70results about How to "Realize automatic registration" patented technology

The invention relates to a point cloud automatic registration method based on normal vector. According to the method, processing objects are two or more than two pieces of three-dimensional point cloud data, wherein overlapped part exists every two pieces of adjacent three-dimensional point cloud data. The method comprises the following processing steps that (1) feature points are selected according to the point cloud local normal vector changes; (2) the histogram feature quantity is designed for carrying out feature description on each obtained feature point; (3) the initial matching dot pair is obtained through comparing the histogram feature vector of the feature points; (4) the precise matching dot pair is obtained through applying the rigid distance constraint condition and combining a RANSAC (random sample consensus) algorithm, and in addition, the initial registration parameters are obtained through calculation by using a four-element method; and (5) an improved ICP (iterative closest point)) algorithm is adopted for carrying out point cloud precise registration. The point cloud can be automatically registered according to the steps. The method has the advantages that feature description is simple, identification degree is high, higher robustness is realized, and registration precision and speed are improved to a certain degree.

A non-rigid registering method of a mouse three-dimensional CT image comprises the following steps: A, a direction and a position of a source image of a mouse three-dimensional CT image are calibrated; B, a threshold segmentation algorithm is used to segment the mouse image to obtain a mouse bone of the source image and a mouse bone of a target image, a center of mass of a bone slice connected domain is extracted to serve as a characteristic point, so that a source image characteristic point and a target image characteristic point are obtained; C, the source image characteristic point and the target image characteristic point in the step B are matched, the matched characteristic point is used to calculate a thin plate batten transformation matrix, and a hierarchical transformation mode is used to carry out the thin plate batten transformation to the mouse source image; and D, the mouse source image after the thin plate batten transformation and the target image carry out a fine registering. According to the invention, when the characteristic points are extracted, the number of characteristic points is reduced; the hierarchical transformation mode is used to overcome the defect of long registering time; an automatic registering in the image registering is basically realized; and registering the three-dimensional mouse image is easier.

The invention discloses a ball target detection-based automatic registration method for laser point cloud data. The method comprises the following steps: respectively extracting ball target characteristics from laser point cloud data of two adjacent stations; building a triangle by taking sphere centers of any three non-collinear ball targets as a peak for any station, and taking the area and three inner angles as four rotational invariants of the triangle, so as to build a reference triangle set comprising a plurality of reference triangles by a reference station; building a to-be-registered triangle set comprising a plurality of to-be-registered triangles by a to-be-registered station; matching the reference triangle set with the to-be-registered triangle set; determining a selected same triangle, and calculating the transformation relation of the to-be-registered station and the reference station. By adopting the method disclosed by the invention, automatic detection and automatic registration of the ball target are achieved by a computer automation mode, reduction of expenses of time, manpower and material resources is facilitated, and a non-professional user can obtain a high-quality three-dimensional data model.

The utility model discloses an automatic registration method for multi-view three-dimensional face scanning data, which is characterized in comprising the following steps: coordinate axis transformation is made to the multi-view three-dimensional face scanning data through the PCA method; the shape index value of a transformed model is calculated, and a plurality of feature regions are screened using the method of threshold segmentation; region screening is restricted by region relative distribution features so as to finally position the symbolic regions such as eyes, outer canthi and nasal tip points; the symbolic regions are matched by the ICP method; and the coordinate translation and rotation transformation are made to the transformation parameters which are obtained from region registration of the whole scanning data so as to complete registration. The coarse registration of the utility model adopts the method of coordinate axis transformation, and the global features are instead of the individual point features, so error caused by symbolic point detection is reduced. The precise registration only makes registration iterative computation to the extracted symbolic regions, so computation complexity is reduced, and the automatic registration of multi-pose three-dimensional scanning data is enabled.

The invention discloses a planar terrain variation detecting method based on remote sensing image and GIS data, which comprises the following steps: first, predisposing the GIS data; second, predisposing the remote sensing image; third, calculating the Label point of planar terrain; fourth, predicting the remote sensing image same-name point corresponding to the GIS planar terrain Label point; fifth, defining a group of similar character vector from coarse to fine; sixth, extracting the same name planar terrain according to the similar character vector; seventh, judging whether the terrain changes according to the similar character vector threshold value; marking the terrain if yes; calculating the gravity coordinate of the polygon as the control point then returning the fourth step if no. The invention can detect the varied terrain and obtains the control point of non-varied terrain, which utilizes the control points to accomplish the automatic registration of image and GIS data.

