199 results about "Digital image correlation" patented technology

The invention relates to a deformation online measurement and control method for multi-robot collaborative assembly. The method comprises the steps that multi-view surface images of workpieces in the assembly process are collected in real time through distributed robots and cameras arranged at the tail ends of the distributed robots; each view angle surface image is input into a deep learning model trained based on a digital image related technology, the optimal pixel displacement corresponding to each view angle surface image is output, and the optimal pixel displacement corresponding to each view angle surface image is converted into a spatial displacement label; the deep learning model takes an encoder-decoder as a trunk network; fusing the spatial displacement labels corresponding to the view angle surface images to obtain a fused displacement field; based on the fusion displacement field and the nominal path planning point, the tail end pose of the distributed robot is determined; the assembly error is calculated based on the reference target positioning and the tail end pose, and the PID controller adjusts the joint space of the distributed robot based on the assembly error. According to the method, the calculation overhead is remarkably reduced, and the measurement precision and robustness are improved.

The invention discloses a thermal shock failure prediction and laser repair device for a thermal barrier coating and an application method. The device comprises a multi-physics field coupling simulation analysis module, a thermal shock experiment loading module, an online damage monitoring and failure diagnosis module, a robot laser repair execution module and a central control and data processing core unit. A thermal-mechanical-chemical coupling model is established to predict a coating failure behavior, a high-frequency induction heating and gas quenching system is adopted to simulate an extreme thermal shock environment, a multi-band thermal infrared imager, an ultrasonic probe and a digital image related system are integrated to monitor damage evolution in real time, and in-situ repair of a damaged area is realized based on a six-degree-of-freedom industrial robot. According to the method, the whole-process closed-loop control from failure prediction to repair regeneration is realized, the problems of single function and lack of multi-field coupling analysis and real-time repair capability in the prior art are solved, and the service reliability evaluation precision and the remanufacturing efficiency of the thermal barrier coating are remarkably improved.

An exemplary system and method that employ inverse-problem analysis that can determine spatially-varying mechanical parameters in a spatially-varying field of a heterogeneous material. Mathematically, the computation simultaneously poses the inversion program and an image registration problem in a continuum limit function space setting to derive a discretization dimension-independent algorithm for the robust inference of heterogeneous material properties. The algorithm can operate using two or more images of a speckled pattern or other non-uniform patterns applied to, or observable of, the surface of the material in a first state and a second state different from the first state. The difference can be used to assess, via a Newtonian-based operator, the infinite-dimensional spatial fields as state variables that are regularized via a regularization model to constrain the inherent ill-posed nature of inverse problems.

The invention discloses a cylindrical roller trajectory tracking method and device, and the cylindrical roller trajectory tracking method comprises the following steps: obtaining an actual measurement displacement sequence of a key point on the end surface of a roller under a global coordinate system based on a multi-reference matching digital image correlation method; drawing a key point displacement curve about key points and time according to the actually measured displacement sequence; judging the motion state of a roller according to the shape characteristics of the key point displacement curve, dividing a smooth part in the key point displacement curve into a rolling area, and dividing a part with jumping or sharp points into a sliding area; calculating the actual revolution angular velocity and the actual rotation angular velocity of the roller based on the actually measured displacement sequence corresponding to the sliding area; according to the method and the device, the image matching precision can be improved, meanwhile, the rolling and sliding components of the roller are accurately distinguished, the precision of the track of the cylindrical roller is improved, and high-precision and visual experimental data are provided for existing dynamics and tribology models.

The invention relates to a slope monitoring point arrangement method based on sparse spatial correlation and displacement sensitivity. The method comprises the following steps: firstly, carrying out geological survey on a site slope to obtain variability parameters of a slope soil body; then, a slope finite element model is constructed on the basis of slope geometric parameters and the variability parameters, and the displacement states of the slope under different parameter conditions are determined on the basis of the slope finite element model; grading the slope sensitive area based on the displacement state; obtaining displacement data based on the grade of the slope sensitive area, and determining a displacement correlation coefficient and a spatial correlation coefficient based on the displacement data by adopting a Pearson's correlation coefficient and a digital image correlation technology; and finally, determining a slope high-correlation area based on the displacement correlation coefficient and the spatial correlation coefficient, and setting a monitoring point position. The scientificity and accuracy of slope monitoring point arrangement are improved, and the method has certain significance for predicting and preventing slope disasters.

