89 results about "Point registration" patented technology

An image processing system, and a method of operation thereof, including: a feature selection module for determining subsets of point clouds, the subsets selected based on key points of a three-dimensional object; a feature matching module, coupled to the feature selection module, for generating matched results based on a matching transformation of the subsets; and a point registration module, coupled to the feature matching module, for refining the matched results based on a refinement transformation to optionally align different data sets of the point clouds for displaying the aligned data sets on a device, wherein the refinement transformation includes a refinement error less than a matching error of the matching transformation.

A method for providing patient registration without fiducials comprises the steps of: spatially placing an ultrasound image of a patient randomly at different starting positions relative to a preoperative image; creating an independent registration corresponding to each different starting positions, by optimizing a spatial transformation between the preoperative image and the ultrasound image to provide a first batch of registrations; executing a second registration to fine-tune the alignment between the preoperative image and the ultrasound image; and concatenating the spatial transformation to obtain spatial transformation between the patient in an operating room and a corresponding preoperative image.

A method and apparatus are disclosed for performing finishing operations on at least one graphics area on a graphics sheet, the graphics sheet having a graphics side, an opposite process side, and reference features, the graphics side bearing the graphics area(s) and registration marks in predetermined positions with respect to the graphics area(s). The method comprises positioning the graphics sheet on a sheet-receiving surface, sensing from the graphics side the positions of the registration marks, determining the coordinates of the graphics area(s) with respect to the sheet-receiving surface as if viewable from the process side, and performing finishing operations on the process side of the graphics sheet based on such determination, whereby such process-side finishing operations compensate for variations of the graphics area(s).

The invention discloses a mark point automatic registration method based on model matching. The method comprises the following steps of (1)obtaining image data containing mark points; (2) constructing a mark point model; (3) reading in the obtained image data, conducting anisotropic diffusion filtering on images, and automatically extracting a skin three-dimensional grid from the images; (4) adopting an ICP algorithm to be matched with the mark point model and the skin three-dimensional grid, and obtaining the coordinate of the center of each mark point on the skin three-dimensional grid in an image space coordinate system; (5) adopting the ICP algorithm to be matched with the center of each mark point of the image space and the center of each mark point of the actual space, obtaining a rotating matrix R and a translational vector quantity T between the image space coordinate system and the actual space coordinate system, and completing registration of the mark points. According to the mark point registration method, the multiple mark points can be rapidly registered, the obtained rotating matrix R and the obtained translational vector quantity T of the image coordinate system and the actual coordinate system are more accurate, manual interference is reduced, the precision of the registration of the mark points is improved, and the mark point automatic registration method has good robustness.

An improved encephalic puncture guiding method comprises the following steps of 1, puncture planning guidance, wherein 1.1, an encephalic scanning image sequence is loaded, a three-dimensional encephalic model is built, and meanwhile measurement angle correction data are loaded; 1.2, reference points are set, perpendicular reference planes are built in the three-dimensional model; 1.3, a target spot and an entry point are set, the length of a puncture path composed of the target spot and the entry point and the included angle between the puncture path and the reference planes are worked out; the final plan puncturing angle and depth are obtained by correcting the angle correction data; 2, puncture execution, wherein in the step 1.3, when an encephalic coordination system and a ground coordinate system are not consistent, the encephalic coordination system and the ground coordination system are registered by adopting the point registration method based on output data of a gyroscope, and the included angle between the reference planes and the puncture path obtained after registration is automatically worked out. The invention provides an improved encephalic puncture guiding device. The improved encephalic puncture guiding method and device are easy to implement and convenient to operate and facilitate clinical application.

An image-based localization feature point registration apparatus includes a camera to capture an image, a feature point extractor to extract a feature point from the captured image, a calculator to calculate depth information about the feature point according to whether the feature point is one of two-dimensional (2D) and a three-dimensional (3D) corner, and a feature point register to register 3D coordinates of the feature point based on the depth information about the feature point and image coordinates of the feature point.

