Contour Tracking Research Articles

Robust immersion and invariance adaptive coordinated control for a class of biaxial gantry systems

This paper proposes a robust Immersion and Invariance (I&I) adaptive coordinated controller for a class of uncertain linear-motor-driven biaxial gantry system subject to external disturbances for high-accuracy contour tracking. Firstly, the dynamic model of the gantry system is transformed into task coordinate frame, through which the contour tracking can be regarded as a regulation problem. Based on the transformed system dynamics, an I&I-based adaptation law with smooth projection is proposed to estimate the unknown parameters. Different from traditional adaptive control, the proposed robust I&I adaptive control introduces a new term called tuning function in adaptation law to shape the dynamic behaviour of the estimation vector. Then the stability of the closed-loop system is proved by Lyapunov theory. Finally, comparative experiments are executed on an industrial biaxial gantry system with two different cases to verify the effectiveness of the proposed control law.

Radiofrequency thermocoagulation of trigeminal nerve assisted by nerve bundle extraction and image fusion based on hamilton-jacobi equation

Background and Objective: Radiofrequency thermocoagulation is an effective method for treating classic trigeminal neuralgia. However, the accurate positioning of thermocoagulation is difficult. The purpose of this study was to design an optimal strategy for performing adjuvant surgery.Methods: A total of 60 patients with trigeminal neuralgia were divided into two groups. One group received conventional computed tomography (CT) guided treatment (CT group). In the other group, neural fiber bundles were firstly extracted based on the Hamilton-Jacobi equation. Then, the MRI, CT, and fiber bundle images were fused to visualize the relationship among semilunar ganglion, trigeminal nerve, and puncture needle (fusion group).Results: Trigeminal fiber bundles were extracted quickly by the contour tracking method, and different types of image fusion were realized for radiofrequency surgery navigation. In the fusion group, 13.3% of patients could not reach semilunar ganglion, and 76.9% of the remaining cases reached the ideal damage area. In the CT group, the preoperative design shows that 26.7% of patients may have puncture difficulty, and 54.5% of remaining cases reached the ideal damage area.Conclusion: The technique of neural bundle extraction and image fusion based on the Hamilton-Jacobi equation can be used to plan the personalized puncture path targeting the semilunar ganglion.

Research on Sheepskin Contour Extraction Method Based on Computer Vision Measurement Technology

Manual trimming of sheepskin is intensive labor, and the working environment is full of rotten smells. The tannery is facing increasingly severe recruitment difficulties. This paper uses computer vision technology to study automatic recognition of sheepskin contours, which is the basis for the subsequent automatic trimming of sheepskin. After observing and analyzing the raw sheepskin images collected by an industrial array camera, a method of sheepskin contour extraction based on computer vision measurement technology is proposed in this paper. This method uses the fast Otsu threshold algorithm based on the pixel set to perform binary image segmentation. Combined with morphological processing for edge defect filling and topology analysis of boundary contour tracking algorithm to extract maximum contour information, it has a pixel-level three-dimensional de-noising preprocessing function and can accurately extract the sheepskin contour in the raw sheepskin image. The experimental results show that using the fast Otsu threshold algorithm proposed in this paper for binary segmentation to extract sheepskin contours, the detection rate is nearly 160% faster than the traditional Otsu algorithm, the edge protection is better, the error segmentation is reduced by nearly 3% and it has good anti-noise performance. It can meet the industrial production requirements of subsequent automatic cutting of sheepskin.

Integration of DE Algorithm with PDC-APF for Enhancement of Contour Path Planning of a Universal Robot

In the robotic engineering field, the main target, especially in industry, manufacturing, and surgical operations, is reaching the optimal performance of manipulators. The purpose of this paper is to quantify the contour tracking performance of collaborative universal manipulator robot (UR5) by setting the gain of position domain controller. In order to improve and enhance the track of manipulator in experimental applications we utilize differential evolution (DE) optimization, using MATLAB toolbox with an applied robot operating system (ROS). The adopted current approach does not only optimize the gain of position domain controller but also prevent collisions by detecting a “border crossing” without turning off the manipulator and allowing the automation agent to be on the scene, coexisting in harmonic mode and avoiding collisions. This requires the implementation of an algorithm that detects an obstacle to avoid anticipated collisions. For this purpose, the adopted algorithm uses the DE algorithm to modify the artificial potential field (APF). The results of this paper present that on one hand, meta-heuristic optimization algorithm features give the best performance indices for linear and non-linear contours, and on the other hand, DE algorithm features give good modification to APF to generate collision free contour path planning.

