Anomalous Change Detection Research Articles

Anomalous Change Detection in Drilling Process Using Variational Autoencoder with Temperature Near Drill Edge

The different flexibility and diversity requirements for respective manufacturing units have made modern cutting tool management much more crucial and complicated, as a greater variety of tools and more frequent tool changes are required to enhance production efficiency and avoid unplanned manufacturing downtime. Developing in-process anomalous change detection methods has been identified as an essential challenge. Machine learning techniques have been widely applied in tool condition monitoring and anomalous change detection. As anomaly data is rare in manufacturing processes, supervised machine learning approaches (such as regression and classification) are not applied to the anomalous change detection problem. Rather, self-supervised machine learning (a representative type of unsupervised machine learning) is applied. This study describes a variational autoencoder (VAE) neural network and proposes a VAE-based method for tool condition monitoring and change detection in a drilling process using the temperature near a drill edge. The proposed VAE evaluates the drill tool condition based on the reconstruction error between the input temperature and its estimate per a drill unit process through the trained network. Computational simulations demonstrate that the proposed VAE network model can avoid overfitting to the anomaly data and that its expressive power is greater than that of the conventional autoencoder model.

Method for Analyzing Complex Natural Data and Detecting Anomalies

A method for analysing natural data of a complex structure based on the use of wavelet data decomposition operations and their combination with threshold functions is proposed. By using adaptive thresholds, operations for noise suppression and detection of anomalous changes in data are built. The implementation operations of the method are described and the application of neutron monitors to data is shown. We used data from the network of ground stations of neutron monitors (www.nmdb.eu), which are secondary cosmic rays. Anomalies in cosmic rays can create a radiation hazard, cause failures in radio communications, as well as defects in the operation of satellites, leading to loss of orientation and destruction. Therefore, the task of timely diagnosis of such events is relevant. The application of the method made it possible to clearly detect and evaluate anomalous changes in cosmic ray data that were observed during disturbed periods in the magnetosphere.

Sketched Multiview Subspace Learning for Hyperspectral Anomalous Change Detection

In recent years, multi-view subspace learning has been garnering increasing attention. It aims to capture the inner relationships of the data that are collected from multiple sources by learning a unified representation. In this way, comprehensive information from multiple views is shared and preserved for the generalization processes. As a special branch of temporal series hyperspectral image (HSI) processing, the anomalous change detection task focuses on detecting very small changes among different temporal images. However, when the volume of datasets is very large or the classes are relatively comprehensive, existing methods may fail to find those changes between the scenes, and end up with terrible detection results. In this paper, inspired by the sketched representation and multi-view subspace learning, a sketched multi-view subspace learning (SMSL) model is proposed for HSI anomalous change detection. The proposed model preserves major information from the image pairs and improves computational complexity by using a sketched representation matrix. Furthermore, the differences between scenes are extracted by utilizing the specific regularizer of the self-representation matrices. To evaluate the detection effectiveness of the proposed SMSL model, experiments are conducted on a benchmark hyperspectral remote sensing dataset and a natural hyperspectral dataset, and compared with other state-of-the art approaches.

Multi-sensor anomalous change detection in remote sensing imagery

Combining multiple satellite remote sensing sources provides a far richer, more frequent view of the earth than that of any single source; the challenge is in distilling these petabytes of heterogeneous sensor imagery into meaningful characterizations of the imaged areas. Meeting this challenge requires effective algorithms for combining multi-modal imagery over time to identify subtle but real changes among the intrinsic data variation. Here, we implement a joint-distribution framework for multi-sensor anomalous change detection (MSACD) that can effectively account for these differences in modality, and does not require any signal resampling of the pixel measurements. This flexibility enables the use of satellite imagery from different sensor platforms and modalities. We use multi-year construction of the SoFi Stadium in California as our testbed, and exploit synthetic aperture radar imagery from Sentinel-1 and multispectral imagery from both Sentinel-2 and Landsat 8. We show results for MSACD using real imagery with implanted, measurable changes, as well as real imagery with real, observable changes, including scaling our analysis over multiple years.

