Search

Object formation is imperative to the recent computer vision, pattern recognition, healthcare, and automation applications. The objects are generated from images by defining edges and the segmentation process. This article introduced a novel method, Outer Totality Cellular Automata (OTCA), for defining actual and continuous edges of the image objects. The OTCA analysis nearby 25 neighbourhood pixels of all the pixels and generate a unique and efficient threshold. The proposed method has three primary functions, i.e. vitality, rule mapping, and improved morphological functions. The key objectives are image smoothing, neighbourhood analysis, defining game of life rule, and edges smoothing. Notably, the proposed method aimed to segment different coloured images, i.e., RGB, HSV, and YUV. The proposed method also aimed to produce more truthful results on blurred, reflected, shaded night vision images. The experimental process demonstrates using standard open-source datasets and validated using image quality assessment parameters, i.e., entropy, PSNR, SSIM, and MSE. The results claim 3% – 12% more structural analogous, factual, and accurate than existing classical methods and recent searches.

White blood cells (WBC) are an important component of immune mechanism, as they protect human body from parasites, viruses, fungi, and bacteria. The number of blood cells provides significant information related to infections such as AIDS, leukemia, deficiencies of immune and autoimmune infections. To heal an infection in a timely manner, it is critical to recognize it early on. Therefore, a method is proposed to accurately segment and classify WBC at an early stage. The RGB image is converted into HSV after which dual thresholding is applied to the saturation component to segment WBC. The 1000 features are extracted from Alexnet to FC8 layer, Logits layer is selected for feature extraction from mobilenetv2, node_202 layer is utilized to extract the features from shuffle net and FC1000 layer is chosen from Resnet-18 model. Four feature vectors are obtained from transfer learning models; these feature vectors are combined serially and create the final optimized vector by non-dominated sorting genetic algorithm (NSGA). The classification results are investigated on the fusion of Alexnet, shuffle net, Resnet-18, mobilenetv2 and the fusion of mobilenetv2, shuffle net and Resnet-18 whereas mobilenetv2 features are fused independently. The method is tested on three publicly available datasets such as LISC, ALL_IDB1, and ALL_IDB2. The method achieved maximum 1.00 accuracy to classify the blast/non-blast cells, 0.9992 accuracy on Basophil cells, and 1.00 accuracy on Lymphocyte, Neutrophil, Monocyte, Eosinophil, and mixture of these cells. When compared to existing modern approaches, the proposed method produces better outcomes.

Suspicious region segmentation is one of the most important parts of CAD systems that are used for breast cancer detection in mammograms. In a CAD system, there can be so many suspicious regions determined for a mammogram because of the complex structure of the breast. This study proposes a hybrid thresholding method to use in the CAD systems for efficient segmentation of the mammograms and reducing the number of the suspicious regions. The proposed method provides fully-automatic segmentation of the suspicious regions. This method is based on determining an adaptive multi-threshold value by using three different techniques together. These techniques are Otsu multilevel thresholding, Havrda & Charvat entropy, and w-BSAFCM algorithm that was developed by the authors of this paper for image clustering applications. In the proposed method, segmentation of a mammogram is performed on two sub-images obtained from that mammogram, the pectoral muscle and the breast region to prevent any information loss. The method was tested on 55 mass-mammograms and 210 non-mass mammograms of the mini-MIAS database, and it was compared with Shannon, Renyi, and Kapur entropy methods and with some of the related studies from the literature. The segmentation results of the tests were evaluated in terms of the number of suspicious regions, the number of correctly detected masses, and the performance measure parameters, accuracy, false-positive rate, specificity, volumetric overlap, and dice similarity coefficient. According to the evaluations, it was shown that the proposed method can both successfully locate the mass regions and significantly reduce the number of the non-mass suspicious regions on the mammograms.

Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast-based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. The proposed technique is then applied to identify surface cracks on the surface of roads, bridges or pavements. An extensive comparison with existing techniques is conducted on various datasets and subject to a number of evaluation criteria including the average F-measure ( $AF_\beta $ ) introduced here for dynamic quantification of the performance. Experiments on crack images, including those captured by unmanned aerial vehicles inspecting a monorail bridge. The proposed technique outperforms the existing methods on various tested datasets especially for GAPs dataset with an increase of about 1.4% in terms of $AF_\beta $ while the mean percentage error drops by 2.2%. Such performance demonstrates the merits of the proposed HCNNFP architecture for surface defect inspection.

