Search

It’s crucial to obtain the dimensions of fish fry accurately and quickly in aquaculture. Traditional manual sampling and measurement are time-consuming and labor-intensive and cannot meet the demands of smart aquaculture development. A vision-based method for rapid measurement of fish length is proposed for grass carp fry with length distribution from 20 to 100 mm in this paper. It allows for quick and accurate length measurement of test fish fry without reference and in a non-contact manner. Firstly, an RGB-D camera is used to capture depth information and gray images of the target. Those images are processed to segment the target fish from the background. For the case of overlapping fish, concave regions and points are extracted to separate individual fish based on concave points. An improved thinning algorithm is then used to extract the fish skeleton, and key skeleton points are selected. Finally, by combining the image depth information, the three-dimensional coordinates of the skeleton points are transformed,allowing for the accurate measurement of the total length of the fish fry. Experimental result shows that the proposed method achieves an average absolute error of 1. 57 mm and an average relative error of 4. 39% in the length measurement of the test fish. It provides a non-contact measurement method that supports applications such as graded feeding and intelligent feeding in the aquaculture industry. [ABSTRACT FROM AUTHOR]

Abstract High‐precision relative position and attitude measurement technology has a wide range of applications in aerospace and industrial production. Currently, the commonly used method for measurement is based on visual cooperative signs. However, its accuracy significantly decreases as the distance increases. Therefore, a relative positioning system is designed based on light field spatial coding and visual recognition. The projector emits spatially encoded structured light within the coverage of the light field, while the receiving end captures, identifies, measures the code, and calculates its pose in the light field coordinate system. Compared with the traditional measurement method, the measurement accuracy of this system does not decrease greatly with the increase in distance, the measurement distance can be adjusted in real‐time and does not depend on an external light source. By changing the projection pattern with different resolutions without changing hardware systems, it can adjust effective measurement distance accordingly. Theoretical and experimental results show that the proposed method can maintain measurement accuracy with the increase in distance.

High‐precision relative position and attitude measurement technology has a wide range of applications in aerospace and industrial production. Currently, the commonly used method for measurement is based on visual cooperative signs. However, its accuracy significantly decreases as the distance increases. Therefore, a relative positioning system is designed based on light field spatial coding and visual recognition. The projector emits spatially encoded structured light within the coverage of the light field, while the receiving end captures, identifies, measures the code, and calculates its pose in the light field coordinate system. Compared with the traditional measurement method, the measurement accuracy of this system does not decrease greatly with the increase in distance, the measurement distance can be adjusted in real‐time and does not depend on an external light source. By changing the projection pattern with different resolutions without changing hardware systems, it can adjust effective measurement distance accordingly. Theoretical and experimental results show that the proposed method can maintain measurement accuracy with the increase in distance. [ABSTRACT FROM AUTHOR]

Emerging computer vision measurement methods overcome the limitations of traditional sensors. However, conventional digital image processing algorithms encounter issues of low precision and timeliness when performing vibration displacement measurements in complex operating conditions. Therefore, this paper builds a deep learning detection algorithm based on a lightweight convolutional neural network to measure the vibration displacement of the structure. In the feature extraction part, the ghost module and depthwise separable convolution are used to condense effective information. In the feature fusion part, it is combined based on the underlying feature similarity principle. The attention mechanism obtains the fine features, edge information and sensitive position information of the target. In the target regression part, preset anchor frames of different sizes are used to return the vibrating targets in the image to obtain precise position information. First, a cable-stayed bridge model is selected for experiments in a laboratory environment, and compared with the measurement results of seven visual algorithms. Furthermore, experiments are conducted outdoors on real bridges to verify the effectiveness of the proposed method. Qualitative and quantitative analysis of the experimental results show that the proposed algorithm can effectively return the small offset of the vibration target, efficiently and precisely measure the vibration displacement signal of the structure in real time, providing an efficient solution for structural damage and health monitoring. [ABSTRACT FROM AUTHOR]

The automatic control of excavator operation trajectories is a pivotal technology for autonomous excavators, with the essential prerequisite being the real-time measurement of manipulator poses. Given the complexity of the operating environment, traditional sensor-based measurement methods face limitations, whereas visual measurement emerges as a promising technique. Accurately measuring excavator manipulator poses involves a crucial aspect: mapping the relationship between image information and poses. First, to address the significant errors in pose prediction encountered with machine learning techniques like artificial neural networks, this work introduces a mathematical model for mapping this relationship, referred to as the pose mapping mathematical model, which includes calibrating model parameters. Second, to address the sensitivity of initial values in the calibration process, we propose a residual-guided initialization algorithm. This algorithm aims to ensure that initial values closely approximate the ground truth values, thus preventing matrix singularity at the source and avoiding parameter estimation divergence. Third, to tackle challenges such as unstable lighting conditions and discrepancies between the dataset and the mathematical model, we introduce the random sample consensus-driven Levenberg–Marquardt parameter optimization algorithm to enhance parameter estimation accuracy. Experiments with static and dynamic online measurement demonstrate that our method reduces pose measurement errors compared to existing methods. This research lays a solid foundation for developing visual measurement techniques for excavators and automated manipulator control based on visual measurements, also serving as a valuable reference for research on mechanical arms. [ABSTRACT FROM AUTHOR]

