This paper studies a method of detecting the position of crankshaft flange hole group based on vision measurement, and sets up the position detection system of crankshaft flange hole group. The relative measurement model of hole group position is established by using the standard crankshaft information, and the system calibration method is studied. In this paper, a multi-camera calibration method based on polynomial fitting two-dimensional image mapping model is adopted. In addition, the image processing technology of hole group is studied. The improved Canny edge detection method is used to extract the contour of the hole group. Redundant edge filtering algorithm is used to eliminate unreliable edges. Then use the gradient interpolation method to extract sub-pixel edges. The measurement results show that the single-direction measurement error of the central coordinate of the crankshaft flange hole group is less than 0.07mm, and the repeatability error is less than 0.009mm, which provides a basis for the realization of industrial online efficient detection.
With the development of laser radar technology, more and more fields have begun to use laser radar to acquire 3D point cloud information. The crux and premise of 3D object recognition and 3D model semantic segmentation is the depth feature of 3d point cloud. Therefore, it is significant for indoor intelligent robots to recognize 3D objects by using laser radar. However, unlike the regular arrangement of pixels in 2D images, the 3D point cloud data is irregular and disordered, which means it is difficult to acquire local related information between the 3D point cloud with direct convolution operation. At present, the research focus of 3D object recognition is the method based on deep learning. At this stage, the deep convolutional neural network constructed by PointConv can achieve a high level in the semantic segmentation of 3D point cloud. First, this paper introduces a model named PointConv. To balance the performance and complexity of the model, this paper simplifies the PointConv which called Mini-PointConv to reduce the occupation of network computing resources while ensuring the accuracy of the model segmentation results. Furthermore, the method of ScanNet is adopted to test the Mini-PointConv, which shows that the improved network has achieved a good experimental result in 3D scene semantic segmentation tasks and gained a better performance as balance as well. Finally, the Mini-PointConv is tested in a variety of indoor environments using laser radar and obtain a good indoor 3D point cloud recognition result.
The steel rule plays an important role in quantity transmission. However, the traditional verification method of steel rule based on manual operation and reading brings about low precision and low efficiency. A machine vison based verification system of steel rule is designed referring to JJG1-1999-Verificaiton Regulation of Steel Rule [1]. What differentiates this system is that it uses a new calibration method of pixel equivalent and decontaminates the surface of steel rule. Experiments show that these two methods fully meet the requirements of the verification system. Measuring results strongly prove that these methods not only meet the precision of verification regulation, but also improve the reliability and efficiency of the verification system.
The definition of dynamic envelope curve is the maximum limit outline caused by various adverse effects during the running process of the train. It is an important base of making railway boundaries. At present, the measurement work of dynamic envelope curve of high-speed vehicle is mainly achieved by the way of binocular vision. There are some problems of the present measuring system like poor portability, complicated process and high cost. A new measurement system based on the monocular vision measurement theory and the analysis on the test environment is designed and the measurement system parameters, the calibration of camera with wide field of view, the calibration of the laser plane are designed and optimized in this paper. The accuracy has been verified to be up to 2mm by repeated tests and experimental data analysis. The feasibility and the adaptability of the measurement system is validated. There are some advantages of the system like lower cost, a simpler measurement and data processing process, more reliable data. And the system needs no matching algorithm.
This paper proposed a method of detection to the grinding wheel layer thickness based on computer vision. A camera is used to capture images of grinding wheel layer on the whole circle. Forward lighting and back lighting are used to enables a clear image to be acquired. Image processing is then executed on the images captured, which consists of image preprocessing, binarization and subpixel subdivision. The aim of binarization is to help the location of a chord and the corresponding ring width. After subpixel subdivision, the thickness of the grinding layer can be calculated finally. Compared with methods usually used to detect grinding wheel wear, method in this paper can directly and quickly get the information of thickness. Also, the eccentric error and the error of pixel equivalent are discussed in this paper.
