Boundary Tracking Research Articles

Mini Kirsch Edge Detection and Its Sharpening Effect

In computer vision, edge detection is a crucial step in identifying the objects’ boundaries in an image. The existing edge detection methods function in either spatial domain or frequency domain, fail to outline the high continuity boundaries of the objects. In this work, we modified four-directional mini Kirsch edge detection kernels which enable full directional edge detection. We also introduced the novel involvement of the proposed method in image sharpening by adding the resulting edge map onto the original input image to enhance the edge details in the image. From the edge detection performance tests, our proposed method acquired the highest true edge pixels and true non-edge pixels detection, yielding the highest accuracy among all the comparing methods. Moreover, the sharpening effect offered by our proposed framework could achieve a more favorable visual appearance with a competitive score of peak signal-to-noise ratio and structural similarity index value compared to the most widely used unsharp masking and Laplacian of Gaussian sharpening methods. The edges of the sharpened image are further enhanced could potentially contribute to better boundary tracking and higher segmentation accuracy.

Misalignment of hemodynamic forces in the left ventricle is associated with adverse remodeling following STEMI

Abstract Funding Acknowledgements Type of funding sources: None. Background Infarct size (IS), area at risk (AAR) and microvascular obstruction (MVO) are well known predictors of adverse remodeling (aLVr) following acute myocardial infarction, while the pathogenic role of left ventricular (LV) hemodynamic forces (HDFs) is still unknown. Recent evidence suggests the role of HDFs in negative remodeling after pathogenic events. Purpose To identify LV HDFs patterns associated with aLVr in reperfused ST-segment elevation MI (STEMI) patients. Methods Forty-nine acute STEMI patients underwent CMR at 1 week (baseline) and 4 months (follow-up) after MI. The following parameters were measured: left ventricular end-diastolic and end-systolic volume index for body surface area (LVEDVi and LVESVi), left ventricular ejection fraction (LVEF) and LV mass index, AAR and IS. LV HDFs were computed at baseline from cine CMR long axis datasets using a novel method based on LV endocardial boundary tracking. LV HDFs were calculated both in apex-base (A-B) and latero-septal (L-S) directions. The distribution of LV HDFs were evaluated by L-S over A-B HDFs ratio (L-S/A-B HDFs ratio %). All HDFs parameters are computed over the entire heartbeat, in systole and diastole. aLVr was defined as an absolute increase in LVESV of at least 15% (ΔLV-ESV ≥15%). Results Patients with aLVr (n = 18; 37%) had significant greater value of AAR (32 ± 23 vs 22 ± 18; p = 0.03) and slightly larger IS (23 ± 16 vs 15 ± 11; p= 0.07) at baseline. In patients with aLVr at FU, baseline systolic L-S HDF were lower (2.7 ± 0.9 vs 3.6 ± 1; p = 0.027) while diastolic L-S/A-B HDF ratio was significantly higher (28 ± 14 vs 19 ± 6; p = 0.03), reflecting higher grade of diastolic HDFs misalignment. At univariate logistic regression analysis, higher IS [Odd ratio (OR) 1.05; 95% confidence interval (95% CI) 1.01-1.1; p= 0.04] L-S HDFs (OR 0.41; 95% CI 0.2-0.9; p= 0.04] and higher diastolic L-S/A-B HDFs ratio (OR 1.1; 95% CI 1.01-1.2; p= 0.05) were associated with aLVr at FU (Table). At multivariate logistic regression analysis, L-S/A-B HDF ratio remained the only independent predictor of adverse LV remodeling after correction for other baseline determinants. Conclusion Misalignment of diastolic HDFs following STEMI is associated with aLVr observed after 4 months. Predictors of adverse remodeling Univariate Multivariate Parameter OR (95% CI) P OR (95% CI) P IS (%) 1.05 (1.01-1.1) 0.042 - - Systolic L-S HDF 0.41 (0.2-0.9) 0.04 - - Diastolic L-S/A-B HDF Ratio 1.1 (1.01-1.2) 0.05 1.1 (1.01-1.2) 0.04 A-B:apex-base; L-S: latero-septal; HDFs: hemodynamic forces Abstract Figure. Diastolic HDFs distribution and aLVr