In the measurement process of aerospace milling parts, traditional image processing methods cannot effectively measure the size of guide holes in milling parts that contain interference factors such as chips and cutting fluid. To address this issue, a visual measurement method for workpiece aperture based on the TransUNet model was proposed to detect interference regions in the workpiece image, and a mixed pooling module was introduced to improve the model's feature recognition range for chips and cutting fluids. Then, an image direction texture repair method was used to repair the detection image, and the guide hole edge pixels were extracted by improving the edge detection algorithm. Combining the random sampling consensus algorithm and least squares method, the guide hole geometric size was obtained by filtering and fitting the edge pixel points. Finally, the effectiveness of the method was verified by an example of aerospace fixture plate. The measurement accuracy of the guide hole aperture is 0.03 mm, which can meets the requirements of quality inspection for aerospace milling parts. [ABSTRACT FROM AUTHOR]

In order to solve the problem of interruption in the positioning of roadheader in the case that the optical target is blocked under the current commonly used integrated navigation positioning of roadheader based on 'inertial navigation+visual measurement+optical target', a positioning solution method for roadheader under optical target occlusion occlusion is proposed. Firstly, the method collects images of an optical target composed of four rectangular distributed target points in unblocked conditions, obtains the pixel coordinates of the imaging spot of the target points in the camera, and constructs a rectangle. Then, the method expands and constructs an auxiliary rectangular area box according to a certain proportion. Secondly, the method collects images of partially blocked target points, obtains the pixel coordinates of the imaging spot of the unblocked target points in the camera. The method determines the corresponding relationship between the unblocked target points and the imaging spot based on the Euclidean distance between the imaging spot of the target points and the vertex of the auxiliary rectangular area box, thereby determining the blocked target points. Thirdly, using the known geometric dimensions of the target and the target attitude information provided by inertial navigation, the method establishes the corresponding relationship between the projected target point and the imaging spot, and then solves for the pixel coordinates of the spot corresponding to the blocked target point. Finally, the spatial coordinates of the center position of the optical target are obtained using the perspective-N-point (PNP) algorithm to achieve the positioning solution of the roadheader. The experimental results show that when the optical target is blocked, by calculating the pixel coordinates of the light spot corresponding to the blocked target point, the problem of interruption in the positioning of the roadheader can be solved. It ensures the real-time positioning of the roadheader, and the positioning error meets the actual positioning requirements of the roadheader.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Railway Construction Technology is the property of Railway Construction Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A measurement method based on the homography matrix and partial area effect is studied to improve the precision of the visual measurement of the bearing size. Firstly, the camera is calibrated to obtain its distortion coefficient, and the image is corrected for distortion. Secondly, the relationship between the pixel plane and the bearing imaging plane is determined by solving the homography matrix with a chessboard. Finally, the sub-pixel edge contour of the bearing is obtained through the improved partial area effect, and the pixel coordinates are mapped to the world coordinates according to the homography matrix. The feature size is obtained by fitting the mapping points. Experimental results showed that the transformation of the homography matrix is more accurate than the pixel equivalent in the process of converting the pixel size to the actual size. The improved partial area effect sub-pixel edge detection results are better than the partial area effect and Zernike moment. The measurement error for the bearing outer diameter is less than 0.05 mm and is within 0.5 pixel. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Microscopic vision has been widely applied in precision assembly. To achieve sufficiently high resolution in measurements for precision assembly when the sizes of the parts involved exceed the field of view of the vision system, an image mosaic technique must be used. In this paper, a method for constructing an image mosaic with non-overlapping areas with enhanced efficiency is proposed. First, an image mosaic model for the part is created using a geometric model of the measurement system installed on a X-Y-Z precision stages with high repeatability, and a path for image acquisition is established. Second, images are captured along the same path for a specified calibration plate, and an entire image is formed based on the given model. The measurement results obtained from the specified calibration plate are utilized to identify mosaic errors and apply compensation for the part requiring measurement. Experimental results show that the maximum error is less than 4 μm for a camera with pixel equivalent 2.46 μm, thereby demonstrating the accuracy of the proposed method. This image mosaic technique with non-overlapping regions can simplify image acquisition and reduce the workload involved in constructing an image mosaic. ARTICLE HIGHLIGHTS: HIGHLIGHTS • A method is proposed for a microscopic vision image mosaic without overlapping region in precision assembly. • The method has high accuracy relative to the camera resolution. • Mosaic error can be compensated by a special calibration plate to improve the precision of measurement. [ABSTRACT FROM AUTHOR]