The invention relates to the technical field of structural design and optimization, and particularly discloses a structural error tolerance model construction method for compartment connection positioning, which comprises the following steps of: obtaining real point cloud data of a bolt connection pair through three-dimensional laser scanning, and realizing parameterized digital geometric modeling in combination with a deep neural network; material attributes are given, and self-adaptive grid division is carried out; generating a dynamic load sequence based on a vehicle driving condition, applying the dynamic load sequence to the model, and extracting full-field displacement vector data by using a digital image correlation technology; further identifying a micro-slip area of the contact interface, and calculating an energy dissipation index of the micro-slip area; a quantitative mapping relation between energy dissipation and fatigue life is established through experimental calibration, key design parameters are iteratively optimized by adopting a pattern search method with the target life as a constraint, and finally a connection structure scheme meeting the durability requirement is output.

The invention provides a ground-air combined road slope collapse measurement system and method, and relates to the field of road slope inspection. According to the system, all-weather non-contact acquisition of millimeter-level displacement data of side slope key points is realized through a scientific-level CMOS camera of the ground detection module and a digital image correlation algorithm, and a high and steep side slope is covered; the aerial detection module carries a synthetic aperture radar and a multispectral sensor through an unmanned aerial vehicle to obtain a slope overall three-dimensional deformation field and soil humidity data. Carrying out high-precision space-time registration on the data layer by adopting a dual-function mark point and a least square method; calibrating aerial deformation data on the feature layer through ground displacement data to realize association of macroscopic and microscopic features; and constructing an improved U-Net network and a hybrid prediction model in the model layer to realize accurate tracking of the crack and prediction of the collapse probability. Visual display is carried out through a digital twin platform, and graded early warning linked with a traffic management system is triggered. According to the invention, the limitation of a single detection mode is overcome, and accurate perception, intelligent prediction and dynamic response of road slope safety are realized.

The invention belongs to the technical field of three-dimensional vision measurement, and relates to a deformation measurement method and system of a composite vision measurement unit. The internal and external parameters of the binocular measurement unit are obtained according to the image of the thrust vectoring nozzle target area calibration plate; obtaining coordinates of all binocular measurement units in the same reference coordinate system according to the internal and external parameters and the images of the thrust vectoring nozzles with the first coded mark points, and obtaining coordinates of all binocular measurement units in a unified coordinate system; and acquiring full-field deformation of all target areas of the thrust vectoring nozzle according to the speckle images of the target areas of the thrust vectoring nozzle in the working state and the coordinates of the unified coordinate system of all binocular measurement units. According to the invention, a digital image correlation method and a close-range photogrammetry technology are utilized to realize coordinate system unification and full-field deformation measurement. Compared with a traditional method, the measurement times and data processing steps are reduced, and the measurement efficiency is improved.

The application discloses a kind of based on transparent soil and pile-soil interface micro evolution measurement method of multi-source sensing, it is related to geotechnical engineering test field.The present application includes the following steps: constructing transparent soil model, pile body pre-embedded sensor arrangement, multi-source sensor calibration and parameter optimization, load application and multi-source data acquisition, improved DIC algorithm's pile-soil interface micro displacement calculation, pile-soil interface pore and particle density calculation, multi-source sensing data's heterogeneous fusion, pile-soil interface micro evolution characteristic quantitative inversion and visualization, test end and data verification.The present application simulates real soil environment by constructing transparent soil model, in combination with image recognition, digital image correlation, fiber-optic sensing and resistance sensor and other multi-source sensing technology, the micro deformation, stress distribution and failure evolution process of pile-soil interface in loading process are monitored and analyzed in real time with high precision, realize the high-precision, full-process, visual measurement of pile-soil interface micro evolution, improve measurement precision.

