Accurate Background Model Research Articles

High-dimensional Bayesian likelihood normalisation for CRESST's background model

Using CaWO4 crystals as cryogenic calorimeters, the CRESST experiment searches for nuclear recoils caused by the scattering of potential Dark Matter particles. A reliable identification of a potential signal crucially depends on an accurate background model. In this work, we introduce an improved normalisation method for CRESST's model of electromagnetic backgrounds, which is an important technical step towards developing a more accurate background model. Spectral templates based on Geant4 simulations are normalised via a Bayesian likelihood fit to experimental background data. Contrary to our previous work, no explicit assumption of partial secular equilibrium is required a priori, which results in a more robust and versatile applicability. This new method also naturally considers the correlation between all background components. Due to these purely technical improvements, the presented method has the potential to explain up to 82.7 % of the experimental background within [1 keV,40 keV], an improvement of at most 18.6 % compared to our previous method. The actual value is subject to ongoing validations of the included physics.

Attention-Aware Spectral Difference Representation for Hyperspectral Anomaly Detection

Hyperspectral Anomaly Detection (HAD) aims to detect the pixel or target whose spectral characteristics are significantly different from the surrounding pixels or targets. The effectiveness of reconstructing the background model is an essential element affecting the improvement of the HAD performance. This paper proposes a Hyperspectral Anomaly Detection method based on Attention-aware Spectral Difference Representation (HAD-ASDR) to reconstruct more accurate background models by using the generated noise distribution matchable to the background as input. The proposed HAD-ASDR mainly includes three modules: Attention-aware Spectral Difference Representation Module (ASDRM), Convolutional Auto-Encoder based Background Reconstruction Module (CAE-BRM) and Joint Spectrum Intensity and Angle based Anomaly Detection Module (JSIA-ADM). First, inspired by Generative Adversarial Network (GAN), ASDRM is proposed to generate a noise distribution that better matches the background by the attention mechanism and the different operation. Then, CAE-BRM is employed to reconstruct the accurate background using the generated noise distribution as input and the convolutional auto-encoder with skip connections. Finally, JSIA-ADM is presented to detect anomalies more accurately by calculating the reconstructed errors from both spectral intensity and angle perspectives. The proposed HAD-ASDR has been verified on five data sets and achieves better or comparable HAD results compared to six other comparison methods. The average AUC of HAD-ASDR on these five data sets is 0.9817 higher than that of the comparison methods, resulting in an improvement of 0.0253. The experimental results demonstrate its superior performance and stability.

AIBM: Accurate and Instant Background Modeling for Moving Object Detection

Detecting moving objects has been widely studied since it plays vital many applications, such as video surveillance and intelligent transportation systems. It is necessary to accurately differentiate the foreground and the background in this technology to analyze object motions in the scene. Conventional detection methods use many reference frames to model the background to detect moving objects; however, the detection is inaccurate when immediate changes occur in the scene because the instant update of the background model is impossible. To be robust illumination changes and dynamic backgrounds, we propose an accurate and instant background modeling (AIBM) method that inpaints the background with superpixels and enhances it in detail with pixel-levels. Unlike the previous approaches, the proposed AIBM method utilizes spatio-temporal information of only two consecutive frames to eliminate the lengthy initialization and update period of the model. In this paper, we illustrate the importance of accurate and instant background modeling in detecting moving objects. The performance of our method is evaluated with three benchmark datasets (CDnet2014, LASIESTA, and SBI). The experimental results show that our AIBM method is robust to sudden changes in the scene and outperforms the other conventional methods with F-measure of 0.8911 and 0.9682 in detection accuracy in CDNet2014 and LASIESTA datasets, respectively. The accuracy of the generated background is also measured on the SBI dataset, which demonstrates the importance of high-quality background modeling.

Efficient and Robust Background Modeling with Dynamic Mode Decomposition

A large number of modern video background modeling algorithms deal with computational costly minimization problems that often need parameter adjustments. While in most cases spatial and temporal constraints are added artificially to the minimization process, our approach is to exploit Dynamic Mode Decomposition (DMD), a spectral decomposition technique that naturally extracts spatio-temporal patterns from data. Applied to video data, DMD can compute background models. However, the original DMD algorithm for background modeling is neither efficient nor robust. In this paper, we present an equivalent reformulation with constraints leading to a more suitable decomposition into fore- and background. Due to the reformulation, which uses sparse and low-dimensional structures, an efficient and robust algorithm is derived that computes accurate background models. Moreover, we show how our approach can be extended to RGB data, data with periodic parts, and streaming data enabling a versatile use.