Predictive Boundary Tracking Based on Motion Behavior Learning for Continuous Objects in Industrial Wireless Sensor Networks

The diffusion of toxic gas, biochemical material, and radio-active contamination – known as continuous objects – endangers the safe production of the petrochemical and nuclear industries. To mitigate these well known hazards, the new paradigm of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">industrial wireless sensor networks</i> (IWSNs) shows great potential in monitoring evolving hazardous phenomena in unfriendly industrial fields. In order to prolong the lifetime of these networks, existing research focuses on energy-efficient boundary nodes selection. However, sensor state cannot be scheduled proactively, due to the difficulty in predicting the spatiotemporal evolution of diffusive hazards. In this article, we propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">motion behavior learning predictive tracking</i> (MBLPT) algorithm for continuous objects in IWSNs. Considering the relatively unpredictable patterns exhibited by continuous objects, the MBLPT uses a data-driven approach for motion state recognition, and then utilizes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Bayesian model averaging</i> (BMA) for future boundary prediction. The prediction of the MBLPT provides the knowledge for establishing a wake-up zone, in which standby nodes are activated in advance to participate in tracking the upcoming boundary. Simulation results demonstrate that the MBLPB achieves superior energy efficiency while keeping effective tracking accuracy.

Retracted] Data Research on Tobacco Leaf Image Collection Based on Computer Vision Sensor

In the process of tobacco silk making, how to better improve the quality of stem and leaf separation has become an issue of concern. His research mainly discusses the data collected from tobacco leaf images based on computer vision sensors. In LM (Levenberg‐Marquarelt) as a training function, the algorithm uses threshing effect samples for training and learning. This paper is aimed at extracting the shape characteristic parameters of tobacco leaves and obtains the shape parameters of the length, width, area, circumference, and roundness of the tobacco leaves. In this paper, boundary tracking is used to obtain the coordinate and direction information of the tobacco leaf boundary pixels in the image, which provides a basis for obtaining the subsequent extraction of tobacco leaf characteristic parameters. In the tobacco leaf grading system, the tobacco leaf feature parameter extraction module displays the geometric characteristics of tobacco leaf, such as length, width, area, aspect ratio, rectangularity, and color characteristic, hue H, saturation S, A channel, and B channel in detail through the computer vision sensor. Finally, the subjective and objective combination weighting method is used to combine and weight the indicators of the threshing effect of the first‐level threshing machine, which not only considers the quantity of information provided by the indicators but also takes into account the subjective view of the experts, which increases the weight of the indicators, accuracy, and scientificity. The approximation accuracy of the training samples of the threshing effect prediction model based on the BP neural network LM algorithm is 99.495%, the approximation accuracy of the validation set is 96.535%, and the approximation accuracy of the test set is 98.392%. This research will greatly improve production efficiency and meet the enterprise’s requirements for high efficiency and low cost.

High order ADER schemes and GLM curl cleaning for a first order hyperbolic formulation of compressible flow with surface tension

In this work, we introduce two novel reformulations of the weakly hyperbolic model for two-phase flow with surface tension, recently forwarded by Schmidmayer et al. In the model, the tracking of phase boundaries is achieved by using a new vector field, rather than a scalar tracer, so that the surface-force stress tensor can be expressed directly as an algebraic function of the state variables, without requiring the computation of gradients of the scalar tracer. An interesting and important feature of the model is that this interface field obeys a curl involution constraint, that is, the vector field is required to be curl-free at all times.The proposed modifications are intended to restore the strong hyperbolicity of the model, and are closely related to divergence-preserving numerical approaches developed in the field of numerical magnetohydrodynamics (MHD). The first strategy is based on the theory of Symmetric Hyperbolic and Thermodynamically Compatible (SHTC) systems forwarded by Godunov in the 60s and 70s and yields a modified system of governing equations which includes some symmetrisation terms, in analogy to the approach adopted later by Powell et al. in the 90s for the ideal MHD equations. The second technique is an extension of the hyperbolic Generalized Lagrangian Multiplier (GLM) divergence cleaning approach, forwarded by Munz et al. in applications to the Maxwell and MHD equations.We solve the resulting nonconservative hyperbolic partial differential equation (PDE) systems with high order ADER-WENO Finite Volume and ADER Discontinuous Galerkin (DG) methods with a posteriori Finite Volume subcell limiting and carry out a set of numerical tests concerning flows dominated by surface tension as well as shock-driven flows. We also provide a new exact solution to the equations, show convergence of the schemes for orders of accuracy up to ten in space and time, and investigate the role of hyperbolicity and of curl constraints in the long-term stability of the computations.

