In the ambit of the computer vision, the moving object detection is an extremely important topic which has drawn the interest of the scientific community. Recently, an emerging dimensionality reduction technique, called Dynamic Mode Decomposition (DMD), has been exploited to make an estimation of the background. The DMD is a pure data-driven technique which provides information about the spatial and temporal evolution of the input video. The main idea behind the usage of the DMD is the possibility of isolating the modes that addresses the background in order to obtain the signal associated with the target by subtraction. In the practice, the DMD produces a unimodal representation of the background, which provides good results under the assumptions that the background is quasi-static, the foreground objects are small and their motion is fast. The objective of this study is to verify the applicability of the DMD in the case of InfraRed videos of maritime scenarios with extended naval targets. In this context, the foreground is neither small, nor fast. To face that problem, we propose a spatial-multiscale approach which slightly improves the detection accuracy of the DMD-based detector. The proposed approach has been tested on a real dataset collected under real operational conditions, during an experimental activity lead by the NATO STO-CMRE in February 2022 in Portovenere (Italy). The performance has been evaluated in terms of precision and recall and has been compared to other state-of-the-art moving target detection algorithms.
In the maritime environment, Situational Awareness (SA) is a crucial task for many applications, including the defense of the naval tactical space. In this context, Electro-Optical (EO) sensors and, particularly InfraRed (IR) sensors, contribute to building the Local Area Picture (LAP). The purpose of this study is to face the challenging task of highlighting extended targets with respect to the open sea background without any prior knowledge about the size and position within the images. In this work, only single-frame object detection algorithms have been considered. As this task has been extensively explored in the three-channel color image domain, we adapted some color native state-of-the-art strategies on the IR monochromatic dimension. The algorithms have been tested on a dataset collected through a cooled Medium Wavelength (MW) sensor and an uncooled Long Wavelength (LW) sensor. The ground truth (GT) has been built through direct observation. Each technique has been then evaluated on the two sub-bands images according to broadly used performance indices.
Exploitation of temporal series of hyperspectral images is a relatively new discipline that has a wide variety of possible applications in fields like remote sensing, area surveillance, defense and security, search and rescue and so on. In this work, we discuss how images taken at two different times can be processed to detect changes caused by insertion, deletion or displacement of small objects in the monitored scene. This problem is known in the literature as anomalous change detection (ACD) and it can be viewed as the extension, to the multitemporal case, of the well-known anomaly detection problem in a single image. In fact, in both cases, the hyperspectral images are processed blindly in an unsupervised manner and without a-priori knowledge about the target spectrum. We introduce the ACD problem using an approach based on the statistical decision theory and we derive a common framework including different ACD approaches. Particularly, we clearly define the observation space, the data statistical distribution conditioned to the two competing hypotheses and the procedure followed to come with the solution. The proposed overview places emphasis on techniques based on the multivariate Gaussian model that allows a formal presentation of the ACD problem and the rigorous derivation of the possible solutions in a way that is both mathematically more tractable and easier to interpret. We also discuss practical problems related to the application of the detectors in the real world and present affordable solutions. Namely, we describe the ACD processing chain including the strategies that are commonly adopted to compensate pervasive radiometric changes, caused by the different illumination/atmospheric conditions, and to mitigate the residual geometric image co-registration errors. Results obtained on real freely available data are discussed in order to test and compare the methods within the proposed general framework.
Anomalous change detection (ACD) in HyperSpectral Images (HSIs) is a challenging task aimed at detecting a set of pixels that have undergone a relevant change with respect to a previous acquisition. Two main problems arise in ACD: a) the two multi-temporal HSIs are not radiometrically comparable because they are usually collected under different atmospheric/illumination conditions; b) it is difficult to obtain a perfect alignment of the two images especially when the sensor is mounted on airborne platforms. Several algorithms were proposed in the past to deal with the problem related to the radiometrical differences in the multi-temporal image pair. Most of them assumes the spatial stationarity of the atmospheric/illumination conditions in each of the two images and does not account for the possible presence of shadows. We propose a new ACD scheme that is robust to space-variant acquisition conditions. The ACD task is performed on two feature images extracted individually from each HSI. The feature images are selected to guarantee the robustness to the space-variant acquisition conditions in both the HSIs. They are the decision statistics provided by the RX anomaly detection algorithm applied individually to each HSI. In the paper, the advantages and the limits of the new ACD strategy are discussed and the results obtained by comparing the performance of such a strategy with that of a state-of-the-art ACD algorithm on real data are presented.
