243results about How to "Precise registration" patented technology

Method (300) for registration of n frames 3D point cloud data. Frame pairs (200i, 200j) are selected from among the n frames and sub-volumes (702) within each frame are defined. Qualifying sub-volumes are identified in which the 3D point cloud data has a blob-like structure. A location of a centroid associated with each of the blob-like objects is also determined. Correspondence points between frame pairs are determined using the locations of the centroids in corresponding sub-volumes of different frames. Thereafter, the correspondence points are used to simultaneously calculate for all n frames, global translation and rotation vectors for registering all points in each frame. Data points in the n frames are then transformed using the global translation and rotation vectors to provide a set of n coarsely adjusted frames.

The invention provides a remote sensing image registration method of a multi-source sensor, relating to an image processing technology. The remote sensing image registration method comprises the following steps of: respectively carrying out scale-invariant feature transform (SIFT) on a reference image and a registration image, extracting feature points, calculating the nearest Euclidean distances and the nearer Euclidean distances of the feature points in the image to be registered and the reference image, and screening an optimal matching point pair according to a ratio; rejecting error registration points through a random consistency sampling algorithm, and screening an original registration point pair; calculating distribution quality parameters of feature point pairs and selecting effective control point parts with uniform distribution according to a feature point weight coefficient; searching an optimal registration point in control points of the image to be registered according to a mutual information assimilation judging criteria, thus obtaining an optimal registration point pair of the control points; and acquiring a geometric deformation parameter of the image to be registered by polynomial parameter transformation, thus realizing the accurate registration of the image to be registered and the reference image. The remote sensing image registration method provided by the invention has the advantages of high calculation speed and high registration precision, and can meet the registration requirements of a multi-sensor, multi-temporal and multi-view remote sensing image.

A general imaging scheme is proposed for applications of CBCT. The approach provides a superior CBCT image quality by effective scatter correction and noise reduction. Specifically, in its implementation of CBCT imaging for radiation therapy, the proposed approach achieves an accurate patient setup using a partially blocked CBCT with a significantly reduced radiation dose. The image quality improvement due to the proposed scatter correction and noise reduction also makes CBCT-based dose calculation a viable solution to adaptive treatment planning.

The invention discloses a real-time video stabilization method based on a homography matrix and is used for stabilizing video sequences obtained by devices such as a handheld DV and an unmanned aerial vehicle. The method comprises the steps of A, extracting angular points uniformly distributed in images; B, calculating an interframe optical flow vector and tracking an interframe motion angular point through utilization of the interframe optical flow vector; C, calibrating the tracked angular point through utilization of a layered affine calibration algorithm; D, solving an interframe homography matrix through utilization of a random sampling unification algorithm; E, separating interframe active motion compensation quantity and distortion calibration quantity by employing a kalman filter; and F, carrying out stabilization conversion on one video image by employing the homography matrix, the motion compensation quantity and the distortion calibration quantity to obtain stabilized current frame output. According to the method, shake existing in the video sequences can be effectively removed, the algorithm complexity is relatively low, the operation speed is fast, and the high application value is provided for the real-time video processing system.

The invention discloses a point cloud and image automatic high-precision registration method based on mutual information. The method comprises the steps of shooting a close-range optical image of a to-be-detected object; collecting ground laser scanning point cloud of the to-be-detected object, and generating an RGB color image and a reflection intensity image; calculating coarse registration parameters by using the close-range optical image and the point cloud RGB color image; extracting Harris operator feature points from the reflection intensity image by grids; a Forstner positioning operator is used for accurate positioning, rough registration parameters are used for calculating the initial positions of corresponding homonymous points of the feature points, the mutual information theory is used for searching for accurate matching point positions of the feature points in the close-range optical images in the initial positions, and accurate homonymous feature point pairs of the two images are obtained; calculating a fine registration parameter; and generating an accurate color point cloud model of the to-be-tested object. The method is not influenced by non-homologous data projection and radiation difference, and meets the requirement for reconstruction of a high-precision three-dimensional color texture model in the cultural relic protection industry.