Dynamic features of cardiac vector as alternative markers of drug-induced spatial dispersion

IntroductionThe abnormal amplification of ventricular repolarization dispersion (VRD) has long been linked to proarrhythmia risk. Recently, the measure of VRD through electrocardiogram intervals has been strongly questioned. The search for an efficient and non-invasive surrogate marker of drug-induced dispersion effects constitute an urgent research challenge. MethodsHerein, drug-induced ventricular dispersion is generated by d-Sotalol supply in an In-vitro rabbit heart model. A cilindrical chamber simulates the thorax and a multi-electrode net is used to obtain spatial electrocardiographic signals. Cardiac vector dynamics is captured by novel velocity cardiomarkers obtained by quaternion methods. Through statistical analysis and machine learning technics, we compute potential dispersion markers that could define proarrhythmic risk. ResultsThe cardiomarkers with the greatest statistical significance, both obtained from the electrical cardiac vector, were: the QTω, which is the difference between first and last maxima of angular velocity and λ21vT, the roundness of linear velocity. When comparing with the performance of the current standards (89%), this pair was able to correctly separate 21 out of 22 experiments achieving a performance of 95%. Moreover, the QTω computes in a much more robust basis the QT interval, the current index for drug regulation. DiscussionThese velocity markers circumvent the problems of accuratelly finding the fiducial points such as the always tricky T-wave end. Given the high performance they achieved, it is provided a promising outcome for future applications to the detection of anomalous changes of heterogeneity that may be useful for the purposes of torsadogenic toxicity studies.

SLiX: A GIS Toolbox to Support Along-Stream Knickzones Detection through the Computation and Mapping of the Stream Length-Gradient (SL) Index

The stream length-gradient (SL) index is widely used in geomorphological studies aimed at detecting knickzones, which are extensive along-stream deviations from the typical concave-up shape assumed for stream longitudinal profiles at steady-state conditions. In particular, SL was practical for identifying anomalous gradients along bedrock stream channels in mountainous catchments. This work presents the GIS toolbox SLiX designed to extract values of the SL index, starting from Digital Elevation Models (DEMs). SLiX is also suitable for the spatial analysis of the SL values, allowing for the identification of landscape portions where anomalous high values of SL occur and, consequently, those catchment sectors where stream channels show peaks in the erosional dynamic. The SLiX main outputs are (i) point shapefiles containing, among stream channels attributes, the extracted values of SL along the stream network analyzed, and (ii) SL anomaly maps in GeoTIFF format, computed through the Hotspot and Cluster Analysis (HCA), that permit the detection of the catchment sectors where the major SL anomalies occur and consequently the principal knickzones. The application of the proposed tool within an experimental catchment located in the Northern Apennines of Italy demonstrated the proper functionality and the potential of its use for different geomorphological and environmental studies. The accurate and cost-effective detection of anomalous changes in stream gradient ensured by SLiX is of great interest and can be useful for studies aimed at unravelling the Earth processes responsible of their formation (e.g., active hillslope processes, such as landslides directly interacting with the streambed, presence of geological structures, and meander cut-off). The applications of SLiX have clear implications for preliminary analyses, at a regional scale in different morpho-climatic contexts, for the hydrological management of river basins and/or to prevent geological hazards related to the fluvial erosional dynamics.

Efficient Kernel Cook's Distance for Remote Sensing Anomalous Change Detection

Detecting anomalous changes in remote sensing images is a challenging problem, where many approaches and techniques have been presented so far. We rely on the standard field of multivariate statistics of diagnostic measures, which are concerned about the characterization of distributions, detection of anomalies, extreme events, and changes. One useful tool to detect multivariate anomalies is the celebrated Cook's distance. Instead of assuming a linear relationship, we present a novel kernelized version of the Cook's distance to address anomalous change detection in remote sensing images. Due to the large computational burden involved in the direct kernelization, and the lack of out-of-sample formulas, we introduce and compare both random Fourier features and Nystrom implementations to approximate the solution. We study the kernel Cook's distance for anomalous change detection in a chronochrome scheme, where the anomalousness indicator comes from evaluating the statistical leverage of the residuals of regressors between time acquisitions. We illustrate the performance of all algorithms in a representative number of multispectral and very high resolution satellite images involving changes due to droughts, urbanization, wildfires, and floods. Very good results and computational efficiency confirm the validity of the approach.

Kernel Anomalous Change Detection for Remote Sensing Imagery

Anomalous change detection (ACD) is an important problem in remote sensing image processing. Detecting not only pervasive but also anomalous or extreme changes has many applications for which methodologies are available. This paper introduces a nonlinear extension of a full family of anomalous change detectors. In particular, we focus on algorithms that utilize Gaussian and elliptically contoured (EC) distribution and extend them to their nonlinear counterparts based on the theory of reproducing kernels' Hilbert space. We illustrate the performance of the kernel methods introduced in both pervasive and ACD problems with real and simulated changes in multispectral and hyperspectral imagery with different resolutions (AVIRIS, Sentinel-2, WorldView-2, and Quickbird). A wide range of situations is studied in real examples, including droughts, wildfires, and urbanization. Excellent performance in terms of detection accuracy compared to linear formulations is achieved, resulting in improved detection accuracy and reduced false-alarm rates. Results also reveal that the EC assumption may be still valid in Hilbert spaces. We provide an implementation of the algorithms as well as a database of natural anomalous changes in real scenarios http://isp.uv.es/kacd.html.