The catenary geometric parameters are important factors that affect the safe operation of the railway. Among them, height of conductor and stagger value are two key parameters. At present, the two parameters are mainly measured by laser distance sensor and angle measuring device with manual aiming method, with low measuring speed and poor efficiency. In order to improve the speed and accuracy of catenary geometric parameters detection, a new automatic measuring method of contact wire’s parameters based on laser scanning and imaging is proposed. The DLT method is used to calibrate the parameters of the linear array CCD camera. The direction of the scanning laser beam and the spatial coordinate of the starting point of the beam are calculated by geometric method. Finally, the equation is established using the calibrated parameters and the imaginary coordinates of the imaging point, to solve the spatial coordinate of the measured point on the contact wire, so as to calculate height of conductor and stagger value. Different from the traditional hand-held laser phase measuring method, the new method can achieve measurement of the catenary geometric parameters automatically without manual aiming. Through measurement results, accuracy can reach 2mm.
Nowadays, as workpieces become more precise and more specialized which results in more sophisticated structures and higher accuracy for the artifacts, higher requirements have been put forward for measuring accuracy and measuring methods. As an important method to obtain the size of workpieces, coordinate measuring machine (CMM) has been widely used in many industries. In order to achieve the calibration of a self-developed CMM, it is found that the parallelism of the base plate used for fixing the standard artifact is an important factor which affects the measurement accuracy in the process of studying self-made high-precision standard artifact. And aimed to measure the parallelism of the base plate, by using the existing high-precision CMM, gauge blocks, dial gauge and marble platform with the tactile approach, three methods for parallelism measurement of workpieces are employed, and comparisons are made within the measurement results. The results of experiments show that the final accuracy of all the three methods is able to reach micron level and meets the measurement requirements. Simultaneously, these three approaches are suitable for different measurement conditions which provide a basis for rapid and high-precision measurement under different equipment conditions.
According to some current problems in the course of measuring the plane shape error of workpiece, an in-situ measuring method based on laser triangulation is presented in this paper. The method avoids the inefficiency of traditional methods like knife straightedge as well as the time and cost requirements of coordinate measuring machine(CMM). A laser-based measuring head is designed and installed on the spindle of a numerical control(NC) machine. The measuring head moves in the path planning to measure measuring points. The spatial coordinates of the measuring points are obtained by the combination of the laser triangulation displacement sensor and the coordinate system of the NC machine, which could make the indicators of measurement come true. The method to evaluate planar straightness error adopts particle swarm optimization(PSO). To verify the feasibility and accuracy of the measuring method, simulation experiments were implemented with a CMM. Comparing the measurement results of measuring head with the corresponding measured values obtained by composite measuring machine, it is verified that the method can realize high-precise and automatic measurement of the planar straightness error of the workpiece.
In the center measuring device consisting of a plurality of laser triangular displacement sensors (LDS) for coaxiality measurement of shaft, it fits the center coordinate of the shaft by obtaining the coordinates of the outer contour, this poses a higher requirement for the relative position calibration accuracy of the multi-LDS. Aiming at the positional relationship between multi-LDS, the CMM is leaded into the calibration of the center measuring device. Randomly moves a standard column and reading the length values of multi-LDS, combined with the known center coordinates of the column from CMM, to establish the over-determined nonlinear equations, the angle and starting position of the laser beam of each LDS in the measuring device are calculated. The experiment result indicates that measuring uncertainty of the system is 30 μm, this proved the validity and feasibility of the multi-LDS center measuring device in the use of coaxiality measurement of shaft. As a result, it is found that the proposed calibration method is accuracy to the multi-LDS center measuring device and can be implemented easily.
The multistep registration(MSR) method in [1] is to register two different classes of sensors deployed on z-arm of CMM(coordinate measuring machine): a video camera and a tactile probe sensor. In general, it is difficult to obtain a very precise registration result with a single common standard, instead, this method is achieved by measuring two different standards with a constant distance between them two which are fixed on a steel plate. Although many factors have been considered such as the measuring ability of sensors, the uncertainty of the machine and the number of data pairs, there is no exact analysis on the squareness between the x-axis and the y-axis on the xy plane. For this sake, error analysis on the squareness of multi-sensor integrated CMM for the multistep registration method will be made to examine the validation of the MSR method. Synthetic experiments on the squareness on the xy plane for the simplified MSR with an inclination rotation are simulated, which will lead to a regular result. Experiments have been carried out with the multi-standard device designed also in [1], meanwhile, inspections with the help of a laser interferometer on the xy plane have been carried out. The final results are conformed to the simulations, and the squareness errors of the MSR method are also similar to the results of interferometer. In other word, the MSR can also adopted/utilized to verify the squareness of a CMM.