Gain parameters optimization strategy of cross-coupled controller based on deep reinforcement learning

In this article, a deep reinforcement learning-based strategy for the optimization of gain parameters of a cross-coupled controller is proposed. First, to compensate the contour error caused by servo lag, a proportional–integral (PI)-type cross-coupled controller is designed, with its gain parameters being determined using the cut-off frequency of the contour error transfer function. Next, on the basis of a deep reinforcement learning algorithm, a neural network structure suitable for contour error compensation is established, through which the optimal gain parameters are obtained. Finally, some experiments are carried out, in which the optimal gain parameters sought through off-line learning schemes are applied to the biaxial motion control. The results indicate that the proposed gain parameters optimization strategy can effectively converge the gain parameters with the optimal intervals, and that the optimal gain parameters obtained by the proposed strategy can significantly improve the contour control accuracy in biaxial contour tracking tasks.

WITHDRAWN: Ear biometric for personal identification using canny edge detection algorithm and contour tracking method

This paper is based on Human ear recognition in a new biometric technology by attracting the interest of biometrics community. Biometrics involves the programmed investigation of strategies in order to understand individual’s dependent on physical or social characteristics. Finding a decent biometric strategy, it has been extensively investigated in an ongoing year. The ear is a steady organ, it does not change with age and feelings, among a few biometric highlights.

Position domain control technology for six-joint robots

In the context of the rapid development of intelligent manufacturing, high-precision motion control of industrial robots has attracted increasing research attention. High-speed and high-precision motion control is a development trend associated with the current industrial robots. Industrial transformation and upgradation can be accelerated only via the independent research and development of robot core technologies, including robot high-precision control systems, ensuring the transition of the manufacturing industry in China toward intelligent and digital development. Currently, the contour tracking error associated with majority of the multiaxes CNC machine tools and multijoint industrial robots is a common problem. A good tracking performance can be achieved in time with respect to each joint axis when the space trajectory of the serial multijoint industrial robot changes under multiaxes linkage. The ideal contour trajectory cannot be fully ensured because of the mechanical and electrical hysteresis effects. Therefore, the synchronization of the motion of each servo axis in the geometric space is very important. In this paper, the existing kinematics and dynamics of industrial robots were combined with the traditional PID control theory for studying position domain control algorithm of the six-joint robot to resolve the problem of low accuracy associated with the robot end profile, which can be attributed to the lag between the motion instruction and the actual position. The algorithm uses the method of real-time establishment of the master–slave motion relation for controlling the spatial contour trajectory of the robot. It further transforms the synchronization control method of each servo joint in the time domain into the master–slave follow control method of each servo joint in the position domain. While realizing synchronization control in the position domain, PD control based on position domain was introduced to reduce the following error of the master–slave following control, improving the overall accuracy of the contour motion of the robot end. The method proposed in this paper has been tested on the Linux CNC numerical control system with a company’s HSR-JR605 robot, indicating that the position of the domain control method employed positively affects the accuracy of six articulated robot space trajectory.

Nonlinear Contour Tracking of a Voice Coil Motors-Driven Dual-Axis Positioning Stage Using Fuzzy Fractional PID Control with Variable Orders

This study aims to develop a variable-order fuzzy fractional proportional-integral-differential (VOFFPID) control system for controlling the mover position of a newly designed voice coil motors- (VCMs-) driven dual-axis positioning stage. First, the operation principle and dynamics of the stage are analyzed. After that, the design of a fuzzy fractional proportional-integral-differential (FFPID) control system is introduced on the basis of a fractional calculus and fuzzy logic system. With an additional degree of freedom to the control parameters and fuzzy operation, the FFPID control system can upgrade the contour tracking performance of a conventional proportional-integral-differential (PID) control system with respect to the specified dynamics of the stage. Moreover, the VOFFPID control system is designed to further improve the tracking responses of the FFPID control system. In this system, the five control parameters are optimized with the cuckoo search algorithm via an adaptive strategy. Lastly, nominal and payload conditions attributed to two nonlinear contour demands are provided to evaluate the contouring performance of the PID, FFPID, and VOFFPID control systems. The experimental results subjected to different performance measures demonstrate that the proposed VOFFPID controller outperforms PID and FFPID controllers in terms of the designed VCMs-driven dual-axis positioning stage under both conditions.

