37results about How to "Troubleshoot registration issues" patented technology

The invention provides a high-efficiency registration method aimed at a CT and optical scanning tooth model, and belongs to the field of computer oral cavity recovery. The method comprises the steps of (1) data preparation in which 3D visualization is carried out on CT data of the oral cavity to obtain a CT reconstructed tooth image, visualization is carried out on optical scanning data of the tooth crown and gum part to obtain an optical scanning tooth crown image, and the CT reconstructed tooth image and the optical scanning tooth crown image are arranged in the unified world coordinate system; (2) initial registration in which characteristic points are selected manually to process the CT reconstructed tooth image and the optical scanning tooth crown image and further to obtain an initial registration model; and (3) accurate registration in which characteristic points are selected automatically to process the initial registration model and further to obtain an accurate registration model. Problems in registration data with scale transformation and different resolution are solved, and a registration result is high in convenience speed and low in registration error.

The invention provides a method for elastically registering medical images by the aid of a combined convex hull matching and multi-scale classification strategy. The method includes performing point cloud preliminary registration on the basis of convex hull matching, in other words, extracting surface structures of volume data by an iso-surface extraction algorithm, and acquiring the optimal rigid registration result by a point cloud and convex hull surface matching process; performing multi-scale partitioning on the images to elastically register the images, performing different-scale blurring on the images by the aid of a multi-scale iteration procedure, and implementing a coarse-to-fine matching procedure; using mutual information as a similarity measure, combining the similarity measure with a volume distribution interpolation algorithm of three linear portions and acquiring the optimal elastic transformation parameters by means of iterative optimization. The method has the advantages that the images can be registered after large-angle transformation is performed on the images, and the image registration precision is improved.

The invention discloses a visible light image and infrared image registering method which comprises the following steps: performing multi-scale decomposition on a visible light image and an infrared image to obtain low-resolution visible light image and infrared image; extracting SIFT (scale invariant feature transform) features, multi-scale corner features and surface point features from the low-resolution image pair; matching the SIFT features and removing exterior points; obtaining an initial transformation model by use of the matched SIFT feature pair, wherein the transformation model refers to any geometric transformation relationship between the infrared image and a high-spectrum image; extracting the multi-scale angular point features and the surface point features based on an image block pair on the original image pair by use of the geometric constraint provided by the initial transformation model; determining a more accurate transformation model according to the initial transformation model and the multi-scale angular point features and surface point features; and transforming the infrared image according to the transformation model to obtain the transformed infrared image.

The invention discloses a multiple-sensor united calibration method and relates to sensor calibration. The multiple-sensor united calibration method comprises the following steps: calibrating camera parameters through a circular hole target component; calibrating a contact-type measuring head through a standard ball; and united calibration of a camera and the contact-type measuring head. Measurement on geometric dimensioning and form and position errors of small structures can be achieved through data processing in the multiple-sensor united calibration method, ranges in practical application are enlarged, and demands in practical application are met.

The invention discloses a geometric constraint-based high-resolution optical satellite staring image registration method. The method comprises the steps of S100, building a free network adjustment directional model of images by utilizing a rational function model of additional image space error compensation; S200, based on the free network adjustment directional model, performing dense matching ona stereoscopic image pair with an optimal rendezvous condition in the images to obtain coordinates of dense homonymy points; S300, generating dense point cloud data, performing gross error point deletion on the dense point cloud data, and generating digital surface model data; and S400, based on the free network adjustment directional model and DSM data, performing geometric correction on the images in sequence. By utilizing geometric locating consistency, high-precision registration of high-resolution optical satellite multi-angle staring sequence images is realized; the multi-angle staringsequence image registration problem caused by satellite platform control inaccuracy and attitude measurement inaccuracy is solved; and a high-precision data basis can be provided for subsequent application.