The invention relates to a virtual unicompartmental knee arthroplasty model construction method based on point-to-point registration technology, and belongs to the technical field of three-dimensional simulation of computers. The method includes the steps: acquiring postoperative CT (computed tomography) images of a UKA (unicompartmental knee arthroplasty); acquiring preoperative MRI (magnetic resonance imaging) images of the UKA; saving data; importing CT two-dimensional images, and rebuilding three-dimensional models; importing MRI two-dimensional images, and rebuilding three-dimensional models; registering and modifying knee joint models; constructing three-dimensional models of prostheses; assembling postoperative knee joint simulation prostheses of the UKA; optimizing the models; dividing grids; defining attributes of materials of various parts; applying loads and boundary conditions; verifying the models. According to the method, imaging scan is performed based on cases, experimental results have pertinence, constructed models are closer to actual situations, the method particularly replies research of failure cases or successful cases and is simple in operating process and less in related software, corresponding prostheses are scanned according to used types in actual operations, experimental time is shortened, and experimental cost is reduced.

The invention discloses an image inking and fusing method and system based on histogram feature point registration. The method comprises the following steps: according to image brightness histogram characteristics, extracting histogram extremum points, and adopting one-dimensional Gaussian to smoothly inhibit the local noise points of a brightness histogram; meanwhile, constructing matching relationship among the histogram extremum points in a way that a matching cost function is used to eliminate a matching matrix M; and taking the matched histogram extremum points as histogram characteristic points. The histogram characteristic points are utilized, and image brightness is corrected by adopting the corresponding brightness values of the histogram characteristic points of an image overlapping region. The image which exhibits a big visual angle and big close-range chromatic aberration can be subjected to hue difference processing, hue differences of a plurality of image overlapping regions and non-overlapping regions can be automatically eliminated, and effects of local zone hue balance of the image and the integral hue balance of a panorama image of spliced streetscape can be achieved.

An extension point virtualization system uses operating system-provided reparse points to provide minimal extension point registration. Reparse points preserve application isolation while removing the scale problem of writing custom extension point proxies for each extension point. Instead, the system can use a single file system filter that generically handles application virtualization reparse points, and store reparse point data for extension points that need redirection. Many extension points can be handled by redirecting the operating system from a typical location for an application resource to a virtualized safe location for the application resource. Thus, the system simplifies the process of handling new extension points by allowing an application virtualization system to simply register new locations that should be handled with reparse points and to then handle registered locations generically.

The invention discloses a device for detecting positioning accuracy of a surgical operation navigation system. The main body of the device is a sealable cylinder, comprising a base, a detachable upper lid and a detachable head die. The base comprises a pedestal, an outer cover and a plurality of organic glass rods. The pedestal is provided on the bottom surface of the base and a plurality of organic glass rods of different lengths are provided on the pedestal. The outer cover which is provided on the side of the base is bonded on the pedestal, and a plurality of organic glass rods of the same length are provided on the cover. The detachable upper lid comprises a sealing lid, a connecting bolt and a water injection hole screw. The connecting bolt is provided in the center of the sealing lid for screwing the upper lid. The water injection hole screw which is used for injecting water is provided beside. The upper lid is contacted and is fixed with the base. The detachable head die is fixed on the pedestal of the base and inside the outer cover of the base. The invention further discloses a detecting method of the device. According to the invention, not only point registration accuracy but also surface registration accuracy can be detected, which promotes higher and more real detection accuracy.

A registration pointer for registering points of surfaces of bodily elements in computer-assisted surgery, comprising a handle for being manipulated by a pointer operator. A stem is connected to the handle and has a first and a second tip configurations each having a respective use relating to a registration of points on specified bodily elements. A detectable device is secured to the stem, and is adapted to be tracked in space for position and orientation by a sensing apparatus. A position of the tip configurations with respect to the detectable device is determinable such that a position of the tip configurations is calculable as a function of the position and orientation of the detectable device. The tip configurations are chosen to register points on given bodily elements as a function of the respective use, by recording a position of points of contact between the tip configurations and the given bodily element.

The invention relates to the field of dental department and particularly relates to an auto-implanting dental robot. The oral implantology robot includes: a modularized structure, an implanting navigation system, a tracing and positioning system, a mechanical arm system, an implanting driving system, and a control system. The oral implantology robot can integrate and analyzes information from allunits, including: CT information, implantology scheme, oral cavity information and mechanical arm information, thereby sending a command to control a mechanical arm to achieve automatic implantology.The modularized structure includes a trolley structure and a support structure connected thereto, wherein the support structure is connected to all the functional units, including the mechanical arm,a tracer and a monitor. The implanting navigation system can achieve pre-operation implanting scheme design, intraoperative registration, information integration and analysis, command sending and feedback receiving. Implantology drill point registration tools are individually designed on the basis of implantology tools in different brands, thus solving a problem of low accuracy of manual registration. Due to the modularized structure, dental implantology operation situations are fully considered, so that auto-implanting operation has better operability.