The clarity evaluation function plays a vital role in the autofocus technique. The accuracy and efficiency of the image clarity evaluation function directly affects the accuracy of autofocus and the speed of focusing. However, classical clarity function values are sensitive to changes in background brightness and changes in object contour length. This paper proposes a normalized absolute values adaptive (NAVA) evaluation function of image clarity. It can eliminate the influence of changes in background brightness and the length of the measured object contour on the image clarity function value. To verify the effectiveness of the NAVA function, several experiments were conducted under conditions of virtual master gear images and actual captured images. For actual captured images, the variation of the evaluation results of the NAVA function is far less than the corresponding variation of the classic clarity function. Compared with classical clarity evaluation functions, the NAVA function can provide normalized absolute clarity values. The correlations between the NAVA function results of image clarity and both the contour length and background brightness of the tested object are weak. The use of the NAVA function in automatic and manual focusing systems can further improve focusing efficiency. [ABSTRACT FROM AUTHOR]

The on-line measurement of medium thickness steel plate length is an important part of the hot rolling production. In this paper, an easy calibration method and a visual measurement method of laser stripe center extraction algorithm based on structured light are proposed to achieve on-line measurement of medium thickness steel plate length. Firstly, an experimental platform is designed and built to fix the intersecting visual fields of each camera. Secondly, the actual detection size of each camera's visual field is calibrated by the calibration method, and a fixed digital image processing range is set according to the thickness of the steel plate. Then, an adaptive image processing range extraction algorithm is proposed to further reduce the redundant image scanning. Moreover, we improve the traditional gray center of gravity method to achieve higher accuracy of laser stripe center extraction. Finally, in the laboratory, three medium thickness steel plates with different lengths are measured by the laser stripe extraction algorithm proposed in this paper. Experimental results show that the measurement error is within ± 1.5 mm, which proves that the algorithm has the characteristics of higher extraction accuracy and has certain engineering application value. [ABSTRACT FROM AUTHOR]

In order to test the accuracy of the weapon hitting the target, it is very important to locate and measure the spatial coordinates of the falling point target. Aiming at the needs of space coordinate positioning and measurement of targets falling into the sea/ground plane, this paper studies a positioning method of UAV camera combined with target, and uses the principle of homography transformation to calculate the space coordinates of targets. The influence of pixel error on the positioning method is simulated by Monte Carlo method, and the shooting attitude range meeting the measurement requirements is determined by simulation. The results show that the positioning method of UAV camera combined with target has high accuracy, which can meet the needs of landing target positioning and measurement.

We developed a novel measurement system to directly visually observe the sliding behavior of rocks inside a triaxial test apparatus. The proposed visual measurement system consists of a steel housing that contains a commercially available digital camera. A series of triaxial compression tests was conducted to visually observe the progressive sliding behavior of precut samples and to measure the evolution of the strain and displacement fields near an artificial joint, using the digital image correlation method. The recorded video frames and their associated digital image correlation results allow a better understanding of the effect of confining pressure on the sliding mode of precut joint asperities. The implementation of the proposed measurement system is simple, safe, and inexpensive, and has the potential to become widely used as a new measurement system because it can be installed into existing triaxial test equipment without modification. Highlights: A new measurement system is proposed for observing the sliding behavior of rock-like materials from the inside of the pressure vessel of a triaxial test apparatus. The measurement system is simple, safe, and inexpensive, and consists of a steel housing containing a digital camera. We successfully observed the effect of confining pressure on the sliding mode of the precut joint asperity. [ABSTRACT FROM AUTHOR]

Ellipse detection has a very wide range of applications in the field of object detection, especially in the geometric size detection of inclined microporous parts. However, due to the processing methods applied to the parts, there are certain defects in the features. The existing ellipse detection methods do not meet the needs of rapid detection due to the problems of false detection and time consumption. This article proposes a method of quickly obtaining defective ellipse parameters based on vision. It mainly uses the approximation principle of circles to repair defective circles, then combines this with morphological processing to obtain effective edge points, and finally uses the least squares method to obtain elliptical parameters. By simulating the computer-generated images, the results demonstrate that the center fitting error of the simulated defect ellipses with major and minor axes of 600 and 400 pixels is less than 1 pixel, the major and minor axis fitting error is less than 3 pixels, and the tilt angle fitting error is less than 0.1°. Further, experimental verification was conducted on the engine injection hole. The measurement results show that the surface size deviation was less than 0.01 mm and the angle error was less than 0.15°, which means the parameters of defective ellipses can obtained quickly and effectively. It is thus suitable for engineering applications, and can provide visual guidance for the precise measurement of fiber probes. [ABSTRACT FROM AUTHOR]

Laser powder bed fusion (LPBF) is of great importance for the visual measurement and analysis of the metallization process, which is the process of solid, liquid, and gas phase transformations of metal powders under high-energy laser irradiation due to the low boiling point/high saturated vapor pressure. Since the evaporation of metals involves the interaction of driving forces such as vapor back pressure, surface tension, and gravity, the movement of the melt pool is not stable. At the same time, it also produces vaporization products such as vapor plumes and sprays, which cause defects such as bubbles, porosity, lack of fusion, inclusions, etc., during the manufacturing process of the parts, affecting the performance and manufacturing quality of the parts. More and more researchers are using imaging technologies, such as high-speed X-ray, high-speed visible light cameras, and high-speed schlieren imaging, to perform noncontact visual measurements and analyses of the melt pool, vapor plume, and spatter during the metal evaporation process, and the results show that the metal evaporation process can be suppressed by optimizing the process parameters and changing the processing atmosphere, thereby reducing part defects and improving part performance and built part quality. This paper reviews the research on metal evaporation mechanisms and visual measurement methods of metal evaporation, then discusses the measures of metal evaporation, and finally summarizes and prospects the future research hotspots of LPBF technology, according to the existing scholars' research on numerical simulation analysis and visual measurement methods of the metal evaporation process. [ABSTRACT FROM AUTHOR]

