107results about How to "Achieve registration" patented technology

The invention discloses a wafer defect detection method based on characteristic matching and relates to the image processing method technology field. The method comprises the following steps of collecting a wafer sample image, matching the wafer sample image with a chip template image and searching a single chip area to be detected in the wafer sample image; describing characteristic vectors of characteristic points of the chip template image and a chip image to be detected; matching the characteristic points of the chip template image and the chip image to be detected, rejecting a mismatching point, and according to a matched result, completing position adjusting and correction of the chip image to be detected; and carrying out binarization on the chip template image and the registered chip image to be detected so as to realize extraction of chip defect information. By using the method, small defects on a wafer can be effectively detected, detection efficiency is high and detection stability is good.

The invention relates to an ORB (oriented brief) image feature registration method based on LK (Lucas-Kanade) optical flow constraint. The method includes three phases; in the first phase, ORB feature matching, ORB feature points in an image are extracted and matched to obtain a homography matrix; in the second phase, LK optical-flow precision matching, local optimal points are searched for by means of multiple iterations by the LK sparse optical flow method and used as optimal matching points, subjected to precision matching; in the third phase, image interpolation registration, two images are subjected to precision matching using the renewed homography matrix by means of bilinear interpolation. The method has the advantages that images of different scenes or images acquired by different sensors are automatically matched by means of image processing, registration precision directly determines quality of following image fusion, the high precision matching is maintained, and an algorithm is enabled to meet the demand for timely processing is met.

The invention discloses a sub-aperture partition PFA (Polar Format Algorithm) radar imaging method, and belongs to the technical field of radar imaging. All apertures are partitioned into a plurality of sub-apertures; the sub-apertures are processed by using PFA to obtain azimuthal low-resolution images; movement error of the sub-aperture images is eliminated by using PGA (Phase Gradient Autofocus) processing; geometric distortion is eliminated through azimuthal up-sampling, space varying filter and geometric correction; partitioned sub-blocks with overlapped images of all the sub-aperture images obtained by the geometric correction are subjected to image registration; finally all the registered sub-aperture images are fused to obtain a final SAR image. The full-aperture data of a large block is partitioned into sub-aperture data of small blocks for processing, so that the imaging processing efficiency is improved; the partitioned sub-blocks with overlapped images are registered during implementation of the sub-aperture image registration, so that the registration of the entire images can be realized better and seamless splicing of the sub-blocks can also be realized after registration.

The invention discloses an integral registration method of high-precision multisource ground laser point clouds, which comprises the following steps: acquiring a primitive feature constraint, inputting a control point, and using the control point as a first ground laser station; selecting a homonymous feature constraint corresponding to the primary feature constraint from all ground laser stations adjacent to the first ground laser station; determining a registration base station; establishing a vertical error equation for the feature constraint of each ground laser station, and solving the registration parameter initial value of each scanning station under control coordinates; carrying out overall adjustment on the registration parameter initial value, carrying out gross error reject until the variation of the two adjacent parameter corrected values is smaller than the threshold, and outputting a registration parameter exact value; and transforming the coordinate systems of all the ground laser station point clouds according to the registration parameter exact value to register all the ground laser station point clouds. The method disclosed by the invention can implement precise registration of multistation ground laser point clouds in a complex scene.

The invention discloses a registering method for a data texture image of a ground laser radar, wherein the method is utilized for fusion of a point cloud and a shot image of a ground laser radar. The method comprises the following steps that: step one, selecting a plurality of characteristic points of from A1 to An on a point cloud of a ground laser radar, wherein the point cloud is formed duringscanning of an image by a laser; meanwhile, selecting a plurality of characteristic points of from B1 to Bn from a shot image, wherein the characteristic points of from B1 to Bn is corresponded to the characteristic points of from A1 to An; step two, setting a three dimensional coordinate original point at a scanned object space and determining a three dimensional coordinates (X, Y, Z) of all thecharacteristic points of from A1 to An on the cloud point of the ground laser radar; meanwhile, setting a focal length of the shot image into a third dimensional coordinate (x, y, -f) of all the characteristic points of from B1 to Bn; step three, carrying out centralization of gravity on the three dimensional coordinate (X, Y, Z) of all the characteristic points of from A1 to An as well as calculating a zoom coefficient and a registering parameter of a orthogonal matrix R; step four, resolving an accuracy value of the registering parameter by taking the parameter as an initial value on the basis of application of a least square iterative method. According to the method provided in the invention, on the condition that the above-mentioned parameter is calculated, the shot image can be fusedinto a laser scanning image by zooming, rotation and translation processes, so that a colored point cloud model is formed.