The high-precision detection for surface defect of ceramic balls, widely used in precise bearings, is a challenging task. Due to the fact that some defects cannot be directly detected by the gray-level of images, we propose a method for surface defect detection based on fringe reflection. Based on specular characteristics of ceramic balls, this method utilizes flat screens with fringes drawn on them. If a ceramic ball is nondefective, the image, formed by reflection on its surface, presents even fringes. The distortion of fringes designed by a reverse exact ray-tracing method occurs at the defective region of ceramic balls. During experiments conducted with silicon nitride (Si3N4) ceramic balls, images are captured by a CMOS camera with high resolution and processed by specific algorithms. Experimental results demonstrate the feasibility of this method, which can be applied for high-precision detection for surface defect of ceramic balls and other objects with similar characteristics.
Construction of high-speed railway in China has entered a period of rapid growth. To accurately and quickly obtain the dynamic envelope curve of high-speed vehicle is an important guarantee for safe driving. The measuring system is based on binocular stereo vision. Considering the difficulties in field calibration such as environmental changes and time limits, carried out a field calibration method based on fast reconstruction of three-dimensional control field. With the rapid assembly of pre-calibrated three-dimensional control field, whose coordinate accuracy is guaranteed by manufacture accuracy and calibrated by V-STARS, two cameras take a quick shot of it at the same time. The field calibration parameters are then solved by the method combining linear solution with nonlinear optimization. Experimental results showed that the measurement accuracy can reach up to ± 0.5mm, and more importantly, in the premise of guaranteeing accuracy, the speed of the calibration and the portability of the devices have been improved considerably.
Before using a series of concentric circles as the target, the target needs to be pre-processed to get characteristic parameters. This paper discusses a new method based on Gaussian sub-pixel to detect the edge of concentric circles, and get the coordinate of the center and radius of concentric circles based on the cross ratio invariability with five points which leads to more stable data. In the end, Levenberg-Marquard algorithm is used to approach the results. To verify the results, two methods are used both in the hands of experiment and simulation. These two results illustrate that the method we discusses have advantages on the accuracy.
High accuracy automatic measurement of engine box is significant for enhancing the quality and performance of the engine. To complete the fast automatic measurement of the engine box shaft hole diameter, a new non-contact methods for inner hole diameter measuring is proposed in this paper, a mathematic model is built according to this method. A probe based on laser displacement sensors is developed to meet the method by distributing the laser displacement sensors in the probe cross-section uniformly. By this method, shaft hole diameter can be got with single measurement. This method eliminates some defects involved in existing shaft hole diameter non-contact measuring methods, it does not need the rotation of the probe and accurate locating of the probe center and the shaft hole center. Experiments proved that the methods can be used to complete the task of the shaft hole diameter measuring with simple operation and accurate result. Experiments have also shown that the proposed method is an effective method of non-contact high accuracy diameter measurement.
The paper proposes a new vision-based inspection of car circlips. Due to the variety of circlips and large quantity, human inspection about its inside diameter, ring width is always subjective, labor-intensive and slow. The detector consists three parts: electromagnetic feeder, vision-based detection system and multi-station workbench. The feeder is customized to accomplish storage, screening, sorting and transmission of circlips. Vision system is made up of bilateral telecentric lens, tablet light and industrial camera. By means of image processing, it can detect dozens of circlips which it maximum outside diameter is less than 25.00mm. And the precision of inside diameter can reach up to 0.02mm. A multi-station workbench method is put forward in order to improve detecting efficiency combined with parallel software. The system can sort 60-80 pieces per minute.
The dynamic envelope curve measurement of high-speed train based on linear CCDs has the advantage of high measuring frequency and speed, and the design of cylindrical lens for linear CCD is essential. A design of cylindrical lens for linear CCD is presented according to the actual measurement requirements. A double-Gauss objective is selected as the basic type in ZAMAX. By appropriately changing the surface of the lens, adjusting various parameters and multiple optimizations, the optical structure is defined. The design can fulfill the requirement of the actual measurement system. Furthermore, by analyzing the image distortion characteristics of cylindrical lens, a kind of distortion model is built. According to the distortion cure of the final optical structure, the cylindrical lens distortion formula is defined based on the primary aberration theory, which provides the basis for the distortion correction of one-dimensional camera.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.