Hole is the most common symmetrical geometric structure of mechanical parts, and aperture and hole center distance are important measured dimensions in machining. However, existing visual measurement methods often require high equipment installation accuracy and low measurement accuracy. To solve the problem of projection deformation of the measured hole: Firstly, a local coordinate system is created, and the coordinate plane of the coordinate is parallel to the end face of the measured hole. Secondly, a cone is established, the end face of the measured hole is alike to the bottom face of the cone, and the optical center of the camera is the vertex. The space equation of the cone is represented by the coordinates of the center point of the hole. Finally, a cutting plane is established near the imaging plane of the camera, and the intersection line equation between the plane and the cone is obtained, and the diameter of the measured hole and the coordinates of the center of the circle are obtained through the parameters of the intersection line equation. In order to solve the problem of errors in edge points of the hole, geometric constraints based on the center of the circle are used to improve measurement accuracy. This experiment takes the automobile insert mold as the measured part and uses the measurement model of this paper to measure the aperture and hole center distance of the mold. The measurement results show that the measurement accuracy of the aperture is 0.018 mm, the measurement accuracy of the center distance of the hole is 0.05 mm, and the maximum relative error is 2.2%. [ABSTRACT FROM AUTHOR]

Micro terminals are often used in every laptop, mobile, and other electrical product. It is challenging to automatically buckle the terminal head to its terminal base during manufacturing because of trouble in accurate positioning and gripping. A double-robots collaborative assembly system is developed to buckle millimeter-scale terminals in three-dimensional space. Robot 1 takes the terminal head horizontally by grasping its flexible line with a customized clamp, including two fingers. Robot 2 presses the aligned terminal head through a force control strategy to ensure that the terminal head and the terminal base can complete buckling accurately, even if there is a certain deviation in the vertical direction. There are two cameras to be used in the system. A horizontally placed camera is used to detect and calculate the angle between the terminal head and the horizontal plane. The angle data will drive robot 1 to make the terminal end face parallel to the horizontal plane to complete the pose correction of the terminal head. Another camera is vertically fixed at the end of industrial robot 1 and used to detect and calculate the position deviation between the terminal head and the terminal base. The position deviation will drive robot 1 to align the terminal head with the terminal base to complete the position correction. The YOLOv3, least square, and feature extraction algorithms are used in image processing. The accuracy of the YOLOv3 target detection model trained by self-made data set can reach more than 95% under different conditions. The detection period is within 65 ms. The experimental results show that the terminal assembly system designed in this paper has excellent reliability and assembly success rate. It also has a significant reference value for other terminals' automatic buckling assemblies. [ABSTRACT FROM AUTHOR]

Copyright of Command Control & Simulation / Zhihui Kongzhi yu Fangzhen is the property of Command Control & Simulation Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Pose measurement of coal mine excavation equipment is an important part of roadway excavation. However, in the underground mining roadway of coal mine, there are some influencing factors such as low illumination, high dust and interference from multiple equipment, which lead to the difficulty in the position and pose measurement of roadheader with low measurement accuracy and poor stability. A combination positioning method based on machine vision and optical fiber inertial navigation is proposed to realize the position and pose measurement of roadheader and improve the accuracy and stability of the position and pose measurement. The visual measurement model of arm roadheader is established, and the optical fiber inertial navigation technology and the spatial coordinate transformation method are used. Finally, the Kalman filter fusion algorithm is used to fuse the two kinds of data to get the accurate roadheader pose data, and the inertia is compensated and corrected. Underground coal mine experiments are designed to verify the performance of the proposed method. The results show that the positioning error of the roadheader body using this method is within 40 mm, which meets the positioning accuracy requirements of roadway construction. This method compensates for the shortcomings of low accuracy and poor reliability of single vision measurement, single inertial navigation measurement and single odometer measurement. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Due to the harsh environment of high humidity and dust in tunnel construction, the vision measurement system needs to be equipped with an explosion-proof glass protective cover. The refractive effect of the plate glass window invalidates the pinhole model. This paper proposes a comprehensive solution for addressing the issue of plane refraction. First, the imaging model for non-parallel plane refraction is established based on dynamic virtual focal length and the Rodriguez formula. Further, due to the failure of the epipolar constraint principle in binocular vision systems caused by plane refraction, this paper proposes the epipolar constraint model for independent refractive plane imaging. Finally, an independent refraction plane triangulation model is proposed to address the issue of triangulation failure caused by plane refraction. The RMSE of the depth of field errors in the independent refraction plane triangulation model is 2.9902 mm before correction and 0.3187 mm after correction. The RMSE of the positioning errors before and after correction are 3.5661 mm and 0.3465 mm, respectively.