基于先验知识的Kmeans聚类生物质颗粒缺陷检测方法

Biomass particle is one of the most important solid briquette fuels for agricultural and forestry biomass energy. Temperature, pressure, moisture and discharge holes are important factors to control biomass particle forming. The inappropriate setting of the parameters or blocking of the discharge hole will lead to the defects of the biomass particles, such as too short or poor roundness or pits or cracks. In order to detect these defects automatically, this paper proposes a method based on K-Means with prior knowledge. Firstly, the inner boundary tracking region detection algorithm and filling algorithm are combined to extract the regions in the backlight image. The regions are divided into debris, independent biomass particle regions and adhesive biomass particle regions. Secondly, K-Means with prior knowledge is used to segment the adhesive regions to get the independent biomass particle regions. Finally, the features of the biomass particles are extracted to judge the type of defects. The proposed method has been tested on images acquired from the vision system of the ring roller pellet mill. Experimental results show the efficiency of the proposed method in high detection accuracy and short detection time.

Relaxed decoupled direct calculation of voltage collapse points and its application in static voltage stability region boundary formation

Static voltage stability is critical for the operation of power grids. With the penetration of renewable energies, region-based method become a choice to present the stability of a power grid. Static voltage stability region is hence a useful and intuitive tool to determine the safety margin of a power grid. The formation of static voltage stability region is however time consuming. To overcome such issue, this work proposes a relaxed decoupled direct calculation (RDDC) method to find voltage collapse points (VCPs). The direct calculation of VCPs is a Newton-Raphson type method and faces the sensitivity issue of the initial values. Boundary tracking method provides a framework to utilize the information from neighbor VCPs and hence is integrated with the proposed RDDC method. The results show that the RDDC method is able to calculating VCPs as precise as continuation power flow with less computational time. When RDDC is integrated with boundary tracking, results show that the static voltage stability region boundary can be generated with high precision, and computational performance improvement can be observed for all the test systems from nine buses to ten thousand of buses. This demonstrates the applicability and scalability of the proposed method to power systems with different scales.

Boundary Tracking of Continuous Objects Based on Binary Tree Structured SVM for Industrial Wireless Sensor Networks

Due to the flammability, explosiveness and toxicity of continuous objects (e.g., chemical gas, oil spill, radioactive waste) in the petrochemical and nuclear industries, boundary tracking of continuous objects is a critical issue for industrial wireless sensor networks (IWSNs). In this article, we propose a continuous object boundary tracking algorithm for IWSNs – which fully exploits the collective intelligence and machine learning capability within the sensor nodes. The proposed algorithm first determines an upper bound of the event region covered by the continuous objects. A binary tree-based partition is performed within the event region, obtaining a coarse-grained boundary area mapping. To study the irregularity of continuous objects in detail, the boundary tracking problem is then transformed into a binary classification problem; a <i>hierarchical soft margin support vector machine</i> training strategy is designed to address the binary classification problem in a distributed fashion. Simulation results demonstrate that the proposed algorithm shows a reduction in the number of nodes required for boundary tracking by at least 50 percent. Without additional fault-tolerant mechanisms, the proposed algorithm is inherently robust to false sensor readings, even for high ratios of faulty nodes ( <inline-formula><tex-math notation="LaTeX">$\approx 9\%$</tex-math></inline-formula> ).