KEYWORDS: Sensors, Signal to noise ratio, Hyperspectral imaging, Data modeling, Interference (communication), Detection and tracking algorithms, Target detection, Data analysis, Signal detection, Statistical analysis
Recent studies on global anomaly detection (AD) in hyperspectral images have focused on non-parametric approaches that seem particularly suitable to detect anomalies in complex backgrounds without the need of assuming any specific model for the background distribution. Among these, AD algorithms based on the kernel density estimator (KDE) benefit from the flexibility provided by KDE, which attempts to estimate the background probability density function (PDF) regardless of its specific form. The high computational burden associated with KDE requires KDE-based AD algorithms be preceded by a suitable dimensionality reduction (DR) procedure aimed at identifying the subspace where most of the useful signal lies. In most cases, this may lead to a degradation of the detection performance due to the leakage of some anomalous target components to the subspace orthogonal to the one identified by the DR procedure. This work presents a novel subspace-based AD strategy that combines the use of KDE with a simple parametric detector performed on the orthogonal complement of the signal subspace, in order to benefit of the non-parametric nature of KDE and, at the same time, avoid the performance loss that may occur due to the DR procedure. Experimental results indicate that the proposed AD strategy is promising and deserves further investigation.
KEYWORDS: Target detection, Hyperspectral target detection, Sensors, RGB color model, Hyperspectral imaging, Short wave infrared radiation, Detection and tracking algorithms, Target acquisition, Spectral resolution, Signal to noise ratio
In surveillance applications, tracking a specific target by means of subsequent acquisitions over the monitored area is of
great interest. Multitemporal HyperSpectral Images (HSIs) are particularly suitable for this application. Multiple HSIs of
the same scene collected at different times can be exploited to detect changes using anomalous change detection (ACD)
techniques.
Moreover, spectral matching (SM) is a valuable tool for detecting the target spectrum within HSIs collected at different
times (target rediscovery – TR). Depending on the monitored area and the specific target of interest, TR can be a
challenging task. In fact, it may happen that the target has spectral features similar to those of uninteresting objects in the
scene and the use of SM techniques without additional information can generate too many misleading detections.
We introduce a new TR strategy aimed at mitigating the number of alarms encountered in complex scenarios. The
proposed detection strategy combines the SM approach with the unsupervised ACD strategy. We focus on rediscovery of
moving targets in airborne HSIs collected on the same complex area. False alarms mitigation is achieved by exploiting
both the target spectral features and the temporal variations of its position. For this purpose, SM is performed only on
those pixels that have undergone changes within multiple acquisitions. Results obtained applying the proposed scheme
on real HSIs are presented and discussed. The results show the effectiveness of the fusion of spectral and multitemporal
analysis to improve TR performance in complex scenarios.
Airborne hyperspectral imagery is valuable for military and civilian applications, such as target identification, detection
of anomalies and changes within multiple acquisitions. In target detection (TD) applications, the performance assessment
of different algorithms is an important and critical issue. In this context, the small number of public available
hyperspectral data motivated us to perform an extensive measurement campaign including various operating scenarios.
The campaign was organized by CISAM in cooperation with University of Pisa, Selex ES and CSSN-ITE, and it was
conducted in Viareggio, Italy in May, 2013. The Selex ES airborne hyperspectral sensor SIM.GA was mounted on board
of an airplane to collect images over different sites in the morning and afternoon of two subsequent days.
