82 results about "Deformation vector" patented technology

The invention relates to an image stitching processing system, which belongs to the field of image processing, and is characterized in that an image reading unit, an overlapping region unit, a preprocessing unit, an optimal stitching line unit, a feature location unit, a feature matching unit, and a deformation propagation and image reconstruction unit are arranged in a digital processing circuit, wherein the image reading unit is used for reading two adjacent images from an image sequence; the overlapping region unit is used for acquiring an overlapping region of the two images; the preprocessing unit is used for preprocessing color of the overlapping region; the optimal stitching line unit is used for obtaining an optimal stitching line in the overlapping region; the feature location unit is used for detecting feature points in an optimal stitching line neighbourhood; the feature matching unit is used for matching the detected feature points; and the deformation propagation and image reconstruction unit is used for obtaining a deformation vector of each pixel point of each image, obtaining a gradient field of each image, and reconstructing a stitched image according to the gradient field. According to the image stitching processing system, the optimal stitching line is used as the most important image feature, so that the limitation of a shape of the overlapping region is solved, a lapped seam can be well eliminated in color and structure, and a real-time processing requirement can be met by utilizing an acceleration algorithm.

A method for determining the effectiveness of an image transformation process includes acquiring a four-dimensional (4D) image data set, sorting the 4D image data set into separate field-of-view bins using a temporal gating system generating a plurality of deformation vectors using the sorted 4D image data set, and using the plurality of deformation vectors to generate a transformation effectiveness value that is representative of the effectiveness of the image transformation process. The method further includes acquiring a respiratory signal, calculating a power spectrum of the respiratory signal, calculating a power spectrum for each of the plurality of deformation vectors, and comparing the power spectrum of the respiratory signal to the power spectrum of the plurality of deformation vectors to generate the transformation effectiveness value.

Apparatuses, computer media, and methods for altering an image of a person' face. Points on a two-dimensional image of a face and a neck of the person are located. A superimposed mesh is generated from the points. A subset of the points is relocated, forming a transformed mesh. Consequently, the face is reshaped from the transformed mesh to obtain a desired degree of fattening or thinning, and a reshaped image is rendered. A subset of points on the face is relocated by applying a deformation vector to each point of the subset of points. The deformation vector is determined from a product of factors. The factors include a weight value factor, a scale factor, a deformation factor, and a direction vector. The weight factor may be determined from a desired amount of fattening or thinning.

The invention discloses a method and device for setting positioning lines on a positioning image and a piece of CT equipment. The method for setting positioning lines on a positioning image comprises the following steps: setting control points on a template image; globally registering the template image with the positioning image; after global registration, locally registering the template image with the positioning image to obtain a deformation vector field of the template image with respect to the positioning image; mapping the control points on the template image to corresponding anatomical positions on the positioning image according to the deformation vector field; and calculating positions and angles of positioning lines according to the control points on the positioning images. The technical scheme of the device for setting positioning lines on a positioning image corresponds to the technical scheme of the method for setting positioning lines on a positioning image. With the technical schemes, the accuracy of setting positioning lines is high and the scanning efficiency can be increased.

A system for displaying lung ventilation information, the system comprising an input (12) and a processing unit (15). The input being provided for receiving multiple CT images (71) of a lung, each CT image (71) corresponding to one phase of at least two different phases in a respiratory cycle. The processing unit (15) being configured to compare CT images (71) corresponding to different phases in the respiratory cycle for determining a deformation vector field for each phase, to generate for each phase a ventilation image (72) based on the corresponding deformation vector field, to spatially align the ventilation images (72), and to generate for at least one common position (62) in each one of the aligned ventilation images (72), a function (81) of a time course of a ventilation value for said common position (62), each ventilation value in the function (81) being based on the deformation vector fields corresponding to the aligned ventilation images (73).

A system for displaying lung ventilation information, the system comprising an input (12) and a processing unit (15). The input being provided for receiving multiple CT images (71) of a lung, each CT image (71) corresponding to one phase of at least two different phases in a respiratory cycle. The processing unit (15) being configured to compare CT images (71) corresponding to different phases in the respiratory cycle for determining a deformation vector field for each phase, to generate for each phase a ventilation image (72) based on the corresponding deformation vector field, to spatially align the ventilation images (72), and to generate for at least one common position (62) in each one of the aligned ventilation images (72), a function (81) of a time course of a ventilation value for said common position (62), each ventilation value in the function (81) being based on the deformation vector fields corresponding to the aligned ventilation images (73).