Boundary tracking control of flexible beams for transferring motions

Although flexible beams for transmitting both translational and rotational large motions are used in practice such as ocean drill pipes, their control has not been considered. This paper develops boundary feedback controllers to stabilise these beams at their reference configurations. Exact nonlinear partial differential equations governing motion of the beams in three-dimensional space are derived and used in the control design. The designed controllers guarantee globally practically asymptotically stability of the beam motions at the reference states (i.e. positions and rotations of a straight beam moving axially with a desired velocity and rotating around its axial axis with a desired velocity). In the control design and analysis of well-posedness and stability, we utilise different transformations between the earth-fixed and body-fixed coordinates, Sobolev embeddings, and a Lyapunov-type theorem developed for a class of evolution systems in Hilbert space. Simulation results are also included to illustrate the effectiveness of the proposed control design.

Estimating an LPV Model of Driver Neuromuscular Admittance Using Grip Force as Scheduling Variable

Humans can rapidly change their low-frequency arm dynamics to resist forces or give way to them. Quantifying driver time-varying arm dynamics is important to develop steer-by-wire and haptic support systems. Conventional linear time-invariant (LTI) identification, and even time-varying techniques such as wavelets, fail to capture fast changing dynamics. Moreover, such techniques require perturbation signals on the steering wheel (SW), which may affect steering feel and control behavior. We propose a novel two-step method to estimate time-varying driver admittance, using unobtrusive grip-force measurements of the hands on the wheel to schedule a linear parameter-varying (LPV) model that captures the full admittance range. A total of 18 subjects participated in two experiments in a simulator with an actuated SW. In a sensorimotor control experiment, we first establish the grip force and admittance relationship, requiring subjects to perform a boundary tracking task where perturbations on the wheel enabled local LTI identification. Six boundary widths is used to evoke admittance changes, after which a global LPV model is obtained through interpolation between the local models. Results show an inverse relationship between grip force and admittance and that the LPV model accurately captures the admittance settings (fit percentage > 90%). Second, a driving experiment is followed that aims to evoke differences in grip force and admittance in response to varying road widths, offering more realistic data to evaluate the LPV model predictions. Results show that the LPV model accurately describes adaptations in admittance to road width. Our method allows for online estimation of time-varying admittance during driving, without applying force perturbations.

Geometric recognition methodology of honeycomb structure based on dynamic window

Defect determination is important for guaranteeing the quality of sandwich structure. The present study, a geometric recognition methodology based on dynamic window was constructed for honeycomb structure, by identifying the vertices from given images captured in the manufacturing process. The combination of traversing window, annihilation window, and tracking window was developed to reconstruct the contoured maximums, locate the vertices positions, and determine the cell–node relationships, respectively. Moore boundary tracking was practically used to deal with the problem caused by the edge effect. Based on these, all relevant vertices as well as their relationship of each honeycomb cell can be determined. Afterward, quality assessment of the honeycomb product was carried out in terms of the maximum, the average, and the maximum average degree deviation. Illustrations validate the present methodology well. All these achievements shed a light on design of the consistency, reliability, and homogeneity of high-standard sandwich structure.

Towards objective identification and tracking of convective outflow boundaries in next-generation geostationary satellite imagery

Abstract. Sudden wind direction and speed shifts from outflow boundaries (OFBs) associated with deep convection significantly affect weather in the lower troposphere. Specific OFB impacts include rapid variation in wildfire spread rate and direction, the formation of convection, aviation hazards, and degradation of visibility and air quality due to mineral dust aerosol lofting. Despite their recognized importance to operational weather forecasters, OFB characterization (location, timing, intensity, etc.) in numerical models remains challenging. Thus, there remains a need for objective OFB identification algorithms to assist decision support services. With two operational next-generation geostationary satellites now providing coverage over North America, high-temporal- and high-spatial-resolution satellite imagery provides a unique resource for OFB identification. A system is conceptualized here designed around the new capabilities to objectively derive dense mesoscale motion flow fields in the Geostationary Operational Environmental Satellite 16 (GOES-16) imagery via optical flow. OFBs are identified here by isolating linear features in satellite imagery and backtracking them using optical flow to determine if they originated from a deep convection source. This “objective OFB identification” is tested with a case study of an OFB-triggered dust storm over southern Arizona. The results highlight the importance of motion discontinuity preservation, revealing that standard optical flow algorithms used with previous studies underestimate wind speeds when background pixels are included in the computation with cloud targets. The primary source of false alarms is the incorrect identification of line-like features in the initial satellite imagery. Future improvements to this process are described to ultimately provide a fully automated OFB identification algorithm.