The invention discloses a visible light image and high-spectrum image registering method which comprises the following steps: performing multi-scale decomposition on a visible light image to form a low-resolution visible light image; generating a high-spectrum image significant waveband image according to the high-spectrum image; extracting SIFT (scale invariant feature transform) features, multi-scale angular point features and surface point features from the low-resolution visible light image and high-spectrum image significant waveband image; matching the SIFT features and removing exterior points; obtaining a transformation model by use of the matched SIFT feature pair; extracting the multi-scale angular point features and surface point features based on an image block pair by taking a registered transformation model of the previous layer as an initial transformation model of the current layer on each layer of visible light image and high-spectrum image significant waveband image; selecting the transformation type and obtaining a transformation parameter according to the initial transformation and the multi-scale angular point features and surface point features in combination with an iteration re-weighted least square method; and transforming the high-spectrum image according to the transformation model to obtain the transformed high-spectrum image.

The invention discloses a visible light full-color image and multi-spectrum image registering method which comprises the following steps of: performing multi-scale decomposition of the full-color image and multi-spectrum image to generate low-resolution full-color image and multi-spectrum image; extracting and matching SIFT characteristics from the low-resolution images and removing the exterior points; obtaining an initial transformation model by use of the matched SIFT characteristic pair and the iteration re-weighting least square method; performing SIFT characteristic extraction and matching as well as exterior point removal based on image block pairs on the original image by use of the geometric constraint provided by the initial transformation model, and selecting the optimal transformation type from all SIFT characteristic pair sets and obtaining the transformation parameter by use of the iteration re-weighting least square method; and transforming the multi-spectrum image according to the transformation model to obtain the transformed multi-spectrum image.

The invention relates to a geo-positioning method of ground panoramic images. An omnibearing characteristic quantity that overall describes space organization and orientation relations; vector retrieval is described at grid points of a satellite imagery map to finish rough positioning; a plurality of matching lines are determined via rough positioning as control lines for use when height information is distorted; under the restraint condition that the relative height sequence is unchanged, iterative initial values are introduced through rough positioning to achieve precise resolving of exterior orientation elements. Unlike the bundle adjustment resolving of multi-frame ground images, the method herein only needs medium to high resolution satellite image data and scenic surface relative elevation information, allows precise external reference resolving of single-frame ground panoramic images to be achieved with no need for other positioning devices (such as GPS (global positioning system)) or addition of manual control points, and is very suitable for image registration of sky and earth fields having great field angle and scale differences.

The invention discloses a point cloud registration method based on a differential evolution algorithm and a TrimmedICP algorithm. The TrimmedICP algorithm can solve the problem of low overlapping rate in point cloud registration, but needs the setting of a proper initial value of a rotation matrix and a proper initial value of a translation matrix at first, otherwise it will fall into the local optimum; the differential evolution algorithm can generate an initial population through a random means and makes the population distributed in all ranges through using mutation, crossover and selection operation; and the differential evolution algorithm and the TrimmedICP algorithm are combined, and therefore, the problem of difficulty in selecting the initial values of the rotation matrix and the translation matrix can be solved, a globe optimal solution can be obtained, and thus, an accurate registration result can be obtained.

The invention discloses a combined target positioning and sensor registration method in multi-source ranging. The method includes the following steps: by analyzing a measurement model of a multi-source ranging sensor, constructing a likelihood function for the features of white gaussian noise by using the measurement noise of the sensor, analyzing, deducing and resolving the likelihood function byusing the maximum likelihood method, and obtaining a target fusion position and the analytical solution of the ranging sensor by performing registration error estimation. The method combines the IMMalgorithm and the maximum likelihood algorithm, on the basis of a previous registration error estimation value of the sensor, can obtain the initial position state information of the target by using the IMM algorithm, substitutes the initial position state information to an estimation formula for registration error, and obtains a registration error estimation value. The registration error estimation value which is obtained from the calculation is further substituted to a next time iteration, by configuring iteration times or a smaller threshold value, the registration error estimation value isconverged, and the registration error estimation value is eventually substituted to the converged registration error estimation to obtain a precise target position fusion value.

