Showing papers on "Centroid published in 2013"

Robust gait-based gender classification using depth cameras

Abstract: This article presents a new approach for gait-based gender recognition using depth cameras, that can run in real time. The main contribution of this study is a new fast feature extraction strategy that uses the 3D point cloud obtained from the frames in a gait cycle. For each frame, these points are aligned according to their centroid and grouped. After that, they are projected into their PCA plane, obtaining a representation of the cycle particularly robust against view changes. Then, final discriminative features are computed by first making a histogram of the projected points and then using linear discriminant analysis. To test the method we have used the DGait database, which is currently the only publicly available database for gait analysis that includes depth information. We have performed experiments on manually labeled cycles and over whole video sequences, and the results show that our method improves the accuracy significantly, compared with state-of-the-art systems which do not use depth information. Furthermore, our approach is insensitive to illumination changes, given that it discards the RGB information. That makes the method especially suitable for real applications, as illustrated in the last part of the experiments section.

Electrical Load Pattern Grouping Based on Centroid Model With Ant Colony Clustering

Abstract: Load pattern clustering based on the shape of the electricity consumption is a key tool to provide enhanced knowledge on the nature of the consumption and assist meaningful customer partitioning. This paper presents new developments to group the load patterns using an initial set of centroids specified according to a user-defined centroid model. The original Electrical Pattern Ant Colony Clustering (EPACC) algorithm is illustrated, highlighting its characteristics and parameters, with centroids evolution during the iterative process until stabilization. The EPACC results are compared with those obtained from the classical k-means algorithm to group the representative load patterns taken from a set of non-residential customers in typical weekdays.

Neutral axis as damage sensitive feature

Abstract: Structural health monitoring (SHM) is the process of continuously or periodically measuring structural parameters and the transformation of the collected data into information on real structural conditions. The centroid of stiffness is a universal parameter and its position in a cross-section can be evaluated for any load-carrying beam structure as the position of the neutral axis under conveniently chosen loads. Thus, a change in the position of the neutral axis within a cross-section can indicate a change in the position of the centroid of stiffness, i.e., unusual structural behaviors. This paper proposes a novel monitoring method based on deterministic and probabilistic determination of the position of the neutral axis under conveniently chosen conditions. Therefore, the method proposed in this paper is potentially applicable to a large variety of beam-like structures. Data from two existing structures were used to validate the method and assess its performance: Streicker Bridge at Princeton University and the US202/NJ23 highway overpass in Wayne, NJ. The results show that the neutral axis location is varying even when damage is not present. Reasons for this variation are determined and the accuracy in the evaluation assessed. This paper concludes that the position of the neutral axis can be evaluated with sufficient accuracy using static and dynamic strain measurements performed on appropriate time-scales and indicates its potential to be used as a damage sensitive feature.

Stochastic framework for quantifying the geometrical variability of laminated textile composites using micro-computed tomography

Abstract: Reference period collation, a method recently proposed for analysing the stochastic nature of a nominally periodic textile reinforcement, is extended to allow application to a laminate of stacked, nested plies. The method decomposes the characteristics of the fibre reinforcement into non-stochastic periodic (or systematic) trends and non-periodic stochastic fluctuations. The stochastic character of every tow is analysed in terms of the centroid position, aspect ratio, area, and orientation of its cross-section. The collation method is tested using X-ray micro-computed tomography data for a seven-ply 2/2 twill woven carbon-epoxy composite produced by resin transfer moulding. All tow characteristics, with exception of the in-plane centroid position, exhibit systematic trends that show only mild differences between plies. They correlate most strongly with cross-over points within a single ply. Of the various parameters, the in-plane centroid position is subject to the largest tow-to-tow variability, with deviations correlated over distances exceeding the unit cell size.

Fast place recognition with plane-based maps

Abstract: This paper presents a new method for recognizing places in indoor environments based on the extraction of planar regions from range data provided by a hand-held RGB-D sensor. We propose to build a plane-based map (PbMap) consisting of a set of 3D planar patches described by simple geometric features (normal vector, centroid, area, etc.). This world representation is organized as a graph where the nodes represent the planar patches and the edges connect planes that are close by. This map structure permits to efficiently select subgraphs representing the local neighborhood of observed planes, that will be compared with other subgraphs corresponding to local neighborhoods of planes acquired previously. To find a candidate match between two subgraphs we employ an interpretation tree that permits working with partially observed and missing planes. The candidates from the interpretation tree are further checked out by a rigid registration test, which also gives us the relative pose between the matched places. The experimental results indicate that the proposed approach is an efficient way to solve this problem, working satisfactorily even when there are substantial changes in the scene (lifelong maps).

