua satellite and the Infrared Atmospheric Sounding Interferometer (IASI) and AMSU/MHS (Microwave Humidity Sounder) on the EUMETSAT MetOp-A satellite. The algorithm is also being developed to provide a highly-accurate quick-look capability during the NPP ICV period. The present work focuses on the cloud impact on the infrared (AIRS/IASI/CrIS) radiances and explores the use of stochastic cloud clearing (SCC) mechanisms together with neural network (NN) estimation. A stand-alone statistical algorithm will be presented that operates directly on cloud-impacted AIRS/AMSU, IASI/AMSU, and CrIS/ATMS (collectively CrIMSS) data, with no need for a physical cloud clearing process. The algorithm is implemented in three stages. First, the infrared radiance perturbations due to clouds are estimated and corrected by combined processing of the infrared and microwave data using the SCC approach. The cloud clearing of the infrared radiances was performed using principal components analysis of infrared brightness temperature contrasts in adjacent fields of view and microwave-derived estimates of the infrared clear-column radiances to estimate and correct the radiance contamination introduced by clouds. Second, a Projected Principal Components (PPC) transform is used to reduce the dimensionality of and optimally extract geophysical profile information from the cloud-cleared infrared radiance data. Third, an articial feedforward neural network (NN) is used to estimate the desired geophysical parameters from the projected principal components. The performance of the method was evaluated using global (ascending and descending) EOS-Aqua and MetOp-A orbits co-located with ECMWF forecasts (generated every three hours on a 0.5-degree lat/lon grid) for a variety of days throughout 2003, 2004, 2005, and 2007. Over 1,000,000 fields of regard (3 × 3/2 × 2 arrays of footprints) over ocean and land were used in the study. The performance of the SCC/NN algorithm exceeded that of the AIRS Level 2 (Version 5) algorithm throughout most of the troposphere while achieving approximately 25-50 percent greater yield. Furthermore, the SCC/NN performance in the lowest 1 km of the atmosphere greatly exceeds that of the AIRS Level 2 algorithm as the level of cloudiness increases. The SCC/NN algorithm requires signicantly less computation than traditional variational retrieval methods while achieving comparable performance, thus the algorithm is particularly suitable for quick-look retrieval generation for post-launch CrIMSS performance validation.

Performance evaluation of cluster-based hyperspectral target detection algorithms

Detection of targets in background clutter using hyperspectral imaging sensors, is a problem of great practical interest [1]. This paper addresses some practical problems related to the adaptive estimation of clutter models and their effects on the performance of matched-signature detection algorithms. More specifically, we compare clutter estimation algorithms using spatially-local adaptation or spectral clustering to deal with the nonstationarity of hyperspectral backgrounds.

False alarm mitigation techniques for hyperspectral target detection

A challenging problem of major importance in hyperspectral imaging applications is the detection of subpixel objects of military and civilian interest. High false alarm thresholds are required to detect subpixel objects due to the large amount of surrounding background clutter. These high false alarm rates are unacceptable for military purposes, requiring the need for false alarm mitigation (FAM) techniques to weed out the objects of interest. The objective of this paper is to provide a comparison of the implementation of these FAM techniques and their inherent benefits in the whitened detection space. The widely utilized matched filter (MF) and adaptive cosine estimator (ACE) are both based on a linear mixing model (LMM) between a background and object class. The matched filter approximates the object abundance, and the ACE measures the model error. Each of these measurements provides inadequate object separation alone, but by using both the object abundance and model error, the objects can be separated from the false alarms.

Improved all-weather atmospheric sounding using hyperspectral microwave observations

We introduce a new hyperspectral microwave remote sensing modality for atmospheric sounding, driven by recent advances in microwave device technology that now permit receiver arrays that can multiplex multiple broad frequency bands into more than ∼ 100 spectral channels, thus improving both the vertical and horizontal resolution of the retrieved atmospheric profile. Global simulation studies over ocean and land in clear and cloudy atmospheres using three different atmospheric profile databases are presented that assess the temperature, moisture, and precipitation sounding capability of several notional hyperspectral systems with channels sampled near the 50–60-GHz, 118.75-GHz, and 183.31-GHz absorption lines. These analyses demonstrate that hyperspectral microwave operation using frequency multiplexing techniques substantially improves temperature and moisture profiling accuracy, especially in atmospheres that challenge conventional non-hyperspectral microwave sounding systems because of high water vapor and cloud liquid water content. Retrieval performance studies are also included that compare hyperspectral microwave sounding performance to conventional microwave and hyperspectral infrared approaches, both in a geostationary and low-earth orbit context, and a path forward to a new generation of high-performance all-weather sounding is discussed.

Recent progress in neural network estimation of atmospheric profiles using microwave and hyperspectral infrared sounding data in the presence of clouds

Recent work has demonstrated the feasibility of neural network estimation techniques for atmospheric profiling in partially cloudy atmospheres using combined microwave (MW) and hyperspectral infrared (IR) sounding data. In this paper, the global retrieval performance of the stochastic cloud-clearing / neural network (SCC/NN) method is examined using atmospheric fields provided by the European Center for Medium-range Weather Forecasting (ECMWF) and in situ measurements from the NOAA radiosonde database. Furthermore, the retrieval performance of the neural network method is compared with the AIRS Level 2 algorithm (Version 4). Comparisons of both forecast and radiosonde data indicate that the neural network retrieval performance is similar to or exceeds that of the AIRS Level 2 (version 4) profile products, substantially so in very cloudy areas. A novel statistical method for the global retrieval of atmospheric temperature and water vapor profiles in cloudy conditions has been developed and evaluated with sounding data from the Atmospheric InfraRed Sounder (AIRS) and the Advanced Microwave Sounding Unit (AMSU). The present work focuses on the cloud impact on the AIRS radiances and explores the use of Stochastic Cloud Clearing (SCC) together with neural network estimation. A stand-alone statistical algorithm will be presented that operates directly on cloud-impacted AIRS/AMSU data, with no need for a physical cloud clearing process. The algorithm is implemented in three stages. First, the infrared radiance perturbations due to clouds are estimated and corrected by combined processing of the infrared and microwave data using the SCC method. The cloud clearing of the infrared radiances was performed using principal components analysis of infrared brightness temperature contrasts in adjacent fields of view and microwave-derived estimates of the infrared clear-column radiances to estimate and correct the radiance contamination introduced by clouds. Second, a Projected Principal Components (PPC) transform is used to reduce the dimensionality of and optimally extract geophysical profile information from the cloud-cleared infrared radiance data. Third, an artificial feedforward neural network (NN) is used to estimate the desired geophysical parameters from the projected principal components. The performance of this method was evaluated using global (ascending and descending) EOS-Aqua orbits co-located with ECMWF fields for a variety of days throughout 2002 and 2003. Over 500,000 fields of regard (3x3 arrays of footprints) over ocean and land were used in the study. The NOAA radiosonde database was also used to assess performance - approximately 2000 global, quality-controlled radiosondes were selected for the comparison. The SCC/NN method requires significantly less computation (up to a factor of three orders of magnitude) than traditional variational retrieval methods, while achieving comparable global performance. Accuracies in areas of severe clouds (cloud fractions exceeding about 60 percent) is particular encouraging.