Parallel and Distributed Computing for Anomaly Detection From Hyperspectral Remote Sensing Imagery

Anomaly detection from remote sensing images is to detect pixels whose spectral signatures are different from their background. Anomalies are often man-made targets. With such target signatures being unknown, anomaly detection has many important applications, such as water quality monitoring, crop stress surveying, and law enforcement-related uses, where prior information of targets is often unavailable. The key to success is accurate background modeling. Anomaly detection from remote sensing images is challenging because spatial coverage is very large and the background is highly heterogeneous. For pixel-based anomaly detection, computing cost in background modeling and a spatial-convolution-type detection process is very expensive. Thus, parallel and distributed computing is critical in reducing execution time, which can fit the need for real-time or near real-time detection from airborne and spaceborne platforms in support of immediate decision-making. This article reviews the recent advances in anomaly detection from hyperspectral remote sensing images and their implementation using parallel and distributed systems. The classical methods, i.e., the Reed-Xiaoli (RX) algorithm and its variants, including its real-time processing version, are illustrated in commodity graphic processing units (GPUs), cloud, and field-programmable gate array (FPGA) implementations. Practical issues and future development trends are also discussed.

Adaptive Feature Fusion and Spatio-Temporal Background Modeling in KDE Framework for Object Detection and Shadow Removal

Moving cast shadow identification and extraction are the commonly encountered problems in visual surveillance applications. In the video object detection problem, a shadow is a category of the dynamic entity which needs to be removed for accurate detection of moving objects. In this paper, we have proposed a new scheme to detect the moving object in video frames while removing the shadow. The proposed scheme is based on the notion of background modeling and model learning. The background is modeled by the proposed Spatio-Temporal Kernel Density Estimation (ST-KDE) based model, but the model learning takes place in online mode in the fused feature space. In the fusion process, the Local Binary Pattern (LBP) features of the ST-KDE model of a frame are determined and are fused probabilistically with the Gabor features of the corresponding original frame. To achieve accurate background modeling, weights in the probabilistic fusion are adaptively determined from the scene dynamics. Background model learning is pixel-based where model histograms learn the background with every temporal frame. Learning and classification of the fused feature frames happen simultaneously with frame by frame. The classified frame thus obtained contains the object with some residual shadow which is eliminated by entropy map and thresholding. The main novelties of our paper are: (i) ST-KDE based background modeling, (ii) Determination of the weights of the fusion process in an adaptive framework and, (iii) online background model learning in feature space. The proposed modeling approach has been tested successfully with different video sequences considered from CDnet, Lasiesta, ATON-CVRR, SRD, and ISTD databases. The performance metrics of the proposed scheme have been compared with many existing methods and it has been found that the proposed method exhibits improved performance.

A gradient-based Markov chain Monte Carlo method for full-waveform inversion and uncertainty analysis

Traditional full-waveform inversion (FWI) methods only render a “best-fit” model that cannot account for uncertainties of the ill-posed inverse problem. Additionally, local optimization-based FWI methods cannot always converge to a geologically meaningful solution unless the inversion starts with an accurate background model. We seek the solution for FWI in the Bayesian inference framework to address those two issues. In Bayesian inference, the model space is directly probed by sampling methods such that we obtain a reliable uncertainty appraisal, determine optimal models, and avoid entrapment in a small local region of the model space. The solution of such a statistical inverse method is completely described by the posterior distribution, which quantifies the distributions for parameters and inversion uncertainties. To efficiently sample the posterior distribution, we introduce a sampling algorithm in which the proposal distribution is constructed by the local gradient and the diagonal approximate Hessian of the local log posterior. Our algorithm is called the gradient-based Markov chain Monte Carlo (GMCMC) method. The GMCMC FWI method can quantify inversion uncertainties with estimated posterior distribution given sufficiently long Markov chains. By directly sampling the posterior distribution, we obtain a global view of the model space. Theoretically speaking, statistical assessments do not depend on starting models. Our method is applied to the 2D Marmousi model with the frequency-domain FWI setting. Numerical results suggest that our method can be readily applied to 2D cases with affordable computational efforts.