The invention provides an automatic contour registration method in rail abrasion dynamic measuring. The method includes: using an RDP algorithm to automatic segment an obtained rail web and a rail bottom arc contour; performing nonlinear quadratic fitting based on radius constraint on the segmented arc contour to obtain circle center coordinates, and using the circle center coordinates as the reference point to perform primary registration on a rail measured contour and a standard contour; using the primary registration result of the reference point as the initial value of an improved ICP algorithm, and performing iterative computation to obtain the optimal rigid body transformation relation to complete the automatic contour registration in rail abrasion dynamic measuring. By the two-section automatic rail contour registration method based on the RDP algorithm and the improved ICP algorithm, high-precision automatic registration of the rail measured contour and the standard contour isachieved.

The invention belongs to the field of computer image process and a remote sensing technology and relates to an automatic registration method for a multi-temporal empty spectrum remote sensing image based on space comprehensive mutual information. The automatic registration method comprises the following steps of: mapping an image for registering by using a registration transformation parameter; extracting the marginal information of a reference image and the mapped image for registering, and calculating the space position information of a characteristic element by the marginal information; calculating a gray similarity index between the reference image and the mapped image for registering; structuring the space comprehensive mutual information index which is a product of the gray similarity index and the space position information, wherein the space position information and the gray similarity index are object functions of the registration transformation parameter; searching an optimal registration transformation parameter by using an optimization algorithm; and registering the image by utilizing the optimal registration transformation parameter. According to the automatic registration method, the space comprehensive mutual information is constructed to be similarity index, so that the automatic registration which is high in precision, robustness and performance among multi-source remote sensing images is achieved.

The invention discloses an automatic register method, system and equipment based on machine vision. The automatic register method based on machine vision includes the following steps: an industrial control computer transmits calculated center distance deviation ([delta]X and [delta]Y) of actual color codes and reference color codes of all groups of cameras and register error data to a control system, the control system calculates transverse and longitudinal register values according to the transmitted center distance deviation ([delta]X and [delta]Y) of the actual color codes and the referencecolor codes of all the groups of the cameras and the register error data, and the control system carries out automatic register according to the calculated transverse and longitudinal register values. Through the method, the recognition of color code images by shooting can be realized by using the machine vision, an actual position is calculated for the automatic register, the register is accurate, and the problem of inaccurate register caused by color code printing can be avoided.

The invention relates to an automatic registration method between multi-station foundation laser radar data based on single tree position and surface information and is mainly applied to the three-dimensional forest scene reconstruction based on multi-station foundation laser radar data. By the automatic registration method between multi-station foundation laser radar data, in the automatic alignment process, an additive foundation laser radar posture measuring device is used, the number of registration parameters required by registration need to be determined to reduce the number of control points required by registration. Simultaneously the similarity of a triangle formed by a plurality of single trees is utilized to recognize the homonymy single trees automatically, and control points are provided for the registration. By the automatic registration method between multi-station foundation laser radar data based on single tree position and surface information, the accuracy requirements and dependence for the control points in the registration process can be reduced, and the automatic registration of the multi-station foundation laser radar data under a forest environment can be realized.

The embodiment of the invention provides a method and apparatus for register two-dimensional centerline and three-dimensional centerline of blood vessel. The method includes extracting features of two-dimensional centerline of target blood vessel from two-dimensional image of target blood vessel, extracting feature of three-dimensional centerline of target blood vessel from three-dimensional imageof target blood vessel. Modeling features of the two-dimensional centerline and features of the three-dimensional centerline, acquiring a feature model corresponding to the feature of the two-dimensional centerline and a feature model corresponding to the feature of the three-dimensional centerline, and constructing an objective function according to the feature model corresponding to the featureof the two-dimensional centerline and the feature model corresponding to the feature of the three-dimensional centerline; The objective function is optimized based on a particle swarm optimization algorithm, and the two-dimensional centerline and the three-dimensional centerline are registered according to the optimized objective function. The embodiment of the invention improves the accuracy ofregistration.