Measurement technology based on machine vision has been widely used in various industries. The development of vision measurement technology mainly depends on the process of photosensitive components and the algorithm of processing a target image. In the high-precision dimension measurement of machined metal parts, the high-resolution imaging device usually exposes the cutting texture of the metal surface and affects the accuracy of measurement algorithm. At the same time, the edges of machined metal parts are often chamfered, which makes the edges of objects in the picture overexposed in the lighting measurement environment. These factors reduce the accuracy of dimensioning metal parts using visual measurements. The traditional vision measurement method based on color/gray image makes it difficult to analyze the physical quantities in the light field except for the light intensity, which limits the measurement accuracy. Polarization information can more carefully depict the edge contour edge information in the scene and increase the contrast between the foreground and the background. This paper presents a method to improve the measurement accuracy of machined metal parts by using polarization vision. The incident angle of the light source is optimized according to the complex refractive index of the metal material, and the degree of polarization image with enhanced edge contour features of the ROI (region of interest) is obtained. The high-precision measurement of cylindrical brass motor components is realized by using the method of reprojection transformation correction and maximum correlation template matching (NCC) for rough positioning, as well as the method of edge extraction and optimal fitting. The experimental results show that for copper parts with a tolerance range of ± 0.1 mm, the average measurement error and maximum measurement error are within 0.01 mm, which are higher than the existing color/gray image measurement methods. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A multi-line structured light measurement method that combines a single-line and a three-line laser, in which precision sliding rails and displacement measurement equipment are not required, is proposed in this paper. During the measurement, the single-line structured light projects onto the surface of an object and the three-line structured light remains fixed. The single-line laser is moved and intersects with the three-line laser to form three intersection points. The single-line light plane can be solved using the camera coordinates of three intersection points, thus completing the real-time calibration of the scanned light plane. The single-line laser can be scanned at any angle to determine the overall complete three-dimensional (3D) shape of the object during the process. Experimental results show that this method overcomes the difficulty of obtaining information about certain angles and locations and can effectively recover the 3D shape of the object. The measurement system's repetition error is under 0.16 mm, which is sufficient to measure the 3D shapes of complicated workpieces. [ABSTRACT FROM AUTHOR]

Copyright of Experimental Technology & Management is the property of Experimental Technology & Management Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Vision‐based displacement measurement is promising and emerging for structural monitoring. However, the accuracy of visual measurement is commonly limited by the resolution of the camera. The super‐resolution (SR) technique can reconstruct high‐resolution images from the corresponding low‐resolution images within the constraints of prior knowledge. Existing SR algorithms mainly focus on improving the overall quality of the image. By contrast, the accurate extraction of the coordinates of feature points is the most important for the visual measurement. Besides, the SR network is usually trained by an artificial dataset whose low‐resolution images are obtained by artificially degrading the corresponding high‐resolution images, instead of those directly captured by cameras. However, this degradation usually is only a simple bicubic downsampling that cannot reflect the real degradation, which will provide inaccurate constraints to the network training. Therefore, this paper proposes a novel SR framework that can significantly preserve the feature coordinators for visual measurement (SRFCP). First, a deep learning‐based SR network that focuses on feature preservation is proposed, which introduces both feature weighted branch and feature preserving loss. Second, an image degradation model is built based on the blur kernel and noise extracted from the images captured in real scene. Experiments on public datasets show that the proposed SRFCP performs well both in terms of the objective evaluation index and the subjective visual effect. Then, a binocular visual measurement platform is set up to measure the distance of adjacent feature points on a chessboard. Lastly, several SR algorithms are evaluated by the improvement they bring to the measurement accuracy. Experimental results show that the distance measurement performance can be significantly improved by the images reconstructed by the SRFCP. Therefore, the proposed SRFCP can accurately reconstruct the high‐resolution images while preserving the features coordinates, which is crucial for the visual measurement in structural monitoring. [ABSTRACT FROM AUTHOR]

The filling with electrolyte and the subsequent wetting of the electrodes is a quality-critical and time-intensive process in the manufacturing of lithium-ion batteries. The exact processes involved in the wetting are still under investigation due to their poor accessibility. The accurate replication of the wetting phenomena in porous media can be demonstrated in other research fields by lattice Boltzmann simulations. Therefore, this paper deals with the comparison of experimental wetting and the simulative investigation of the wetting processes of lithium-ion battery materials by a lattice Boltzmann simulation. Particular attention is paid to the interfaces between the battery materials. These effects are relevant for a simulation of the wetting properties at the cell level. The experimental results show a 43% faster wetting of the interface between an anode and a separator than with only an anode. Overall, the simulation results show a qualitatively successful reproduction of the experimental wetting phenomena. In addition, the steps for a more precise simulation and the development of the Digital Twin are shown. This extension enables simulations of the electrolyte wetting phenomena in manufacturing lithium-ion batteries and the quantification of the wetting times. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The representation of cotton color is a key element in deciding the cotton grade. The color of cotton fibre is measured with instruments as well as visual assessment. But, these two methods always represent disagreement in the measurements. The main reason for disagreement is the trash particles on the cotton surface. The threshold segregation technique is used for the segmentation of trash and cotton fibres from the image of cotton sample. It is used in this research for the trash segmentation and precise color measurement. The reduction of disagreement between visual and instrument measurements is observed and the color of cotton is presented in more precise manner by using different correlation methods. In the presence of trash particles on the surface, it is not possible to measure the accurate color of cotton sample and the trash particles have to be removed. But, in this research image analysis method is used and the final color value will not include the trash color as it will be segmented from the image. [ABSTRACT FROM AUTHOR]