The present invention provides a micro-facial expression detection method. The method comprises: extracting N feature points from each image frame in a to-be-detected image sequence and aligning human faces; selecting K key feature points from the N feature points and dividing the K key feature points into M feature point clusters; selecting to-be-detected clusters from the M feature point clusters; selecting a base frame; calculating key point vectors of the to-be-detected clusters in each image frame; taking the key point vector of the base frame as a base vector, and calculating a deformation vector of each image frame; taking D times a maximum deformation vector as a deformation threshold; adding all image frames with the deformation vectors greater than the deformation threshold into the quasi-micro-facial expression frame sequence; and when there are consecutive frames in the quasi-micro-facial expression frame sequence, and the number of frames is greater than or equal to the preset frame threshold, taking the continuous frames as the micro-expression frame sequence. According to the method provided by the present invention, the micro-facial expression required to be detected is detected from the to-be-detected image sequence, and the recognition capability of the micro-facial expression and the robustness of the detection method are greatly improved.

A method registers a source image with a target image, wherein the images are deformable, by first measuring dissimilarity between the source image and the target image. The dissimilarity minimized using a discrete energy function. At multiple scales, multi-scale Markov random field registration is applied to the source and target images to determine a deformation vector field. Then, the target image is warped according to the deformation field vector to obtain a warped target mage registered to the source image.

The location of the tumor in the patient changes according to the breathing of the patient. Radiography of the region containing the tumor is performed at a number of different respiratory phases. The X-ray image deformation calculation unit (14) of the device calculates deformation vectors of other images with respect to the reference image by performing nonlinear registration between images in the reference respiratory phase and images in other respiratory phases. A position calculating unit (15) calculates data indicating the position of the tumor in each respiratory phase by applying a deformation vector to the data indicating the position of the tumor in the reference respiratory phase. On the other hand, a template matching unit (16) recognizes a region (83) matching a template image (81a-81n) including a tumor image (M) in an image (82) at each respiratory phase. The template matching unit (16) thus calculates data indicating the position of the tumor in each respiratory phase. The error of the output of the template matching unit (16) relative to the output of the position calculation unit (15) is obtained. Optimizing the parameters for template matching makes the error small.

The invention discloses a method for indirectly measuring the deformation of an antenna structure based on strain sensors. The method comprises the following steps: (1) sorting alternative modals based on a modal coordinate evaluation vector and according to the participation deformation degree, and obtaining a minimum complete modal set capable of describing the deformation of an antenna structure according to the linear correlation between deformation vectors before and after modal deletion; (2) adopting an effective independence method to carry out sensor arrangement, and deleting the degree of freedom with minimum contribution to the independence of a target modal until the remaining number of degree of freedom is the same with the number of the sensors; (3) calculating a mapping matrix with the use of numerical simulation and measured data according to the linear relationship between the displacement and strain of the antenna structure under the condition of small deformation; and (4) using the sensors arranged in specified positions to measure the displacement, obtained through the mapping matrix after strain of the antenna structure, of the antenna structure according to the corresponding relationship between strain and displacement. By the adoption of the method of the invention, the deformation of an antenna can be indirectly measured by strain sensors, and the method has the advantages of small amount of calculation, high computing speed and high real-time performance.

A medical image analysis system is for first and second anatomical image data of a same body area and subject to deformation, with the first and second anatomical image data including respective first and second sets of voxels. The medical image analysis system may include a processor cooperating with a memory and configured to generate a plurality of cost arrays, with each cost array based upon probabilities of a subset of voxels of the second anatomical image data matching voxels of the first anatomical image data. The processor may also solve each cost array using three-dimensional, N-way belief propagation to thereby generate a deformation vector array between the first and second anatomical image data, where N is an integer greater than or equal to six.