The invention relates to a polarization image registration method. Compared with the prior art, the method has the advantage that the defect of having no registration method for a polarization image is solved. The method comprises the following steps of obtaining polarization images; extracting features of the polarization images; matching primary selection features; obtaining a transformation parameter model; adjusting translation parameters of the transformation model; and obtaining a registration result. According to the method, the image features of the polarization images are taken into full consideration, the registration between the polarization images is realized, and the registration precision of the polarization images in various environments can reach a subpixel demand.

The invention discloses a multi-view ISAR image fusion method, which mainly solves the problems of redundancy of feature points extracted by the prior art, complexity of processing and large operationamount. The scheme is as follows: a series of N ISAR images are segmented by superpixel simple linear iterative clustering to obtain superpixel coordinates X, Y and brightness information L; a brightness threshold is set, and the super pixel information whose L is larger than the threshold is retained; the first ISAR image is selected as the reference image, and the rigid transformation relationship between the nth ISAR image and the reference image is established by using the reserved parameters, and the transformation matrix Bn is obtained; a cost function Jn between the nth ISAR map and the reference map is set; the rigid transformation matrix Bn' which minimizes Jn is solved, and the inverse matrix An of Bn' is obtained; the n-th ISAR map is transformed into the reference map coordinate system according to the inverse matrix An, and all the transformed ISAR maps and the reference maps are superposed to obtain the fusion map. The feature points extracted by the invention are refined, and the operation amount is small, and can be used for three-dimensional image reconstruction, target recognition and attitude estimation.

The invention discloses a spatial and angular assembling device for micro-devices. The spatial and angular assembling device is used for spatially and angularly assembling micron-grade fine filaments and the cylindrical micro-devices and comprises a control host, a two-dimensional orthogonal microscopic vision observing device, a cylindrical micro-device attitude adjusting device and a thin filament pose adjusting device. The spatial and angular assembling device has the advantages that the cylindrical micro-device attitude adjusting device has three rotational degrees of freedom, three rotary shafts intersect with one another at a point owing to structural designs, the geometric centers of the cylindrical micro-devices are positioned at the intersection point of the three rotary shafts, accordingly, the micro-devices are assuredly always positioned in microscopic vision fields of view when attitudes of the cylindrical micro-devices are adjusted, the random attitudes of the cylindrical micro-devices can be adjusted in three-dimensional spaces, and various spatial and angular assembly requirements can be met; a fine filament pose adjusting mechanism has five degrees of freedom and is used for positioning spatial poses of the micron-grade fine filaments and fittingly assembling the micron-grade fine filaments; the micron-grade fine filaments and the cylindrical micro-devices can be spatially and angularly assembled under high-precision conditions by the spatial and angular assembling device, and the assembly precision can reach 0.3 degree.

The invention discloses an image registration method and an image registration device. The image registration method comprises the following steps: acquiring a first image and a second image of a target object, wherein, and the spatial resolution of the first image and the spatial resolution of the second image are the same, the first image and the second image are images collected by a first device and a second device respectively in a state that the imaging planes of the first and second devices are parallel to each other; determining the image registration information according to the target object in the first image and the second image; carrying out image registration on the images collected by the first device and the second device according to the image registration information. Theimage registration method and image registration device solve the technical problem that the image registration can only be carried out on each single image in the prior art.

