Hyperspectral Target Detection Applications Research Articles

Investigating the Effects of a Combined Spatial and Spectral Dimensionality Reduction Approach for Aerial Hyperspectral Target Detection Applications

Target detection and classification is an important application of hyperspectral imaging in remote sensing. A wide range of algorithms for target detection in hyperspectral images have been developed in the last few decades. Given the nature of hyperspectral images, they exhibit large quantities of redundant information and are therefore compressible. Dimensionality reduction is an effective means of both compressing and denoising data. Although spectral dimensionality reduction is prevalent in hyperspectral target detection applications, the spatial redundancy of a scene is rarely exploited. By applying simple spatial masking techniques as a preprocessing step to disregard pixels of definite disinterest, the subsequent spectral dimensionality reduction process is simpler, less costly and more informative. This paper proposes a processing pipeline to compress hyperspectral images both spatially and spectrally before applying target detection algorithms to the resultant scene. The combination of several different spectral dimensionality reduction methods and target detection algorithms, within the proposed pipeline, are evaluated. We find that the Adaptive Cosine Estimator produces an improved F1 score and Matthews Correlation Coefficient when compared to unprocessed data. We also show that by using the proposed pipeline the data can be compressed by over 90% and target detection performance is maintained.

Loss of target information in full pixel and subpixel target detection in hyperspectral data with and without dimensionality reduction

In most hyperspectral target detection applications, targets are usually small and require both spatial as well as spectral detection. Hyperspectral imaging facilitates target detection (TD) applications greatly, however, due to large spectral content, hyperspectral data requires dimensionality reduction (DR) which also leads to loss of target information both at full pixel and subpixel level. Literature reports many DR and TD algorithms in practice. Several studies have focussed on assessing the loss of target information in DR, however, not much work seems to have been done to assess loss of target information in full pixel and subpixel TD in hyperspectral data with and without DR. This paper seeks to study various combinations of DR techniques combined with full pixel and subpixel TD algorithms. The results indicate that in the case of full pixel targets, both DR and TD contribute to the loss of target information, however, there is more loss of target information in the case when DR precedes TD in comparison to a case where TD is applied without DR. In the case of subpixel TD, however, there appears to be loss of subpixel target information in the case where TD alone is performed in comparison to a case where DR precedes TD.

An Automatic Dictionary Construction Framework for Sparsity-Based Hyperspectral Target Detectors

The mechanisms behind the sparsity-based techniques for hyperspectral target detection and classifications applications are quite similar except the construction methods of the dictionaries used by the algorithms. In hyperspectral image classification, the dictionaries are formed using some known labeled training samples for each class. In contrast, the only a priori target spectrum information is available for the target detection applications. In addition, most of the time, the background materials are unknown in an arbitrary scene. Although some practical approaches such as sliding window exist, their performances are highly unsatisfactory. In order to increase the detection performance of the sparsity-based methods, we propose an automatic dictionary construction framework which is based on a couple of stages consisting of dimension reduction, k-means clustering, connected component labeling via spatial techniques, and spectral methods such as constrained energy minimization filtering. Our experiments show that the proposed approach outperforms the conventional methods, and it is a promising framework for hyperspectral target detection applications.

Covariance-based band selection and its application to near-real-time hyperspectral target detection

The matched filter (MF) and adaptive coherence estimator (ACE) show great effectiveness in hyperspectral target detection applications. Practical applications in which on-board processing is generally required demand real-time or near-real-time implementation of these detectors. However, a vast amount of hyperspectral data may make real-time or near-real-time implementation of the detection algorithms almost impossible. Band selection can be one of the solutions to this problem by reducing the number of spectral bands. We propose a new band selection method that prioritizes spectral bands based on their influence on the detection performance of the MF and ACE and discards the least influential bands. We validate the performance of our method using real hyperspectral images. We also demonstrate our technique on near-real-time detection tasks and show it to be a feasible approach to the tasks.

FPGA Implementation of an Algorithm for Automatically Detecting Targets in Remotely Sensed Hyperspectral Images

Timely detection of targets continues to be a relevant challenge for hyperspectral remote sensing capability. The automatic target-generation process using an orthogonal projection operator (ATGP-OSP) has been widely used for this purpose. Hyperspectral target-detection applications require timely responses for swift decisions, which depend upon (near) real-time performance of algorithm analysis. Reconfigurable field-programmable gate arrays (FPGAs) are promising platforms that allow hardware/software codesign and the potential to provide powerful onboard computing capabilities and flexibility at the same time. In this paper, we present an FPGA implementation for the ATGP-OSP algorithm. Our system includes a direct memory access module and implements a prefetching technique to hide the latency of the input/output communications. The proposed method has been implemented on a Virtex-7 XC7VX690T FPGA and tested using real hyperspectral data collected by NASA’s Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the Cuprite mining district in Nevada and the World Trade Center in New York. Experimental results demonstrate that our hardware version of the ATGP-OSP algorithm can significantly outperform a software version, which makes our reconfigurable system appealing for onboard hyperspectral data processing.

