Search results

The purpose of this paper is to review and provide a detailed performance evaluation of a number of texture descriptors that analyse texture at micro‐level such as local binary patterns (LBP) and a number of standard filtering techniques that sample the texture information using either a bank of isotropic filters or Gabor filters.

The experimental tests were conducted on standard databases where the classification results are obtained for single and multiple texture orientations. The authors also analysed the performance of standard filtering texture analysis techniques (such as those based of LM and MR8 filter banks) when applied to the classification of texture images contained in standard Outex and Brodatz databases.

The most important finding resulting from this study is that although the LBP/C and the multi‐channel Gabor filtering techniques approach texture analysis from a different theoretical perspective, in this paper the authors have experimentally demonstrated that they share some common properties in regard to the way they sample the macro and micro properties of the texture.

Texture is a fundamental property of digital images and the development of robust image descriptors plays a crucial role in the process of image segmentation and scene understanding.

This paper contrast, from a practical and theoretical standpoint, the LBP and representative multi‐channel texture analysis approaches and a substantial number of experimental results were provided to evaluate their performance when applied to standard texture databases.

The Hurst exponent has been very important in telling the difference between fractal signals and explaining their significance. For estimators of the Hurst exponent, accuracy and efficiency are two inevitable considerations. The main purpose of this study is to raise the execution efficiency of the existing estimators, especially the fast maximum likelihood estimator (MLE), which has optimal accuracy.

A two-stage procedure combining a quicker method and a more accurate one to estimate the Hurst exponent from a large to small range will be developed. For the best possible accuracy, the data-induction method is currently ideal for the first-stage estimator and the fast MLE is the best candidate for the second-stage estimator.

For signals modeled as discrete-time fractional Gaussian noise, the proposed two-stage estimator can save up to 41.18 per cent the computational time of the fast MLE while remaining almost as accurate as the fast MLE, and even for signals modeled as discrete-time fractional Brownian motion, it can also save about 35.29 per cent except for smaller data sizes.

The proposed two-stage estimation procedure is a novel idea. It can be expected that other fields of parameter estimation can apply the concept of the two-stage estimation procedure to raise computational performance while remaining almost as accurate as the more accurate of two estimators.

The purpose of this paper is to provide a robust method for automatic detection of seam lines based only on digital images of the garments.

A local standard deviation pre‐processing filter is applied to enhance the contrast between the seam line and the texture and the Prewitt operator extracts the edges of the enhanced image. The seam line is detected by a maximum at the Radon transform. The proposed method is invariant to the illumination intensity and it has been also tested with moving average and fast Fourier transform low‐pass filters used in the pre‐processing module. Extensive experiments are carried out in the presence of additive Gaussian and uniform noise.

The proposed method detects 109 out of 118 seams when the local standard deviation is used at the pre‐processing stage, giving a mean distance error between the real and the estimated line of 2 mm when the image is digitised at 97 dpi. However, in case the images are distorted by additive Gaussian noise at 20 dB signal‐to‐noise ratio, the moving average low‐pass filtering method gives the best results, detecting 104 noisy images.

The proposed method detects seam lines that can be approximated by a continuation of straight lines. The current work can be extended in the detection of the curved parts of seam lines.

Since the method addresses garments instead of seam specimens, the proposed approach can be imported in automatic systems for online quality control of seams.

Local standard deviation belongs to first‐order statistics, which makes it suitable for texture analysis and that is why it is mostly used in web defect detection. The novelty in the approach, however, is that by considering the seam as an abnormality of the texture, the authors applied that method at the pre‐processing stage to enhance the seam before the detection. Moreover, the presented method is illumination invariant, a property that has not been addressed in similar methods.

The paper aims to propose a new method for estimating the time of arrival (TOA) of ultra-wideband (UWB) signals under IEEE 802.15.4a multipath channel model.

The proposed approach is based on a proportionality test and consists in finding out whether two autoregressive (AR) processes, modeling two frames, are proportional or not. The latter operation uses a distance to measure the proportionality between the two AR processes.

The developed technique may be used in two ways, sample-by-sample or block-by-block, according to the required ranging accuracy. It is important to note that the method offers flexibility between the computational load and the needed estimation accuracy. Moreover, the proposed method uses a threshold that is derived analytically according to a preset false alarm probability.

Simulation experiments are conducted to assess the performance of the new TOA estimation algorithm. Thereby, the comparison is done against the well-known CLEAN algorithm for a sample-by-sample based TOA estimation and against three energy detector based receiver algorithms. The obtained results highlight the effectiveness of the developed approach.

The developed TOA estimation algorithm is completely different from other techniques in the literature, and it is based on a proportionality test between two sliding frames. These latter are modeled by two AR processes. Then a distance measure is used to check whether or not the power spectral densities are proportional.

The purpose of this paper is to examine the use of a new feature reduction technique with novelty detection on vibration and acoustic‐emission sensors monitoring bearings mounted in the test benches of automotive manufacturers.

Signals from standard accelerometers and acoustic‐emission sensors were gathered from bearings operating under steady conditions on an accessory‐drive test bench. The bearings under test were subject to a variety of faults including fretting. These signals were processed and reduced to standard feature vectors, the dimensionality of which was reduced using a new principal‐component‐like technique optimized for novelty detection. The reduced data were analyzed with a novelty detection technique called the Support Vector Data Descriptor.