A Decentralized Controller-Observer Scheme for Multi-Agent Weighted Centroid Tracking

Abstract: In this technical note a decentralized controller-observer scheme for a multi-agent system is presented. The key idea is to develop, for each agent, an observer of the collective system's state and a motion controller. The observer is updated using only information from the agent itself and from its neighbors; the motion controller is designed in order to allow the team's weighted centroid to track an assigned time-varying reference. Convergence of the overall scheme is proven for directed and undirected communication graphs; moreover the extensions to the case of switching communication topologies and to the presence of saturation in the control input are discussed. Finally, numerical simulations are illustrated to validate the approach.

A new algorithm for allocating multiple distributed generation units based on load centroid concept

Abstract: Allocation of distributed generation (DG) units is commonly formulated as a constrained nonlinear optimization problem solved by complex iterative mathematical or heuristic techniques. Heavy computational burden, very long solution time, probable divergence and possibility of getting only a sub-optimal solution are some serious drawbacks. In this paper, a systematic simple approach to allocate multiple DG units in radial/meshed distribution network is proposed. The concept of equivalent load is introduced and extended to identify the load centroid precisely with two methods. A performance index that combines the power system real power loss and average node voltage is defined. Based on load centroid and performance index, a straightforward algorithm for sizing and locating multiple DG units is developed. The proposed technique is applied to radial and meshed test systems. Results confirm stability, integrity and efficacy of the proposed approach.

Shack-Hartmann wavefront sensor image analysis: a comparison of centroiding methods and image-processing techniques

Abstract: Spot estimation accuracy of Shack-Hartmann images and its impact on Airborne Aero-Optic Laboratory (AAOL) wavefront statistics are addressed. A study is conducted of an individual spot simulated using a double sinc function under varying degrees of additive non-zero mean Gaussian noise within a 15×15 pixel area-of-interest. The focus of this paper is two-fold. First, the accuracy of four existing centroiding methods including first moment, convolution, Gaussian, and weighted first moment are compared. It is found that the weighted first moment centroid most accurately estimates spot centers but requires significantly more computational time with respect to the first moment method. Second, three image-processing techniques, including gamma correction, thresholding, and windowing, are analyzed to determine their influence on each centroiding method’s spot estimation accuracy. A fourth order gamma correction significantly reduces spot estimation error for three centroiding methods. The key result is that the accuracy of the first moment centroid with an applied gamma correction is comparable to the weighted first moment without the computational burden. Finally, the first moment centroid with gamma correction and weighted first moment centroid are applied to AAOL flight data. Wavefront statistics are computed and compared to the commonly used first moment centroid.

Jeffreys Centroids: A Closed-Form Expression for Positive Histograms and a Guaranteed Tight Approximation for Frequency Histograms

Abstract: Due to the success of the bag-of-word modeling paradigm, clustering histograms has become an important ingredient of modern information processing. Clustering histograms can be performed using the celebrated k-means centroid-based algorithm. From the viewpoint of applications, it is usually required to deal with symmetric distances. In this letter, we consider the Jeffreys divergence that symmetrizes the Kullback-Leibler divergence, and investigate the computation of Jeffreys centroids. We first prove that the Jeffreys centroid can be expressed analytically using the Lambert W function for positive histograms. We then show how to obtain a fast guaranteed approximation when dealing with frequency histograms. Finally, we conclude with some remarks on the k-means histogram clustering.

Measuring device and calibration method for optical lens distortion

Abstract: Provided is a measuring device and a calibration method for optical lens distortion. The measuring device comprises a single star light simulator, an adjusting rack, a to-be-tested lens, a CCD (charge coupled device) camera, a one-dimensional air flotation turntable, an angle encoder, a computer and an optical platform. The calibration method includes the steps of using a centroid localization algorithm to determine centroid position coordinates of a star point image when the to-be-tested lens is under different fields of view, establishing a calibration model for the to-be-tested lens distortion based on the distribution of the centroid position coordinates of the star point image under the entire field of view, and realizing the calibration of the distorted to-be-tested lens. The measuring device and the calibration method for the optical lens distortion has the advantages that the device is simple; the method is convenient; measurement accuracy is high; and the optical lens distortion can be easily measured and calibrated.