The invention discloses a DCS algorithm-based satellite-borne video SAR (synthetic aperture radar) imaging processing method. The method includes the following steps that: 1, satellite-borne SAR beam bunching mode echo simulation data and corresponding parameters are read; 2, Doppler bandwidth and synthetic aperture time required by frame images are determined; 3, a data partitioning mode is determined, and data are partitioned; 4, de-sloping processing is performed on frame segment data in an azimuth direction; 5, signals obtained after the de-sloping processing are subjected to azimuth-direction Fourier transform, multiplied by an CS factor, subjected to range-direction Fourier transform, and multiplied by a range-direction compensation factor sequentially; 6, the phase difference between the center slope distance of each frame of data and the center slope distance of the entire echo data is compensated; 7, range-direction Fourier transform, azimuth-direction compensation processing, azimuth-direction inverse Fourier transform are performed, so that an imaging result can be obtained; 8, step 4 to step 7 are repeated, so that all frame images can be obtained; and a video SAR product can be obtained. With the DCS algorithm-based satellite-borne video SAR imaging processing method of the invention adopted, the resolutions of the frame images can be consistent.

A multi-modality image registration method includes the following steps: sampling reference images and images to be registered according to a first sampling proportion to obtain the reference images and the images to be registered with first resolution ratio, adopting a B spline surface as a deformation model to perform matching on the reference images and the images to be registered, calculating matching measure and obtaining first matching parameters, and increasing sampling proportion to repeat the processes until the matching measure reaches a reset threshold value, wherein in matching, matching parameters of last time are used as initial matching parameters after each-time sampling proportion is increased. An operation navigation method based on multi-modality image registration is further provided.

The invention discloses an improved approximate projection transformation image splicing method, relating to the technical field of image processing. The image splicing method includes S1 image preprocessing, S2 image feature point extraction, and S3 image feature point matching based on an optical flow pyramid. The image processing in S1 includes noise suppression, enhancement of texture and contrast, and normalization of histograms, and further includes calibration of the camera lens, establishment of the corresponding mathematical model based on the cause of image distortion, and correction of contaminated or distorted images by using the calibrated parameters; and the image feature point extraction in S2 adopts a BRISK and/or ORB feature descriptor. The method provided is improved based on the approximate projection transformation (APAP) image splicing method, the pre-processing step is added before the feature extraction step, and the BRISK and/or ORB binary feature descriptor is creatively used in the feature extraction step, and the optical flow pyramid is creatively used in the matching step, so that the image splicing is timesaving and accurate in registering.

The invention relates to a double-track registration and medical consultation service system which comprises a double-track registration system, a double-track number calling system, a prepayment, charging and automated clearing system, a consultation transferring system, a doctor automatic allocation system and a control center; wherein, the double-track registration system consists of an obscure registration system and an accurate registration system; the double-track number calling system consists of an accurate registration check in system, an accurate number calling system, an obscure number calling system, a blank time automatic position supplementing system and a preferential number calling system. The invention also relates to a double-track registration and medical consultation service method. The patients can register and wait to see the doctor by the double-track registration system, and the hospital is equipped with the double-track number calling system to call the patients waiting to see the doctor; the method also comprises blank time automatic position supplementing, obscure registration medical consultation, accurate registration medical consultation and medical expert consultation automatic mutual consultation transferring, and VIP senior members have the privilege of preferential number calling for medical consultation. The invention solves the problem that the patients in the hospital wait for a long non-medical time, and makes up the defect the existing medical resources can not be used in a balancing way.

The invention belongs to the technical field of computer vision, image processing and three-dimensional measurement, and particularly relates to a 3D-RGB point cloud registration method based on a local gray scale sequence model descriptor. The method comprises the following steps: 1, calculating a four-neighborhood gray average value of each point in two point clouds; 2, dividing adjacent pointsof the key points into six parts according to gray values, and finally connecting the feature vectors of the six parts in series to form a key point feature descriptor; 3, constructing a point-to-point mutual corresponding relationship between the source point cloud and the target point cloud according to a nearest neighbor ratio method and an Euclidean distance threshold, and removing an error corresponding relationship by utilizing random sampling consistency and color consistency; and 4, solving a conversion matrix between the source point cloud and the target point cloud by using the corresponding relationship, and performing spatial transformation on the source point cloud to complete registration of the point cloud. According to the method, the influence of unobvious geometric information and light intensity change on point cloud registration can be effectively reduced. The method has a wider application range. The precision and the robustness of three-dimensional point cloud registration are improved.

The invention discloses a satellite-borne InSAR (Interferometric Synthetic Aperture Radar) long-short baseline image joint registration method, which comprises the steps of S1, inverting three-dimensional coordinate information of ground points in an imaging region by using two SAR images under a short baseline; S2, selecting characteristic pixels of a short baseline main image, substituting ground three-dimensional coordinates corresponding to each characteristic point and satellite parameters of a long baseline image into a Doppler equation, and searching an optimal solution meeting imaging conditions; S3, solving an azimuth pixel position and a range pixel position of each characteristic point in the long baseline SAR image; S4, carrying out polynomial fitting on the azimuth and range offset of the characteristic points in the long baseline image by taking the pixel positions of the characteristic points in the short baseline main image as a benchmark so as to acquire the offset of each pixel; and S5, carrying out interpolation and resampling processing on the long baseline SAR image by using the offset acquired in the step S4 so as to finally generate a registered image which is consistent with the short baseline main image in size.