This paper describes the hyperspectral data collection of the trial. Four different sites were set up, representing a complex
urban scenario, two parking lots and a rural area. Targets with dimensions comparable to the sensor ground resolution
were deployed in the sites to reproduce different operating situations. An extensive ground truth documentation
completes the data collection.
Experiments to test anomalous change detection techniques were set up changing the position of the deployed targets.
Search and rescue scenarios were simulated to evaluate the performance of anomaly detection algorithms. Moreover, the
reflectance signatures of the targets were measured on the ground to perform spectral matching in varying atmospheric
and illumination conditions. The paper presents some preliminary results that show the effectiveness of hyperspectral
data exploitation for the object detection tasks of interest in this work.
The paper introduces the analysis carried out by Selex ES (SE) for the development of a third generation IRST system
based on large format MWIR sensors, separable in blue and red bands. In the feasibility study, physical constraints have
been evaluated relying on different optics and scanning options.
The goal is a system based on distributed heads to cover 360° with a resolution better than 0.3 mrad and high frame rate
that allow to take advantage of the typical atmospheric phenomena of the maritime environment as scintillation and super
and sub refraction.
Two critical aspects were investigated:
(i) the setting of an adequate scanning mechanism to assure a high frame rate and (ii) the stitching of the collected
images while maintaining the bit-depth so as to avoid abrupt changes of SNR at the seams between two subsequent
images.
Modern thermal cameras acquire IR images with a high dynamic range because they have to sense with high thermal resolution the great temperature changes of monitored scenarios in specific surveillance applications. Initially developed for visible light images and recently extended for display of IR images, high dynamic range compression (HDRC) techniques aim at furnishing plain images to human operators for a first intuitive comprehension of the sensed scenario without altering the features of IR images. In this context, the maritime scenario represents a challenging case to test and develop HDRC strategies since images collected for surveillance at sea are typically characterized by high thermal gradients among the background scene and classes of objects at different temperatures. In the development of a new IRST system, Selex ES assembled a demonstrator equipped with modern thermal cameras and planned a measurement campaign on a maritime scenario so as to collect IR sequences in different operating conditions. This has led to build up a case record of situations suitable to test HDRC techniques. In this work, a survey of HDRC approaches is introduced pointing out advantages and drawbacks with focus on strategies specifically designed to display IR images. A detailed analysis of the performance is discussed in order to address the task of visualization with reference to typical issues of IR maritime images, such as robustness to the horizon effect and displaying of very warm objects and flat areas.
The high thermal sensitivity of modern infrared (IR) cameras allows us to distinguish objects with small temperature variations. In comparison with the dynamics of standard displays, the sensed IR images have a high dynamic range (HDR). In this context, suitable techniques to display HDR images are required in order to improve the visibility of the details without introducing distortions. In the recent literature of IR image processing, a common framework to perform HDR image visualization relies on DR reduction (DRR) with a cascaded processing for local contrast adjustment (CA). In this work, a novel method, named cluster-based DRR and contrast adjustment (CDCA) is introduced for the visualization of IR images. The CDCA method is composed of two cascaded steps: (1) DRR clustering-based approach and (2) a CA module specifically designed to account for IR image features. The effectiveness of the introduced technique is analyzed using IR images of surveillance scenarios collected in different operating conditions. The results are compared with those given by other IR-HDR visualization methods and show the benefits of the proposed CDCA in terms of details enhancement, robustness against the horizon effect and presence of hot objects.
KEYWORDS: Interference (communication), Signal to noise ratio, Detection and tracking algorithms, RGB color model, Optical engineering, Sensors, Hyperspectral imaging, Cameras, Data modeling, Signal detection
A novel technique for anomalous change detection (ACD) in hyperspectral images is presented. The technique embeds a strategy robust to residual misregistration errors that typically affect data collected by airborne platforms. Furthermore, the proposed technique mitigates the negative effects due to random noise, by means of a band selection technique aimed at discarding spectral channels whose useful signal content is low compared to the noise contribution. Band selection is performed on a per-pixel basis by exploiting the estimates of the noise variance accounting also for the presence of the signal-dependent noise component. Real data collected by a new generation airborne hyperspectral camera on a complex urban scenario are considered to test the proposed method. Performance evaluation shows the effectiveness of the proposed approach with respect to a previously proposed ACD algorithm based on the same similarity measure.