The invention discloses an automatic registration method of a high-precision SAR image. The method comprises the following steps that pixel level translation parameters between a main image and an auxiliary image are obtained; translation is conducted on the main image according to the pixel level translation parameters, and a translational main image is obtained; a normalization phase correlation matrix of the translational main image and the auxiliary image is obtained; stable phases of the normalization phase correlation matrix are obtained, the stable phases are respectively averaged in the row direction and the column direction of pixels, and a column vector V1 and a row vector V2 are obtained; a false SVD method is adopted for the column vector V1 and the row vector V2, and sub pixel level translation parameters between the translational main image and the auxiliary image are obtained; translation is conducted on the main image according to the sub pixel level translation parameters. The invention further discloses an automatic registration device of the high-precision SAR image. By the adoption of the automatic registration method and device, sub pixel level image registration can be achieved.

The invention discloses a navigation registration method in the brain neurosurgery department based on a thermodynamic diagram and facial key points, and belongs to the technical field of digital medical treatment. According to the method, an n-layer piling sand glass nerve network for extracting the key points based on the thermodynamic diagram is trained by utilizing human face key point data; then a CT three-dimensional image or MRI three-dimensional image of the head of the patient is acquired, and a facial three-dimensional grid key point cloud corresponding to the image is acquired and serves as a target point cloud; a binocular camera is utilized for capturing facial images of the patient in real time in an operation, and a binocular facial key point cloud of the patient is obtainedand serves as a source point cloud; finally, a singular value decomposition method is utilized for registration for the target point cloud and the source point cloud. The method is convenient to implement, low in cost, accurate in registration result and saves time, and additional wounds cannot be caused to the patient.

The invention provides a LASIS waveband image registration method and system based on a geometric model. The method comprises steps of: enabling a LASIS imaging model to be equivalent to a multi-linear-array push-scan model, performing camera calibration, constructing a parallel observation value by using the overlapped area of different waveband images, detecting platform vibration by using the parallel observation amount of two wavebands, and compensating pixel offset caused by the vibration of other wavebands by using detected vibration features; updating the attitude information of the imaging model, aligning the refined new imaging model to the undistorted imaging model, and resampling the original image to achieve waveband image automatic registration. In a conventional method, every two wavebands are matched and cumulative errors exist in a constructed interference sequence so that a poor precision is presented. The method and system prevent the defect, achieve overall high-precision registration of interference sequence image, improve the conventional method in which each waveband is self-compensated, and greatly increase processing efficiency.

The invention discloses a registration method applied to a retina fundus image, and belongs to the field of medical image processing. On the basis of an SIFT (Scale Invariant Feature Transform) method, a new feature point detection and feature description method is proposed, the detection amount and the registration precision of the feature points of the retina fundus image can be improved, and an image registration effect is better. In order to further improve registration accuracy, a mismatching fiducial point rejection strategy is introduced into registration. A great quantity of registration experiments indicates that the registration method can realize the accurate and stable registration of the retina fundus image and overcomes a defect that the SIFT method can not realize the registration in parts of retina fundus images.

The invention discloses a triangulation optical matching based medical image rigid registration method. The triangulation optical matching based medical image rigid registration method comprises obtaining three-dimensional medical image data; segmenting to obtain identical tissues and organs in a three-dimensional medical image; extracting surface point cloud information of the tissues and organs; subdividing the point clouds of the two groups of tissues and organs into a set of two groups of a plurality of tetrahedrons through a triangulation method; selecting any tetrahedron from the two groups of the plurality of tetrahedrons, performing rigid registration on the two tetrahedrons and obtaining a rotation matrix and a translation vector; calculating the range error of the two groups of point clouds according to the obtained rotation matrixes and the translation vectors and selecting the rotation matrix and the translation vector with the minimum range error to be served as an optimal registration matrix; horizontally moving the three-dimensional medical image in a rotary mode and fuse display the three-dimensional medical image. The triangulation optical matching based medical image rigid registration method can accurately achieve matching of the three-dimensional medical image and provides theoretical basis for clinical multi-modal image fusion display.