Time-frequency analysis deals with signals for which the underlying spectral characteristics change over time. The essential tool is the short-time Fourier transform, which localizes the Fourier transform in time by means of a window function. In a white noise model, we derive rate-optimal and adaptive estimators of signals in modulation spaces, which measure smoothness in terms of decay properties of the short-time Fourier transform. The estimators are based on series expansions by means of Gabor frames and on thresholding the coefficients. The minimax rates have interesting new features, and the derivation of the lower bounds requires the use of test functions which approximately localize both in time and in frequency. Simulations and applications to audio recordings illustrate the practical relevance of our methods. We also discuss the best $N$ -term approximation and the approximation of variational problems in modulation spaces by Gabor frame expansions. [ABSTRACT FROM AUTHOR]

This paper studies the performance of OMP in comparison to Thresholding in the case in which only a perturbed version of the generating dictionary is known. Both theory and numerical simulations show that simple Thresholding is a viable alternative to OMP in applications where only a perturbed version of the generating dictionary is given, such as dictionary learning. [ABSTRACT FROM AUTHOR]

Functional connectivity (FC) networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used in automated identification of brain disorders, such as Alzheimer’s disease (AD) and attention deficit hyperactivity disorder (ADHD). To generate compact representations of FC networks, various thresholding methods have been designed for FC network analysis. However, these studies usually use a pre-defined threshold or connection percentage to threshold whole FC networks, thus ignoring the diversity of temporal correlation (e.g., strong associations) between brain regions in subject groups. In this work, we propose a distribution-guided network thresholding learning (DNTL) method for FC network analysis in brain disorder identification with rs-fMRI. Specifically, for each connection of a pair of brain regions, we propose to determine its specific threshold based on the distribution of connection strength (i.e., temporal correlation) between subject groups (e.g., patients and normal controls). The proposed DNTL can adaptively yield an FC-specific threshold for each connection in an FC network, thus preserving diversity of temporal correlation among different brain regions. Experiment results on $ 365$ subjects from two datasets (i.e., ADNI and ADHD-200) suggest that the DNT method outperforms state-of-the-art methods in brain disorder identification with rs-fMRI data. [ABSTRACT FROM AUTHOR]

Objective: Computed tomography (CT) scan is a fast and widely used modality for early assessment in patients with symptoms of a cerebral ischemic stroke. CT perfusion (CTP) is often added to the protocol and is used by radiologists for assessing the severity of the stroke. Standard parametric maps are calculated from the CTP datasets. Based on parametric value combinations, ischemic regions are separated into presumed infarct core (irreversibly damaged tissue) and penumbra (tissue-at-risk). Different thresholding approaches have been suggested to segment the parametric maps into these areas. The purpose of this study is to compare fully-automated methods based on machine learning and thresholding approaches to segment the hypoperfused regions in patients with ischemic stroke. Methods: We test two different architectures with three mainstream machine learning algorithms. We use parametric maps as input features, and manual annotations made by two expert neuroradiologists as ground truth. Results: The best results are produced with random forest (RF) and Single-Step approach; we achieve an average Dice coefficient of 0.68 and 0.26, respectively for penumbra and core, for the three groups analysed. We also achieve an average in volume difference of 25.1 ml for penumbra and 7.8 ml for core. Conclusions: Our best RF-based method outperforms the classical thresholding approaches, to segment both the ischemic regions in a group of patients regardless of the severity of vessel occlusion. Significance: A correct visualization of the ischemic regions will guide treatment decisions better. [ABSTRACT FROM AUTHOR]