The invention provides automatic detection equipment for a power transmission tower plate and a method. The automatic detection equipment comprises a sensor module, a motion mechanism module and a motion controller module, wherein the motion controller module is used for controlling the operation of the motion mechanism module; the motion mechanism module is used for driving a plurality of targetobjects to move, so that the target objects are detected by the sensor module; the sensor module is used for detecting the distance between the sensor and a target object, capturing a plurality of target object contours and sending the laser contours and measurement results to external equipment through an output interface; and the external equipment collects the received plurality of laser contours and measurement results, generates a point cloud, and performs three-dimensional reconstruction and error analysis of the point cloud. By adopting the automatic detection equipment, the contours ofthe power transmission tower plates of various sizes can be rapidly measured, and measurement errors are reduced; and the registration problem of large-scale point clouds can be solved, so that the registration efficiency is improved, and the measurement error is further reduced.

The present invention discloses a high dynamic range three-dimensional image registration method, and relates to the computer vision field. The improved SURF feature descriptor in the method combines an Haar-like feature to increase description of opposite side features and opposite angle features, in the matching process, the improved RANSAC algorithm selects relatively high-quality feature matching points as initial data to reduce the nondeterminacy of model parameters and improve the registration accuracy. The improved SURF algorithm solves the registration problem of multi-exposure image sequences in the condition that three-dimensional parallax cannot be neglected, has fast speed and is suitable for the real-time registration condition.

The invention discloses a vehicle workpiece non-rigid 3D point cloud registration method based on linear mixed deformation. The invention relates to the vehicle workpiece non-rigid 3D point cloud registration method based on linear mixed deformation. The invention aims to solve a disadvantage that the an original ICP method is not applicable when a reference point cloud P is deformed due to gravity of the reference point cloud P or external force for the reference point cloud P which is subjected to non-rigid downsampling at present. The method comprises the steps of (1) obtaining Q and P, (2) constructing a control vector S, (3) constructing a linear mixed deformation model, (4) calculating an initial rigid transformation matrix, (5) constructing a least squares error function, (6) obtaining Delta S, (7) obtaining P', (8) allowing P' to rotate and translate, (9) obtaining the transformation relation between initial source point cloud and the reference point cloud, and (10) judging whether the obtained transformation relation between the initial source point cloud and the reference point cloud satisfies a convergence condition, outputting a result if so, otherwise going to the step (4). The method is used in the field of automobile workpiece registration.

The invention relates to a two-dimensional contour fast registration method. The two-dimensional contour fast registration method comprises six major steps: step 1, setting a reference data set and a target data set; step 2, for each point in the target data set, seeking a point with the shortest distance corresponding to the point from reference data set in a centralized manner; step 3, establishing a matching target function; step 4, optimizing the target function, and figuring out an optimal solution of the target function to obtain a new target data set; step 5, performing error analysis and calculation, and if error conditions are met or a maximum number of iterations is reached, going to the step 6, and otherwise, going to step 2, step 6, outputting an error analysis report according to a matching relation after the optimal matching relation is obtained, and realizing two-dimensional contour fast registration. The invention provides the two-dimensional contour fast registration method to realize an ICP (iterative closest point) algorithm, by adopting the method, curve contour registration is efficiently and stably realized, and the method provided by the invention is widely applied to measurement and detection of workpieces after processing, reconstruction of surfaces, identification of three-dimensional objects, calibration of cameras and the like.