In embodiments, the invention discloses registration method and device, wherein the registration method includes: acquiring the translation relationship between a marker coordinate system correspondedto a marker on a needle holder and a flange ring coordinate system corresponded to a flange ring on a mechanical arm, thus achieving registration of the mechanical arm and the marker; then acquiringthe position relationship between the marker coordinate system and a needle-tip coordinate system of a surgical needle, thus achieving registration of the marker and the surgical needle. According tothe embodiment, automatic registration between the mechanical arm and the marker and between the marker and the surgical needle are achieved without manual intervention, registration precision being increased.

The invention discloses a zoom multi-channel microscopic imaging system of eye retina, which comprises a lighting subsystem, a zooming module, a multi-channel imaging module and a controller, wherein the lighting subsystem is used for emitting light to light eye ground, and the light is reflected by retina tissues and then forms imaging light beams; the zooming module is suitable for optical zooming so as to focus-image all the depth zones of the retina and lead to different magnifying powers and fields of view; the multi-channel imaging module is used for filtering and arranging the imaging beams spatially after the imaging beams are split and finally focusing the light on the target surface of a photoelectric detector to form a plurality of twin images; and the controller is used for connecting and controlling all the other parts, taking pictures of the eye ground of the tested person continuously, and collecting and obtaining a video or an image sequence directly. The zoom multi-channel microscopic imaging system also comprises a self-adaptive optical subsystem which is used for correcting higher order aberration of human eyes in real time so as to reach an optical resolution ratio approaching the diffraction limit and realize microscopic observation of the living eye retina.

The invention discloses a touch sensitive type registering tool for surgical navigation and a registering tool method of the registering tool. The registering tool comprises a handheld body, a positioning signal generating device for generating a positioning signal, and a touch sensor for sensing human skin and starting the positioning signal generating device while sensing the body skin; when the registering tool is put into use, the touch sensor is used for sensing the body skin, and the positioning signal generating device is started while the body skin is sensed; the positioning signal generating device is used for generating the positioning signal; an external positioning system can position the registering tool according to the positioning signal, so as to finish registering; the registering can be performed without adhering a mark point; the operation is simple and convenient.

The invention belongs to the field of three-dimensional measurement, and specifically discloses a point cloud registration method based on hand-eye calibration. The point cloud registration method includes the steps: driving a measuring device by a tail end of a robot to move twice, and respectively obtaining a transformation matrix of a coordinate system at the tail end of the robot and a transformation matrix of a coordinate system of the measuring device during two times of movement; calibrating an equation according to a hand-eye calibration equation; solving a transformation matrix from arobot tail end coordinate system to a measuring device coordinate system; obtaining a transformation matrix from a robot base coordinate system to a measuring device coordinate system; according to the transformation matrix, converting the to-be-measured object measurement point cloud obtained by the measurement device into a robot base coordinate system to complete point cloud coarse registration between the measurement point cloud and the model point cloud; and finally completing point cloud fine registration through the relationship between matching point pairs in the measurement point cloud and the model point cloud under the robot base coordinate system. Marking points do not need to be pasted on the surface of a measured object in the whole process, and the point cloud registrationprocess is simplified, and point cloud registration during measurement of a high-temperature object can be achieved.

The invention provides an integral aerial triangulation method for an airborne laser scanning point cloud and an optical image. An integral aerial triangulation strict balancing model for connecting the point cloud and the image is built according to a related relation between the point cloud and a system error of the image; and the integral compensation is carried out on the system error, so that the positioning precision of the point cloud and the image can be improved, and the registering of the point cloud and the image is realized. A relation process of the technical scheme disclosed by the invention is simple; the automatic operation is supported; the accuracy of a result is high; and the key problem of an integrated system of an airborne LiDAR (Light Detection And Ranging,) and an aviation camera is solved.