The invention discloses a face in-vivo validation method and device. The method includes the steps that face images captured by at least two cameras are acquired; feature point registration is carried out on the face images according to preset face feature points, and corresponding feature point combinations are obtained; homography matrixes between the feature point combinations are fitted according to a preset algorithm; conversion errors of the feature points are calculated based on the homography matrixes, an error calculation result is obtained, and face in-vivo validation is carried out according to the error calculation result. According to the face in-vivo validation method and device, it is unnecessary to calibrate the cameras, calibration errors are eliminated, feature point matching is carried out directly on the captured face images, the homography matrixes are fitted, and thus the calculation amount of an in-vivo discrimination algorithm can be reduced; besides, the cameras can be freely placed, and thus the flexibility and convenience of in-vivo discrimination can be improved.

The invention relates to a fingerprint feature point registration method based on security levels, an authentication method based on the security levels and terminal equipment. The fingerprint feature point registration method based on the security levels comprises the steps of forming the multiple security levels, wherein the multiple security levels comprise the basic security level and at least one higher security level, and each security level corresponds to one or more types of fingerprint feature points; acquiring fingerprints of a user and extracting multiple fingerprint feature points; selecting a preset number of feature points of corresponding types from the multiple fingerprint feature points based on the security levels, and registering the fingerprint feature points as fingerprint feature points with the corresponding security levels.

A method and apparatus for enabling the registration of co-located, disparate imaging sensors by computing the optical flow of each sensor as all the sensors simultaneously observe a moving object, or as all the sensors simultaneously move observing an object. The tie point registration of disparate imaging sensors is made more robust by matching optical flow and by levering the temporal motion within a pair of video sequences and using an additional constraint to minimize the disparity in optical flow between registered video sequences. The method includes parametrically computing the optical flow of each video sequence separately relative to a reference frame pair, identifying a matching constellation of tie-points in the reference pair of images, for all frames, computing the positions of tie-points bi=b0+ei where ei=predictive term to generate a new set of tie-points, after transformation by optical flow. For each frame, the total squared error resulting from an over-determined solution of affine registration problem is computed. The choice of ei is adjusted to minimize the total squared error over all frames of video.

The present invention provides a coastline area remote sensing map-based satellite borne spectrograph pointing registration method. According to the method, under a nadir observation mode, pointing registration is performed through using the characteristic that large-area uniform landforms exist in a special ground feature-coastline area in a high-and-middle-resolution remote sensing image and the characteristic that surface reflectance changes abruptly; the longitudes and latitudes of measurement points of a satellite borne spectrograph in an observation area are in one-to-one correspondence with the longitudes and latitudes of the pixels of a remote sensing image outputted by a remote sensing camera in a corresponding area; and the errors of the longitudes and latitudes of the measurement points and the longitudes and latitudes of the pixels are corrected, and are put into statistics and are monitored in real time. Arithmetic processing such as spectral data fitting and comparison and pixel grid geometric coordinate transformation is adopted; and a reference base map required by the pointing registration of the satellite borne spectrograph can come from other satellite loads, that is, the satellite borne spectrograph can be in non-rigid coaxial connection with the remote sensing camera, or the reference base map required by the pointing registration of the satellite borne spectrograph can come from different satellites, and thus the application range of the registration method of pointing between the non-imaging satellite spectrograph and the imaging remote sensing camera can be extended.

The invention discloses a storage medium, method and device for constructing a navigation map. The method comprises the following steps: preprocessing the 3D point cloud data of an acquired target location by using a map construction algorithm based on feature point registration; converting the preprocessed 3D point cloud data into point cloud data of a predetermined format; and based on a model of an octree data structure, converting the point cloud data of the predetermined format into a navigation map of the octree data structure. The storage medium, method and device of invention solve thetechnical problems of point discontinuity, excessive useless points and inability to achieve position and attitude estimation in the prior art.