The invention belongs to the technical field of underground engineering space position deformation, and particularly relates to a three-dimensional laser scanning underground engineering similar material simulation test surface layer deformation method. A five-point mark control point method is adopted, five points serve as point cloud matching references, after scanning parameters are determined,underground engineering before and after excavation is scanned by using three-dimensional laser so as to obtain data of point cloud deformation of the similar material simulation test surface layer,the data are processed and modeled, then visualized processing is carried out, and a visual cloud diagram is generated. According to the method, the problems which exist when a similar material simulation test is carried out to obtain surface layer deformation information in a laboratory by adopting a theodolite and a total station are solved, a three-dimensional laser scanning technology is utilized, and a data card and visual processing are formed, so that a more visual and higher-precision test result is obtained.

The present invention discloses a polarimetric SAR (Synthetic Aperture Radar) image matching method and apparatus based on orientation angle inversion. The method comprises the following steps: obtaining DEM (Digital Elevation Model) data and polarimetric SAR data; performing inversion according to the DEM data, so as to obtain a first orientation angle; performing inversion according to the polarimetric SAR data, so as to obtain a second orientation angle; respectively performing visualization processing for the first orientation angle and the second orientation angle; and matching the first orientation angle and the second orientation angle through a BFSIFT algorithm after the visualization processing. According to the polarimetric SAR image matching method in an embodiment of the present invention, a polarimetric SAR image is matched with a DEM based on orientation angle inversion, thus matching time is shortened, and operation accuracy is improved, therefore, the polarimetric SAR image matching method not only has low operational complexity, but also has high operation stability.

The invention belongs to the technical field of image data processing, and discloses a white light data and CT data registration method based on an improved iteration nearest point algorithm. The method comprises the following steps of preprocessing the collected CT data, white light data and fluorescence data; reconstructing and segmenting the CT data, and performing surface extraction and segmentation on the CT data to obtain body surface data; carrying out mouse 3D surface gridding reconstruction by adopting an improved voxel-based method; registering the 3D CT data and the 3D white light data by adopting an ICP algorithm based on bidirectional distance proportion improvement; and carrying out multiple pieces of fluorescence information fusion and 3D surface fluorescence luminous flux reconstruction so as to realize fusion of CT data and optical data. According to the method, the registration precision of the white light data and the CT data can be improved, the registration speed is increased, optical reverse reconstruction is facilitated, observation judgment in medical diagnosis, prediction simulation in virtual surgery and training practice in clinical teaching are facilitated, and convenience is brought to a user.

The invention discloses an interpretable thermal infrared visible light image registration method and system. The method comprises the following basic steps: 1) simulating the process of extracting descriptors, matching and estimating transformation parameters and transforming images by using a neural network through a traditional registration algorithm; 2) adopting a coarse-to-fine registration strategy of firstly carrying out global transformation and then carrying out local transformation; 3) constructing a loss function to train the network; and 4) processing the thermal infrared image-visible light image registration problem under different internal and external parameters by using the trained network. According to the explainable registration deep neural network (ERDNN) provided by the invention, the pixel-level registration of the thermal infrared camera and the visible light camera which are not overlapped with the optical center can be realized. The invention further provides a method for realizing the pixel-level registration of the thermal infrared camera and the visible light camera which are not overlapped with the optical center. The trained descriptor sub-network can be used as a general descriptor extractor to extract thermal infrared-visible light cross-modal descriptors. The method has wide use value and application prospect in the fields of computer vision, automatic driving, monitoring security and protection and the like.

The invention discloses a telescope, which comprises a micro display, a light combiner, a dichroic spectroscope and an image sensor, and is characterized in that the light combiner receives light from an objective lens and light from the micro display and mixes the light with the light from the micro display; the dichroism spectroscope enables most visible light in the light mixed by the light combining mirror to enter a first light path leading to the eyepiece, and at least part of invisible light and a small amount of visible light with preset wavelength enter a second light path leading to the image sensor; and the image sensor obtains a detection image representing an optical image formed by the objective lens and an electronic image displayed by the microdisplay. The invention also discloses an electronic eyepiece and an eyepiece adapter for a telescope. According to the embodiment of the invention, a detection image representing an optical image formed by a telescope objective lens and an electronic image displayed by the micro display can be obtained. This makes it possible to acquire registration information of the optical image and the electronic image, thereby solving the registration problem between the electronic image and the optical image.