Vehicle Detection and Counting Using Adaptive Background Model Based on Approximate Median Filter and Triangulation Threshold Techniques

Background subtraction method is widely used for vehicle detection. One of the issues in this method is to find a suitable and accurate background model that works in all conditions. Moreover, setting an appropriate threshold value to discriminate between the moving objects and stationary background plays a crucial role in increasing the detection performance. In this paper, an adaptive background model combined with an adaptive threshold method is proposed. It is demonstrated that the proposed method can efficiently differentiate between moving vehicles and background in urban roads under different weather conditions (i.e., normal, rainy, foggy, and snowy). Comparisons between the proposed method and other methods, such as the adaptive local threshold (ALT) and the three frame-differencing methods show the potential of our approach. The experimental results show that the proposed method increases the average recall value by 16.4% and the average precision value by 21.7% in comparison to the ALT method with a negligible increase in the processing time.

CVABS: moving object segmentation with common vector approach for videos

Background modelling is a fundamental step for several real‐time computer vision applications that requires security systems and monitoring. An accurate background model helps to detect the activity of moving objects in the video. In this work, the authors have developed a new subspace‐based background‐modelling algorithm using the concept of common vector approach (CVA) with Gram–Schmidt orthogonalisation. Once the background model that involves the common characteristic of different views corresponding to the same scene is acquired, a smart foreground detection and background updating procedure is applied based on dynamic control parameters. A variety of experiments is conducted on different problem types related to dynamic backgrounds. Several types of metrics are utilised as objective measures and the obtained visual results are judged subjectively. It was observed that the proposed method stands successfully for all problem types reported on CDNet2014 dataset by updating the background frames with a self‐learning feedback mechanism.

Background Modeling in the Fourier Domain for Maritime Infrared Target Detection

The estimation of the sea background from maritime infrared video sequences is necessary for target detection. It is challenging to obtain an accurate background model when the scene is a complex and fluctuating sea surface. However, the amplitude spectrum sequences at each frequency point of the pure seawater frames in the Fourier domain are more stable than the gray value sequences of each pixel in the spatial domain. Thus, the background is modeled with a Gaussian distribution in the Fourier domain with the mean and variance adapted over time. In addition, the sea background dynamics are introduced by the variance of the amplitude spectrum sequence, and the dynamic Gaussian discriminant coefficient is set up for each frequency point. Two target discrimination flags are presented based on the background dynamics and Gaussian discriminant process to extract the target more accurately. Furthermore, the entropy filter in the Fourier domain is designed to enhance the target and suppress the sea clutter. The proposed method is successfully tested over several maritime infrared video sequences and has better detection effects compared with several existing state-of-the-art methods.

ECG anomaly class identification using LSTM and error profile modeling

Automatic diagnosis of cardiac events is a current problem of interest in which deep learning has shown promising success. We have earlier reported the use of Long Short Term Memory (LSTM) networks-trained on normal ECG patterns-to the detection of anomalies from the prediction errors for real-time diagnostic applications. In this work, we extend our anomaly detection algorithm by introducing a second stage predictor that can identify the actual anomaly class from the error outputs of the first stage model. Results from seven types of anomalies have been presented including Atrial Premature Contraction (APC), Paced Beat (PB), Premature Ventricular Contraction (PVC), Right Bundle Branch Block (RBBB), Ventricular Bigeminy (VB), Ventricular Couplets (VCs) and Ventricular Tachycardia (VT). To optimize anomaly class prediction performance, multiple choices of second stage models such as multilayer perceptron (MLP), support vector machine (SVM) and logistic regression have been employed. A featurization scheme for LSTM prediction errors in the form of overall summaries has been proposed and a successful predictor for the same was developed with good performance. Our results indicate that the error vectors represented by their summary features carry useful predictive information about actual ECG anomaly type. We discuss how the accuracy scores without attention to inherent class imbalances and paucity of data instances may produce misleading performance estimates and hence accurate background models are needed to estimate true predictive performance of multi-class predictors such as those presented in this work. The training data sets and related resources for this study are provided at http://ecg.sciwhylab.org.

Efficient background subtraction for thermal images using reflectional symmetry pattern (RSP)

Nowadays, thermal image processing has gained more attention. Thermal camera’s cost is decreasing, and so many real-time applications use thermal cameras since they have an ability to detect objects in darkness and track objects in the video. A background subtraction approach using Reflectional Symmetry Pattern (RSP) for thermal image background subtraction is proposed based on the assumption that the geometric reflectional symmetrical pattern of each of the objects (person) is much lower than the surrounding background. Reflectional symmetrical texture pattern can be used to create a subspace from the result of frame differencing approach. Statistical parameters such as VP (Vector Product), VD (Vector Direction) can be used to create an accurate background model. As a result, the proposed scheme can provide a high precision and less error rate to meet the requirements of object detection from real-time thermal videos.