The invention provides a map mapping method based on affine and nonlinear point transformation. According to the method, acquiring longitude and latitude data of marking points in a three-dimensional campus map and corresponding position coordinates in a three-dimensional map picture, and calculating affine transformation relationships from real longitudes and latitudes of the campus map to the position coordinates of the three-dimensional map picture after being drawn in a projection manner; acquiring real longitudes and latitudes of GPSs of a large number of characteristic points, converting position coordinate point sets A in the corresponding three-dimensional map picture by the affine transformation relationships, calibrating real-picture position coordinate point sets B corresponding to the characteristic points in the three-dimensional map picture to obtain a training sample point set {A,B}, correcting coordinate errors by the aid of a nonlinear point registration technology of a free-form deformation module based on a B-spline; enabling the mapped points to project and display on a calibrated road center line by the aid of normal projection technologies. The mapping method achieves excellent map navigation effects.

The invention discloses a local area accurate deformation registration algorithm combining point registration. The local area accurate deformation registration algorithm is characterized in that the feature-based point registration method is combined with the intensity-based image registration method, especially the result of point registration is converted to a deformation field through a spline model, the deformation field serves as a follow-up initial deformation field of intensity-based image registration, and thus the two different registration methods are combined. The local area accurate deformation registration algorithm combining point registration ingeniously makes use of the characteristic of high registration accuracy of point registration, improves the registration accuracy of areas of interest, accordingly improves accuracy of illuminated accumulated dose, and achieves accuracy interference, regulation and control on registration of local areas in the images. The local area accurate deformation registration algorithm combining point registration can be widely applied to the field of image deformation registration.

The invention belongs to the fields of forensic anthropology and computer graphics and relates to a criminology-oriented computer-assisted facial reconstruction method for skulls of unknown body sources. The criminology-oriented computer-assisted facial reconstruction method mainly includes steps of 1 three-dimensional modeling of a skull of an unknown body source, 2 gender discrimination of the skull of the unknown body source, 3 dense point based facial soft tissue rule analysis, 4 dense point registration based skull facial reconstruction method, 5 principal component analysis based facial estimation of the skull of the unknown body source, 6 generating of investigated photos based on three-dimensional facial model. The criminology-oriented computer-assisted facial reconstruction method can fast achieve facial reconstruction for skulls of unknown body sources, and can predict the facial features of victims before their death for criminal case investigation.

The invention discloses a human body lower limb registration method applied to a mechanical axis navigation system. The method comprises the following steps that: (1) human body lower limb CT data are obtained through scanning, a human body lower limb three-dimensional model is reconstructed according to the obtained human body lower limb CT data, and the human body lower limb three-dimensional model is saved as an STL grid model by means of a high-precision storage mode, so that the STL grid model can be used for subsequent data processing; (2) bone surface point cloud data in the human body lower limb three-dimensional model are extracted through a feature point extraction algorithm, so that feature points to be matched on the surface of the three-dimensional model are obtained, the bone surface point cloud data are stored so as to be used for subsequent matching; (3) an optical tracking device is adopted to obtain diseased bone feature area point cloud data, and the diseased bone feature area point cloud data are preprocessed, so that smooth diseased bone characteristic area point cloud data can be obtained; (4) the step (2) is repeated, so that the space coordinates of the feature points of diseased bone specified area point cloud data are extracted; and (5) a three-point registration algorithm is used to realize the spatial registration of a diseased bone model and a diseased bone. With the method adopted, the registration time of feature points can be effectively shortened, and the efficiency of an operation is high.

The invention is to operate two or more different functions on one processor (CPU) and to simultaneously display an image of each function in divided multiple screens. The CPU 12 performs route guide control processing for retrieving a route from a present position to a destination based on a present position detection part 1 and a map information part 2, and displaying a route guide on a monitor 8. A processing for displaying images based on one or two or more different names of functions designated by a remote control 10 from function of communicating or acquiring information through a communication part 3, and functions relevant to the route guide control such as position retrieval function and point registration function on the monitor 8 by one screen or divided multiple screens is performed by this CPU 12 alone.

An airborne infrared moving target detection method based on geographical homologous point registration comprises the following steps: mapping an image plane imaging point to a ground target point; performing region registration on a reference image and a to-be-matched image; compensating the motion of the reference image and the to-be-matched image to get motion-compensated images; performing inter-frame difference operation on the motion-compensated reference image and the motion-compensated to-be-matched image to get a suspected moving target; and reversely verifying the motion features of a suspected moving region to get a final moving target detection result. The method involves a small amount of calculation, and takes less time. The hardware delay time and the software processing burden are greatly reduced. The detection efficiency of the system is improved.