The Unlimited Sensing Framework (USF) was recently introduced to overcome the sensor saturation bottleneck in conventional digital acquisition systems. At its core, the USF converts a continuous-time high-dynamic-range (HDR) signal into folded, low-dynamic-range, modulo samples and allows the recovery of the HDR signal via algorithmic unfolding. In hardware, however, implementing ideal modulo folding requires careful calibration, analog design and high precision. At the interface of theory and practice, this paper explores a computational sampling strategy that relaxes strict hardware requirements via a novel, mathematically guaranteed reconstruction. We start with a generalized model for USF with two new parameters modeling hysteresis and folding transients in addition to the modulo threshold. Hysteresis accounts for mismatches between the reset threshold and the amplitude displacement at the folding time and the folding transient is a continuous transition period in the implementation of a reset. Both these effects are motivated by our hardware experiments and also occur in previous, domain-specific applications. We show that hysteresis is beneficial for USF and leverage it to derive the first recovery guarantees in the context of our generalized USF model for a certain sampling rate regime. Additionally, we show how the sampling rate requirement can be greatly reduced via a direct generalization of the proposed recovery. Our theoretical work is corroborated by hardware experiments with a hysteresis enabled, modulo ADC testbed comprising off-the-shelf electronic components. Thus, by capitalizing on a collaboration between hardware and algorithms, our paper enables an end-to-end pipeline for HDR sampling allowing more flexible hardware implementations. [ABSTRACT FROM AUTHOR]

We consider the problem of robust deconvolution, and particularly the recovery of an unknown deterministic signal convolved with a known filter and corrupted by additive noise. We present a novel, non-iterative data-driven approach. Specifically, our algorithm works in the frequency-domain, where it tries to mimic the optimal unrealizable non-linear Wiener-like filter as if the unknown deterministic signal were known. This leads to a threshold-type regularized estimator, where the threshold at each frequency is determined in a data-driven manner. We perform a theoretical analysis of our proposed estimator, and derive approximate formulas for its Mean Squared Error (MSE) at both low and high Signal-to-Noise Ratio (SNR) regimes. We show that in the low SNR regime our method provides enhanced noise suppression, and in the high SNR regime it approaches the optimal unrealizable solution. Further, as we demonstrate in simulations, our solution is highly suitable for (approximately) bandlimited or frequency-domain sparse signals, and provides a significant gain of several dBs relative to other methods in the resulting MSE. [ABSTRACT FROM AUTHOR]

We are seeing a growth in the number of connected vehicles in Vehicular Ad-hoc Networks (VANETs) to achieve the goal of Intelligent Transportation System (ITS). This is leading to a connected vehicular network scenario with vehicles continuously broadcasting data to other vehicles on the road and the roadside network infrastructure. The presence of a large number of communicating vehicles greatly increases the number and types of possible anomalies in the network. Existing works provide solutions addressing specific anomalies in the network only. However, since there can be a multitude of anomalies possible in the network, there is a need for better anomaly detection frameworks that can address this unprecedented scenario. In this paper, we propose an anomaly detection framework for VANETs based on deep neural networks (DNNs) using a sequence reconstruction and thresholding algorithm. In this framework, the DNN architectures are deployed on the roadside units (RSUs) which receive the broadcast vehicular data and run anomaly detection tasks to classify a particular message sequence as anomalous or genuine. Multiple DNN architectures are implemented in this experiment and their performance is compared using key evaluation metrics. Performance comparison of the proposed framework is also drawn against the prior work in this area. Our best performing deep learning-based scheme detects anomalous sequences with an accuracy of 98%, a great improvement over the set benchmark. [ABSTRACT FROM AUTHOR]

The image segmentation refers to the extraction of region of interest and it plays a vital role in medical image processing. This work proposes multilevel thresholding based on optimization technique for the extraction of region of interest and compression of DICOM images by an improved prediction lossless algorithm for telemedicine applications. The role of compression algorithm is inevitable in data storage and transfer. Compared to the conventional thresholding, multilevel thresholding technique plays an efficient role in image analysis. In this paper, the Particle Swarm Optimization (PSO), Darwinian Particle Swarm Optimization (DPSO), and Fractional Order Darwinian Particle Swarm Optimization (FODPSO) are employed in the estimation of the threshold value. The simulation results reveal that the FODPSO-based multilevel level thresholding generate superior results. The fractional coefficient in FODPSO algorithm makes it effective optimization with fast convergence rate. The classification and blending prediction-based lossless compression algorithm generates efficient results when compared with the JPEG lossy and JPEG lossless approaches. The algorithms are tested for various threshold values and higher value of PSNR indicates the proficiency of the proposed segmentation approach. The performance of the compression algorithms was validated by metrics and was found to be appropriate for data transfer in telemedicine. The algorithms are developed in Matlab2010a and tested on DICOM CT images.

