Multidimensional particle swarm optimization-based unsupervised planar segmentation algorithm of unorganized point clouds

Color is the major source of information widely used in image analysis and content-based retrieval. Extracting dominant colors that are prominent in a visual scenery is of utter importance since human visual system primarily uses them for perception. In this paper we address dominant color extraction as a dynamic clustering problem and use techniques based on Particle Swarm Optimization (PSO) for finding optimal (number of) dominant colors in a given color space, distance metric and a proper validity index function. The first technique, so-called Multi-Dimensional (MD) PSO, re-forms the native structure of swarm particles in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Therefore, in a multidimensional search space where the optimum dimension is unknown, swarm particles can seek both positional and dimensional optima. Nevertheless, MD PSO is still susceptible to premature convergences due to lack of divergence. To address this problem we then present Fractional Global Best Formation (FGBF) technique, which basically collects all promising dimensional components and fractionally creates an artificial global-best particle (aGB) that has the potential to be a better ldquoguiderdquo than the PSOpsilas native gbest particle. We finally propose an efficient color distance metric, which uses a fuzzy model for computing color (dis-) similarities over HSV (or HSL) color space. The comparative evaluations against MPEG-7 dominant color descriptor show the superiority of the proposed technique.

This paper addresses dynamic data clustering as an optimization problem and propose techniques for finding optimal (number of) clusters in a multi-dimensional data or feature space. In order to accomplish this objective we first propose two novel techniques, which successfully address several major problems in the field of particle swarm optimization (PSO) and promise a significant breakthrough over complex, multi-modal optimization problems at high dimensions. The first one, so-called multi-dimensional (MD) PSO, re-forms the native structure of swarm particles in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Therefore, in a multidimensional search space where the optimum dimension is unknown, swarm particles can seek both positional and dimensional optima. This eventually removes the necessity of setting a fixed dimension a priori, which is a common drawback for the family of swarm optimizers. Nevertheless, MD PSO is still susceptible to premature convergences due to lack of divergence. To address this problem we propose fractional global best formation (FGBF) technique, which basically collects all promising dimensional components and fractionally creates an artificial global-best particle (aGB) that has the potential to be a better ldquoguiderdquo than the PSO's native gbest particle. We investigated both individual and mutual applications of the proposed techniques and demonstrated that the best clustering performance can be achieved by their mutual operation. In order to test and evaluate their clustering performance in terms of accuracy, robustness and scalability, a synthetic data-set, which contains ground-truth clusters and offers a broad range of complexity levels is used. An extensive set of experiments demonstrate that the proposed dynamic clustering technique based on MD PSO with FGBF can extract the optimal (number of) clusters by converging to the global optimum of the validity index function at the true dimension.

The registration of long-strip, terrestrial laser scanning (TLS) point clouds is a prerequisite for various engineering tasks, including tunnels, bridges, and roads. An artificial target-based registration method is proposed in this paper to automatically calculate registration parameters (i.e., rotation, translation) of scanned pairs without initial estimations. The approach is based on the well-known Random Sample Consensus (RANSAC) method and effectively searches the point cloud for corresponding returns from a system of artificial targets. In addition, Closed Constraint Adjustment (CCA) is integrated into the registration method to significantly reduce the accumulative error. Experimental results demonstrate the robustness and feasibility of the proposed approach. It is a promising approach to register automatically long strips with limited external control points with satisfactory precision.

Recently, the use of the particle swarm optimization (PSO) technique for the reconstruction of microwave images has received increasing interest from the optimization community due to its simplicity in implementation and its inexpensive computational overhead. However, the basic PSO algorithm is easily trapping into local minimum and may lead to the premature convergence. When a local optimal solution is reached with PSO, all particles gather around it, and escaping from this local optima becomes di-cult. To overcome the premature convergence of PSO, we propose a new hybrid algorithm of particle swarm optimization (PSO), simulated annealing (SA) and tabu search algorithm (TS) for solving the scattering inverse problem. The incorporation of tabu search (TS) and simulated annealing (SA) as local improvement approaches enable the hybrid algorithm to overleap local optima and intensify its search ability in local regions. Reconstructions of dielectric scatterers from experimental inverse- scattering data are flnally presented to demonstrate the accuracy and e-ciency of the hybrid technique.

Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

Cloud computing and big data: Technologies and applications

Mobile laser scanning (MLS) has emerged as a pivotal tool for accurately collecting tunnel point cloud data and enabling the detection of tunnel deformation. This study introduces a novel approach for the precise monitoring of tunnel cross-section deformation, a critical factor in assessing stability and lining safety. The MLS system used in this study is the Self-mobile Intelligent Laser Scanning System (SILSS) for data acquisition. A comparison with corresponding data acquired by Leica P16 demonstrates that the data collected by SILSS are accurate. The methodology developed utilizes ellipticity parameters and deformation analysis indices based on the ellipse-fitting analysis of circular shield tunnel deformation. A key innovation is the robust denoising of data using the Random Sample Consensus (RANSAC) method, ensuring accurate ellipse fitting and extraction of tunnel lining. Subsequently, an algorithm segmented the tunnel cross-section lining into individual shield tunnels, enabling the calculation of ellipticity parameters for shield tunnels, which are the objects for deformation analysis. The experimental results underscore the novelty and effectiveness of this approach in monitoring deformation across different indices. The method proves to be a reliable tool for assessing tunnel health, providing a detailed evaluation of the cross-section’s condition through statistical and graphical visualization. This study significantly advances shield tunnel monitoring, offering a practical and precise methodology for tunnel deformation analysis based on MLS point cloud data.

Faults generated by seismic motion and stratigraphic lithology changes are essential research objects for seismic motion and hydrocarbon prospecting. This paper emphatically concentrates on the fault reconstruction from the existing fault probability volume. The core idea is to transform the separation of different fault sticks into a fitting and segmentation problem of point cloud data. First, we utilize the point cloud filtering algorithm to preprocess the probability volume and then complete the coarse segmentation of the fault sticks by the region growth algorithm. For the intersecting faults, we employ an enhanced random sample consensus methodology with the constraints of fault orientation and effective inliers to accomplish the detailed segmentation of different fault sticks. Finally, we take the faults identified by the region growth and the random sample consensus method as a priori to construct a random forest model to predict the fault sticks of additional data. By examining and comparing the proposed method with some other approaches with both synthetic and field data, the experimental results manifest that the novel method achieves better segmentation results than others. Moreover, the proposed method is efficient based on the fact that it can handle billions of voxels within a few minutes.

Particle swarm optimisation (PSO) was developed by Kennedy and Eberhart in 1995 (Kennedy & Eberhart, 1995) inspired by the collective behaviour of natural birds or fish. PSO is a stochastic optimisation technique that uses a behaviour of population composed by many search points called particle. In spite of easy implementation in computer algorithms, it is well known as a powerful numerical optimizer. In the typical PSO algorithms, a set of particles searches the optimal solution in the problem space efficiently, by sharing the common attractor called global best. There are many modified versions of PSO by improving convergence property to a certain problem. While, a standard PSO is defined by Bratton and Kennedy (Bratton & Kennedy, 2007) to give a real standard for PSO studies. PSO seems as one of the evolutionary computations (ECs), and it has been shown that PSO is comparable to a genetic algorithm (Angeline, 1998). Thus, a lot of studies have demonstrated the effectiveness of PSO family in optimizing various continuous and discrete optimization problems. And a plenty of applications of PSO, such as the neural network training, PID controller tuning, electric system optimisation have been studied and achieved well results (Kennedy, 1997). However, PSO is often failed in searching the global optimal solution in the case of the objective function has a large number of dimensions. The reason of this phenomenon is not only existence of the local optimal solutions, the velocities of the particles sometimes lapsed into the degeneracy, so that the successive range is restricted in the sub-plain of the whole search hyper-plain. The sub-plane that is defined by finite number of particle velocities is a partial space in the whole search space. The issue of local optima in PSO has been studied and proposed several modifications on the basic particle driven equation (Parsopoulos et al., 2001; Hendtlass, 2005; Liang et al., 2006). There used a kind of adaptation technique or randomized method (e.g. mutation in evolutionary computations) to keep particles velocities or to accelerate them. Although such improvements work well and have ability to avoid fall in the local optima, the problem of early convergence by the degeneracy of some dimensions is still remaining, even if there are no local optima. Hence the PSO algorithm does not always work well for the high-dimensional function.

