Hyperspectral anomaly detection using Sony PlayStation 3

: Robotics is a fundamental enabling technology required to meet the U.S. Army's vision to be a strategically responsive force capable of domination across the entire spectrum of conflict. The U.S. Army Research, Development and Engineering Command (RDECOM) Tank Automotive Research, Development and Engineering Center (TARDEC), in partnership with the U.S. Army Research Laboratory, is developing a leader-follower capability for Future Combat Systems. The Robotic Follower Advanced Technology Demonstration (ATD) utilizes a manned leader to provide a high-level proofing of the follower's path, which operates with minimal user intervention. This paper will give a programmatic overview and discuss both the technical approach and operational experimentation results obtained during testing conducted at Ft. Bliss, New Mexico in February-March 2003.

Most existing hyperspectral anomaly detection algorithms primarily rely on spatial information to identify anomalous targets. However, they often overlook the spatial–spectral gradient information inherent in hyperspectral images, which can lead to decreased detection accuracy. To address this limitation, we propose a novel hyperspectral anomaly detection algorithm that incorporates both local sub-block contrast and spatial–spectral gradient features. In this approach, a grid block window is utilized to capture local spatial information. To effectively detect low-contrast targets, we introduce a novel local sub-block ratio-multiply contrast method that enhances anomalous regions while suppressing the background. Additionally, to mitigate the challenges posed by complex backgrounds, a feature extraction technique based on spatial–spectral gradients is proposed. To account for the spectral reflectance differences between anomalous targets and the background, we further introduce a local sub-block ratio-difference contrast method to compute preliminary detection scores. The final anomaly detection results are obtained by merging these two detection scores. The key advantage of the proposed method lies in its ability to exploit local gradient characteristics within hyperspectral images, thereby resolving the issue of edge features being misidentified as anomalies. This method also effectively reduces the impact of noise on detection accuracy. Experimental validation based on four real-world datasets demonstrates that the proposed method outperforms seven state-of-the-art techniques, showing superior performance in both qualitative and quantitative evaluations.

In this chapter, the algorithm summary of the proposed autonomous anomaly detection (AAD) algorithm described in Chap. 6 is provided. Numerical examples based on both the synthetic and benchmark datasets are presented for evaluating the performance of the AAD algorithm. Well-known traditional anomaly detection approaches are used for a further comparison. It was demonstrated through the numerical experiments that the AAD algorithm is able to provide a more objective, accurate way for anomaly detection, and its performance is not influenced by the structure of the data and is equally effective in detecting collective anomalies as well as individual anomalies. The pseudo-code of the main procedure of the AAD algorithm and the MATLAB implementation can be found in Appendices B.1 and C.1, respectively. © 2019, Springer Nature Switzerland AG.

This report summarizes our observations using the longwave infrared (LWIR) hyperspectral data subset of the Spectral and Polarimetric Imagery Collection Experiment (SPICE) dataset, which emphasizes the inherent challenges associated with applying autonomous spectral pattern recognition methods to LWIR hyperspectral imagery, as well as data quality and qualitative validation of expected atmospheric spectral features. SPICE is a collaborative effort between the US Army Research Laboratory, US Army Armament Research, Development, and Engineering Center, and the US Air Force Institute of Technology. It focused on the long-term LWIR hyperspectral and polarimetric data collection of a target site, under various weather and non-ideal conditions, and exploitation of this dataset for pattern recognition tasks. We concluded from this effort that the quality of SPICE hyperspectral LWIR data is categorically comparable to other datasets recorded by a different sensor of similar specifications and is adequate for algorithmic research. The vast dataset and associated ground-truth information are a great asset for research.

The shape of a low-frequency pulse that propagates to the far side of a hill depends primarily on two physical mechanisms: a diffracted wave and a surface wave. Both of these mechanisms depend on frequency, so that the pulse shape and frequency spectrum of the received pulse differ significantly from those near the source. As is well known, diffraction acts like a low-pass filter. The surface wave has a more complicated frequency dependence that depends on the terrain, the frequency dependence of the ground impedance, and the near-ground sound speed profile. For a given range, these parameters determine a frequency band that contains most of the surface wave energy. The surface wave thus functions as a low-frequency bandpass filter. The combined effects of diffraction and surface wave propagation on pulse propagation over a hill are studied using a parabolic equation model and a piecewise linear mapping to flatten the irregular terrain. Numerical calculations are presented for selected terrain features, ground impedances, and sound speed profiles. [Research supported by the U.S. Army Armament, Research Development and Engineering Center (ARDEC).]