Experimental and numerical investigation of the origin of surface roughness in laser powder bed fused overhang regions

ABSTRACT Surface roughness of laser powder bed fusion (L-PBF) printed overhang regions is a major contributor to deteriorated shape accuracy/surface quality. This study investigates the mechanisms behind the evolution of surface roughness (Ra) in overhang regions. The evolution of surface morphology is the result of a combination of border track contour, powder adhesion, warp deformation, and dross formation, which is strongly related to the overhang angle (θ). When 0° ≤ θ ≤ 15°, the overhang angle does not affect Ra significantly since only a small area of the melt pool boundaries contacts the powder bed resulting in slight powder adhesion. When 15° < θ ≤ 50°, powder adhesion is enhanced by the melt pool sinking and the increased contact area between the melt pool boundary and powder bed. When θ > 50°, large waviness of the overhang contour, adhesion of powder clusters, severe warp deformation and dross formation increase Ra sharply.

Adaptive Fuzzy Velocity Field Control for Navigation of Nonholonomic Mobile Robots

This paper presents a novel contour tracking scheme based on a well-posed kinematic representation of differential-driven nonholonomic mobile robots. Firstly, a fuzzy aggregation of spatial sets in cluttered environments allows designing a velocity field to encode the desired velocity vector pointing to the target (the contour). Thus, the resultant smooth trajectory avoids obstacles by combining spatially distributed velocity fields that enable the robot navigation. Finally, the universal approximation property of fuzzy systems facilitates the design of an adaptive PI-like controller, whose closed-loop stability leads to the precise tracking of the velocity field. The results of the performed numerical simulations illustrate the reliability of the proposed scheme.

Coral reef pore recognition and feature extraction based on borehole image

The coral reef pores are the main reservoir space of oil and gas resources. Through determining the structural form and distribution characteristics of pores, it can be helpful for scientific and reasonable stratigraphic division and reservoir evaluation, and provide basic data for the efficient development of using coral reefs as oil and gas reservoir sites. The core difficulty of interpretation and evaluation of coral reef pore structure and distribution characteristics is the pore recognition and feature extraction. In view of problems of low accuracy and efficiency in the recognition and feature extraction of coral reef pore at present, this paper proposes a method of coral reef pore recognition and feature extraction based on borehole image data. First of all, based on the borehole image and combined with the pore characteristics in borehole image, this paper proposes the coral reef pore recognition method. By using the feature of color gradient difference between the pore and the non pore in the borehole image, it realizes the segmentation of coral reef pore with low noise and weak interference. On the basis of obvious coral reef pores, the contour tracking method and image filling system of coral reef pore are established. Then, on the basis of traditional eight connected region marking algorithm, a pore region feature extraction method is proposed. The equivalent relationship between the temporary mark and the final mark is established, and an evaluation criterion that can comprehensively reflect the pore region feature parameters in the borehole image is formed. Finally, a systematic analysis and a comparison of results are carried out based on the actual coral reef borehole images. The results are consistent with the real values, which verifies the correctness of method.

Impact of Preprocessing Features on the Performance of Ultrasound Tongue Contour Tracking, via Dynamic Programming

Impact of Preprocessing Features on the Performance of Ultrasound Tongue Contour Tracking, via Dynamic Programming

Contour Tracking Control of a Linear Motors-Driven X-Y-Y Stage Using Auto-Tuning Cross-Coupled 2DOF PID Control Approach

Linear motors (LMs) are widely used in numerous industry automation where precise and fast motions are required to convert electric energy into linear actuation without the need of any switching mechanism. This study aims to develop a control strategy of auto-tuning cross-coupled two-degree-of-freedom proportional-integral-derivative (ACC2PID) to achieve extremely high-precision contour control of a LMs-driven X-Y-Y stage. Three 2PID controllers are developed to control the mover positions in individual axes while two compensators are designed to eliminate the contour errors in biaxial motions. Furthermore, an improved artificial bee colony algorithm is employed as a powerful optimization technique so that all the control parameters can be concurrently evaluated and optimized online while ensuring the non-fragility of the proposed controller. In this way, the tracking error in each axis and contour errors of the biaxial motions can be concurrently minimized, and further, satisfactory positioning accuracy and synchronization performance can be achieved. Finally, the experimental comparison results confirm the validity of the proposed ACC2PID control system regarding the multi-axis contour tracking control of the highly uncertain and nonlinear LMs-driven X-Y-Y stage.