The terminal beam collimation problem of laser processing systems has traditionally been a headache. The deflection of the terminal beam seriously affects the processing accuracy and success. In this article, A novel method for measuring, collimating, and maintaining the spatial pose of the terminal beam in a five-axis laser processing system based on 3-D and 2-D hybrid vision is proposed. The beam pose in the working space of the laser processing system is measured by using a 3D scanner and an alignment sensor. The functional relationship between the galvanometer coordinates and the deflection angles of the terminal beam is established. The coordinates corresponding to the minimum deflection angle are solved to collimate the beam. Moreover, a camera is used to monitor the laser spot and re-collimate the deflected beam. The experimental results show that the method proposed in this article can effectively measure the deflection angle of the terminal beam, collimate the terminal beam and monitor the spot position of the terminal beam. The method can effectively improve the processing accuracy when applied to the laser processing system and has excellent potential application value. [ABSTRACT FROM AUTHOR]

Monitoring vehicle axle loads is very important for preventing infrastructure degradation and traffic accidents. However, developing an accurate, cost-effective, and easy-to-implement axle load identification technology still remains challenging. In this study, a vehicle axle load identification method based on visual measurement is proposed. The principle of the method is that each axle load of the vehicle is determined based on the vehicle unsprung masses, the ratio of vehicular sprung mass to unsprung mass, and the centroid position of the sprung mass. While the vehicle unsprung masses can be treated as a known with the vehicle model identified, the mass ratio can be predicted from the visually captured free damped vibrations of the vehicle as it passes over a speed bump. To be more specific, the vibration responses of a vehicle passing over a speed bump are firstly measured by a camera, and the vehicle system matrix, which is composed of the mass matrix, stiffness matrix, and damping matrix, can be obtained from the vehicle responses. The axle load can then be determined based on the element ratios in the system matrix of the vehicle whose unsprung masses are known. The performance of the proposed method was evaluated by numerical simulations and field tests. The results show that the errors of the simulation results are all less than 1% under ideal conditions. In the field test, the average error in identifying axle loads at different vehicle speeds was 7.01% when the vehicle speed was below 20 m sâˆ'1, which proved the accuracy and effectiveness of the proposed method. This study has demonstrated a novel application of computer vision technology to identify the axle loads of moving vehicles. The proposed method does not require installation of sensors on the roadway or the vehicle, making it a promising alternative for traditional weigh-in-motion systems. [ABSTRACT FROM AUTHOR]

In the biomedical field, polyurethane (PU) is widely used in interventional catheters, artificial hearts, artificial blood vessels, orthopedic materials, medical adhesives, and other medical devices. In this paper, a method based on machine vision was proposed to control the drafting and winding accuracy of PU filament in order to solve the problem of centrifugal runout when the mold rotates. The centrifugal runout of the mold directly affected the preparation efficiency and quality of long artificial blood vessel by wet spinning. Through non-contact real-time detection of the filament diameter and the angle between the axis of filament and the axis of mold, the motion parameters of the two motors driving the moving platform and the drafting roller could be adjusted in real time to achieve the purpose of online real-time control of filament drafting and winding accuracy. The vision control method proposed in this paper was used to carry out the PU tube preparation experiment. The visual measurement results of the filament diameter and the included angle were compared with the manual measurement results. The average value of the diameter error is 0.0096mm, and the average value of winding angle is 0.4777°. The results proved the accuracy of the visual measuring method and testified it feasible to using machine vision instead of manual method to detect filament diameter and winding angle. Properties of the prepared PU tube were tested and analyzed. The filament diameter measured by the 3D microscope was about 0.87 mm and significantly smaller than the filament diameter before winding. This indicated that the winding was uniform, the extrusion was tight, and the adhesion was good.

Laser powder bed fusion (LPBF) is of great importance for the visual measurement and analysis of the metallization process, which is the process of solid, liquid, and gas phase transformations of metal powders under high-energy laser irradiation due to the low boiling point/high saturated vapor pressure. Since the evaporation of metals involves the interaction of driving forces such as vapor back pressure, surface tension, and gravity, the movement of the melt pool is not stable. At the same time, it also produces vaporization products such as vapor plumes and sprays, which cause defects such as bubbles, porosity, lack of fusion, inclusions, etc., during the manufacturing process of the parts, affecting the performance and manufacturing quality of the parts. More and more researchers are using imaging technologies, such as high-speed X-ray, high-speed visible light cameras, and high-speed schlieren imaging, to perform noncontact visual measurements and analyses of the melt pool, vapor plume, and spatter during the metal evaporation process, and the results show that the metal evaporation process can be suppressed by optimizing the process parameters and changing the processing atmosphere, thereby reducing part defects and improving part performance and built part quality. This paper reviews the research on metal evaporation mechanisms and visual measurement methods of metal evaporation, then discusses the measures of metal evaporation, and finally summarizes and prospects the future research hotspots of LPBF technology, according to the existing scholars’ research on numerical simulation analysis and visual measurement methods of the metal evaporation process.