The embodiment of the invention provides a cursor ruler. The cursor ruler comprises a bracket and at least three markers, wherein the markers are fixed on the bracket; at least three markers of whichthe geometric centers are non-collinear exist in all the markers; one or more of dimensions and shapes of any two markers are different, and any different markers are not in mutual contact; and through the materials of the markers and the bracket, in three-dimensional images obtained through a three-dimensional imaging technique, the difference between the gray scale of the markers and that of thebracket exceeds a firs preset value. The embodiment of the invention also provides a method for registering a coordinate system. The embodiment of the invention also provides a method for registeringthe coordinate system using the cursor ruler.

A both-side pressed terminal is connected as a first anode (cathode) lead tab terminal to an anode (a cathode) foil. A first connection surface of a connection portion of a one-side pressed terminal as a second anode (cathode) lead tab terminal is connected to an inner circumferential surface of the anode (cathode) foil. A position in a radial direction of a lead of the second anode (cathode) lead tab terminal is shifted inward to be in registration with a position in a radial direction of a lead of the first anode (cathode) lead tab terminal. Thus, an electrolytic capacitor free from position displacement of an anode (a cathode) lead tab terminal while maintaining characteristics as an electrolytic capacitor can be obtained.

The invention discloses a Zigbee-based found objects reminding system, which comprises a PC (personal computer), a Zigbee coordinator communicated with the PC through a serial port, and a label node having Zigbee communication function, wherein the Zigbee coordinator is connected to the label node through a Zigbee protocol stack. The Zigbee-based found objects reminding system has the advantages that the Zigbee protocol has low power consumption, low complexity, self-organization and low cost, the functions of registering, managing, querying and looking for the indoor goods can be realized, and the system is specially fit for the old people and the forgetful young people.

The invention discloses an aircraft skin detection method based on contour feature constraint registration. The method comprises the following steps: acquiring measurement data and a CAD model point set of an aircraft skin; obtaining contour point clouds of the aircraft skin through point cloud boundary extraction, discretizing independently the skin contour point clouds in the CAD model, and obtaining corresponding point sets; calculating Ck feature points on the contour based on curvature mean square error, and clustering the feature points based on Euclidean distance; introducing distance features on the basis of the fast point feature histogram, proposing an FPFH-d feature point description algorithm, and calculating corresponding points in a skin measurement data contour point set and a CAD data contour point set; and solving an initial registration matrix of a skin measurement data contour point set and a CAD data contour point set according to corresponding points on the contour, solving an optimal spatial transformation matrix by taking contour feature point registration as a constraint, and calculating deformation according to a root-mean-square error of a registration result. The method can effectively solve the problem that the aircraft skin cannot be accurately registered due to few surface features.

The invention discloses a neuron activity image dynamic registration method based on CUDA acceleration. The method comprises the steps that mean stretching is performed on an input image so that the image after mean stretching is obtained; the overall translation of the image after mean stretching is calculated by using Fourier transform; rigid transformation is performed on the image after mean stretching by using the translation and a template image so that the image after primary rigid transformation is obtained; the image after primary rigid transformation and the template image are divided into multiple small areas, and the translation of each small area is calculated by using Fourier transform; and the translation of each pixel point in the image after primary rigid transformation is calculated by using the translation of the small areas, and each pixel point in the image after primary rigid transformation is updated by using the translation and the template image so that the registration image is obtained. Parallel acceleration calculation of neuron activity image registration is realized based on the CUDA frame so that real-time registration of the neuron activity image can be realized.

The invention discloses a method for realizing the registration of user equipment to a personal network, which comprises the following steps: a PNM server senses that the access state of the user equipment in a CS domain changes; and the PNM server adjusts the registration state of the user equipment in the personal network (PN) according to the change of the access state of the user equipment in the CS domain. The invention also discloses a method for obtaining capacity information of the user equipment, which comprises the following steps: a DM server obtains the capacity information of the user equipment; the DM server is taken as a proxy, which presents a user or a network of a Presence server, and inputs the capacity information of the user equipment into the Presence server; and the capacity information of the user equipment obtains the capacity information of the user equipment and then releases to network elements which have subscribed the capacity information of the user equipment.