A short message processing method and apparatus, which analyzes a short message received from a mobile communication network and provides via a packet data service node (PDSN) a supplementary service such as a credit card settlement details notifying service, a contact point registration service, a spam filtering service, a schedule registration service, a message history management service, and so forth, based on the result of the analysis. The short message processing method and apparatus can execute a supplementary service corresponding to the short message received through a PDSN, in corporation with a platform such as WIPI or BREW.

The present application discloses a live human face verification method and device. The device acquires face images captured by at least two cameras and performs feature point registration on the face images according to preset face feature points, to obtain corresponding feature point combinations between the face images. After fitting out a homography transformation matrix among the feature point combinations, the device calculates transformation errors of the feature point combinations using the homography transformation matrix to obtain an error calculation result, and performing live human face verification of the face images according to the error calculation result. The embodiments of the present application do not need to calibrate the cameras, so the amount of calculation of a living body judgment algorithm can be reduced; moreover, the cameras can be freely placed, and thereby the flexibility and convenience of living body judgment can be increased.

A feature point is a point at which a correlation value is greater than a threshold value, wherein the correlation value is calculated between a template and partial image within an area that is one portion of each genuine tablet image. With regard to a cross-check image, which represents a tablet the authenticity of which is to be verified, a correlation value is calculated between a partial image within an area that is one portion of the cross-check image and the template image, and multiple feature points of the cross-check image at which the calculated correlation value is greater than a predetermined threshold value are extracted. The degree of similarity between the cross-check image and the genuine tablet image is calculated using a geometric characteristic of the extracted multiple feature points and a geometric characteristic of the stored multiple feature points of the genuine tablet image.

The invention discloses an SF6 gas leakage automatic detection method based on an infrared video. Video acquisition is carried on the location where SF6 leakage occurs, the alignment of different frame images is completed based on a feature point registration method, the sampled frame image is subjected to the image enhancement by an image enhancement method, the first frame image is taken as the comparison template, the image comparison of the different frame images is carried out by a multi-feature fusion comparison method, the difference between the adjacent frame images is found, the area having changed content between the frame images is recorded, and whether there is SF6 gas leakage in the monitoring point is determined according to the detection of the image change area. The method provided replaces the on-site detection method of the artificial carrying equipment, thereby reducing the working burden of electric inspection personnel and improving the safety.

The invention discloses a point registration algorithm capable of keeping local topology invariance. The point registration algorithm comprises the following steps: converting the point registration problem into an image matching problem, wherein points in a point set serve as nodes in an image; defining a neighbourhood region of each node in the image, wherein the node and the neighbourhood region thereof form a local subgraph, the node and one point in the neighbourhood region thereof are connected to form one edge in the local subgraph; carrying out dynamic planning on the local subgraphs to obtain matching probability between the local subgraphs; carrying out processing on global matching probability through the matching probability between the local subgraphs and a relaxation labeling method to obtain correspondence relation of point pairs; and according to the correspondence relation of the point pairs, carrying out elastic deformation regularization processing on the point set through a thin plate spline function to obtain model parameters. The point registration algorithm capable of keeping local topology invariance accurately quantizes local topology difference, improves accuracy of non-rigid registration when large deformation occurs and improves algorithm robustness when an abnormity point exists.

The invention discloses an image splicing method under a non-concentric imaging condition. The image splicing method comprises the following steps: selecting a target candidate homography matrix conforming to a current scene by adopting a registration error-oriented cyclic selection mechanism; performing two-dimensional transformation coarse registration based on the target candidate homography matrix; densifying a sparse feature point registration error corresponding to the target candidate homography matrix by adopting an interpolation algorithm; obtaining a registration error of the whole overlapping region; carrying out error compensation, optimizing the image alignment, and increasing the image alignment area of the overlapping area, thus facilitating suture lookup; in addition, optimizing the suture line search by combining a feature point registration error constraint function, thus facilitating the stitching line searching function cost to be minimum, and finding the corresponding optimal stitching line, so as to realize perfect alignment of geometric structures of the images at two sides of the stitching line while the image content is not increased or deleted, and solve adouble image problem appearing in the complex scene image stitching process.

An image processing system, and a method of operation thereof, including: a feature selection module for determining subsets of point clouds, the subsets selected based on key points of a three-dimensional object; a feature matching module, coupled to the feature selection module, for generating matched results based on a matching transformation of the subsets; and a point registration module, coupled to the feature matching module, for refining the matched results based on a refinement transformation to optionally align different data sets of the point clouds for displaying the aligned data sets on a device, wherein the refinement transformation includes a refinement error less than a matching error of the matching transformation.