The invention discloses a multifunctional asphalt mixture rut test method which is implemented by using a device integrating loading and measurement, test piece supporting and temperature control drainage, environment simulation and optical measurement and a central control and data acquisition system. A test piece is arranged in the test piece groove, temperature control is realized through circulating a heat-conducting medium in the temperature-conducting cavity, different gradients are formed through the hoisting mechanism and the angle adjusting assembly, the test wheel is driven to perform one-way circulating loading along a closed track and snub at a preset moment, and rolling and sliding friction forces are synchronously collected; in the test process, rainfall is simulated by adopting the watering assembly, incoming water is recycled by the drainage tank, speckle images are acquired by the high-frequency industrial camera, and surface full-field displacement and strain are obtained through digital image correlation analysis. Through time registration and fusion of temperature, gradient, wheel speed, rainfall and friction-deformation data, rut deformation, skid resistance and apparent structure evolution laws of the asphalt mixture under multi-climate and multi-gradient conditions are obtained.

Methods, systems, and non-transitory computer readable storage media are disclosed for generating neural network based perceptual artifact segmentations in synthetic digital image content. The disclosed system utilizing neural networks to detect perceptual artifacts in digital images in connection with generating or modifying digital images. The disclosed system determines a digital image including one or more synthetically modified portions. The disclosed system utilizes an artifact segmentation machine-learning model to detect perceptual artifacts in the synthetically modified portion(s). The artifact segmentation machine-learning model is trained to detect perceptual artifacts based on labeled artifact regions of synthetic training digital images. Additionally, the disclosed system utilizes the artifact segmentation machine-learning model in an iterative inpainting process. The disclosed system utilizes one or more digital image inpainting models to inpaint in a digital image. The disclosed system utilizes the artifact segmentation machine-learning model detect perceptual artifacts in the inpainted portions for additional inpainting iterations.

A data uploader uploads a first plurality of data values associated with a transaction. A document uploader uploads digital images of a plurality of documents associated with the transaction, wherein a second plurality of data values are embedded in the documents. The digital images are stripped of numerical (or other) data values before being transmitted to a first machine learning engine to identify documents associated with the digital images. A second machine learning engine identifies categories of numerical data values (and other data values) that are included in the second plurality of data values and that are embedded in the documents. The first and second plurality of data values can be compared for accuracy and corrected. The first and second machine learning engine are sent bifurcated feedback regarding the respective identification performed by each to improve future accuracy.

The invention discloses a self-adaptive illumination adjustment image measurement method, and belongs to the technical field of image measurement. According to the method, adaptive adjustment is carried out on hardware and a related algorithm simultaneously according to environment illumination changes, the exposure amount of an image is changed by adjusting the exposure time of a camera on the hardware, and exposure adjustment is used for ensuring that the gray level distribution of an image sequence obtained by the camera in an interested area is consistent with that of a reference image as much as possible in the measurement process. Exposure adjustment of a camera is global adjustment for an image, and overexposure or underexposure pixel points still possibly appear in a local area of the image. Therefore, an illumination robust digital image correlation algorithm is provided, the gray level distribution of the sub-regions is adjusted in real time during correlation calculation, the registration precision of the sub-regions is improved by removing saturated pixels in the sub-regions, the sizes of the sub-regions are adaptively adjusted according to illumination changes, it is ensured that the sub-regions contain enough and rich gray level information, and the registration precision of the sub-regions is improved. And the robustness of a related algorithm in suppressing illumination interference is improved.

The invention relates to an electric arc additive mixed end plate connecting device and a performance prediction method, and the method comprises the steps: manufacturing a WAAM end plate at the end part of a conventional steel pipe through multi-axis metal 3D printing, and forming a mixed connecting piece; the two mixed connecting pieces are in butt joint through high-strength bolts to form the mixed end plate connecting device; geometric characteristic parameters of the mixed end plate connecting device are obtained by adopting a three-dimensional scanning technology, and the mechanical response of the mixed end plate connecting device is measured by combining a four-point bending test with a digital image correlation technology; and on the basis of the geometrical characteristic parameters and the mechanical response data, the yield bearing capacity is predicted through a correction yield line analysis method, and the ultimate bearing capacity is predicted by adopting an equivalent beam model considering the strain hardening effect. The device and the method have the beneficial effects that geometric characteristic measurement, interface connection characteristic and yield performance test, bearing prediction evaluation and application design of the mixed end plate connecting device combining the electric arc additive manufacturing stainless steel, low-carbon steel and high-strength steel end plates with the conventional steel pipe can be effectively realized.