In this work we propose two pixel-wise change detection techniques for unsupervised network infrastructure monitoring in SAR imagery applications. The first algorithm is inspired by a well known algorithm, named RX, proposed to deal with anomaly detection in optical images. The second algorithm is a statistical based procedure, which exploits a nonparametric approach for estimating the probability density function of the image pair. In order to test and validate the proposed methods, we analyze a spot light amplitude COSMO-SkyMed image pair at one-meter spatial resolution acquired on a complex urban scenario. Experimental results obtained on the available dataset are presented and discussed.
A novel technique for anomalous change detection in hyperspectral images is presented. It adaptively measures the spectral distance between corresponding pixels in multi-temporal images by exploiting the local estimates of the signal to noise ratio for each spectral component of the pixel under test. Different metrics have been compared, based on multidimensional angular distance. Results obtained by applying the new algorithm to real data are presented and discussed. Performance evaluation highlighted the effectiveness of the proposed approach with respect to traditional methods, resulting in a consistent improvement of both the probability of detection of changes and the capability of suppressing the background.
In this work, we focus on Anomalous Change Detection (ACD), whose goal is the detection of small changes occurred between two hyperspectral images (HSI) of the same scene. When data are collected by airborne platforms, perfect registration between images is very difficult to achieve, and therefore a residual mis-registration (RMR) error should be taken into account in developing ACD techniques. Recently, the Local Co-Registration Adjustment (LCRA) approach has been proposed to deal with the performance reduction due to the RMR, providing excellent performance in ACD tasks. In this paper, we propose a method to estimate the first and second order statistics of the RMR. The RMR is modeled as a unimodal bivariate random variable whose mean value and covariance matrix have to be estimated from the data. In order to estimate the RMR statistics, a feature description of each image is provided in terms of interest points extending the Scale Invariant Feature Transform (SIFT) algorithm to hyperspectral images, and false matches between descriptors belonging to different features are filtered by means of a highly robust estimator of multivariate location, based on the Minimum Covariance Determinant (MCD) algorithm. In order to assess the performance of the method, an experimental analysis has been carried out on a real hyperspectral dataset with high spatial resolution. The results highlighted the effectiveness of the proposed approach, providing reliable and very accurate estimation of the RMR statistics.
In remote sensing, hyperspectral sensors are effectively used for target detection and recognition because of their high
spectral resolution that allows discrimination of different materials in the sensed scene. When a priori information about
the spectrum of the targets of interest is not available, target detection turns into anomaly detection (AD), i.e. searching
for objects that are anomalous with respect to the scene background. In the field of AD, anomalies can be generally
associated to observations that statistically move away from background clutter, being this latter intended as a local
neighborhood surrounding the observed pixel or as a large part of the image. In this context, many efforts have been put
to reduce the computational load of AD algorithms so as to furnish information for real-time decision making.
In this work, a sub-class of AD methods is considered that aim at detecting small rare objects that are anomalous with
respect to their local background. Such techniques not only are characterized by mathematical tractability but also allow
the design of real-time strategies for AD. Within these methods, one of the most-established anomaly detectors is the RX
algorithm which is based on a local Gaussian model for background modeling.
In the literature, the RX decision rule has been employed to develop computationally efficient algorithms implemented
in real-time systems. In this work, a survey of computationally efficient methods to implement the RX detector is
presented where advanced algebraic strategies are exploited to speed up the estimate of the covariance matrix and of its
inverse. The comparison of the overall number of operations required by the different implementations of the RX
algorithms is given and discussed by varying the RX parameters in order to show the computational improvements
achieved with the introduced algebraic strategy.