The invention relates to a plane component deformation decomposition and vibration mode identification method based on an orthogonal decomposition theory. The method comprises the following steps: step 1, the plane deformation of a four-node square unit is formed by laminating eight basic deformation such as the rigid body displacement in an x direction, the rigid body displacement in a y direction, the extruding deformation in the x direction, the extruding deformation in the y direction, the bending deformation in the x direction, the bending deformation in the y direction, the shear deformation and the rigid body rotation displacement; targeting for the four-node square unit, an orthogonal decomposition method is adopted to respectively establish the basic deformation vector of each of the rigid body displacement in the x direction, the rigid body displacement in the y direction, the extruding deformation in the x direction, the extruding deformation in the y direction, the bending deformation in the x direction, the bending deformation in the y direction, the shear deformation and the rigid body rotation displacement. The method is also applicable when the structure of a plane component is divided into large units, the calculation workload is alleviated; moreover, the bending deformation and the shear vibration mode can be identified, and the stress situation and vibration type inside a component can be more accurately and completely reflected.

A multifunctional test system for car body safety comprises a test bed, a loading control system and a data acquisition and processing system. deformation vectors are measured accurately through an image three-dimensional measuring method, three large devices are replaced, the strength and the rigidity of key parts of side doors, the car roof, bumpers and the like are tested, and the whole test process is collected, represented, analyzed and evaluated. The test bed is applicable to test of passenger cars of various types, and displacement control, loading force control and logical control methods are provided. Side door and bumper tests can be performed when the interchangeable loading device is a column loading device, and the car roof test can be performed through a car body location device when the interchangeable loading device is changed into a plate type loading device. Distribution of yield points can be determined through an infrared thermogram, and the static position before and after the test of the datum point and interpolation moving positions of deformation points can be obtained by arranging laser measurement points. By means of the system, accurate boundary conditions are provided for calculation of theories of finite elements and the like.

A deformation vector field (DVF) (22) is computed that relatively spatially registers a first image (16) and a second image (14). A contour (26) delineating a structure in the first image is adapted using the DVF to generate an initial contour (52) for the structure in the second image (14). A final contour (56) is received for the structure in the second image. The DVF is corrected based on the initial and final contours for the structure in the second image to generate a corrected DVF (32).The correction may comprise computing an adjustment DVF (62) relating the initial and final contours and combining the DVF and the adjustment DVF to generate the corrected DVF. The final contour may be received by displaying the second image overlaid with the initial contour, and receiving user adjustments of the overlaid contour with the overlaid contour updated for each received user adjustment.

A medical image analysis system is for first and second anatomical image data of a same body area and subject to deformation. The first and second anatomical image data includes respective first and second sets of voxels. The medical image analysis system includes a processor cooperating with a memory to generate a respective reach array for each voxel of the second anatomical image data, with each reach array being a subset of contiguous voxels. The processor also generates a cost array for each reach array, with each cost array based upon probabilities of voxels of the reach array matching voxels of the first anatomical image data. The processor may also solve each cost array using belief propagation to thereby generate a deformation vector array between the first and second anatomical image data.

A method for determining the effectiveness of an image transformation process includes acquiring a four-dimensional (4D) image data set, sorting the 4D image data set into separate field-of-view bins using a temporal gating system generating a plurality of deformation vectors using the sorted 4D image data set, and using the plurality of deformation vectors to generate a transformation effectiveness value that is representative of the effectiveness of the image transformation process. The method further includes acquiring a respiratory signal, calculating a power spectrum of the respiratory signal, calculating a power spectrum for each of the plurality of deformation vectors, and comparing the power spectrum of the respiratory signal to the power spectrum of the plurality of deformation vectors to generate the transformation effectiveness value.

The invention discloses a real-time system for simulating the deformation of soft-issue objects in a surgery simulation system, belonging to the graphic processing technical field, which is characterized in that: a boundary meta-module first establishes a physical model for the deformed object and divides grid units on the surface of the object, carries out discretization for the boundary integral equation and figures out a deformation vector of each grid unit; according to the well-divided grid units, a shape matching module establishes mapping relations between the deformation positions and initial positions of each grid unit; a kinematics equation is established according to the positions of the grid units and the material properties of the object, to calculate the deformation recovery of the object; in the deformation process of the soft-issue object, a finite state machine makes an analysis for the stressing states of the object, and controls a currently-used deformation calculating module through the switching of the basic states. The real-time system for simulating the deformation of soft-issue objects in a surgery simulation system realizes real-time and precisely simulations for the deformation of the soft issues in interactive systems, in particular to renders the interaction between the surgical instruments and the soft issues in the surgery simulation systems are more accurate and quicker.