The invention provides an ammonia hydrogen energy structure material constant strain rate and constant load stress corrosion synchronous monitoring platform based on acoustic emission and an implementation method thereof. Comprising a gas supply and pressurization system, a constant strain rate and constant load stress corrosion synchronous test system, a gas leakage safety control system, an acoustic emission and digital image correlation (DIC) technology online monitoring analysis system, a temperature control system and a computer integrated analysis system. In-situ dynamic analysis of stress corrosion crack propagation is realized in combination with a DIC technology; the temperature control system realizes accurate temperature control on the corrosion test reaction kettle through an independent temperature control module; the computer integrated analysis system processes multi-source data, and establishes dynamic mapping between acoustic emission characteristic parameters and corrosion crack growth rate. The platform solves the problems of off-line monitoring, single loading mode and the like of a traditional corrosion test, captures a corrosion-induced crack propagation process in real time, improves test efficiency and analysis comprehensiveness, and provides powerful support for research on corrosion behaviors of ammonia hydrogen energy structural materials.

The invention discloses a non-contact measurement system and method for full-field deformation of a fuselage in an airplane crash test, and belongs to the technical field of airplane structure strength testing, and the method comprises the steps: making a high-quality speckle pattern on the surface of the fuselage, and laying cooperation mark points; a binocular camera flexible self-calibration method is used for completing calibration of the stereo measurement system; unification of global coordinates of multiple systems is assisted through unmanned aerial vehicle photogrammetry; a synchronous controller is adopted to trigger multiple sets of systems to synchronously collect images in the falling and collision process; obtaining the motion trail and speed of the key measuring point based on a mark point positioning tracking and stereoscopic vision principle; acquiring a full-field three-dimensional displacement field and a strain field based on a digital image correlation method guided by a control point and a stereoscopic vision principle; and deformation visualization representation is realized through image splicing and data fusion. According to the invention, non-contact, high-precision and full-field dynamic measurement of the three-dimensional deformation field in the falling and collision process of the whole large aircraft is realized, and technical support is provided for analysis and evaluation of falling adaptability of the aircraft structure and verification of anti-falling and anti-collision design.

The invention provides a side slope deformation video monitoring method and system based on a night vision system, and relates to the technical field of geotechnical engineering safety monitoring. The method comprises the following steps: acquiring all-weather video stream data of a slope area to be monitored through a dual-mode night vision camera device, and preprocessing to obtain a slope deformation image; the slope deformation image is analyzed by adopting a digital image related technology to obtain a slope surface deformation condition, and the slope surface deformation amount is calculated to carry out multi-stage early warning; and inputting the slope surface deformation amount into the trained deformation trend prediction model based on the LSTM, and obtaining the predicted deformation amount for early warning. According to the invention, the bottleneck of night side slope on-line monitoring is broken through, 0.05 mm submillimeter level displacement measurement precision is realized through combination of the visible light-infrared dual-mode camera and the improved video image DIC flow analysis technology, the spatial-temporal feature fusion model is innovatively introduced to improve the early warning accuracy, and a reliable technical means is provided for side slope safety protection in a complex environment.

To provide a system for evaluation that can precisely and easily evaluate the fracture toughness value of a joined body on a joined interface.SOLUTION: The present invention relates to a system for evaluation that comprises: a crack gauge which has its surface coated with a random pattern for a DIC method and is stuck on a joined part for evaluation using a tension testing machine for a joined body; a digital camera which photographs a random pattern; software for analysis which analyses the strain of the joined part; and a computer, wherein the computer can send and receive electric signals between the crack gauge and digital camera, and synchronizes a crack progress length at time X when the joined part cracks that the crack gauge outputs with the strain of the joined part that the digital camera photographs at the time X, and the software for analysis evaluates a progress behavior of the crack at the joined part, and calculates a threshold for determining the progress of the crack based upon the strain at the time X.SELECTED DRAWING: Figure 1

This invention discloses a method and system for real-time stress monitoring during laser additive repair of fatigue long cracks in turbine casings. The method includes: preparing a high-temperature resistant speckle pattern in the pre-treated repair area; simultaneously acquiring a sequence of speckle images and a sequence of temperature field images during the laser repair process; calculating the strain field based on digital image correlation and calculating the real-time stress evolution using thermo-elastic-plastic stress-strain increment theory. The real-time stress value is compared with a dynamic threshold set based on the material's yield strength, and the laser power or scanning speed is controlled based on the feedback of the result to achieve closed-loop control of the repair stress. This invention achieves high-precision real-time online monitoring of stress under extreme repair environments, providing a basis for optimizing and intelligently controlling repair process parameters, effectively suppressing residual stress and the risk of secondary cracks, and significantly improving the repair quality and reliability of turbine casings.