In this paper, we propose an effective THresholding method based on the Order Statistic, called THORS, to convert an arbitrary scoring-type classifier, which can induce a continuous cumulative distribution function of the score, into a cost-sensitive one. The procedure uses the order statistic to find an optimal threshold for classification, requiring almost no knowledge of the classifier itself. Unlike common data-driven methods, we analytically show that the THORS has theoretical guaranteed performance, theoretical bounds for the costs, and low-time complexity. Coupled with empirical results on several real-world data sets, we argue that the THORS is the preferred cost-sensitive learning technique.

This paper proposes an automatic eyeblink artifacts removal method from corrupted-EEG signals using discrete wavelet transform (DWT) and meta-heuristically optimized threshold. The novel idea of thresholding approximation-coefficients (ACs) instead of detail-coefficients (DCs) of DWT of EEG in a backward manner is proposed for the first time for the removal of eyeblink artifacts. EEG is very sensitive and easily gets affected by eyeblink artifacts. First, the eyeblink corrupted EEG signals are identified using support vector machine (SVM) as a classifier. Then the corrupted EEG signal is decomposed using DWT up to the sixth level. Both the mother wavelet and the level of decomposition are selected using appropriate techniques. Then the ACs are thresholded in backward manner using the optimum threshold values followed by inverse DWT operation to reconstruct the original EEG signal. The AC at level 6 is thresholded and is used in IDWT with DC to get back the AC at level 5. Likewise, the backward thresholding of the ACs followed by IDWT is continued till the artifact free EEG signal is reconstructed at level 1. The optimum values of the thresholds of the ACs at different levels are optimized using two meta-heuristic algorithms, particle swarm optimization (PSO) and grey wolf optimization (GWO) for comparison. The results reveal that the proposed methodology is superior to the recently reported methods in terms of average correlation coefficient (CC) which states that the proposed method is better in terms of the quality of reconstruction in addition to being fully automatic. [ABSTRACT FROM AUTHOR]

The Spherical Densiometer is a method of measuring the luminosity present inside the forest ecosystem. This information is essential to know the probability of survival and growth of seedlings; it also allows the estimation of the establishment and development of plants in the understory. This indirect measurement method is considered to be of acceptable efficiency; however, it presents complexity of operability in its application, generating an exposure of the researcher to long periods of solar radiation, physical wear and risks of interaction with wildlife, besides maintaining avariability due to subjectivity and overestimation due to the wide angle of vision and interpretation of the user. In order to obtain samples, it is necessary to have a guidance system, stabilization indicator and a system for recording the results. In the development of this research, a methodology is proposed for the measurement of the opening and coverage of the light environment under the forest canopy, using artificial vision techniques such as image processing in mobile devices. At the same time, the sensors integrated in the device are used to guarantee stabilization and orientation, including the persistent storage of data. As a result of the comparison between the two methods, the proposed methodology demonstrates a 73.49% reduction in canopy measurement times, reducing user exposure to the extreme conditions present in the ecosystem, eliminating subjectivity and overestimation of the results obtained. [ABSTRACT FROM AUTHOR]

Multiclass image segmentation is a challenging task due to the uncertainties involved with the process of segmentation. To handle those uncertainties, we propose an automatic multiclass image segmentation method based on an interval type-2 fuzzy set (IT2FS). In the proposed method in this article, the accurate multiclass segmentation is achieved by minimizing an energy function. This energy function is based on IT2FS and weak continuity constraints present in the membership values. The theory of weak continuity constraints helps to localize the segmentation boundaries between the classes accurately with the minimization of the energy. The proper localization of segmentation boundaries helps to minimize the uncertainties in the segmentation process. We also theoretically show that the minimization of the energy function reduces the uncertainties present in the segmentation process. Furthermore, the method automatically determines the number of clusters without a priori knowledge. The proposed method is found to be superior to the existing conventional, fuzzy type-1 and fuzzy type-2 based segmentation techniques. The superiority is verified using synthetic and benchmark datasets. The noise immunity of the proposed method is found to be better than that of the state-of-the-art methods when benchmark against the modified Cramer–Rao bound. [ABSTRACT FROM AUTHOR]

