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 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 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 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 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.