• Vibration measurement of all tube in bundle based on visual technique is achieved. • Tube vibration characteristics due to non-uniform flow in transverse direction is obtained. • Tube bundle is prone to FEI under one-third opening baffle. • FEI Vibration under one third opening baffle has severe vibration region, transition region and reversed flow region. • Tubes in reversed flow region vibrates at a lower frequency with the inactive supports of TSPs. The study investigates cross flow-induced vibration under conditions of transverse flow nonuniformity through a visualization-based experimental approach. Flow-induced vibration characteristics of a two-span rotated triangular tube bundle, supported by two tube support plates (TSPs), are examined. Tube positions at the upper extremity are captured using a high-speed camera. Findings reveal that the tube bundle exhibits a higher susceptibility to fluid elastic Instability (FEI) when subjected to non-uniform cross flow induced by a one-third opening baffle, in contrast to a uniform hole baffle configuration. With the one-third opening baffle configuration, substantial variations in tube vibration amplitudes are observed among different tubes. and the tube bundle can be divided into three kinds of regions, i.e. the severe vibration region, transition region and reversed flow region. The severe vibration region encompasses the central tubes within the three columns directly facing the opening of the baffle. This region serves as the initiation zone for FEI and warrants particular design considerations. [ABSTRACT FROM AUTHOR]

Currently, traditional tactile sensors based on the principles of capacitance or piezoelectricity have complex structures and difficulty in obtaining tactile information. A vision-based tactile sensor is introduced which can realize visual measurement of three-dimensional displacement in this paper. The vision-based tactile sensor is mainly composed of an elastomer embedded with marker point array, a transparent acrylic plate, 8 LED lights and a micro monocular camera. The elastomer deforms when the tactile sensor contacts an object, and the micro monocular camera is used to capture the elastomer deformation and transmit it to the computer in the form of image, and then the three-dimensional displacement information is obtained by processing the image. In order to more accurately recover the missing dimensional information in the three-dimensional displacement detection of monocular camera, an improved DFD (Depth from Defocus) method based on finite element theory is proposed in this paper. It is verified by experiments that the improved DFD method proposed in this paper can measure the three-dimensional displacement information more accurately compared with the DFD method. In addition, an experiment is conducted to prove the robustness of the improved DFD method on the robotic gripper. The experimental results demonstrate that the three-dimensional displacement measurement method proposed in this paper can provide technical support for the design and development of vision-based tactile sensors. [Display omitted] • The improved DFD method allows for the change of the marker points' diameter. • The finite element theory is used to calculate the true diameter of the marker points. • The experiment shows the improved DFD method increases the accuracy by 64 %. [ABSTRACT FROM AUTHOR]

Vision-based deep-learning methods are widely employed for Surface Defect Detection (SDD). However, as learning often needs extensive high-precision annotations, the practical application is always inconvenient and expensive. In this study, we alleviate the heavy requirement and further improve the accuracy. Specifically, a novel semi-supervised paradigm based on Diffusion Probabilistic Model (DPM) is proposed, namely SDDiff. It starts with unsupervised pre-training for DPM using low-cost image samples to learn the overall distribution. Next, we construct a detection pipeline that collects high-value features based on the trained model, which needs only a small amount of labeled data for supervised training. SDDiff combines the extensive data understanding of unsupervised learning and the precise pattern recognition of supervised learning, consequently reshaping the landscape of SDD. Sufficient experiments show that our method is effective, stable, and has low annotation dependence, which is better for practical visual measurement. • A novel semi-supervised paradigm with low annotation dependence. • Pioneering the application of DPM for visual measurement. • Effectively extracting rich features via unsupervised training. • Feature enhancement through frequency domain modulation. • Ensembling classifiers diminish the randomness in diffusion. [ABSTRACT FROM AUTHOR]

To address the measurement issues posed by fine pitch gears, due to the characteristics such as low stiffness and narrow tooth space, this paper proposes a rapid and high-precision measurement method which does not require precise installation by combining optical and visual principles. A calibrated artifact, featuring cylindrical and flat surfaces, was designed to accurately determine the relative positions of the line laser sensor, camera, and rotary table. An experimental setup was constructed, and measurement experiments were conducted on two types of cylindrical gears. To validate the precision of the measurement system, gear profile deviation, helix deviation and pitch deviation were evaluated according to ISO 1328-1:2013. The results were compared with the reference evaluations from Klingelnberg Gear Measuring Center P26, with difference less than 2.4 µm. Eight repeatability experiments were conducted, demonstrating that the method proposed satisfies the measurement requirements for fine pitch gears with an accuracy of class 6. • Measurement method for fine pitch gears without high-precision installation. • A calibrated artifact was designed to accurately calibrate the measurement system. • Profile, helix and pitch deviations were evaluated and compared to P26. • The method meets measurement needs for fine pitch gears with class 6 accuracy. [ABSTRACT FROM AUTHOR]