This invention specifically relates to a biomimetic underwater robot body perception and autonomous obstacle avoidance method based on dual-path 1D-CNN, comprising: measuring the deformation data of the structure during water movement using digital image correlation equipment; deploying multiple flexible sensors in an array in areas of significant deformation to accurately acquire deformation signals; a central control unit monitoring the sensor signals in real time and performing collision detection using a lightweight dual-path 1D-CNN algorithm; when a collision signal is detected, the central control unit automatically issues control commands, which are converted into motor output parameters by a central pattern generator to change the robot's motion posture, enabling autonomous obstacle avoidance. This invention achieves real-time motion monitoring and highly robust, low-latency autonomous obstacle avoidance for biomimetic underwater robots in complex aquatic environments, providing an effective self-protection mechanism and improving its swimming safety and intelligence level.

A tracking system for quantifying retinal traction on a retina of a patient eye includes an indicator device, a stereo camera, and an electronic control unit (ECU). The stereo camera collects and outputs stereo image data. The ECU, which is in communication with the indicator device, executes a method by receiving the stereo image data from the stereo camera during an ophthalmic procedure and thereafter assigning tracking points as coinciding pixels within stereo image pairs. The ECU also automatically performs a digital image correlation (DIC) process using the stereo image pairs to ascertain relative motion of the tracking points, and associates relative motion of the tracking points with the retinal traction using a traction map. A numeric traction quotient is generated that is indicative of magnitude of retinal traction. The ECU executes a control action using the indicator device based on the numeric traction quotient.

The invention discloses a multi-field coupling intelligent inclination angle plane physical similar simulation experiment system and method. The system comprises an experiment platform with a controllable inclination angle, a stress monitoring module, an optical deformation monitoring module and an acoustic emission monitoring module. The experiment platform realizes high-precision adjustment and stable maintenance of an inclination angle of + / -0.1 degree through cooperation of hydraulic drive and a mechanical lock. The stress module adopts a wireless sensor network to monitor a stress field; the optical module is used for measuring full-field displacement strain based on a CCD camera and a digital image related technology; and the acoustic emission module positions a rock stratum fracture signal through the probe array. The method comprises the steps of platform deployment, inclination angle adjustment, system debugging, synchronous mining monitoring and the like. According to the invention, inclination angle accurate control and multi-physical field information synchronous integrated acquisition are realized, and the system is suitable for inclined coal seam mining rock stratum movement and disaster mechanism research.

A digital image correlation deformation field reconstruction method based on a physical information neural network comprises the following steps: constructing a neural network model with input as a coordinate domain and output as a displacement field and a loss function containing a data loss item and a physical loss item; neural network pre-training and displacement field pre-reconstruction only including a data loss item are performed to determine a weight value of a physical loss item, neural network training and displacement field reconstruction including the data loss item and the physical loss item are performed, automatic differential operation is performed on a reconstructed displacement field, and a strain field is solved. According to the method, manual parameter setting is not needed, the advantages of PINNs fusion physical prior and nonlinear fitting can be fully utilized, the problems of low automation degree and poor smoothing effect of post-processing of a traditional digital image related deformation field are solved, and the precision of the deformation field is remarkably improved.

This application provides a biological soft tissue material performance measurement system and method based on digital image correlation, belonging to the field of measurement technology. The biological soft tissue material performance measurement system includes: a tensile module configured to deform the biological soft tissue based on tensile force; a polarized light source configured to emit polarized light and irradiate the biological soft tissue during the deformation process to obtain reflected light; a polarizer, wherein the transmission axis of the polarizer is perpendicular to the polarization direction of the polarized light, so that the polarization component of the reflected light is filtered out after passing through the polarizer to obtain a first reflected light; an imaging module configured to receive the first reflected light to obtain multiple tensile images of the biological soft tissue during deformation; and a measurement module configured to obtain the material performance parameters of the biological soft tissue based on the multiple tensile images.