Segmentation is considered an important part of image processing. There are commonly used segmentation techniques to improve the thresholding process, such as Otsu and Kapur. The use of these techniques allows us to find the regions of interest in an image by accurately grouping the pixel intensity levels. On the other hand, the use of thermal images makes it possible to obtain information about the temperature of an object and to capture the infrared radiation of the electromagnetic spectrum through cameras that transform the radiated energy into heat information. The segmentation of this kind of images represents a challenging problem that requires a huge computational effort. This work proposes the use of metaheuristic algorithms, combined with segmentation techniques and applied to thermal images, to detect faults and contribute to the preventive maintenance of electronic systems. [ABSTRACT FROM AUTHOR]

Endmember is defined as the spectral signature of pure material present in hyperspectral imagery. Estimation of the number of endmembers (NOE) present in a scene is an important preprocessing step and plays a crucial role in hyperspectral image processing, since over- or under-estimation of the NOE will lead to heavily incorrect results. In this article, we develop a thresholding ridge ratio (TRR) criterion based on eigendecomposition for NOE determination. Different from the widely used eigenvalue difference analysis methods, the TRR seeks an adaptive thresholding operation to the ridge ratio of eigenvalue differences, and ridge ratio combined with adaptive thresholding can theoretically guarantee a consistent estimate even when there are several local minima. Based on the TRR criterion, an algorithm is introduced to perform the estimation of NOE. Experimental results on both the simulated and real hyperspectral data sets have demonstrated that the proposed TRR-based algorithm has comparable and even better performances to several benchmark algorithms in the estimation accuracy of the NOE. [ABSTRACT FROM AUTHOR]

The strong temporal backscatter signature of rice growing above the water's surface allows for the use of synthetic aperture radar (SAR) for paddy rice crop mapping in Southern Vietnam (Mekong Delta). In Northern Vietnam (Red River Delta), rice mapping using SAR is a challenge and is rarely performed because of the complex land-use/land-cover. Nevertheless, information about rice fields is needed for hydrological simulations in river basins such as the Cau River basin. The objective of this research is to investigate the potential of RADARSAT-2 band- C in identifying rice fields over a large and fragmented land-use area. Two methods are proposed, one for each data type, adapted to the land-use/land-cover of the study area. The thresholding technique, with a statistical analysis of the temporal variation of rice backscattering, was applied to the HH like-polarized ratio of dual-pol data. The support vector machine (SVM) algorithm was applied to the full quad-pol and a single HH-polarization calculated from polarimetric data. This study demonstrates that RADARSAT-2 dual- and quad-pol data can be successfully used to identify cultivated rice fields. However, the dual-pol data seems less efficient than the quad-pol data and the SVM classification is more flexible than the thresholding technique. Between the full quad-pol and a single polarization, the overall classification accuracy shows that the results derived from the single HH polarization are 3 to 10% less accurate than those derived from the classification of full quad-pol data. The results show the usefulness of polarimetric C-band data for the identification of rice fields in Northern Vietnam.