Simulation model size reduction using volume of investigation by fast marching method

The numerical methods have been widely utilized to conduct history matching work in the formations with complex in-situ conditions. Due to the fact that the history matching process normally requires running numerous models to find the best match between the history production data and the simulated production data, it is necessary to improve the computational efficiency of the numerical method in order to reduce the computational time. In this work, the author introduces a dynamic-volume-of-investigation (DVOI) implicit-finite-difference (IMFD) method to increase the computational efficiency of the conventional IMFD method. In the DVOI-IMFD method, the computational efficiency has been improved by reducing the simulation model size using volume of investigation (VOI) by fast marching method (FMM).This proposed DVOI-IMFD method is developed based on the concept of VOI. The VOI initiates at the wellbore and extends to the further region of the reservoir as production proceeds. Beyond the VOI, the pressure disturbance in the reservoir is regarded as negligible. Following this scenario, the author assumes that, at each timestep, the pressure response in the region that is beyond the VOI can be neglected, and we only study the pressure response in the region that is within the VOI to approximately characterize the transient flow behavior in the reservoir. Therefore, this proposed numerical approach is composed of two parts, namely, predicting the VOI at each timestep and applying the IMFD within the VOI. In this work, the DVOI is captured with a boundary tracking technique which is called FMM. The author applies this proposed DVOI-IMFD method to different scenarios and compares the simulation outputs and computational time of the DVOI-IMFD method to those of the conventional IMFD method. The calculated results show that the outputs of this proposed method exhibit negligible difference from those of the conventional IMFD method, whereas the computational speed of this proposed method can be significantly faster than that of the conventional IMFD method.

Real-Time Mine Road Boundary Detection and Tracking for Autonomous Truck.

Road boundary detection is an important part of the perception of the autonomous driving. It is difficult to detect road boundaries of unstructured roads because there are no curbs. There are no clear boundaries on mine roads to distinguish areas within the road boundary line and areas outside the road boundary line. This paper proposes a real-time road boundary detection and tracking method by a 3D-LIDAR sensor. The road boundary points are extracted from the detected elevated point clouds above the ground point cloud according to the spatial distance characteristics and the angular features. Road tracking is to predict and update the boundary point information in real-time, in order to prevent false and missed detection. The experimental verification of mine road data shows the accuracy and robustness of the proposed algorithm.

An extension of the differential image foresting transform and its application to superpixel generation

The Image Foresting Transform (IFT) is a graph-based framework to develop image operators based on optimum connectivity between a root set and the remaining nodes, according to a given path-cost function. Its applications involve a variety of tasks, such as segmentation, boundary tracking, skeletonization, filtering, among others. The Differential Image Foresting Transform (DIFT) allows multiple IFT executions for different root sets and a same monotonically incremental path-cost function, making the processing time proportional to the number of modified nodes. In this paper, we extend the DIFT algorithm for non-monotonically incremental functions with root-based increases. This proposed extension, called Generalized DIFT (GDIFT), has been successfully used as the core part of some modern superpixels methods with state-of-the-art results. Experimental results show considerable efficiency gains over the sequential flow of IFTs for the generation of superpixels, also avoiding inconsistencies in image segmentation, which could occur with the regular DIFT algorithm.

Accelerated Piston Problem and High Order Moving Boundary Tracking Method for Compressible Fluid Flows

Reliable tracking of moving boundaries is important for the simulation of compressible fluid flows, and there are a lot of contributions in literature. We recognize from the classical piston proble...