GPU-Accelerated Foreground Segmentation and Labeling for Real-Time Video Surveillance

Real-time and accurate background modeling is an important researching topic in the fields of remote monitoring and video surveillance. Meanwhile, effective foreground detection is a preliminary requirement and decision-making basis for sustainable energy management, especially in smart meters. The environment monitoring results provide a decision-making basis for energy-saving strategies. For real-time moving object detection in video, this paper applies a parallel computing technology to develop a feedback foreground–background segmentation method and a parallel connected component labeling (PCCL) algorithm. In the background modeling method, pixel-wise color histograms in graphics processing unit (GPU) memory is generated from sequential images. If a pixel color in the current image does not locate around the peaks of its histogram, it is segmented as a foreground pixel. From the foreground segmentation results, a PCCL algorithm is proposed to cluster the foreground pixels into several groups in order to distinguish separate blobs. Because the noisy spot and sparkle in the foreground segmentation results always contain a small quantity of pixels, the small blobs are removed as noise in order to refine the segmentation results. The proposed GPU-based image processing algorithms are implemented using the compute unified device architecture (CUDA) toolkit. The testing results show a significant enhancement in both speed and accuracy.

MADGiC: a model-based approach for identifying driver genes in cancer.

Motivation: Identifying and prioritizing somatic mutations is an important and challenging area of cancer research that can provide new insights into gene function as well as new targets for drug development. Most methods for prioritizing mutations rely primarily on frequency-based criteria, where a gene is identified as having a driver mutation if it is altered in significantly more samples than expected according to a background model. Although useful, frequency-based methods are limited in that all mutations are treated equally. It is well known, however, that some mutations have no functional consequence, while others may have a major deleterious impact. The spatial pattern of mutations within a gene provides further insight into their functional consequence. Properly accounting for these factors improves both the power and accuracy of inference. Also important is an accurate background model.Results: Here, we develop a Model-based Approach for identifying Driver Genes in Cancer (termed MADGiC) that incorporates both frequency and functional impact criteria and accommodates a number of factors to improve the background model. Simulation studies demonstrate advantages of the approach, including a substantial increase in power over competing methods. Further advantages are illustrated in an analysis of ovarian and lung cancer data from The Cancer Genome Atlas (TCGA) project.Availability and implementation: R code to implement this method is available at http://www.biostat.wisc.edu/ kendzior/MADGiC/.Contact: kendzior@biostat.wisc.eduSupplementary information: Supplementary data are available at Bioinformatics online.

Tracking Vehicles Through Shadows and Occlusions in Wide-Area Aerial Video

We present a new approach for simultaneous tracking and segmentation of multiple targets in low frame rate aerial video. We focus on building an accurate background model that accounts for both global camera motion and moving objects in the scene. We then apply a probabilistic framework for simultaneous tracking and segmentation that incorporates this background model. By using a background model, we are able to track the object through dramatic appearance changes caused by shadows and lighting changes. Furthermore, the incorporation of segmentation into the tracking algorithm reduces the impact of common tracking problems, such as drift and partial occlusion. Results are shown for the Columbus Large Image Format (CLIF) 2007 data set, demonstrating successful tracking under significant occlusions, target appearance changes, and near similar moving objects.

Case-based background modeling: associative background database towards low-cost and high-performance change detection

Background modeling and subtraction is an essential task in video surveillance applications. Many researchers have discussed about an improvement of performance of a background model, and a reduction of memory usage or computational cost. To adapt to background changes, a background model has been enhanced by introducing various information including a spatial consistency, a temporal tendency, etc. with a large memory allocation. Meanwhile, an approach to reduce a memory cost cannot provide better accuracy of a background subtraction. To tackle the trade-off problem, this paper proposes a novel framework named "case-based background modeling". The characteristics of the proposed method are (1) a background model is created, or removed when necessary, (2) case-by-case model sharing by some of the pixels, (3) pixel features are divided into two groups, one for model selection and the other for modeling. These approaches realize a low-cost and high accurate background model. The memory usage and the computational cost could be reduced by half of a traditional method and the accuracy was superior to the method.