In our changing world, floods are a threat of increasing concern. Within this context, flood mapping is important for both damage assessment and forecast improvement. Due to the suitability of synthetic aperture radar (SAR) for flood mapping, a broad range of SAR-based flood mapping algorithms has been developed during the past years. However, most of these algorithms were presented based on a single test case only and comparisons between methods are rare. This paper presents an in-depth assessment and comparison of the established pixel-based flood mapping approaches, including global and enhanced thresholding, active contour modeling and change detection. The methods were tested on medium-resolution SAR images of different flood events and lakes across the U.K. and Ireland and were evaluated on both accuracy and robustness. Results indicate that the most suited method depends on the area of interest and its characteristics as well as the intended use of the observation product. Due to its high robustness and good performance, tiled thresholding is suited for automated, near-real time flood detection and monitoring. Active contour models can provide higher accuracies but require long computation times that strongly increase with increasing image sizes, making them more appropriate for accurate flood mapping in smaller areas of interest. [ABSTRACT FROM AUTHOR]

In this paper, four iterative algorithms for learning analysis operators are presented. They are built upon the same optimization principle underlying both Analysis K-SVD and Analysis SimCO. The forward and sequential analysis operator learning (AOL) algorithms are based on projected gradient descent with optimally chosen step size. The implicit AOL algorithm is inspired by the implicit Euler scheme for solving ordinary differential equations and does not require to choose a step size. The fourth algorithm, singular value AOL, uses a similar strategy as Analysis K-SVD while avoiding its high computational cost. All algorithms are proven to decrease or preserve the target function in each step and a characterization of their stationary points is provided. Further they are tested on synthetic and image data, compared to Analysis SimCO and found to give better recovery rates and faster decay of the objective function, respectively. In a final denoising experiment the presented algorithms are again shown to perform similar to or better than the state-of-the-art algorithm ASimCO. [ABSTRACT FROM AUTHOR]

Heart rate is an important physiological parameter to assess the cardiac condition of an individual and is traditionally determined by attaching multiple electrodes on the chest of a subject to record the electrical activity of the heart. The installation and handling complexities of such systems does not prove feasible for a user to undergo a long-term monitoring in the home settings. A small-sized, battery-operated wearable monitoring device is placed on the suprasternal notch at neck to record acoustic signals containing information about breathing and cardiac sounds. The heart sounds obtained are heavily corrupted by the respiratory cycles and other external artifacts. This paper presents a novel algorithm for reliably extracting the heart rate from such acoustic recordings, keeping in mind the constraints posed by the wearable technology. The methodology constructs the Hilbert energy envelope of the signal by calculating its instantaneous characteristics to segment and classify a cardiac cycle into S1 and S2 sounds using their timing characteristics. The algorithm is tested on a dataset consisting of 13 subjects with an approximate data length of 75 h and achieves an accuracy of 94.34%, an RMS error of 3.96 bpm and a correlation coefficient of 0.93 with reference to a commercial device in use. [ABSTRACT FROM AUTHOR]

Several areas of science have used Digital Image Processing techniques to extract information, one of these areas of application is Medicine. Radiologists currently use 3D software for the exploitation of digital content in medical images. The method currently used for organ segmentation is manual and may not be effective for exploring the content present in the images, since manual segmentation of organs requires time and may not produce effective results. This work aims to present three techniques developed for automatic segmentation of the liver from medical images. This organ was selected because of the complexity to create a technique for segmentation of all organs of the human anatomy using the techniques of Digital Image Processing, such as: image smoothing, image segmentation and morphological operations. According to the results of the experiments performed, the three techniques proposed had a good rate of liver segmentation. [ABSTRACT FROM AUTHOR]

Efficient and accurate detection of cell nuclei is an important step toward automatic analysis in histopathology. In this work, we present an automatic technique based on generalized Laplacian of Gaussian (gLoG) filter for nuclei detection in digitized histological images. The proposed technique first generates a bank of gLoG kernels with different scales and orientations and then performs convolution between directional gLoG kernels and the candidate image to obtain a set of response maps. The local maxima of response maps are detected and clustered into different groups by mean-shift algorithm based on their geometrical closeness. The point which has the maximum response in each group is finally selected as the nucleus seed. Experimental results on two datasets show that the proposed technique provides a superior performance in nuclei detection compared to existing techniques. [ABSTRACT FROM AUTHOR]