: A computational tool that models the terminal descent characteristics of a single or a cluster of parachutes is a technology that is needed by parachute designers and engineers. As part of a technology program annex (TPA), a joint effort between the U.S. Army Natick Research, Development, and Engineering Center (NRDEC) and the U.S. Army Research Laboratory (ARL) to develop this computational tool is now under way. As a first effort, attempts are being made to analyze both two-dimensional (2- D) and three-dimensional (3-D) flow fields around a parachute using a coupling procedure in which the fluid dynamics are coupled to 2-D and 3-D structural dynamic (SD) codes. This effort uses computational fluid dynamic (CFD) codes to calculate a pressure field, which is then used as an input load for the SD code. Specifically, this report presents the methods and results of the flow field plus the structural characteristics of a single axisymmetric parachute and a 3-D gore configuration for the terminal descent velocity. Computed results have been obtained using the payload weight and unstretched constructed geometry of the canopies as input. Significant progress has been made in determining the terminal descent flow field along with the terminal shape of the parachute. A discussion of the fluid and structural dynamics codes, coupling procedure, and the associated technical difficulties is presented. Examples of the codes' current capabilities are shown.

ABSTRACTAnomaly detection is an active research topic in hyperspectral remote sensing and has been applied in many areas including environmental monitoring, urban survey, mineral mapping, and national security. Usually, it makes a detection decision without any prior target information or background information. Several anomaly detection algorithms (e.g. Reed–Xiaoli detector, blocked adaptive computationally efficient outlier nominator and random-selection-based anomaly detector) have been developed, which rely on estimating background information only from a hyperspectral image without considering target information in making a detection decision. These methods may be efficient in general but sometimes with high false alarm rate (FAR). In order to reduce FAR, this study proposes a novel method that incorporates both background and target information, derived from the hyperspectral imagery, into anomaly detection algorithms. The target information is helpful to detect anomalies as outliers. With a scene of real airborne visible infrared imaging spectrometer data, the experimental results demonstrate that the proposed method has produced better detection results and higher time efficiency compared with those using the traditional algorithms that only consider background information.

The Fiberoptic Guided Missile (FOG-M) was developed in the U.S. Army's Research, Development, and Engineering Center (RDEC) as a demonstration system for killing armor in an infantry application. The RDEC design uses a television sensor in the nose of the missile for in-flight target acquisition, bringing the video signal down a fiberoptic link that pays out behind the missile as it flies, to a gunner securely hidden in a defiladed launch vehicle. The gunner is able to select the target on a video screen and lock on an autotracker or alternately manually track the target to impact. The system design would use a common warhead for either armor or helicopter targets. The system is currently mounted on the High Mobility, Multipurpose Wheeled Vehicle (HMMWV), containing the gunner's station, launcher, and flight missiles. The gunner's station includes the capability for detailed mission planning, digital map display based on the Defense Mapping Agency's digital map databases, and display of the air battle situation for the gunner. Automatic targeting, control of multiple missiles in the air simultaneously, navigation using a digital correlator, and autotracking of moving targets in cluttered backgrounds with gunner selectable offset tracking capability are also available. The system has a capability to train the gunner using a perspective view scene generator that mimics the video scene he would be presented during missile flight. The scene generator uses the same hardware that displays the digital map, while a simulation of the missile runs in one of the system's computer processors to accurately move the seeker presentation around the scene. All of the other hardware used in embedded training is the same as the actual firing hardware. The system concept has been chosen by the Army as the non-line-of-sight (NLOS) component of the Forward Area Air Defense System (FAADS). The initial design is being upgraded for the MIL SPEC environment to allow early operational evaluation by the user. The lessons learned by these tests will be used to aid the full scale development program beginning in FY88. This paper describes aspects of the system designed by the Army's RDEC, with special emphasis on the mechanics of fiberoptic datalink winding and payout concerns.

Traditional Intrusion Detection Systems (IDS) can be complemented by an Anomaly Detection Algorithm (ADA) to also identify unknown attacks. We argue that, as each ADA has its own strengths and weaknesses, it might be beneficial to rely on multiple ADAs to obtain deeper insights. ADAs are very resource intensive; thus, real-time detection with multiple algorithms is even more challenging in high-speed networks. To handle such high data rates, we developed a controlled load allocation scheme that adaptively allocates multiple ADAs on a multi-core system. The key idea of this concept is to utilize as many algorithms as possible without causing random packet drops, which is the typical system behavior in overload situations. We developed a proof of concept anomaly detection framework with a sample set of ADAs. Our experiments confirm that the detection performance can substantially benefit from using multiple algorithms and that the developed framework is also able to cope with high packet rates.

A large amount of work has been done on the KDD 99 dataset, most of which include the use of a hybrid anomaly and misuse detection model done in parallel with each other. In order to further classify the intrusions, our approach to network intrusion detection includes the use of two different anomaly detection models followed by misuse detection applied to the combined output obtained from the previous step. The end goal of this is to verify the anomalies detected by the anomaly detection algorithm and clarify whether they are actually intrusions or random outliers from the trained normal (and thus to try and reduce the number of false positives). We aim to detect a pattern in this novel intrusion technique itself, and not the handling of such intrusions. The intrusions were detected to a very high degree of accuracy.