An online graph-based anomalous change detection strategy for unsupervised video surveillance

Due to various accidents and crime threats to an unspecified number of people, many surveillance technologies have been studied as an interest in individual security continues to increase throughout society. In particular, intelligent video surveillance technology is one of the most active research areas in the field of surveillance; this popularity has been spurred by recent advances in computer vision/image processing and machine learning. The main goal is to automatically detect, recognize, and analyze objects of interest from collected sensor information and then efficiently extract/utilize this useful information, such as by detecting abnormal events or intruders and recognizing objects. Anomalous event detection is a key component of security, and many existing anomaly detection algorithms rely on a foreground subtraction process to detect changes in the foreground scene. By comparing input image frames with a reference image, changed areas of the image can be efficiently detected. However, this technique can be insensitive to static changes and has difficulties in noisy environments since it depends on a reference image. We propose a new strategy for improved dynamic/static change detection that complements the weak points of existing detection methods, which have low robustness in noisy environments. To achieve this goal, we employed a self-organizing map (SOM) for data clustering and regarded the cluster distribution of neurons, represented by the weight of the optimized SOM, as a directed graph problem. We then applied the shortest path algorithm to recognize anomalous events. The real-time monitoring capability of the proposed change detection system was verified by applying it to self-produced test data and the CDnet-2014 dataset. This system showed robustness against noise that was superior to other surveillance systems in various environments.

Hyperspectral anomalous change detection based on joint sparse representation

Anomalous change detection aims at finding small but unusual changes from the unchanged or generally changed background in multi-temporal hyperspectral remote sensing images. It is important to model the spectral variations of background so as to highlight the anomalous changes. In this paper, we proposed a hyperspectral anomalous change detection method based on joint sparse representation. A background dictionary is constructed by the randomly selected pixels in the stacked multi-temporal images. The local neighborhood pixels surrounding the test pixel are presented by joint sparse representation with the background dictionary. Thus, the change tendencies in the local background are modeled by the active dictionary bases. The difference of separate reconstruction coefficients of the test pixel with the active bases will reflect the probability to be anomalously changed. Three detectors, which are coefficient difference, Mahalanobis distance of coefficient difference and multi-temporal residual analysis, are proposed to measure the change intensity. Two experiments with the datasets of “Viareggio 2013 Trial” and one Hyperion indicate that the proposed method obtains better performances than the comparative methods.

Recurrence statistics for anomalous diffusion regime change detection

For many real-time series, specific behaviors are observed where the character of the time series changes over time. This temporal evolution may indicate that some properties of the data evolve or fluctuate. One can find such problems in many different applications including physical and biological experiments as well as in technical diagnostics. From the mathematical point of view, this complexity can be considered as a segmentation problem, i.e. extraction of the homogeneous parts from the original data. Most segmentation methods assume that a simple characteristic of the time series changes, for example the mean or the variance. However, many physical applications involve a more complex situation dealing with transient statistics. Here, a new technique of the critical change point detection is introduced for the case when the data consist of anomalous diffusion processes with transient anomalous diffusion exponents. The precise mathematical formulation of a new statistics based on recurrence statistics is provided. The proposed recurrence analysis counts the number of data points falling into the appropriate circle built from consecutive observations. This approach proves to be helpful in recognizing subdiffusive and superdiffusive regions, which characterize anomalous diffusion behaviors. The main characteristics of the recurrence statistics are presented and the application to the segmentation problem is described. The effectiveness of the proposed technique is validated for a family of classical anomalous diffusive models, namely fractional Brownian motion. Finally, the methodology is applied to biological data exhibiting anomalous diffusion behavior with transient anomalous diffusion exponents.

Introductory view of anomalous change detection in hyperspectral images within a theoretical gaussian framework

Exploitation of temporal series of hyperspectral images is a relatively new discipline that has gained a lot of attention from the image processing scientific community. In this paper, we consider the specific problem of anomalous change detection (ACD) in hyperspectral images and 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. We introduce the ACD problem using an approach based on the statistical decision theory and we derive a common framework including different ACD approaches. Far from being inclusive of all the methods proposed in the literature, this tutorial 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. The unification of different approaches under a single rigorous statistical scheme provides both a tutorial overview of ACD techniques, and a useful instrument for researchers already familiar with the ACD problem. Dedicated preprocessing methods aimed at improving the robustness of the ACD process are also discussed. Real data are exploited to test and compare the presented methods, highlighting advantages and drawbacks of each approach. The tutorial aspect of the paper has suggested the use of a freely available data set. This should hopefully motivate the interested reader to experiment with the processing methods and performance evaluation chain presented herein.