The invention discloses a vehicle workpiece non-rigid 3D point cloud registration method based on linear mixed deformation. The invention relates to the vehicle workpiece non-rigid 3D point cloud registration method based on linear mixed deformation. The invention aims to solve a disadvantage that the an original ICP method is not applicable when a reference point cloud P is deformed due to gravity of the reference point cloud P or external force for the reference point cloud P which is subjected to non-rigid downsampling at present. The method comprises the steps of (1) obtaining Q and P, (2) constructing a control vector S, (3) constructing a linear mixed deformation model, (4) calculating an initial rigid transformation matrix, (5) constructing a least squares error function, (6) obtaining Delta S, (7) obtaining P', (8) allowing P' to rotate and translate, (9) obtaining the transformation relation between initial source point cloud and the reference point cloud, and (10) judging whether the obtained transformation relation between the initial source point cloud and the reference point cloud satisfies a convergence condition, outputting a result if so, otherwise going to the step (4). The method is used in the field of automobile workpiece registration.

The invention discloses a visible light image and infrared image registering method which comprises the following steps: performing multi-scale decomposition on a visible light image and an infrared image to obtain low-resolution visible light image and infrared image; extracting SIFT (scale invariant feature transform) features, multi-scale corner features and surface point features from the low-resolution image pair; matching the SIFT features and removing exterior points; obtaining an initial transformation model by use of the matched SIFT feature pair, wherein the transformation model refers to any geometric transformation relationship between the infrared image and a high-spectrum image; extracting the multi-scale angular point features and the surface point features based on an image block pair on the original image pair by use of the geometric constraint provided by the initial transformation model; determining a more accurate transformation model according to the initial transformation model and the multi-scale angular point features and surface point features; and transforming the infrared image according to the transformation model to obtain the transformed infrared image.

The invention discloses a non-rigid brain image registration method, which comprises the steps of 1, preprocessing a target image according to a reference image to obtain a rough registration image; 2, respectively calculating the candidate characteristic points of the reference image and the rough registration image; 3, constructing characteristic descriptors of the candidate characteristic points, and obtaining matched characteristic points according to the characteristic descriptors; 4, calculating a light stream model of the rough registration image according to the characteristic points to obtain a registration result. Through adopting a descriptor vector based on a Zernike matrix to depict the geometrical characteristics under different scales for describing the regional characteristics of the characteristic points, the characteristic point matching problem during non-rigid registration is solved, and in addition, through fusing characteristic point constraints into the Brox light stream model, the problem of registration of brain magnetic resonance images is solved.

The invention discloses a disposable hard endoscope sleeve lens and a lens alignment method. The lens comprises a rigid head and a flexible sleeve; a connecting end of the flexible sleeve is connected with the rigid head, and the other end of the flexible sleeve is an open free end; a 1:1 nonopaque lens group is arranged in the head to form a sealed front end; the connecting end of the flexible sleeve is provided with a first rigid ring, the free end of the flexible sleeve is provided with a second rigid ring, and first and second limiting devices are arranged on the first and second rigid rings; the flexible sleeve is sheathed on an outer surface of a hard endoscope; and the first and second rigid rings locate the lens group on a position overlapped with the main optical axis of the lens group of the hard endoscope by means of the first and second limiting devices. The method comprises the following steps: keeping the first rigid ring to be coaxial with the lens group through the rigid head; and keeping the first rigid ring to be coaxial with the second rigid ring through the first and second limiting devices. By adoption of the sleeve lens and the alignment method thereof provided by the invention, the sterilization and imaging problems of the existing endoscopes are solved.