Modern InfraRed (IR) cameras have High Dynamic Range (HDR) and excellent sensitivity. They collect images using a
number of bits much higher than the 8-bits used in displays or than those effectively perceived by the human visual
system. In IR imagery, suitable techniques to display HDR images are therefore required in order to improve the
visibility of the details while preserving the global perception of the scene. Visualization of HDR images has already
been widely studied for visible-light images. In the IR framework only a few works have been proposed which tightly
depend on the operating scenario and on the application of interest. In most cases such works have been obtained by
modifications of methods proposed for visible light images rather than by developing visualization techniques taking into account the specific mechanism of IR image formation. In the literature, the techniques developed to display HDR
images are mainly based on two approaches: contrast enhancement (CE)-oriented techniques and dynamic range
compression (DRC)-oriented techniques. The former operate on image contrast to increase the perceptibility of details.
The latter reduce the signal dynamic thus attenuating the large-scale intensity changes that do not contain relevant
information. In addition, some of the proposed methods for HDR take advantage of both the approaches. In this work, a DRC approach is considered for visualization of HDR-IR images of maritime scenarios. A new method is presented that exploits clustering information and maps the output image according to the information content of each cluster by means of a suitable weighting function. The effectiveness of the presented technique is analyzed using IR images of a maritime scenario acquired in two different case studies. Moreover, the output images obtained with the proposed method are compared with those given by techniques previously proposed for visualization of IR images. The results show the effectiveness of the proposed technique in terms of details enhancement, robustness against the horizon effect and presence of very warm objects.
We propose a novel method to estimate the first- and second-order statistics of the residual misregistration noise (RMR), which severely affects the performance of anomalous change detection techniques. Depending on the specific distribution of the RMR, the estimates allow for precisely defining the size of the uncertainty window, which is crucial when dealing with misregistration noise, as in the local coregistration adjustment approach. The technique is based on a sequential strategy that exploits the well-known scale-invariant feature transform (SIFT) algorithm cascaded with the minimum covariance determinant algorithm. The SIFT procedure was originally developed to work on gray-level images. The proposed method adapts the SIFT procedure to hyperspectral images so as to exploit the complementary information content of the numerous spectral channels, further improving the robustness of the outliers filtering by means of a highly robust estimator of multivariate location. The approach has been tested on different real hyperspectral datasets with very high spatial resolution. The analysis highlighted the effectiveness of the proposed strategy, providing reliable and very accurate estimation of the RMR statistics.
A well-established scheme for target detection in infrared (IR) surveillance systems consists of applying a suitable decision rule on the images with background clutter previously removed. Background removal is accomplished by subtracting, from the original image, the estimate of the spatially varying background signal obtained by a background estimation algorithm (BEA). The overall target detection performance is strongly influenced by the effectiveness of the employed BEA. Particularly, the BEA and its design parameters should be chosen so as to get an accurate estimate of the background signal and to avoid biases caused by the possible presence of targets (target leakage). In this work, we present a novel method for the choice and setting of the best performing background removal technique for the detection of dim point targets. The proposed procedure is based on the simulation of dim targets implanted on an acquired sample image representing the scenario of interest. The choice of the best performing BEA is made by exploring the performance of the detection scheme for several configurations of the characteristic parameters of the BEAs. The effectiveness of the BEA selection procedure is evaluated in two case studies where real image sequences acquired by IR cameras are employed. The results confirm the benefits introduced by the proposed technique. Indeed, the performance of the IR detection system with the BEA tuned according to the proposed selection criterion is improved in that the number of false alarms is reduced up to 2 orders of magnitude compared with BEAs in other common configurations.