Pitfalls in prestack inversion of merged seismic surveys

Modern 3D seismic surveys are often of such good quality and 3D interpretation packages so user-friendly that seismic interpretation is no longer exclusively carried out by geophysicists. This ease-of-use has also been extended to more quantitative workflows, such as 3D prestack inversion, putting it in the hands of the “nonexpert” — be it geologist, engineer, or new-hire geophysicist. Indeed, given good quality input seismic data, almost any interpreter who can generate good well ties and define an accurate background model of P-impedance, S-impedance, and density can generate a quality prestack inversion. Two of the authors are new geophysicists who fell into the prestack inversion “pit.” Fortunately, they were able to recognize that something was wrong. We applied prestack inversion to gathers that were carefully reprocessed by a major service company. The problem, however, was not with the processing, but with our lack of understanding of the input legacy data that formed part of a larger “megamerge” survey. Not all of the surveys that were merged had the same offset range. In the migration step, gaps in long offsets of the older surveys were not muted. Migration noise from newer surveys was allowed to fill this space. We share our initial workflow and suspicious results. We also clarify the meaning of “fold” and “offset” for prestack-migrated gathers. In addition to presenting some QC tools useful in analyzing megamerge surveys, we show how, by limiting the offsets used in our prestack inversion, we obtain less aggressive but still useful results.

Models of Somatic Hypermutation Targeting and Substitution Based on Synonymous Mutations from High-Throughput Immunoglobulin Sequencing Data

Analyses of somatic hypermutation (SHM) patterns in B cell immunoglobulin (Ig) sequences contribute to our basic understanding of adaptive immunity, and have broad applications not only for understanding the immune response to pathogens, but also to determining the role of SHM in autoimmunity and B cell cancers. Although stochastic, SHM displays intrinsic biases that can confound statistical analysis, especially when combined with the particular codon usage and base composition in Ig sequences. Analysis of B cell clonal expansion, diversification, and selection processes thus critically depends on an accurate background model for SHM micro-sequence targeting (i.e., hot/cold-spots) and nucleotide substitution. Existing models are based on small numbers of sequences/mutations, in part because they depend on data from non-coding regions or non-functional sequences to remove the confounding influences of selection. Here, we combine high-throughput Ig sequencing with new computational analysis methods to produce improved models of SHM targeting and substitution that are based only on synonymous mutations, and are thus independent of selection. The resulting “S5F” models are based on 806,860 Synonymous mutations in 5-mer motifs from 1,145,182 Functional sequences and account for dependencies on the adjacent four nucleotides (two bases upstream and downstream of the mutation). The estimated profiles can explain almost half of the variance in observed mutation patterns, and clearly show that both mutation targeting and substitution are significantly influenced by neighboring bases. While mutability and substitution profiles were highly conserved across individuals, the variability across motifs was found to be much larger than previously estimated. The model and method source code are made available at http://clip.med.yale.edu/SHM

Bayesian Formulation of Image Patch Matching Using Cross-correlation

A classical solution for matching two image patches is to use the cross-correlation coefficient. This works well if there is a lot of structure within the patches, but not so well if the patches are close to uniform. This means that some patches are matched with more confidence than others. By estimating this uncertainty, more weight can be put on the confident matches than those that are more uncertain. To enable this two distribution functions for two different cases are used: (i) the correlation between two patches showing the same object but with different lighting conditions and different noise realisations and (ii) the correlation between two unrelated patches.Using these two distributions the patch matching problem is, in this paper, formulated as a binary classification problem. The probability of two patches matching is derived. The model depends on the signal to noise ratio. The noise level is reasonably invariant over time, while the signal level, represented by the amount of structure in the patch or its spatial variance, has to be measured for every frame.A common application where this is useful is feature point matching between different images. Another application is background/foreground segmentation. This paper will concentrate on the latter application. It is shown how the theory can be used to implement a very fast background/foreground segmentation algorithm by transforming the calculations to the DCT-domain and processing a motion-JPEG stream without uncompressing it. This allows the algorithm to be embedded on a 150 MHz ARM based network camera. It is also suggested to use recursive quantile estimation to estimate the background model. This gives very accurate background models even if there is a lot of foreground present during the initialisation of the model.

Object detection based on a robust and accurate statistical multi-point-pair model

In this paper, we propose a robust and accurate background model, called grayscale arranging pairs (GAP). The model is based on the statistical reach feature (SRF), which is defined as a set of statistical pair-wise features. Using the GAP model, moving objects are successfully detected under a variety of complex environmental conditions. The main concept of the proposed method is the use of multiple point pairs that exhibit a stable statistical intensity relationship as a background model. The intensity difference between pixels of the pair is much more stable than the intensity of a single pixel, especially in varying environments. Our proposed method focuses more on the history of global spatial correlations between pixels than on the history of any given pixel or local spatial correlations. Furthermore, we clarify how to reduce the GAP modeling time and present experimental results comparing GAP with existing object detection methods, demonstrating that superior object detection with higher precision and recall rates is achieved by GAP.