The present invention relates to a three-dimensional dynamic deformation vector simulation equipment. It is composed of branch mechanisms capable of moving along X, Y, Z three axis directions and electric control mechanism for controlling their movement. The branch mechanism capable of moving along X axis is fixed on the supporting frame in box body by means of connecting bolt, the branch mechanism capable of moving along Y axis is placed over the X branch mechanism, the branch mechanism capable of moving along Z axis is placed over the Y branch mechanism, on the branch mechanism capable of moving along Z axis a GPS antenna seat is set. Said invention also provides the working principle and concrete operation method of said simulation equipment and its application field.

The invention discloses a GNSS monitoring data processing method based on inclination sensing, and the method comprises the following steps: S1, acquiring a central plane displacement component of a GNSS monitoring device at a monitoring point by GNSS, acquiring the installation tilt angle of a vertical column by a dual-axis tilt sensor array, and preprocessing the plane displacement component; S2, synthesizing the preprocessed X displacement component and the preprocessed Y displacement component to form a displacement vector, and performing the inclination correction of the displacement vector, wherein the plane displacement component includes the X displacement component and the Y displacement component; S3, projecting the corrected displacement vector to a main deformation direction when the main deformation direction of the monitoring point is known, drawing a deformation process curve of the monitoring point according to the time sequence by the projection analytical value so asto represent the deformation characteristic of the monitoring point. The method solves a problem that a real deformation vector is not matched with the data representation vector in the GNSS displacement monitoring process, is reliable in monitoring data, is high in observation precision, is simple and convenient in data analysis, and is visual in characterization result.

The invention relates to a diffeomorphism demons image registration method and a diffeomorphism demons image registration system based on mode transformation. Firstly, affine transformation is performed on a reference image and a floating image, and then the mode transformation is performed on the reference image and the floating image; pixel gray value data in the images after the mode transformation is read, a deformation vector is obtained, space transformation is obtained through the deformation vector, and the deformation vector is updated to the space transformation; and after updating times reach first preset times and when mode transformation times reach second preset times, initial space transformation is used for the transformation of the floating image. According to the image registration method and the image registration system, advantages of two image registration methods of a mode transformation demons algorithm and a diffeomorphism demons algorithm in an image registration aspect are integrated, the initial space transformation passes through multiple iterations, so as to obtain relatively better initial space transformation, and when the relatively better initial space transformation is applied to the transformation of the floating image, image registration can be realized better. The method and the system are suitable for single-mode and multi-mode image registration and can be used for processing large or small deformation registration.

A system for validating motion estimation comprising a field unit (110) for obtaining a deformation vector field (DVF) estimating the motion by transforming a first image at a first phase of the motion into a second image at a second phase of the motion, a metric unit (120) for computing a metric of a local volume change at a plurality of locations, and a conformity unit (130) for computing a conformity measure based on the computed metric of the local volume change at the plurality of locations and a local property of the first or second image defined at the plurality of locations. Based on the value of the conformity measure, the DFV estimating the motion is validated. Experiments show that the conformity measure based on the computed metric of a local volume change at a plurality of locations and the local property of the first or second image, defined at the plurality of locations, does not necessarily favor a large weight for the outer force to provide a more accurate registration. One reason for this observation may be that large deformations providing more accurate alignment often lead to deformations resulting in unreasonably large volume changes. DVFs comprising such deformations thus are more likely to be discarded by the system of the invention.

The invention discloses a method for monitoring early deformation of large-section underground caverns on the basis of accurate zone measurement, and belongs to the ranges of technologies for measuring deformation of underground caverns during geotechnical engineering. The method includes mounting zone accurate measurement devices including a laser measurement module, a rotation mechanism, a quick mounting plate and a base; accurately measuring concerned positions of section sides of the caverns zones by zones by the aid of the zone accurate measurement devices in different durations, splicing zone measurement data obtained in the different durations and directly comparing and computing the direct zones to obtain deformation vectors of the concerned positions. The method has the advantages that the early deformation of the large-section underground caverns can be monitored, the zone accurate measurement devices are small, are easy and convenient to use and free of target points, influence of blasting and accurate centering and can be quickly mounted adjacent to tunnel faces, the method is particularly applicable to monitoring early deformation of underground spaces excavated by the aid of drilling and blasting processes, and the like.