The invention discloses a vehicle-mounted panorama camera based on a POS (position and orientation system) and an external parameter calibrating method of a linear array laser scanner. The external parameter calibrating method comprises the following steps: (1) establishing an outdoor calibrating field with absolute coordinate points in advance, wherein data acquisition is performed in the field, time for obtaining each group of panorama images and each laser-point cloud is obtained according to time information after acquisition, and the position and attitude information of the POS in each moment is obtained according to the high-density position and attitude information obtained by the POS; (2) resolving external parameters of the panorama camera; (3) resolving external parameters of the linear array laser scanner. The external parameter calibrating method has the beneficial effects that when a linear array laser sensor is calibrated, a large quantity of feature points do not need to be measured in advance, and only repeatable measurement features of the images are utilized, so as to reduce the workload to the minimum. More importantly, the panorama images determined by an algorithm principle and the point cloud scanned by a linear array laser can be accurately rectified after calibration.

The invention discloses a registration method and apparatus. The registration method comprises steps of carrying out registration of a digital reconstruction ray image and a two-dimension medical image acquired at the same angle, and calculating a two-dimension image offset vector; determining the selection range of a three-dimension image offset vector according to the two-dimension image offset vector; determining a final three-dimension image offset vector based on image mutual information between the digital reconstruction ray image and the two-dimension medical image in the range; and taking the three-dimension image offset vector as an offset vector for registration of the two-dimension medical image and a three-dimension medical image. The technical scheme can rapidly and conveniently carry out registration of the two-dimension medical image and the three-dimension medical image, and is particularly accurate in positioning registration of a verification patient.

The embodiment of the invention provides a splicing method and a splicing device of Lidar measurement data. The method mainly comprises the following steps of: carrying out multiple times of data acquisition on the same object in difference positions by utilizing LiDAR so as to acquire multiple point cloud data, carrying out two-to-two paring treatment on the multiple point cloud data, and uniformly segmenting two paired point cloud data to generate multiple segmenting units; selecting multiple feature units from a candidate feature unit set of the two paired point cloud data to form a matched feature unit set; forming a transformation matrix R according to a rotating shaft L and a rotating angle theta, and solving the values of the rotating shaft L and the rotating angle theta according to the principle of minimal error sum of squares of all the matched feature units; transforming all data points in the first point cloud data by virtue of the transformation matrix R and adding the obtained transformation data into the second clod point data to be combined into a complete data set. According to the embodiment of the invention, the feature regions of all the cloud point data and multiple matched feature unit pairs can be accurately and quickly determined based on the working parameters of LiDAE acquisition data, so as to quickly carry out effective splicing on the point cloud data subjected to multiple times of LiDAR sampling.

The invention provides low-temperature-hot-stamped gold-stamped type tipping paper for cigarettes and a preparation method of the tipping paper. The low-temperature-hot-stamped gold-stamped type tipping paper for the cigarettes and the preparation method of the tipping paper are used for overcoming the disadvantages in existing high-temperature hot-stamping that the energy consumption is high, and that the rate of finished products is low and the cold hot-stamping effect is poor. The gold-stamped type tipping paper for the cigarettes, provided by the invention, is prepared through firstly printing environment-friendly alcohol-soluble white ink and printing ink on a base paper layer, then, additionally printing a layer of an adhesion-assisting glue material on the environment-friendly alcohol-soluble ink layer, then, carrying out low-temperature hot-stamping at the temperature of 85-100 DEG C, and carrying out laser boring, slitting and rewinding. According to the low-temperature-hot-stamped gold-stamped type tipping paper for the cigarettes, provided by the invention, an adhesion-assisting layer is additionally printed on the ink layer and has the functions of protecting the ink layer, enhancing the hydrophobicity of the ink layer and improving the adherence with a gold-stamped layer and the fastness of adhering of winding-adhesive glue, and special electrochemical aluminum hot-stamping foil for low-temperature hot-stamping is used in a matched manner, so that a low-temperature hot-stamping procedure can be completed at the temperature of 85-100 DEG C, and the energy consumption of a gold-stamping process is greatly lowered, and the service efficiency of a gold-stamping plate is increased, and thus the cost of gold-stamping is reduced.