RETRACTED: Virtual simulation design and effect of high jump technology action optimization based on complex embedded system

Abstract It proposes a programmed human movement investigation and movement acknowledgement for serious video test programs. Four significant human focuses are recognized and used by powerful camera estimation and target localization methods to calculate human contour tracking. Statistical analysis of tracking point movements finds time divisions for upward runs and jump levels. This method uses a motion image test from camera movement, and the athlete's performance characteristics are robust and independent of pole vaulting, high jumps, triple jumps and long jumps. Experimental results are sufficient to show that the program is running with complex content and motion sequences. The proposed Extended Convolutional Neural Network (RCNN) architecture contains two main modules. First, four significant people are measured and tracked using pre-calculated silhouettes of people. It is calculated using standard algorithms to detect silhouettes and find moving objects in the video. The algorithm's necessary steps are camera motion estimation, change detection based on Bayesian statistics, and label propagation. The long human axis, upper running and jumping stages of the walk cycle and time division are estimated using a statistical analysis of the tracking point movement. In the second module, the above features are used for behavior recognition tasks.

Prediction-Model-Based Contouring Error Iterative Precompensation Scheme for Precision Multiaxis Motion Systems

In order to achieve both accurate contouring error estimation and excellent contouring control performance for multiaxis motion systems, this article proposes an online iterative precompensation control method based on a third-order contouring error prediction model. Specifically, the closed-loop dynamical model of each axis is first used to predict tracking errors at future sampling instants. And then the related contouring error of the multiaxis system at future time can be expressed by the predicted tracking error and the theoretical third-order model of the reference contour. To reduce the influence of modeling error and uncertain disturbances on the prediction performance of contouring error, the numerical calculation method is utilized to obtain absolutely accurate contouring error, through which the deviation between the proposed contouring error model and the accurate one can be corrected accordingly. Based on the accurate contouring error prediction model, the optimal contouring error compensation can be generated through online iterative calculation. To achieve excellent contouring performance, the compensation is added to the original reference contour as a kind of trajectory precompensation. Comparative experiments are carried out on an industrial three-axis machine tool. A series of contour tracking experiments consistently demonstrate that the proposed method can predicate the contouring error accurately. Additionally, the contouring motion performance can also be significantly improved in the case of a variety of different trajectories.

3D Printing of Oil Paintings Based on Material Jetting and Its Reduction of Staircase Effect.

Material jetting is a high-precision and fast 3D printing technique for color 3D objects reproduction, but it also suffers from color accuracy and jagged issues. The UV inks jetting processes based on the polymer jetting principle have been studied from printing materials regarding the parameters in the default layer order, which is prone to staircase effects. In this work, utilizing the Mimaki UV inks jetting system with a variable layer thickness, a new framework to print a photogrammetry-based oil painting 3D model has been proposed with the tunable coloring layer sequence to improve the jagged challenge between adjacent layers. Based on contour tracking, a height-rendering image of the oil painting model is generated, which is further segmented and pasted to the corresponding slicing layers to control the overall printing sequence of coloring layers and white layers. The final results show that photogrammetric models of oil paintings can be printed vividly by UV-curable color polymers, and that the proposed reverse-sequence printing method can significantly improve the staircase effect based on visual assessment and color difference. Finally, the case of polymer-based oil painting 3D printing provides new insights for optimizing color 3D printing processes based on other substrates and print accuracy to improve the corresponding staircase effect.

Development of a software algorithm for comprehensive right ventricular strain analysis employing meshes derived from three-dimensional speckle-tracking echocardiography