Open remote sensing data is subjected to certain decryption processing according to requirements of security policies, and when a user tries to superpose own vector data and the remote sensing data, the situation that the vector data and the remote sensing data are not matched occurs. In order to solve the problem, the invention discloses an automatic registration method for vector data and a remote sensing image. The method comprises the following specific steps: 1) based on vector data, extracting a three-valued matrix A by using a scanning line algorithm; 2) extracting a gray matrix G basedon the remote sensing image, and obtaining an edge matrix E of the gray matrix G by using a Canny operator; 3) traversing on the three-valued matrix A by using an edge matrix E to generate a normalized edge registration factor matrix F'edge; 4) traversing on the three-valued matrix A by using the gray scale matrix G to generate a normalized gray scale registration factor matrix F'gray scale, 5) automatically registering the vector data and the remote sensing image based on the characteristics of the registration factors, and 6) extracting the remote sensing image data in a specified range ofthe vector elements.

The invention discloses a radiation therapy curative effect evaluation device and a radiation therapy curative effect evaluation method based on CT/MRI double-body position scanning automatic registration and fusion and belongs to the technical field of medical treatment. The device comprises a CT/MRI machine body, a CT/MRI scanning bed, a four-quadrant scanning plate and a computer equipped with image registration and fusion software; the four-quadrant scanning plate is of a square, slant rods which are intersected are embedded in two diagonals of the square; end parts of the two slant rods are sealed and insides of the slant rods are both formed with cavities, and the cavities are communicated and filled with greases; and the computer is connected with the CT/MRI machine body; the radiation therapy curative effect evaluation method comprises the following steps of: manufacturing and wearing a head mould, locating CT/MRI by the assistance of the four-quadrant scanning plate, locating and scanning CT/MRI and carrying out registration and fusion based on pixel points and evaluating a curative effect. The device and the method have the advantages of using pixel values to achieve automatic registration and fusion of arbitrary radiotherapy positioning scanned images of a double-body position, and providing convenience to medical staffs to carry out an objective evaluation on a radiation therapy.

The invention discloses an intelligent community entrance guard system, which comprises a first entrance guard system, a second entrance guard system and a center management system, wherein the first entrance guard system comprises a first entrance guard host and a registration host; an identity card recognizer is arranged on the first entrance guard host; a first processor, a wireless module and a data storage module are also arranged in the first entrance guard host; an identity card recognizer is arranged on the registration host; a second processor is arranged in the registration host; a camera is also arranged on the registration host; an infrared sensing device is arranged behind the first door and is connected with the first processor; the second entrance guard system comprises a second entrance guard host; an identity card recognizer is arranged on the second entrance guard host; a third processor, a wireless module and a warning device are arranged in the second entrance guard host. The intelligent community entrance guard system has the advantages that the automatic registration of outcomers can be realized; the outcomers can be prevented from entering a gate in a following manner; the community safety is greatly improved.

The invention discloses a bidirectional neighborhood filtering policy based remote sensing image registration method. The bidirectional neighborhood filtering policy based remote sensing image registration method comprises the steps of: combining grey characteristics with spatial structure characteristics of characteristic points; iterating to obtain a matching point pair with the same bidirectional neighborhood structure through the difference of the bidirectional neighborhood structure by regarding a grey characteristics based matching result as an initial matching point pair and regarding neighborhood structural characteristics of the characteristic points as limitations; and recovering candidate wrong matching point pairs which are deleted wrongly in the iteration process by adopting a bidirectional neighborhood filtering policy. The bidirectional neighborhood filtering policy based remote sensing image registration method is used under the conditions that relatively great affine transformation exists in the to-be-registered image, the to-be-registered image is a heterogenous image and similar patterns exist in an image scene, and can increase registration precision under the condition of no manual intervention.

The invention discloses a power failure information management system based on a trouble call management system, which includes a trouble call management system, a power transmission and distribution production management system, and a load control information system, wherein the trouble call management system is provided with a power failure information management module used for power failure information sheet management, power failure information distribution and power failure information statistics as per scheduled power failure information and information of power supply outage and ration; the power transmission and distribution production management system is used for outputting the scheduled power failure information to the trouble call management system; and the load control information system is used for outputting the information of power supply outage and ration to the trouble call management system. According to the invention, a unified power failure information management platform is provided for related personnel to share and distribute power failure information of all kinds in a unified manner, thereby reducing links and time for information transmission, improving the power line repair and information sharing capability of daily operation, and realizing the lean management; and reply to power failure and power recovery of various types such as scheduled outage and outage caused by failure can be quickly carried out, and cross-system and cross-department power failure integration and procedure coherence are realized, so that the quality of the service for users is improved.