Systems and methods for generating spherical images

Abstract: An imaging system comprises four image sensors each pointing outwardly from the vertices of a notional tetrahedron with the optical axes of the image sensors substantially collinear with respective medians of the notional tetrahedron, with the focal plane array of each image sensor positioned between the lens system of its respective image sensor and the centroid of the notional tetrahedron. The imaging system and can be used to obtain image data for generating a spherical image of the space surrounding the imaging system. A method for generating a spherical image from this image data assigns spherical coordinates to the pixels in the images according to a cylindrical projection that is individually aligned with the image plane of each image, and blends overlapping pixels and fills blank pixel spaces. The method can be applied to image data representing outward views from the vertices or centroids of faces of any Platonic solid.

Supervised term weighting centroid-based classifiers for text categorization

Abstract: In this paper, we study the theoretical properties of the class feature centroid (CFC) classifier by considering the rate of change of each prototype vector with respect to individual dimensions (terms). We show that CFC is inherently biased toward the larger (dominant majority) classes, which invariably leads to poor performance on class-imbalanced data. CFC also aggressively prune terms that appear across all classes, discarding some non-exclusive but useful terms. To overcome these CFC limitations while retaining its intrinsic and worthy design goals, we propose an improved centroid-based classifier that uses precise term-class distribution properties instead of presence or absence of terms in classes. Specifically, terms are weighted based on the Kullback–Leibler (KL) divergence measure between pairs of class-conditional term probabilities; we call this the CFC–KL centroid classifier. We then generalize CFC–KL to handle multi-class data by replacing the KL measure with the multi-class Jensen–Shannon (JS) divergence, called CFC–JS. Our proposed supervised term weighting schemes have been evaluated on 5 datasets; KL and JS weighted classifiers consistently outperformed baseline CFC and unweighted support vector machines (SVM). We also devise a word cloud visualization approach to highlight the important class-specific words picked out by our KL and JS term weighting schemes, which were otherwise obscured by unsupervised term weighting. The experimental and visualization results show that KL and JS term weighting not only notably improve centroid-based classifiers, but also benefit SVM classifiers as well.

Decentralized centroid and formation control for multi-robot systems

Abstract: In this paper, a decentralized control strategy for networked multi-robot systems that allows the tracking of the team centroid and the relative formation is presented. The proposed solution consists of a distributed observer-controller scheme where, based only on local information, each robot estimates the collective state and tracks the two assigned control variables. We provide a formal stability analysis of the observer-controller scheme and we relate convergence properties to the topology of the connectivity graph. Experiments are presented to validate the approach.

Design and characterization of precise laser-based autofocusing microscope with reduced geometrical fluctuations

Abstract: Due to consumer preference for products with ever higher performance, a requirement exists for precise autofocusing microscope systems to perform the inspection process in automated mass production lines. Accordingly, the present study proposes a laser-based microscope system in which a precise autofocusing capability is achieved using a position feedback signal based on the distance L between the geometrical center (X c , Y c ) of the image captured by the CCD sensor and the centroid (x centroid , y centroid ) of the image. The experimental results show that the proposed system has a positioning accuracy of 2.2 μm and a response time of 1 s given a working range of ±200 μm. The autofocusing performance of the proposed system is thus better than that of a conventional centroid-based system, which typically achieves a positioning accuracy of around 5.2 μm.

Detecting and identifying method for annular coding mark point

Abstract: The invention belongs to the field of close-range photogrammetry and relates to a detecting and identifying method for an annular coding mark point. The method includes that first, canny edge detection is conducted on a collected image, an outline centroid is closed through a series of limiting conditions and calculation, and noise and non-coding mark points are filtered; then least square ellipse fitting is adopted, coding mark point location is conducted, an ellipse fitting error is combined to judge a partition coding mark point outline, and the outline is filled; finally, ALPC transformation for transforming a local concentric ellipse into parallel straight lines is provided, the ALPC transformation is conducted on the partitioned coding mark point, and transformed image characteristics are used for decoding. By means of the detecting and identifying method, location of the coding mark point can reach a sub pixel level, local shape characteristics of a concentric ellipse are transformed into shape characteristics of parallel straight lines which are easy to detect and calculate, coding mark point identifying speed is improved, and effects of an included angle of a camera optical axis and a coding mark point normal on the coding mark point identifying accuracy can be reduced.

Joint tracking and classification of extended object using random matrix

Abstract: Most practical extended objects can be classified by their size and shape. The random-matrix approach to extended object tracking provides efficient estimation of both the centroid state and the extension. For effective classification of objects, however, prior size and shape information of the objects needs to be sufficiently modeled into the random-matrix-based framework. For joint tracking and classification of an extended object using a random matrix, we propose a Bayesian framework within which the probability density function of the object state and extension and the probability mass function of the object class are obtained jointly. Only measurements of scattering centers are needed in this framework. The size and shape properties distinguishing objects of different classes are treated as constraints and integrated into the framework as pseudo-measurements. Online orientations of the objects are obtained by a maximum likelihood method. Both the derived estimator and the likelihood for classification have a simple closed form. Simulation results demonstrated the effectiveness of the proposed approach.