Introduction Although right ventricular (RV) function assessment is important in cardiac surgical patients, dedicated software solutions to measure RV strain on three-dimensional (3D) speckle-tracking echocardiography-based (STE) meshes are lacking. Hence, a novel tool to do so was developed and tested for its feasibility in a clinical setting. Methods RV meshes were generated using dedicated 3D-STE software (4D RV-Function 2.0, Tomtec). A software algorithm was programmed in the Visualization Toolkit (www.vtk.org) to measure systolic peak strains of four regional longitudinal and circumferential contours on the mesh surface (see figure). Longitudinal strains were tracked using fixed-angle pathways (“fixed”) and compared with frame-to-frame angle definition (“variable”). The four circumferential strain layers were defined by strict long-axis segmentation in each frame (“constant”) and compared to “pinning” the planes to points along the anterior and posterior edge (“tilted”). For longitudinal strains, different strategies for the segmentation into basal and apical segments were tested. Global strain values were calculated by averaging the corresponding regional strains. Results 22 patients undergoing mitral valve surgery (MVS) received intraoperative 3D transesophageal echocardiography (TEE) before and after cardiopulmonary bypass. STE yielded 44 meshes for inclusion. 44 percutaneous mitral valve repair (PMVR) patients received 3D-TEE before and after PMVR and 88 meshes were generated. Altogether, 132 total meshes were included. Complete strain analysis was feasible in 126 meshes (95%). Visual validation of each mesh carried out by experienced investigators revealed that “fixed” longitudinal strain calculation resulted in more plausible contour tracking and shortening patterns compared to “variable” calculation, whereas peak longitudinal strain values did not differ (-0.04%, p=0.12). Baso-apical segmentation was best achieved by fixing the segment border in planes defined by neighboring mesh points in the end-diastolic frame. Regarding circumferential strains, “tilted” tracking was visually superior to “constant” segmentation in maintaining functionally matching surface units in the circumferential planes along the heart cycle. “Tilted” vs. “constant” tracking resulted in significantly different global strain values (1.5%, p Discussion RV strain analysis on meshes derived from transesophageal 3D-STE using a custom-made algorithm is feasible. In patients undergoing cardiac surgery, this approach might able be to detect subtle changes of RV function more sensitively than established parameters.

Encoder-decoder CNN models for automatic tracking of tongue contours in real-time ultrasound data.

One application of medical ultrasound imaging is to visualize and characterize human tongue shape and motion in real-time to study healthy or impaired speech production. Due to the low-contrast characteristic and noisy nature of ultrasound images, it requires knowledge about the tongue structure and ultrasound data interpretation for users to recognize tongue locations and gestures easily. Moreover, quantitative analysis of tongue motion needs the tongue contour to be extracted, tracked and visualized instead of the whole tongue region. Manual tongue contour extraction is a cumbersome, subjective, and error-prone task. Furthermore, it is not a feasible solution for real-time applications where the tongue contour moves rapidly with nuance gestures. This paper presents two new deep neural networks (named BowNet models) that benefit from the ability of global prediction of encoding-decoding fully convolutional neural networks and the capability of full-resolution extraction of dilated convolutions. Both qualitatively and quantitatively studies over datasets from two ultrasound machines disclosed the outstanding performances of the proposed deep learning models in terms of performance speed and robustness. Experimental results also revealed a significant improvement in the accuracy of prediction maps due to the better exploration and exploitation ability of the proposed network models.

Contour Tracking Control of Networked Motion Control System Using Improved Equivalent-Input-Disturbance Approach

This article deals with contour tracking control of a networked multiaxis motion control system with repetitive tasks. To improve the control performance of the system under the overall effects of aperiodic time-varying delays and exogenous disturbances, a network-induced delay is first modeled to be a disturbance. Next, an improved equivalent-input-disturbance (IEID) approach is devised to suppress the overall effect. Then, an iterative learning controller is designed in combination with the IEID estimator to perform individual-axis tracking control. The stability of the system is analyzed using the separation theorem. After that, a cross-coupled controller is used to further improve the contour-tracking performance. Finally, simulations and experiments are carried out to verify the feasibility and effectiveness of the new approach.

Study on automatic recognition method of continental shale lamination based on electrical imaging logging

In this paper, the shale oil shale stratum in Jiyang Depression is taken as the object to study the characteristics of the complex shale lithology, the frequent development of calcareous or sandy stratum, and the difficulty of manual identification. Firstly, the development characteristics of the stratigraphic layer of continental shale oil reservoir are studied. Then the electric imaging logging image is processed to restore the whole borehole wall, and then the target geological object is extracted through the operations of automatic image segmentation, connected area labeling, area contour tracking extraction and storage. Finally, the target geological objects are automatically classified and identified, the location of the continental shale texture layer is predicted, and the texture layer development index is calculated. The research results show that: after verification analysis with the core description, this method can identify the texture layer more accurately, and the coincidence rate reaches 92%. It provides support for the identification of stratigraphic facies favorable for reservoir development in the study area, and also lays a foundation for shale oil layer selection and fracturing.