Segmentation is a low-level processing aimed at the partition of an image in disjoint regions, each one homogeneous with respect to some properties like intensity, texture, shape, etc. Such a task is needed in many high-level processing and applications in such diverse fields as remote-sensing, medical imaging, video coding, and industrial automation, just to name a few. In this work of thesis, we first deal with the problem of color based image segmentation, that is based on some form of homogeneity in the color/spectral properties of the image, and then move to the more complex task of texture based segmentation, where the aim is to recognize complex structures in the image which are typically non homogeneous in terms of spectral properties. Concerning color based segmentation, we focus on a specific class of Markov Random Field (MRF) probability models, namely the Tree-Structured Markov Random Fields (TS-MRF), recently proposed to provide a hierarchical multiscale description of images. Based on such a model, the unsupervised image segmentation is carried out by means of a sequence of nested class splits, where each class is modeled as a local binary MRF. As a first contribution, we first extend the model to generic tree structures removing the unnecessary binary constraint, and then devise a new TS-MRF unsupervised segmentation technique which improves upon the original algorithm by selecting a better tree structure and eliminating spurious classes. Such results are obtained by using the Mean-Shift procedure to estimate the number of pdf modes at each node, and to obtain a more reliable initial clustering for subsequent MRF optimization. To this end, we devise a new reliable and fast clustering algorithm based on the Mean-Shift technique, which makes use of a variable-bandwidth strategy based on the k-Nearest Neighbors (k-NN) technique, and is implemented with a speed-up strategy that cuts significantly the computational complexity. Experimental results on synthetic data and real life images from the remote sensing domain prove the potential of the proposed method. Turning to texture based segmentation, we present a novel multiscale texture model, and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled in turn by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The ``fragmentation'' step allows one to find the elementary textures of the model, while the ``reconstruction'' step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural images from the Berkeley dataset. Finally, an application of the TFR algorithm for the unsupervised segmentation of multiresolution remotely sensed images is proposed, based on the significant presence of textural content in last generation high-resolution satellite images. The obtained results further assess the potential of the proposed method for such real life applications.

Sub-pixel displacement measurement in Digital Image Correlation (DIC) is an optimization problem in search of a point of the deformed image where has the maximum correlation coefficient value to the point of the reference image. Particle Swarm Optimization (PSO) is a novel swarm intelligence algorithm which has great prospect in multidimensional nonlinear optimization because of its advantages of high convergence rate, global search effectiveness, robustness and having few parameters. In this paper, PSO is first applied into DIC to get sub-pixel displacement fields with our aim of proving the feasibility of this method. Two displacements and four deformation gradients for a subset of DIC can all be taken into PSO, while we only take the first two displacements into calculation in consideration of rigid body translation. With set iterative time 20, an accuracy of 0.005 pixels has been achieved between two computer-simulated images by using basic PSO algorithm. In order to limit positions of particles within small areas and thus reduce iterative calculation, an improved integer pixel displacement search method called Grid Method is put forward for accurate integer pixel displacement measurement. Besides, through empirical study, Inverse Function Decreasing Inertia Weight has been proposed and other parameters of PSO have been discussed concerning DIC correlation coefficient function while we attempt to minimize the iterative calculation. We compare the proposed parameters with commonly used PSO parameters and find that PSO with the proposed parameters has much higher convergence rate. So Inverse Function Decreasing Inertia Weight and the set parameters are recommended for use in the PSO method of DIC.

In many sensor fusion algorithms, the vision based RANdom Sample Consensus (RANSAC) method is used for estimating motion parameters for autonomous robots. Usually such algorithms estimate both translation and rotation parameters together which makes them inefficient solutions for merely rotation estimation purposes. This paper presents a novel 3-point RANSAC algorithm for estimating only the rotation parameters between two camera frames which can be utilized as a high rate source of information for a camera-IMU sensor fusion system. The main advantage of our proposed approach is that it performs less computations and requires fewer iterations for achieving the best result. Despite many previous works that validate each hypothesis for all of data points and count the number of inliers for it, we use a voting based scheme for selecting the best rotation among all primary answers. This methodology is much more faster than the traditional inlier based approach and is more efficient for parallel implementation of RANSAC iterations. We also investigate parallel implementation of the proposed 3-point RANSAC using CUDA technology which leads to a great improvement in the processing time of estimation algorithm. We have utilized real datasets for evaluation of our algorithm and also compared it with the well-known 8-point algorithm in terms of accuracy and speed. The results show that the proposed approach improves the speed of estimation algorithm up to 150 times faster than the 8-point algorithm with similar accuracy.

This paper presents a new variant of Basic Particle Swarm Optimization (BPSO) algorithm named QI-PSO for solving global optimization problems. The QI-PSO algorithm makes use of a multiparent, quadratic crossover/reproduction operator defined by us in the BPSO algorithm. The proposed algorithm is compared it with BPSO and the numerical results show that QI PSO outperforms the BPSO algorithm in all the sixteen cases taken in this study.

Difference between acoustic characteristics of speakers can be applied to segment conversational speech. In this paper, an unsupervised speech segmentation algorithm is emphasized while Euclidean distance measure and the distance measure based on GLR (Generalized Likelihood Ratio) and duration model are compared. The latter measure makes use of the likelihood ratio to describe the similarity and text-independent two-speaker verification system shows it is effective in verifying segment points as the result of being sensitive to speaker changes.

A Validation Framework for Brain Tumor Segmentation