The invention discloses a registration method between multi / hyperspectral remote sensing image bands. Through feature extraction and calculation analysis, the gray features of different bands and image space features are combined to solve the registration between multi / hyperspectral image bands. The problem is used for preprocessing of multispectral image color synthesis and hyperspectral image data cube synthesis, thereby improving the universality of multi / hyperspectral remote sensing data.

The invention discloses a visible light image and high-spectrum image registering method which comprises the following steps: performing multi-scale decomposition on a visible light image to form a low-resolution visible light image; generating a high-spectrum image significant waveband image according to the high-spectrum image; extracting SIFT (scale invariant feature transform) features, multi-scale angular point features and surface point features from the low-resolution visible light image and high-spectrum image significant waveband image; matching the SIFT features and removing exterior points; obtaining a transformation model by use of the matched SIFT feature pair; extracting the multi-scale angular point features and surface point features based on an image block pair by taking a registered transformation model of the previous layer as an initial transformation model of the current layer on each layer of visible light image and high-spectrum image significant waveband image; selecting the transformation type and obtaining a transformation parameter according to the initial transformation and the multi-scale angular point features and surface point features in combination with an iteration re-weighted least square method; and transforming the high-spectrum image according to the transformation model to obtain the transformed high-spectrum image.

The invention discloses an unmanned aerial vehicle detection image registration method, and relates to an unmanned aerial vehicle detection image registration method, comprising a Harris corner algorithm and an image registration process, and further comprising the following steps: S1, acquiring video information acquired by an unmanned aerial vehicle, and setting a source image set and a registration image set; S2, carrying out the same preprocessing of the source image and the registered image, carrying out the preliminary image rotation, translation and scale transformation through the basic statistical features, and removing the redundant noise; S3, performing Harris corner detection on the source image and the registration image by using a Harris corner algorithm, and recording cornercoordinates; S4, setting a registration area; S5, calculating a correlation coefficient of a registration area of the source image and the registration image; S6, judging the matching degree of the source image and the registration image by using the correlation coefficient; and S7, entering an image registration process. According to the unmanned aerial vehicle detection image registration method, the problem of unmanned aerial vehicle video frame image registration can be effectively solved, and an ideal registration image set is obtained; and the unmanned aerial vehicle detection image registration method has good feature invariance, uniqueness, stability and independence.

The invention discloses a geometric constraint-based high-resolution optical satellite staring image registration method. The method comprises the steps of S100, building a free network adjustment directional model of images by utilizing a rational function model of additional image space error compensation; S200, based on the free network adjustment directional model, performing dense matching ona stereoscopic image pair with an optimal rendezvous condition in the images to obtain coordinates of dense homonymy points; S300, generating dense point cloud data, performing gross error point deletion on the dense point cloud data, and generating digital surface model data; and S400, based on the free network adjustment directional model and DSM data, performing geometric correction on the images in sequence. By utilizing geometric locating consistency, high-precision registration of high-resolution optical satellite multi-angle staring sequence images is realized; the multi-angle staringsequence image registration problem caused by satellite platform control inaccuracy and attitude measurement inaccuracy is solved; and a high-precision data basis can be provided for subsequent application.

The invention belongs to the technical field of radars, discloses a multi-station radar signal fusion detection method based on tracking information, and solves the problem in a multi-station radar networking system that the signal fusion detection probability is low. The realization process of the method comprises the steps of: according to a track initial algorithm, obtaining a target initial state estimated value and an original state estimated covariance matrix, and determining a target prediction port door at the kth moment according to the target state estimated value at the (k-1)th moment and the state estimated covariance matrix at the (k-1)th moment; dividing the target prediction port door at the kth moment into a plurality of fusion detection units, calculating the detection threshold of each fusion detection unit in the target prediction port door, and obtaining a measured data set at the kth moment; according to the measured data set at the kth moment, calculating the target state estimated value and the state estimated covariance matrix at the kth moment; and judging whether the track ends. Compared with an existing signal fusion detection method, the target detection probability is improved.