Featured Application: This study is meaningful for the design and analysis of the flexible skin wings for long-endurance low-speed aircraft. Flexible membrane structure is generally used as wing skin for long-endurance low-speed aircraft, such as solar aircraft, to control the structure weight within the allowable range. Predictably, the elastic deformation of the membrane under complex loads will cause uncertain impacts on the aerodynamic performance. The existing research indicates that the deformation of the membrane wing is helpful to improve the aerodynamic characteristics. However, most of the research objects are non-thickness membrane wings. In this paper, wind tunnel experiments are performed on double membrane wings. The experiment results indicate that the membrane deformation behavior is related to the surface curvature distribution and will change the camber and thickness of the airfoil. The deformation has little effect on lift but has a significant effect on drag and pitching moment. On this basis, a high-precision fluid structure coupling analysis method for the wider range of research is introduced. The numerical analysis indicates that the deformation can delay the stall angle by 1°. Furthermore, based on the numerical results, suggestions on prestress setting during membrane skin laying are provided, and the numerical simulation results of two flexible skin wings are compared. The research results of this paper provide a scientific basis for the aerodynamic design and analysis of long-endurance low-speed aircraft. [ABSTRACT FROM AUTHOR]

To improve the robotic arm system’s ability of perceiving the environment, a multi-station precise alignment technique of robotic arms guided by far-near-sight vision system is proposed. First, a configuration is built with one far-sight camera and one near-sight camera, and an eye-in-hand robotic arm is built up. Second, intrinsic and extrinsic parameters of the vision system and the transformation relationship between the vision system and the robotic arm are calibrated and a task table is established by a local priori alignment method. Third, a three-stage alignment strategy is proposed, i.e., the acquisition of the starting pose of the multi-station operation, the initial positioning of the global camera, and the fine alignment of the local camera. Thus, the robotic arm can achieve precise alignment between the end tool and targets in multiple stations. The feasibility of our method is verified experimentally. The angle’s standard deviation is below 0.015° by 50 times repeated single-station pin-hole alignment, and the position standard deviation is below 0.078 mm. The three-stage alignment experiment in multi-stations alignment shows that the angle error is below 0.05° and the position error below 0.17 mm. [ABSTRACT FROM AUTHOR]

In the digital drilling and riveting process of complex surfaces such as aircraft panels, the reference hole is pre-drilled on the skin surface. Generally, four laser displacement sensors (LDSs) are used as a group for normal adjustment. The camera vision is used to determine the position of the reference hole to obtain the accurate positioning of the drilling position. However, while dealing with large curvature complex panel surface and panel edge, four LDSs have the problem of reflection laser disappearance or matching failure. Applying two LDSs for normal adjustment on one side, the projection of the reference hole on the camera focal plane is an ellipse which means a further normal adjustment is desired in the direction of the ellipse's minor axis. Therefore, this paper proposes a 3-dimensional pose estimation method (TDPEM) combining multi-sensor fusion and space geometry to realize the normal adjustment and position measurement of reference holes with a monocular camera and two LDSs. Firstly, two LDSs are used to adjust the reference hole's horizontal (or vertical) direction. And then, an ellipse contour extraction algorithm is proposed to determine the ellipse parameters. Finally, the pose of the reference hole on the panel is determined by a spatial circle reverse algorithm. The experiment proves that the position error and angle error between this algorithm and the traditional four-LDS–based measurement method are within 0.03 mm and 0.2°, respectively, which verifies the feasibility and reliability of this algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a novel robust orientation estimator to enhance the accuracy and robustness of orientation estimation for inertial–magnetic sensors of the small consumer–grade drones. The proposed estimator utilizes a trust–region strategy within a nonlinear optimization framework, transforming the orientation fusion problem into a nonlinear optimization problem based on the maximum likelihood principle. The proposed estimator employs a trust–region Dogleg gradient descent strategy to optimize orientation precision and incorporates a Huber robust kernel to minimize interference caused by acceleration during the maneuvering process of the drone. In addition, a novel method for evaluating the performance of orientation estimators is also presented based on visuals. The proposed method consists of two parts: offline calibration of the basic cube using Augmented Reality University of Cordoba (ArUco) markers and online orientation measurement of the sensor carrier using a nonlinear optimization solver. The proposed measurement method’s accuracy and the proposed estimator’s performance are evaluated under low–dynamic (rotation) and high–dynamic (shake) conditions in the experiment. The experimental findings indicate that the proposed measurement method obtains an average re–projection error of less than 0.1 pixels. The proposed estimator has the lowest average orientation error compared to conventional orientation estimation algorithms. Despite the time–consuming nature of the proposed estimator, it exhibits greater robustness and precision, particularly in highly dynamic environments.