The classification results from these sensors, after being reduced with the proposed feature reduction technique, are substantially improved over those achievable with only standard novelty detection; nearly zero‐percent classification error was achieved.

The feature reduction technique depends, in part, on the availability of the fault type in question – potentially violating the normal novelty detection assumption of limited abnormal data. This may require the manufacturer to gather real or simulated fault data prior to running tests.

Incipient faults may be detectable at a much earlier stage in a manufacturer's component failure analysis. Test engineers may use this technique to reliably automate the fault detection process and enable improved root‐cause analysis through the earlier identification of faults.

The application of the feature reduction technique will provide manufacturers and researchers with a new means of improving fault detection in machinery components.

The purpose of this paper is to deal with the anomaly detection problem in multi-unmanned aerial vehicles (UAVs) formation that can be transformed to identify some unknown parameters; a more general nonlinear dynamical model for each UAV is considered to include two terms. Due to an unknown parameter corresponding to the normal or abnormal state for each UAV, the bias-compensated approach is proposed to obtain the unbiased parameter estimation. Meanwhile, the biased error and accuracy analysis are also given in case of strict statistical description of the uncertainty or white noise. To relax this strict statistical description on external noise, an analytic center approach is proposed to identify the unknown parameters in presence of bounded noise, such that two inner and outer ellipsoidal approximations are constructed to include the membership set. To be precise, this paper is regarded as one extension and summary for the author’s previous research on the anomaly detection in multi-UAV formation. Finally, one simulation example is given to confirm the theoretical results.

Firstly, one extended nonlinear relation is constructed to embody the mutual relationship of UAVs. Secondly, to obtain the unbiased parameter estimations, the bias-compensated approach is applied to achieve it under the condition of white noise. Thirdly, in case of unknown but bounded noise, an analytic center approach is proposed to deal with this special case. Without loss of generality, the author thinks this paper can be used as one extension and summary for research on multi-UAVs formation anomaly detection.

An anomaly detection problem in multi-UAVs formation can be transformed into a problem of nonlinear system identification, and in modeling the nonlinear dynamical model for each UAV, two terms are considered simultaneously to embody the mutual relationships with other nearest UAV.

To the best knowledge of the authors, this problem of the anomaly detection problem in multi-UAVs formation is proposed by the authors’ previous work, and the problem of multi-UAVs formation anomaly detection can be transferred into one problem of parameter identification. In case of unknown but bounded noise, an analytic center approach is proposed to identify the unknown parameters, which correspond to achieve the goal of the anomaly detection.

Doppler-Bearing Tracking (DBT) is commonly used in target tracking applications for the underwater environment using the Hull-Mounted Sensor (HMS). It is an important and challenging problem in an underwater environment.

The system nonlinearity in an underwater environment increases due to several reasons such as the type of measurements taken, the speeds of target and observer, environmental conditions, number of sensors considered for measurements and so on. Degrees of nonlinearity (DoNL) for these problems are analyzed using a proposed measure of nonlinearity (MoNL) for state estimation.

In this research, the authors analyzed MoNL for state estimation and computed the conditional MoNL (normalized) using different filtering algorithms where measurements are obtained from a single sensor array (i.e. HMS). MoNL is implemented to find out the system nonlinearity for different filtering algorithms and identified how much nonlinear the system is, that is, to measure nonlinearity of a problem.

Algorithms are evaluated for various scenarios with different angles on the target bow (ATB) in Monte-Carlo simulation. Computation of root mean squared (RMS) errors in position and velocity is carried out to assess the state estimation accuracy using MATLAB.

The purpose of this paper is to present the methods of concurrent optimization of the analogue and digital parts (software‐hardware) of estimating, identifying and filtering systems with adaptively adjusted analogue parts – adaptive estimation systems (AES).

Concurrent (complete) optimization of AES permits the determination of the most efficient algorithms for computing the estimates and the controls adjusting analogue units of AES in the way maximally improving the quality of observations delivered by them to the digital part. Performance of AES is assessed by the mean square error (MSE) of estimates which is constructed employing the models of input excitation, analogue and digital parts. Global extremum of MSE is searched by Bayesian methods taking into account the always bounded input range of AES and its possible overloading.

There are determined upper boundaries of potentially achievable accuracy of estimates, as well as optimal estimating and controlling observation units' algorithms, ensuring their achievement. New effects appearing in completely optimal AES are analysed.

The paper presents the backgrounds of new and analytically complex approach. To clarify basic ideas and methods, the simplest but useful for applications single input‐single output and single input‐multiple output models of ASE were considered. The obtained results create wide field for further investigations.

The results of the paper can be applied in the development of new classes of high‐efficient adaptive data acquisition, measurement, controlling, communication and other systems.

Concurrent optimisation of AES is important task having no general solution until now. Known approaches allow only the separate optimisation of the analogue and digital parts. Presented original approach enables the correct formalisation and solution of this task that permits the design and realization of systems with characteristics close to theoretically achievable ones and exceeding the characteristics of the known systems of similar predestination.