Detection of moving objects in a video captured by a freely moving camera is a challenging problem in computer vision. Most existing methods often assume that the background (BG) can be approximated by dominant single plane/multiple planes or impose significant geometric constraints on BG, or utilize a complex BG/foreground probabilistic model. Instead, we propose a computationally efficient algorithm that is able to detect moving objects accurately and robustly in a general 3D scene. This problem is formulated as a coarse-to-fine thresholding scheme on the particle trajectories in the video sequence. First, a coarse foreground (CFG) region is extracted by performing reduced singular value decomposition on multiple matrices that are built from bundles of particle trajectories. Next, the BG motion of pixels in the CFG region is reconstructed by a fast inpainting method. After subtracting the BG motion, the fine foreground is segmented out by an adaptive thresholding method that is capable of solving multiple-moving-objects scenarios. Finally, the detected foreground is further refined by the mean-shift segmentation method. Extensive simulations and a comparison with the state-of-the-art methods verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a general adaptive procedure for budget-limited predictor design in high dimensions called two-stage Sampling, Prediction and Adaptive Regression via Correlation Screening (SPARCS). The SPARCS can be applied to high-dimensional prediction problems in experimental science, medicine, finance, and engineering, as illustrated by the following. Suppose that one wishes to run a sequence of experiments to learn a sparse multivariate predictor of a dependent variable Y (disease prognosis for instance) based on a p dimensional set of independent variables \mathrm X=[X1,\ldots , Xp]^{T} (assayed biomarkers). Assume that the cost of acquiring the full set of variables X increases linearly in its dimension. The SPARCS breaks the data collection into two stages in order to achieve an optimal tradeoff between sampling cost and predictor performance. In the first stage, we collect a few ( n ) expensive samples \yi, {\mathrm {x}i\}i=1^{n} , at the full dimension $p\gg n$ of X, winnowing the number of variables down to a smaller dimension $l < p$ using a type of cross correlation or regression coefficient screening. In the second stage, we collect a larger number $(t-n)$ of cheaper samples of the $l$ variables that passed the screening of the first stage. At the second stage, a low-dimensional predictor is constructed by solving the standard regression problem using all $t$ samples of the selected variables. The SPARCS is an adaptive online algorithm that implements false positive control on the selected variables, is well suited to small sample sizes, and is scalable to high dimensions. We establish asymptotic bounds for the familywise error rate, specify high dimensional convergence rates for support recovery, and establish optimal sample allocation rules to the first and second stages. [ABSTRACT FROM PUBLISHER]

In practical Orthogonal Frequency Division Multiplexing (OFDM) systems, due to the presence of virtual subcarriers, the OFDM input–output relation is ill-conditioned in the Fourier basis. Therefore, an unbiased estimator does not exist and regularization methods, generally used to estimate the channel, provide biased time domain estimates. To estimate exact channel sparsity, we propose an unbiased estimator in discrete prolate spheroidal sequences (DPSS) basis. We theoretically show that our estimates recover exact sparsity information as the SNR increases. [ABSTRACT FROM PUBLISHER]

The strong temporal backscatter signature of rice growing above the water's surface allows for the use of synthetic aperture radar (SAR) for paddy rice crop mapping in Southern Vietnam (Mekong Delta). In Northern Vietnam (Red River Delta), rice mapping using SAR is a challenge and is rarely performed because of the complex land-use/land-cover. Nevertheless, information about rice fields is needed for hydrological simulations in river basins such as the Cau River basin. The objective of this research is to investigate the potential of RADARSAT-2 band- C in identifying rice fields over a large and fragmented land-use area. Two methods are proposed, one for each data type, adapted to the land-use/land-cover of the study area. The thresholding technique, with a statistical analysis of the temporal variation of rice backscattering, was applied to the HH like-polarized ratio of dual-pol data. The support vector machine (SVM) algorithm was applied to the full quad-pol and a single HH-polarization calculated from polarimetric data. This study demonstrates that RADARSAT-2 dual- and quad-pol data can be successfully used to identify cultivated rice fields. However, the dual-pol data seems less efficient than the quad-pol data and the SVM classification is more flexible than the thresholding technique. Between the full quad-pol and a single polarization, the overall classification accuracy shows that the results derived from the single HH polarization are 3 to 10% less accurate than those derived from the classification of full quad-pol data. The results show the usefulness of polarimetric C-band data for the identification of rice fields in Northern Vietnam. [ABSTRACT FROM PUBLISHER]