Knowing the unknowable unknowns: subpixel anomalous source detection in hyperspectral imagery
Abstract
A novel and computationally efficient algorithm for autonomous detection and localization of anomalies in hyperspectral imagery is presented. Anomaly refers to any object whose spectral radiance does not comport with that of its immediate neighborhood. It is assumed that the spatial extent of the anomaly is smaller than a sensor detector footprint, and that it is entirely confined to a single image pixel. The technique developed here is an unsupervised learning algorithm that examines each pixel in the context of its immediate neighborhood without any a priori knowledge about the spatial and spectral characteristics of the expected background or potential anomalies. The image representing each of the spectral bands of the hyperspectral image under consideration is independently converted to a two-dimensional binary anomaly map, which lends itself to straightforward parallelization of the computational process. The composite anomaly map is then obtained by adding the entire set of anomaly maps to which a threshold is applied and detection decisions are subsequently made. The results of the application of the algorithm to hyperspectral cubes obtained from the AVIRIS data and color RGB images are presented. It is shown that the algorithm provides a robust anomaly detection methodology with very-low computational overhead. This new algorithm has demonstrated computational efficiency of over three orders of magnitude better than the Boeing computationally-enhanced version of the N-FINDR. Unlike the N-FINDR, real-time application of the new anomalous source detection algorithm appears practicable.
Keywords
Download Options
Introduction
The ability to detect potential threats in the early engagement phase of a mission improves the survivability of military assets and may provide enhanced protection for commercial aircraft. For example, the ability to detect an antiaircraft system while the physical distance between the aircraft and an unknown missile site is significant, offers greater opportunities for initiation of evasive action or deployment of defensive devices. The capability to scan a large area at high frame rate and detect objects that do not conform to their background is also of great value to many reconnaissance and surveillance systems. Long-range wide-area imagery of a suspected threat region can result in the concealed targets being confined to zones limited to less than a detector footprint. Algorithms for detection of targets smaller than the detector footprint cannot utilize spatial properties and must be entirely reliant on the spectral characteristics of potential targets. The objective of this research is to construct an algorithm to detect and locate subpixel anomalies in hyperspectral imagery (HSI). The algorithm must concurrently provide high probability of detection (PD) and low false-alarm rate (FAR) with the concomitant low-latency requirement of practical real-time systems. A computationally efficient and robust anomaly detection engine is a vital module in any hyperspectral target detection and tracking system where no a priori information about the spectral and spatial characteristics of the expected background and potential targets are available. Coupling such an algorithm with a fast frame-rate HSI data acquisition system, in principle, will make possible the simultaneous tracking of multiple targets each smaller than a detector footprint.
The proliferation of HSI equipped sensor platforms, for both civilian and military applications, has led to the development of a plethora of analysis techniques for exploitation of the vast amounts of information contained within these images [1- 12]. HSI comprises potentially hundreds of spatially co-registered images taken at narrow, and generally contiguous, spectral bands spanning visible, near infrared, mid-wave and long-wave infrared (IR), and/or millimeter wave of the electromagnetic spectrum. A HSI is a three-dimensional array consisting of one spectral and two spatial dimensions. Each spatially corresponding pixel of the data cube represents a portion of the spectrum of the emitted energy collected by the respective detector; this set of pixels along the spectral dimension is referred to as a spectral pixel array. The spectral radiance emanating from a pixel footprint containing an anomalous source is a blend of the anomalous source and a portion of the uncontaminated pixel spectral radiances. Theresulting signal from each detector in the spectral pixel array is determined by common radiometric methods [13–14]. The spectral signature of any pixel array is affected by the radiometric characteristics of materials located within the detector footprint, illumination, thermal self-emission, the intervening atmosphere, shadowing, and scattering.
Conclusion
A novel method has been presented for detection and localization of subpixel anomalies in hyperspectral imagery. The conceptually intuitive HSI anomalous source detection algorithm, SASD, has been shown to be robust and remarkably computationally efficient. This anomaly detection procedure does not rely on any a priori information about the spatial and spectral characteristics of the expected background or of potential anomalies. The subpixel anomalous source detection algorithm converts the input HSI data cube into a 2D binary anomaly map, using two user-prescribed thresholds, in a computationally straightforward approach. Each pixel is examined in the context of its immediate neighborhood in each of the HSI image planes and an incongruence score is assigned to it which results in an incongruence pseudo-image for each spectral band. The incongruence score of a pixel has an inverse relationship to the degree of its conformity to its neighborhood. The user-prescribed incongruence threshold is used to convert each of the band-specific incongruence pseudo-images into a respective binary incongruence-map. These maps are subsequently combined to compute the binary anomaly map using the user-prescribed band-threshold. It has been shown through many simulations, using actual HSI and RGB images, that the subpixel anomalous source detection algorithm (SASD) is capable of detecting subtle anomalies with high probability of detection and low false-alarm rates. Comparisons with the Boeing Enhanced N-FINDR algorithm has confirmed that the computational processing power required for the implementation of the described subpixel anomalous source detection algorithm is several orders of magnitude less than for the Enhanced N-FINDR. The SASD algorithm can be implemented for processing high spatial-spectral resolution HSI with low latency requirements using commercial offthe-shelf (COTS) processing platforms. The low computational overhead afforded by this algorithm makes it a good candidate for real-time processing of high frame-rate HSI video streams in both commercial and military applications.
Future research is planned to (1) further understand the relationship of hyperspectral image data cubes' complexity and unresolved and subpixel-scale object anomalies detect ability from their immediate neighborhood, (2) investigate spectral bands selection of image data cubes to improve performance and reduce computational resources, (3) study the efficacy of algorithms if synthetic resolution-enhancement is applied to image data cube, (4) experimentally validate the algorithms, and (5) extending the algorithm to include imagery signal-to-noise information. It is anticipated that providing technology to detect and locate unknown unresolved and subpixel-scale anomalous objects in unknown scenes can positively impact industrial and military security needs by affording the ability to detect potential threats in the early engagement phase of a mission to improve (i) survivability of military assets and enhance protection for commercial aircraft, (ii) locating buried mines and IED detection, (iii) monitoring of pollution in smokestack plumes, (iv) chemical and biological agent detection, and (v) detection of small floating objects to aid in search and rescue operations to name a few potential applications.