A medical image analysis system is for first and second anatomical image data of a same body area and subject to deformation. The medical image analysis system may include a processor cooperating with a memory to generate a deformation vector array between the first and second anatomical image data. The processor may also display, on a display, first and second anatomical images respectively based upon the first and second anatomical image data. A first cursor may be displayed on the first anatomical image, and a second cursor may be displayed on the second anatomical image based upon a mapping of the first cursor using the deformation vector array.

The invention provides a membrane structure deformation decomposition method based on an orthogonal theory, which comprises the following steps of 1, constructing spatial deformation of a four-node square unit, and obtaining a complete orthogonal coordinate basis matrix P; 2, dividing the membrane structure by adopting a four-node square unit, and forming a node coordinate displacement deformationvector d e of the four-node square unit; 3, obtaining a projection coefficient vector p of a node coordinate displacement deformation vector d e projected to the complete orthogonal coordinate basismatrix P; and 4, judging the main deformation of the four-node square unit according to the size of the projection coefficient vector p so as to carry out deformation decomposition on the membrane structure system. According to the method, the stress deformation conditions of the whole and local parts of the membrane structure can be reflected more accurately and more perfectly.

Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

Apparatuses, computer media, and methods for altering a camera image, in which the source image may be angularly displaced from a camera image. A plurality of points on the camera image is located and a mesh is generated. Compensation information based on the displacement is determined, and a reshaped image is rendered from the mesh, the compensation information, and the camera image. The camera image is reshaped by relocating a proper subset of the points on the camera image. Deformation vectors are applied to corresponding points on the mesh using the compensation information. A correction factor is obtained from an angular displacement and a translation displacement of the source image from the camera image. The deformation factor is multiplied by the compensation factor to form a deformation vector to compensate for angular and translational displacements of the source image from the camera image.

The invention discloses a magnetic resonance perfusion-diffusion image registration method for an acute ischemic stroke. The magnetic resonance perfusion-diffusion image registration method comprisesthe steps of firstly, through pretreatment of resampling and the like, keeping a structural image, a functional image and a template space of the stroke consistent in spatial resolution; secondly, registering the structural image of the stroke into the template space and obtaining a deformation vector field; thirdly, mapping the functional image (a cerebral blood flow chart and a diffusion-weighted image) of the stroke into the template space by using the deformation vector field and achieving correspondence of a perfusion image and a diffusion image of the stroke at a spatial anatomical position; and finally, quantitatively analyzing clinical diagnosis and treatment indicators, such as mismatch, size, volume and position of an infarct core / penumbra in a magnetic resonance diffusion-perfusion image of the stroke. Accurate magnetic resonance perfusion-diffusion image registration for the stroke is conducive to effective evaluation of a time window and a tissue window of a patient with the stroke, and the patient is benefited.

Deformation maps (e.g. deformation vector fields) used for correcting image-type data used in the treatment of patients in radiotherapy may be processed to eliminate inverse inconsistency and transitivity type errors which produce different results depending on the order or path of the calculation of deformation. The correction permits registration of a treatment plan with the changing patient image and accumulation of dose to a common reference frame without transformation dependent artifacts.

The invention discloses an automatic generation method of a facial beautifying recommendation scheme. The method mainly comprises the following steps: firstly, acquiring a high-definition face front photo of a user, and inputting the face photo into a face feature parameterization model to obtain face parameterization data of the user; secondly, comparing the user face parameters with the facial features and the five sense organ parameters of the star face in the constructed star face library to obtain the most similar star face and the deformation vector of the five sense organ parameters ofthe user; and inputting the photo and the deformation vector of the user into a face beautifying effect model, and automatically generating a beautifying effect and a quantification scheme corresponding to the user. In the whole process, a user only needs to shoot a high-definition face picture in a matched mode, the whole face beautifying recommendation scheme can be automatically generated, themethod has the advantages of being convenient to operate, short in consumed time and high in precision, and the parameterized data difference before and after facial beautifying and the high-precisionportrait effect after facial beautifying are provided for the user.