The invention discloses an image velocity measurement system for blood vessels, a vascular lesion risk assessment method, a blood vessel detection device-nanoparticle composition and application thereof, and relates to the field of image processing. The system comprises a targeted visual nanoparticle drug delivery unit, a double-ring scanning optical probe, a CMOS imaging device, an image acquisition and double-domain correlation processing module and a coupling mechanical parameter calculation module. According to the invention, the dual-ring scanning optical probe is combined with the external CMOS imaging device, so that efficient transceiving and transmission of the fluorescence signals of the nanoparticles are realized; and performing digital image correlation and microscopic particle image velocity measurement on the image sequence to finally obtain time synchronization data of various mechanical parameters such as vascular wall deformation, near-wall blood flow velocity, shear stress and the like, and performing vascular lesion risk assessment and early warning based on the time synchronization data.

A computer-implemented method and system relate to an image encoder that receives a digital image as input. The image encoder generates a weight map using the prior feature map. A prior feature map is generated using pixels of the digital image. A weight map is generated based on Lie data associated with the digital image. The homography is interpolated between the two planar projections of the digital image using at least the weight map and the homography matrix. The homography matrix provides a mapping between two planar projections of the digital image. A homography kernel is generated by applying homography to the convolution kernel. A homographic transform kernel is applied to the prior feature map to convolve different planar regions appearing in the digital image, and a new feature map is generated for computer vision tasks involving three-dimensional (3D) perception.

The invention provides a method for testing fracture strain temperature correlation of a metal material, and belongs to the technical field of material mechanical property testing. The method is based on a global digital image correlation (Globe-DIC) technology, and accurate positioning and measurement of surface displacement and strain of a sample in a high-temperature environment are realized through accurate matching of a finite element grid and an image of the sample. Through the characteristics that high-temperature-resistant ceramic speckles are prefabricated, thermal radiation interference is restrained through blue light illumination, and a global method DIC is not affected by the thermal expansion effect of materials, the consistency of scale distance sections at different temperatures is guaranteed. The fracture strain is indirectly extracted by selecting a local area far away from the fracture, and the problem of speckle falling caused by a new free surface generated by the fracture is avoided. According to the method, accurate measurement of fracture strain and determination of temperature correlation under the high-temperature condition can be realized, and reliable data support is provided for temperature term calibration of a material constitutive model and a fracture criterion.

The invention relates to the technical field of cement-based material performance detection, in particular to a cement-based material stability evaluation method based on a digital image correlation method. According to the method, a digital image correlation method (DIC) is introduced, and a complete stability evaluation process from speckle image acquisition and boiling processing to geometric parameter calculation and correlation model establishment is constructed. The method has the core advantages that the limitation that a traditional Reynolds clamp method can only indirectly measure the single swelling amount is broken through, and multi-dimensional quantification of macroscopic deformation (such as perimeter variation, area variation, perimeter change rate and area change rate) and local deformation characteristics before and after the test piece is boiled is realized through full-field speckle image analysis; a more comprehensive and accurate technical path is provided for cement stability evaluation, and the method is high in process standardization degree and suitable for engineering popularization.

This invention discloses a deep learning-based method and system for measuring large deformations. It extracts features and deformation information from a reference image and a deformed image to estimate initial values. Then, it uses a recursive iterative approach to refine the initial displacement values, constructing a measurement model. Finally, the obtained measurement model is trained and optimized to obtain the final model. Inputting the image to be measured into the trained measurement model yields the deformation field between images. Compared to existing deep learning digital image correlation measurement methods, this method can measure both small and large deformations. By estimating initial values ​​on low-scale features and then using the estimated initial values ​​for iterative refinement on high-scale features, it ensures the model can adapt to both small and large deformation measurements. Compared to traditional methods, it overcomes the limitations of slow computation speed and the need for manual parameter setting in digital image correlation methods. This method no longer relies on sub-region size settings and has a significant advantage in measuring high-frequency changing deformation fields.