Hyperspectral Airborne “Viareggio 2013 Trial” Data Collection for Detection Algorithm Assessment

For many years, the entire target detection scientific community has felt the urge for fully ground-truthed hyperspectral imagery data sets expressly released for testing and comparing detection algorithms. Although a few excellent data-sharing efforts have been carried out in the last decade, the use of either restricted or not well ground-truthed imagery still remains a common practice in the target detection literature. In this paper, we provide an overview of a new hyperspectral data set that we release to the scientific community with the specific goal of fostering unbiased comparison and scientific discussions of anomaly detection (AD), object detection, and anomalous change detection (ACD) algorithms. The data set is fully ground-truthed and documented and includes scenarios and experiments specifically conceived for detection algorithm comparison and benchmarking. Insights about the various possible data exploitation tasks are provided by making reference to noise estimation and reduction, AD, spectral signature-based target detection (SSBTD), and ACD. Experimental results concerning ACD and SSBTD are presented and highlight the usefulness of this new data set from the data sharing and algorithmic comparison perspectives.

Theoretical foundations of NRL spectral target detection algorithms.

The principal spectral detection algorithms developed at the Naval Research Laboratory (NRL) over the past 20 years for use in operational systems are described. These include anomaly detectors, signature-based methods, and techniques for anomalous change detection. Newer derivations are provided that have motivated more recent work. Mathematical methods facilitating the use of forward models for the prediction of spectral signature statistics are described and a detection algorithm is derived for ocean surveillance that is based on principles of clairvoyant fusion.

Robust technique for anomalous change detection in airborne hyperspectral imagery based on automatic and adaptive band selection

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.

Global variation of ULF geomagnetic fields and detection of anomalous changes at a certain observatory using reference data

AbstractBy using multiple reference stations, we have developed a method to get reliable ULF global geomagnetic variations. This background is extremely useful for detecting local anomalous behaviors. In this paper we report on variable tools developed to identify the anomalies in two frequency ranges: daily variations and variations of 10‐ to 1000‐second span. For estimating background daily variations, the periodical model has been applied for data observed at three reference stations and a study station. Comparison between the first principal component of the periodical data from the reference stations and the periodical data derived from the target station generally provides high correlation. For data with 100‐second periods after wavelet filtering, the nighttime energy variations have been investigated among three reference stations and a study station. Similar principal component analysis as the diurnal variation has been performed and results also show high correlation between the variation at the target and the global background. These tendencies suggest that the two proposed methods are effective in automatically identifying the anomalous patterns. Examining the original data, we can obtain details of waveforms and distinguish whether the anomalies are related to underground activities or simply to some artificial noises. © 2012 Wiley Periodicals, Inc. Electr Eng Jpn, 182(3): 9–18, 2013; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/eej.22299

Local Coregistration Adjustment for Anomalous Change Detection

We describe an approach for improving the robustness to misregistration of pixel-wise anomalous change detection (ACD) algorithms. The aim of ACD is to distinguish actual anomalous changes from the irrelevant incidental differences that occur throughout the scene. For such change detection to be effective, it is important that corresponding pixels in the two images of interest correspond to the same location in the scene. Indeed, one of the most confounding sources of incidental differences is the inevitable imprecision in the coregistration of the two images. We address this with small local adjustments to the coregistration which leads to a modified misregistration-insensitive measure of anomalousness. Several variants are considered, and the resulting performance improvements are evaluated using both real and simulated changes, and real and simulated misregistration.

A SEMIAUTOMATIC ANOMALOUS CHANGE DETECTION METHOD FOR MONITORING AIMS

Abstract. In the framework of the development of a web site devoted to the documentation and monitoring of the cultural heritage (above all monumental buildings), a semiautomatic method for anomalous change detection has been set up. The method uses the grouping of the image difference values, to detect both small and diffused changes. Three tests are described to evaluate the performances of the method. The results show that good performances are obtained in case of cloudy days, while the presence of shadows requires the interpretation of an operator to distinguish true and false changes.

Residual misregistration noise estimation in hyperspectral anomalous change detection

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.

Sparse Matrix Transform for Hyperspectral Image Processing

A variety of problems in remote sensing require that a covariance matrix be accurately estimated, often from a limited number of data samples. We investigate the utility of several variants of a recently introduced covariance estimator-the sparse matrix transform (SMT), a shrinkage-enhanced SMT, and a graph-constrained SMT-in the context of several of these problems. In addition to two more generic measures of quality based on likelihood and the Frobenius norm, we specifically consider weak signal detection, dimension reduction, anomaly detection, and anomalous change detection. The estimators are applied to several hyperspectral data sets, including some randomly rotated data, to elucidate the kinds of problems and the kinds of data for which SMT is well or poorly suited. The SMT is based on the product of <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> pairwise coordinate (Givens) rotations, and we also introduce and compare two novel approaches for estimating the most effective choice for <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> .