An Automatic Robust Iteratively Reweighted Unstructured Detector for Hyperspectral Imagery

Unstructured background model-based detectors, which usually utilize a single a priori target spectral signature as the input, have been successfully applied in various hyperspectral target detection applications. However, the detection results are greatly affected by the quality of the a priori target spectral signature, as the spectral variability phenomenon is universal in hyperspectral image data. This paper proposes an iteratively reweighted method to generate an optimal target spectrum from limited target training spectra, which is able to alleviate the spectral variation. When the priori target spectral can only be chosen from the hyperspectral image, an optimal target spectrum can be iteratively generated by adjusting the pixel signals with varying weights. The experimental results with three different types of real hyperspectral images confirm the robust performance of the proposed method.

A Background Self-Learning Framework for Unstructured Target Detectors

Unstructured background model based detectors have been successfully applied in various hyperspectral target detection applications. The background statistics of an image can be estimated in a global way or a local way. The global approach involves modeling the background directly from the whole image, which can prove to be inaccurate due to target contamination of the background information. The local approach usually involves estimating the background statistics using a spatially sliding local window. However, this approach can also fail to reflect reality, due to sensitive parameters, like the window size, and presents high computational costs. This letter proposes a self-learning method to adaptively determine the background statistics for unstructured detectors, with the consideration of exploiting both the spatial and spectral information, and accelerating the computation speed. The experimental results with two real hyperspectral images confirm the superior performance when compared to the other two approaches to modeling background statistics.

A Kernel-Based Target-Constrained Interference-Minimized Filter for Hyperspectral Sub-Pixel Target Detection

The target-constrained interference-minimized filter (TCIMF) method has been successfully applied to various hyperspectral target detection applications. This paper presents a nonlinear version of TCIMF, called kernel-based TCIMF (KTCIMF), employing the kernel method to resolve the issue of nonlinear endmember mixing in hyperspectral images (HSI). Input data are implicitly mapped into a high-dimensional feature space, where it is assumed that target signals are more separable from background signals. Conventional TCIMF performs well in suppressing undesired signatures whose spectra are similar to that of the targets, thereby enhancing performance, and with less false alarms. KTCIMF not only takes into consideration the nonlinear endmember mixture but also fully exploits the other spectrally similar interference signatures. In this way, it is effective in suppressing both the background and those undesired signatures that may cause false alarms in traditional methods. Experimental results with both simulated and real hyperspectral image data confirm KTCIMF's performance with intimately mixed data. Compared with conventional kernel detectors, KTCIMF shows improved ROC curves and better separability between targets and backgrounds.

Hyperspectral target detection via discrete wavelet-based spectral fringe-adjusted joint transform correlation

Spectral variability remains a major challenge for target detection in hyperspectral imagery (HSI). Recently, the spectral fringe-adjusted joint transform correlation (SFJTC) technique has been used effectively for hyperspectral target detection applications. In this paper, we propose to use discrete wavelet transform (DWT) coefficients of the signatures as features for detection in order to make the SFJTC technique more insensitive to spectral variability. We devised a supervised training algorithm that uses the pure target signature and randomly selected samples from input scenery to select an optimal set of DWT coefficients for detection. We have inserted target signatures into urban and vegetative hyperspectral scenery with varying levels of spectral variability to explore the performance of our DWT-based SFJTC technique in different operating conditions. Detection results in the form of receiver-operating-characteristic (ROC) curves and area-under-the-ROC (AUROC) curves show that the proposed scheme yields the largest mean AUROC values compared to SFJTC using the original signatures and traditional hyperspectral detection algorithms.

Realistic matched filter performance prediction for hyperspectral target detection

The linear matched filter is widely used in hyperspectral target detection applications. Its detection performance is typically evaluated based on Gaussian (or normal) probability density models. However, it is well known that hyperspectral backgrounds exhibit "long-tail" behavior, which cannot be accurately modeled by normal distributions. In this work, we model the distribution of hyperspectral backgrounds using a more accurate model based on elliptically contoured multivariate t distributions. For the target class, we still use a normal distribution model, because the body of the distribution is important for detection applications. We show that the tails of the background distribution deteriorate the performance of the matched filter. In this sense, performance predictions based exclusively on normal models, which ignore the long tails, can be inaccurate and overly optimistic. The proposed technique, which allows for an easy control of the tail's heaviness, can be a very useful tool for evaluating target detection performance for backgrounds with both light and heavy tails.

Feature reduction and morphological processing for hyperspectral image data.

An automatic target detection system that uses hyperspectral (HS) imagery is proposed. HS images contain both spatial and spectral response information that provides detailed descriptions of an object. These new, to our knowledge, sensor data are useful in automatic target recognition applications. To provide discrimination information from the HS images and to select features that generalize well, we describe a new, to our knowledge, high-dimensional generalized discriminant feature-extraction algorithm and compare its performance with that of other feature-reduction methods for two HS target detection applications (mine and vehicle detection) by using a nearest-neighbor classifier. We also advance an approach to simultaneously optimize both spatial and spectral responses.