The invention discloses a face multimodal image acquisition and processing device and method. The face multimodal image acquisition and processing device comprises a box body; an industrial personal computer main board for processing face images, as well as a visible light camera and an infrared camera which are used for collecting the face images and are electrically connected with the industrialpersonal computer main board are installed in the box body; the visible light camera and the infrared camera are arranged side by side; through holes corresponding to the visible light camera and theinfrared camera are formed in the box body; the industrial personal computer main board comprises a control module; the control module is connected with an image registration module for aligning visible light images collected by the visible light camera with infrared images collected by the infrared camera, a color correction module for normalizing the colors of the collected face images, a faceidentification module for precisely positioning a face region, and a face region segmentation module used for segmenting the face region so as to put the temperature of each area into statistics.

The invention discloses an augmented reality navigation method based on indoor natural scene image deep learning. The method comprises the steps of firstly scanning an indoor natural scene through a three-dimensional laser scanner to extract three-dimensional scene feature recognition points, then calculating an internal reference matrix of a smart phone camera, collecting an indoor natural sceneimage through a smart phone to extract two-dimensional image feature recognition points, and establishing an indoor natural scene topological network structure chart through an indoor planar map; binding and mapping the two-dimensional image feature recognition points, the three-dimensional scene feature recognition points and the topological network path nodes through specific descriptors; carrying out deep learning-based image classification on the indoor natural scene images acquired by the smart phone, and segmenting the indoor natural scene into a plurality of sub-scenes; and then tracking and recovering the three-dimensional scene feature recognition points by using an optical flow tracking algorithm, further synthesizing a three-dimensional registration matrix required by scene registration, and finally finishing virtual navigation object real scene registration and finishing indoor natural scene path navigation.

The invention relates to the digital image processing technical field and discloses an image registration and splicing method of a multi-view camera and a device thereof. The multi-view camera in the invention comprises at least two cameras; the registration method comprises following steps: obtaining multiple time domain continuous synchronous image sets; extracting feature points of the synchronous images in the synchronous image sets and calculating the depth values of the synchronous images; self-adaptively dividing the feature points of the synchronous images into different feature point planes according to the depth values; matching the feature points divided into the same feature point plane, thus obtaining the matched feature points of the feature point planes, building the mapping matrixes of the feature point planes according to the matched feature points; and generating registration parameters based on the multi-dimensional mapping matrixes corresponding to the multiple feature point planes. According to the method and the device of the invention, the multi-dimensional mapping matrixes are built according to the depth information self-adaptively classified feature points; the registration of the multi-view video images are more accurate; and the problems such as irregular image splicing resulted from that single plane mapping cannot give consideration to the relatively higher depth of field problem are solved.

The invention discloses a gradient distribution-based non-rigid medical image registration method. The steps are as follows: (S1) a normalized mutual information similarity measure is constructed; (S2) a gradient distribution distance is constructed; (S3) a non-rigid registration model is created; (S4) the registration model is solved. The gradient distribution-based non-rigid medical image registration method not only utilizes the gray distribution characteristics of images to be registered, but also takes the gradient distribution information of the medical images into consideration, thus effectively fulfilling the non-rigid registration of the medical images. Moreover, preprocessing, such as feature extraction and splitting, does not need to be carried out on the images to be registered, but the joint probability distribution of gray values of two images is utilized to calculate normalized mutual information between the images to be registered, the gradient distribution-based non-rigid medical image registration method also has a good registration effect on medical images with great grayscale difference, and adaptivity and robustness are high.

A method and system for a printing device is disclosed. The method and system comprise printing a test pattern on a print medium and generating a digital image of the printed test pattern by an imaging device. The method and system include analyzing an interference pattern to measure for distortion of the print medium and calibrating the printing device based upon the measured distortion. In a preferred embodiment, the present invention utilizes the reticle patterns, which are printed in the margins of the paper, which are measured real-time during printing. The interference or Moiré patterns created by superimposed reticles may be used to measure image distortion, process direction misalignment, and misregistration caused by web distortion. The advantage of this invention is that image distortion compensation, RIP (Raster Image Processor) parameters, timing, or other printer characteristics may be adjusted on-the-fly in a closed feedback system, for high-speed textile or paper color printing, utilizing on-the-fly distortion or stretch measurement for accurate color and/or duplex images registration. In a duplex printer, automatic images alignment front-to-back is obtained by combining optically or logically the two images for the evaluation of interference patterns and amount of distortion in the process and scan direction.