An Improved Method of Discrete Point Cloud Filtering based on Complex Environment

Abstract: Under keep the geometrical characteristics of point cloud, efficient processing of the original point cloud data of noise and outliers can greatly improve the search efficiency. A filtering algorithm is proposed to improve existing methods. Firstly, 3D voxel grid is created for the massive point cloud data approximating other points inside the voxel with the centroid of all points; then, the neighborhood of discrete points is analyzed statistically, calculating average distance of every point to its neighboring points and filtering the outliers outside the reference ranges of average distance from the data set; finally, the segmentation rules are improved according to the characteristics of KD-Tree. A large amount of experimental results show that this stable and reliable algorithm can compress and filter the point cloud data quickly and effectively. At the same time, it greatly accelerates the search speed.

Ranking Generalized Trapezoidal Fuzzy Numbers with Euclidean Distance by the Incentre of Centroids

Abstract: This paper proposes a method on the incentre of Centroids and uses of Euclidean distance to ranking generalized fuzzy numbers. In this method, splitting the generalized trapezoidal fuzzy numbers into three plane figures and then calculating the centroids of each plane figure followed by the incentre of the centroids and then finding the Euclidean distance. For the validation the results of the proposed approach are compared with dieren t existing approaches.

Selection of Initial Centroids for k-Means Algorithm

Abstract: Clustering is one of the important data mining techniques. k-Means (1) is one of the most important algorithm for Clustering. Traditional k-Means algorithm selects initial centroids randomly and in k-Means a lgorithm result of clustering highly depends on selection of initial centroids. k-Means algorithm is sensitive to initia l centroids so proper selection of initial centroids is necessa ry. This paper introduces an efficient method to start the k -Means with good initial centroids. Good initial centroids are useful for better clustering.

Mapping shape quantitative trait loci using a radius-centroid-contour model.

Abstract: As the consequence of complex interactions between different parts of an organ, shape can be used as a predictor of structural–functional relationships implicated in changing environments. Despite such importance, however, it is no surprise that little is known about the genetic detail involved in shape variation, because no approach is currently available for mapping quantitative trait loci (QTLs) that control shape. Here, we address this problem by developing a statistical model that integrates the principle of shape analysis into a mixture-model-based likelihood formulated for QTL mapping. One state-of-the-art approach for shape analysis is to identify and analyze the polar coordinates of anatomical landmarks on a shape measured in terms of radii from the centroid to the contour at regular intervals. A procrustes analysis is used to align shapes to filter out position, scale and rotation effects on shape variation. To the end, the accurate and quantitative representation of a shape is produced with aligned radius-centroid-contour (RCC) curves, that is, a function of radial angle at the centroid. The high dimensionality of the RCC data, crucial for a comprehensive description of the geometric feature of a shape, is reduced by principal component (PC) analysis, and the resulting PC axes are treated as phenotypic traits, allowing specific QTLs for global and local shape variability to be mapped, respectively. The usefulness and utilization of the new model for shape mapping in practice are validated by analyzing a mapping data collected from a natural population of poplar, Populus szechuanica var tibetica, and identifying several QTLs for leaf shape in this species. The model provides a powerful tool to compute which genes determine biological shape in plants, animals and humans.

Advanced leaf image retrieval via Multidimensional Embedding Sequence Similarity (MESS) method

Abstract: A novel method for shape analysis and similarity measurement is introduced based on a time series matching approach. It applies to shapes represented through one-dimensional signals and has as objectives to utilize efficiently the provided information and to optimize the shape matching process. The new technique is tested on boundaries from leaf images, after their conversion into 1D sequences using either the Centroid Contour Distance (CCD) or the Angle code (AC) measurements. In the core of the new method lies the `time delay'-based transformation of a given 1D sequence to an ensemble of vectors embedded in a multivariate phase space. The resulting point set is considered as representative of the leaf identity. Inter-leaf comparisons are carried out in a pairwise fashion by employing the multidimensional, Wald---Wolfowitz, statistical test for the `two-sample problem', which implicitly performs shape matching and similarity quantification. The comparative experimentation shows that the complexity of our method is moderate, while the leaf retrieval performance, compared to that achieved by standard matching procedures usually employed with the CCD and AC representations, is greatly improved.