In many civilian and military applications, early warning IR detection systems have been developed over the
years to detect long-range targets in scenarios characterized by highly structured background clutter. In this
framework, a well-established detection scheme is realized with two cascaded stages: (i) background clutter
removal, (ii) detection over the residual clutter. The performance of the whole detection system is especially
determined by the choice and setting of the background estimation algorithm (BEA). In this paper, a novel
procedure to automatically select the best performing BEA is proposed which relies on a selection criterion
(BEA-SC) where the performances of the detection system are investigated via-simulation for the available
BEAs and for different values of their parameters setting.
The robustness of the BEA-SC is investigated to examine the performance of the detection system when the
characteristics of the targets in the scene sensibly differ from the synthetic ones used in the BEA-SC, i.e. when
the BEA is not perfectly tuned to the targets of interest in the scene. We consider target detection schemes
that include BEAs based on well-established two-dimensional (2-D) filters. BEA-SC is applied to sequences of
IR images acquired on scenarios typical of surveillance applications. Performance comparison is carried out in
terms of experimental receiver operating characteristics (EX-ROC). The results show that the recently introduced
BEA-SC is robust in the detection of targets whose characteristics are those expected in typical early warning
systems.
In this work, Spectral Signature-Based Target Detection (SSBTD) as applied to airborne monitoring for surveillance and
reconnaissance of ground targets is addressed, and techniques that can help to approach in-flight processing are analyzed
from this perspective. In fact, SSBTD is a challenging task from an operating viewpoint, mainly due to the crucial
atmospheric compensation step, which is required to make the target measured reflectance comparable to the sensoracquired
radiance. Both physics-based radiative transfer modeling techniques and empirical scene-based methods are
considered for atmospheric compensation, and their applicability and adaptability to in-flight processing are discussed.
Experimental data acquired by a hyperspectral sensor operating in the Visible Near-InfraRed range are employed for
analysis. The data consist in multiple images collected during subsequent flights performed over the same scene. Such a
situation well reproduces the typical scenario of regularly monitoring an area of interest, and can, therefore, be adopted
for examining the aforementioned approaches from an in-flight applicability perspective. Target detection results are
analyzed and discussed by examining objective performance measures such as the Receiver Operating Characteristic
(ROC) curves.
Hyperspectral sensors allow a considerable improvement in the performance of a target recognition process to be achieved. This characteristic is particular interesting in a lot of military and civilian remote sensing applications, such as automatic target recognition (ATR) and surveillance of wide areas. In this framework, real time processing of the observed scenario is becoming a key issue, because it permits the operator to provide immediate assessment of the surveyed area. In the literature is presented a line-by-line real time implementation of the widely used Constrained Energy Minimization (CEM) target detector. However, experimental results show that sometimes the CEM filter produces False Alarms (FAs) corresponding to rare objects, whose spectra are angularly very different from the target signature and from the natural background classes in the image. A solution to such a problem is presented in this work: the proposed strategy is based on the decision fusion of the CEM and the SAM algorithms. Only those pixels that pass the CEM-stage are processed by the SAM algorithm. The second stage allows false alarms to be reduced by preserving most of target pixels. The fusion strategy is applied to an experimental hyperspectral data set to recognize a known green target. Detection performance is numerically evaluated and compared to the one of the classical CEM detector.
Anomaly detectors reveal the presence of objects/materials in a multi/hyperspectral image simply searching for those pixels whose spectrum differs from the background one (anomalies). This procedure can be applied directly to the radiance at the sensor level and has the great advantage of avoiding the difficult step of atmospheric correction. The most popular anomaly detector is the RX algorithm derived by Yu and Reed. It is based on the assumption that the pixels, in a region around the one under test, follow a single multivariate Gaussian distribution. Unfortunately, such a hypothesis is generally not met in actual scenarios and a large number of false alarms is usually experienced when the RX algorithm is applied in practice. In this paper, a more general approach to anomaly detection is considered based on the assumption that the background contains different terrain types (clusters) each of them Gaussian distributed. In this approach the parameters of each cluster are estimated and used in the detection process. Two detectors are considered: the SEM-RX and the K-means RX. Both the algorithms follow two steps: first, 1) the parameters of the background clusters are estimated, then, 2) a detection rule based on the RX test is applied. The SEM-RX stems from the GMM and employs the SEM algorithm to estimate the clusters' parameters; instead, the K-means RX resorts to the well known K-means algorithm to obtain the background clusters. An automatic procedure is defined, for both the detectors, to select the number of clusters and a novel criterion is proposed to set the test threshold. The performances of the two detectors are also evaluated on an experimental data set and compared to the ones of the RX algorithm. The comparative analysis is carried out in terms of experimental Receiver Operating Characteristics.