The invention discloses a method for automatically registering storehouse access operation. According to the method, a door control system is arranged in a storehouse and has an identity recognition function; an indoor radio-frequency card reader and an outdoor radio-frequency card reader are arranged on the inner side and the outer side of a door control device respectively; and the storehouse access operation is automatically registered by reading and processing RFID electronic tags of goods and materials. By use of the method, information such as who is a person, when the person enters the storehouse, when the person leaves from the storehouse, which goods are stored, which goods are extracted and the like can be completely and autonomously registered. Compared with other methods, the method provided by the invention is simple and feasible, is lower in cost and is especially suitable for goods and materials management of unmanned storehouses.

The invention discloses a method for automatically registering bent bone fracture and pre-bending modeling of an internal fixation steel plate, which comprises the following steps: S1, extracting maindirection of broken bone model point set by PCA algorithm and selecting clustering seed point along main direction; S2, extracting main direction of broken bone model point set by PCA algorithm; S2,respectively constructing capsule mapping models at both ends of the broken bone model; S3, clustering the feature points of the mapping model constructed in S2 by using OPTICS algorithm; 4, extracting and segmenting the point set of the cross-section part of the broken bone model; S5, precisely registering the broken bone model according to the two section point sets obtained by the segmentation;S6: selecting the control point at the fracture position of the fracture model, and thickening the triangular patch within the range of the control point to obtain the steel plate model. The method utilizes many algorithms such as curve fitting, clustering, feature point mapping and so on, realizes the automatic splicing of bending bones efficiently and accurately, realizes the automatic registration of bending bones model and prebending of steel plate, and does not need manual operation.

The invention discloses an archives management system which comprises an identity right recognizing module and a human face recognizing system. The identity right recognizing module is mounted on an electronic lock for connecting an archives storage bag and an archives cabinet for recognizing identity right information of a user, sending the recognized information to a server and receiving a command of the server to control the electronic lock to be locked and unlocked; and the human face recognizing system is mounted at the door access for recognizing the identity information of the user entering an archives management room. The archives storage bag is a cuboid PVC bag opened in three edges, zipper parts are sewed to the three edges, the zipper parts are opened and closed through two zipper heads, the two zipper heads are movably connected through the electronic lock, the electronic lock is connected to a tension sensor through a cable, and the tension sensor is mounted in the archives cabinet in an embedded manner. The archives management system achieves confirmation of an archives borrowing right and automatic registration of borrowing information, so that the workload of an administrator is alleviated, and the masquerading condition can be avoided well.

The invention discloses an intelligent firearm supervision system and platform. The system comprises a use management module, a technical state supervision module, a maintenance management module anda statistical analysis module. The use management module is used for managing gun taking and returning; the technical state supervision module divides gun grades and updates the technical state of each gun in real time; the maintenance management module is used for summarizing and counting the information of the guns to be repaired, maintained and scrapped, and judging whether the guns meet the conditions of repairing and scrapping or not; establishing a gun maintenance electronic record file, and updating the gun spare part consumption condition in real time; the statistical analysis module is used for summarizing information such as gun storage, use, technical conditions, service life, maintenance, spare part consumption, inventory and the like in the affiliated unit and the storeroom ina hierarchical manner; and according to different units, different time and different personnel, carrying out longitudinal and transverse comparative analysis on the summarized information to obtainrelated statistics and analysis charts.

The invention discloses an automatic registration method for panchromatic images and multispectral images of a Gaofen-7 satellite, which comprises the following steps of: S1, acquiring geometric imaging model parameters of the panchromatic images and the multispectral images in various wave bands, and constructing geometric imaging models of the panchromatic images and the multispectral images in various wave bands; S2, constructing a unified virtual CCD geometric imaging model of the panchromatic image and the multispectral image of each wave band by using geometric imaging model parameters of the panchromatic image and the multispectral image of each wave band; and S3, generating a strictly registered panchromatic image and a strictly registered multispectral image based on a unified virtual CCD geometric imaging model of the panchromatic image and the multispectral image of each wave band. The method has the advantages that the registration problem of the panchromatic image and the multispectral image of the Gaofen-7 satellite can be effectively solved, and automatic registration of the two images is realized by constructing a virtual unified CCD in sensor correction processing.