Organ Dynamics and Hemodynamic of the Whole HH25 Avian Embryonic Heart, Revealed by Ultrasound Biomicroscopy, Boundary Tracking, and Flow Simulations

Congenital heart malformations occur to substantial number of pregnancies. Studies showed that abnormal flow biomechanical environments could lead to malformations, making it important to understand the biomechanical environment of the developing heart. We performed 4D high-frequency ultrasound scans of chick embryonic hearts at HH25 to study the biomechanics of the whole heart (atria and ventricle). A novel and high-fidelity motion estimation technique, based on temporal motion model and non-rigid image registration algorithm, allowed automatic tracking of fluid-structure boundaries from scan images, and supported flow simulations. Results demonstrated that atrial appendages were the most contractile portion of the atria, having disproportionately high contribution to atrial blood pumping for its volume in the atria. However, the atria played a small role in blood pumping compared to the ventricle, as it had much lower ejection energy expenditure, and as the ventricle appeared to be able to draw inflow from the veins directly during late diastole. Spatially and temporally averaged wall shear stresses (WSS) for various cardiac structures were 0.062–0.068 Pa, but spatial-averaged WSS could be as high as 0.54 Pa in the RV. WSS was especially elevated at the atrial inlet, atrioventricular junction, regions near to the outflow tract, and at dividing lines between the left and right atrium and left and right side of the ventricle, where septation had begun and the lumen had narrowed. Elevated WSS could serve as biomechanics stimulation for proper growth and development.

A robust multi phase model to investigate molten material relocation during total flow blockage in SFR fuel subassembly

A transient, multi-phase enthalpy based computational model is developed to analyse the streaming and freezing characteristics of the molten fuel in a blocked fuel subassembly (SA) during Total Flow Blockage (TFB) at the foot of the SA. During TFB accident progression, a molten material pool is formed following the meltdown of fuel pins. The molten fuel has the potential to relocate axially through the available subchannels in the downward direction. The mathematical model comprises of two modules; a Fluid Dynamics module and a Heat Transfer module. The model adopts both implicit and explicit type of finite difference techniques employing a variable grid system for boundary tracking. The mathematical model has been validated against benchmark experimental data and SIMMER III code prediction reported in open literature. The developed model is employed to simulate the relocation of molten fuel in a prototype fast reactor fuel SA under accident condition. The simulation results indicate that the molten fuel is unable to penetrate the axial blankets in fuel SA without freezing and forming a blockage mainly owing to the rapid freezing of melt. Further, a parametric analysis is carried out to ascertain the influence of critical parameters on the relocation and freezing characteristics. It is observed that the design of the fuel SA has a potential effect on the streaming behaviour and enhancement in fuel relocation is substantially achieved by dwindling the fuel pin size, especially axial length and diameter of the pin, thus preventing the accident progression to the neighbouring SAs.

Environmental Feature Exploration With a Single Autonomous Vehicle

In this paper, a sliding mode-based guidance strategy is proposed for the control of an autonomous vehicle. The aim of the autonomous vehicle deployment is the study of unknown environmental spatial features. The proposed approach allows the solution of both boundary tracking and source-seeking problems with a single autonomous vehicle capable of sensing the value of the spatial field at its position. The movement of the vehicle is controlled through the proposed guidance strategy, which is designed on the basis of the collected measurements without the necessity of preplanning or human intervention. Moreover, no a priori knowledge about the field and its gradient is required. The proposed strategy is based on the so-called suboptimal sliding mode controller. The guidance strategy is demonstrated by computer-based simulations and a set of boundary tracking experimental sea trials. The efficacy of the algorithm to autonomously steer the C-Enduro surface vehicle to follow a fixed depth contour in a dynamic coastal region is demonstrated by the results from the trial described in this paper.

Hierarchical Merging &amp;amp; Generalization Method of Three-Dimension City Model Group Based on the Theory of Spatial Visual Cognition

In order to simplify the three-dimensional building group model, this paper proposes a clustering generalization method based on visual cognitive theory. The method uses road elements to roughly divide scenes, and then uses spatial cognitive elements such as direction, area, height and their topological constraints to classify them precisely, so as to make them conform to the urban morphological characteristics. Delaunay triangulation network and boundary tracking synthesis algorithm are used to merge and summarize the models, and the models are stored hierarchically. The proposed algorithm should be verified experimentally with a typical urban complex model. The experimental results show that the efficiency of the method used in this paper is at least 20% higher than that of previous one, and with the growth of test data, the higher efficiency is improved. The classification results conform to human cognitive habits, and the generalization levels of different models can be relatively unified by adaptive control of each threshold in the clustering generalization process.