Traditionally, condition has been the desired metric for establishing maintenance and repair (M&R) needs for building components. Different approaches have been developed for that condition assessment, including the use of condition indexes. While having a condition metric is critical for identifying M&R work needs, this metric does not tell the complete story. Often, facility work needs go beyond degradation based maintenance, repair, rehabilitation, or replacement because components or systems also require capability upgrading or altering due to a change in user needs, technical obsolescence, and/or the invoking of regulatory requirements. These capability based needs can be significant and in some instances, exceed the condition based needs. Therefore, there is a need to have a metric for measuring capability that also can be used to support work planning. The U.S. Army Engineering and Research Development Center, Construction Engineering Research Laboratory (ERDC-CERL) has, in the past, developed inspection based condition indexes for building components, systems, and the overall building. ERDCCERL has developed capability metrics for building components and systems. These capability metrics will supplement the previously developed condition indexes and together measure of functionality which is the total ability of a component to do what it is intended to. This paper discusses condition metrics as used in BUILDER EMS and the development of the capability metrics for the various building components. These metrics are intended to support network level management activities for communities ranging from relatively few buildings to large numbers of buildings such as found at large military installations and college campuses. i Principal Investigator, U.S. Army Engineer Research and Development Center, Construction Engineering Research laboratory, P.O. Box 9005, Champaign, IL 61826. E-mail: d-uzarski@cecer.army.mil 2 Principal Investigator, U.S. Army Engineer Research and Development Center, Construction Engineering Research laboratory, P.O. Box 9005, Champaign, IL 61826. E-mail: d-hicks@cecer.army.mil 3 Assistant Investigator, U.S. Army Engineer Research and Development Center, Construction Engineering Research laboratory, P.O. Box 9005, Champaign, IL 61826. E-mail: j -zahorak@cecer.army.mil

Deep learning has achieved excellent performance in the field of computer vision and gained attention in the field of hyperspectral anomaly detection (HAD). Convolutional neural networks (CNN) based on pixel pairing features have achieved a certain detection effect, which is limited by background complexity in practical applications. This study proposes an adaptive weighted HAD algorithm that combines an autoencoder (AE) and CNN. Labelled hyperspectral images (HSIs) are used to train a CNN as a binary classifier for similarity discrimination in the data preparation stage, where morphological attribute filtering (MAF) is performed on images in the spatial dimension of the HSIs to highlight anomaly. The spectral angle is used as a measure of reconstruction error to train the AE, and the reconstruction error obtained using the AE is used as an adaptive weight to calculate the anomaly score, which considerably eliminates the blurring of the boundary between the background and anomalies. Through comparisons with some state-of-the-art methods, the effectiveness of the proposed method in improving detection accuracy and increasing background and anomaly discrimination is verified on three real datasets.

In the field of launch vehicles, high launch density, heavy work intensity and large data volume have brought the traditional automatic anomaly detection with incomplete coverage, and complex design of criterion, which influencing performance evaluation of launch vehicle. In order to fully mine the data variation law implied in the massive telemetry data, the intelligent anomaly detection algorithm is proposed and designed as a beneficial supplement to the traditional anomaly detection algorithm, and improve the anomaly detection coverage and efficiency. With the telemetry data generated by the liquid launch vehicle taken as the research object, and the intelligent anomaly detection algorithm is compared with the traditional algorithm. It is shown that the algorithm proposed adapts to the anomaly detection scenarios with frequency anomaly and frame loss, which may be difficult for traditional algorithms to design anomaly detection criteria, and the average anomaly detection performance is improved by nearly 30% and the variance is reduced by 85%, providing a reference for improving anomaly detection system and applying intelligent anomaly detection algorithms in aerospace.

Anomaly detection in big data is a key problem in the big data analytics domain. In this paper, the definitions of anomaly detection and big data were presented. Due to the sampling and storage burden and the inadequacy of privacy protection of anomaly detection based on uncompressed data, compressive sensing theory was introduced and used in the anomaly detection algorithm. The anomaly detection criterion based on wavelet packet transform and statistic process control theory was deduced. The proposed anomaly detection technique was used for through-wall human detection to demonstrate the effectiveness. The experiments for detecting humans behind a brick wall and gypsum based on ultra-wideband radar signal were carried out. The results showed that the proposed anomaly detection algorithm could effectively detect the existence of a human being through compressed signals and uncompressed data.

Anomaly detection in streaming data is an important task for many real-world applications, such as network security, fraud detection, and system monitoring. However, streaming data often exhibit concept drift, which means that the data distribution changes over time. This poses a significant challenge for many anomaly detection algorithms, as they need to adapt to the evolving data to maintain high detection accuracy. Existing streaming anomaly detection algorithms lack a unified evaluation framework that validly assesses their performance and robustness under different types of concept drifts and anomalies. In this paper, we conduct a systematic technical review of the state-of-the-art methods for anomaly detection in streaming data. We propose a new data generator, called SCAR (Streaming data generator with Customizable Anomalies and concept dRifts), that can synthesize streaming data based on synthetic and real-world datasets from different domains. Furthermore, we adapt four static anomaly detection models to the streaming setting using a generic reconstruction strategy as baselines, and then compare them systematically with 9 existing streaming anomaly detection algorithms on 76 synthesized datasets that have various types of anomalies and concept drifts. The challenges and future research directions for anomaly detection in streaming data are also presented.