This paper addresses the problem of sub-pixel target detection in hyperspectral images assuming that the target spectral signature is deterministic and known. Hyperspectral image pixels are frequently a combination or mixture of disparate materials or components. The need of a quantitative pixel decomposition arises in many civilian and military applications such as material classification, anomaly and target detection. The Linear Mixing Model (LMM) is a widely used method in hyperspectral data analysis. It represents a mixed pixel as the sum of the spectra of known pure materials, called endmembers, weighted by their relative concentrations called abundance coefficients. However, the LMM does not take into account the natural spectral variability of the endmembers. This variability is well represented by the Stochastic Mixing Model (SMM), which provides a model for describing both mixed pixels in the scene and endmember spectral variations through a statistical model. Modeling the background spectrum as a Gaussian random vector with known mean spectrum and unknown covariance matrix, a novel SMM based Detector (ASMMD) is derived in this paper. The ASMMD theoretical performances are evaluated in a case study referring to actual conditions. The analysis is conducted by estimating the ASMMD parameters on an experimental data set acquired by the AVIRIS hyperspectral sensor and the results are compared with the ones achieved by the Adaptive Matched Subspace Detector (AMSD), based on the LMM.
Infrared surveillance systems have the task of detecting small moving targets having low signal-to-clutter ratio. Detection is usually accomplished by (1) removing the background structures from each frame and (2) integrating the target signal over consecutive frames of the residual sequence. We focus on the analysis of background removal techniques based on linear and nonlinear two-dimensional filters such as the window average, median, max-median, and max-mean. We introduce two modified versions of the window average and max-mean filters, where an appropriate guard window is used to reduce the bias due to the target. We define an ad hoc methodology to compare the different background estimation techniques on the basis of their ability to suppress background structures and to preserve the target of interest. Finally, we present and discuss the results obtained over two experimental IR sequences containing a highly structured background.
Anomaly detectors are used to reveal the presence of objects having a spectral signature that differs from the one of the surrounding background area. Since the advent of the early hyper-spectral sensors, anomaly detection has gained an ever increasing attention from the user community because it represents an interesting application both in military and civilian applications. The feature that makes anomaly detection attractive is that it does not require the difficult step of atmospheric correction which is instead needed by spectral signature based detectors to compare the received signal with the target reflectance. The aim of this paper is that of investigating different anomaly detection strategies and validating their effectiveness over a set of real hyper-spectral data. Namely, data acquired during an ad-hoc measurement campaign have been used to make a comparative analysis of the performance achieved by four anomaly detectors. The detectors considered in this analysis are denoted with the acronyms of RX-LOCAL, RX-GLOBAL, OSP-RX, and LGMRX. In the paper, we first review the statistical models used to characterize both the background and the target contributions, then we introduce the four anomaly detectors mentioned above and summarise the hypotheses under which they have been derived. Finally, we describe the methodology used for comparing the algorithm performance and present the experimental results.
A clutter removal procedure for Infra-Red (IR) naval surveillance
systems is presented. The proposed method is specifically
designed to manage the maritime scenario and it is not sensitive
to the sharp transition between sea and sky across the horizon
line. It is also effective for the removal of striping noise
which arises as a consequence of the non-uniform calibration
of the detector array. The effectiveness of the clutter
removal procedure is illustrated on a set of experimental
IR data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.