12results about How to "Achieve registration" patented technology

The invention discloses an image registration method and device, a panoramic stitching method and device, a storage medium and electronic equipment, and relates to the field of computer vision. The method comprises the following steps: acquiring sub-images shot by an unmanned aerial vehicle, wherein the sub-images are from different shooting directions; a preset image adjacency relation table is inquired, adjacent images corresponding to all the sub-images are determined, and the adjacency relation between all the sub-images is recorded in the preset image adjacency relation table; determining a plurality of adjacent image pairs to be matched according to the adjacent images corresponding to the sub-images; performing feature matching on the plurality of adjacent image pairs to obtain feature matching results of the plurality of adjacent image pairs; and performing image registration on the plurality of sub-images according to the plurality of feature matching results. According to the method, the feature matching process of image registration can be optimized, so that the calculation amount can be reduced, and the image registration efficiency can be improved.

The invention discloses a multi-modal image registration method and equipment based on deep learning. The method comprises the following steps: acquiring a 4DCT image and a plurality of other medical images with different modalities; preprocessing the 4DCT image, determining each phase of a respiratory cycle, and calculating the motion range of different organs in the respiratory cycle; the medical image of each of the other modals is preprocessed; selecting an expiration or inspiration image in one respiratory cycle from the medical images of other modalities; carrying out feature extraction on the selected 4DCT image and other medical images of each modal, and extracting feature points of each image; performing registration on different modal image feature points and 4DCT image feature points by using the trained deep learning model; and rendering the registration result. According to the method, the complex relation between different modal image feature points is learned through the deep learning model, a more accurate registration result can be achieved, registration errors are reduced, and cross-modal image registration precision is improved.

This invention relates to the field of image registration technology, specifically to a dynamic monitoring system for pulmonary nodules using dose-dependent CT scans. The invention obtains an edge cluster encompassing all lung images based on the positional distances between corresponding contour points on edge lines in all lung images; it obtains multiple sets of isotopic contour points based on the positional distribution of all contour points in different lung images; it obtains the referenceability of each set of isotopic contour points by considering the positional relationship between each set of isotopic contour points and other sets of isotopic contour points with the same number of angles on the lung images, as well as the fluctuation characteristics of the corresponding angles of each set of isotopic contour points, and selects anchor points; it constructs a relative positional model of the nodule region in each lung image based on the positional distribution of anchor points and nodule regions in each lung image; and it achieves lung image registration for dynamic monitoring of pulmonary nodules. This invention improves the accuracy of dynamic monitoring of pulmonary nodules by flexibly registering the patient's lung images.

The present application relates to a point cloud registration method, device, readable storage medium and program product, the method comprising: obtaining a source point cloud and a target point cloud to be registered; mapping the source point cloud to a first image point set in a pre-shaped space, and mapping the target point cloud to a second image point set in the pre-shaped space; transforming the first image point set based on a transformation matrix to obtain a transformed point set corresponding to the first image point set; measuring the posture difference between the transformed point set and the second image point set to obtain a measurement value; determining a target transformation matrix based on a transformation matrix that meets a preset measurement value condition; and registering the source point cloud to the target point cloud according to the target transformation matrix. The present application can improve the robustness of point cloud registration.

The present invention provides a surgical navigation method, system, medium and electronic device based on DSA images, and the method includes the following steps: Step 1, obtaining the patient's CT angiography data, extracting the vascular structure therefrom, and constructing a 3D vascular model. The present invention significantly reduces the situation of interactive overlap of vascular positions by constructing the preoperative CT angiography data into a 3D vascular model, and aligning it with the DSA image in real time during the operation, thereby avoiding the need for multiple projections, thereby reducing the patient's irradiation dosage, examination time, contrast agent dosage and economic burden, and also reducing equipment loss; by processing the DSA image and predicting the camera parameters through the CNN neural network model, the accuracy and effectiveness problems existing in the registration of two-dimensional images and three-dimensional images are effectively overcome. By simulating the generation and training of DSA images, the CNN model can accurately predict the camera parameters corresponding to the intraoperative DSA image, thereby achieving high-precision image registration and improving the safety and success rate of the operation.

The present invention belongs to the field of visual synthesis technology and moving target tracking technology of optoelectronic systems, and specifically relates to a real-time heterogeneous dynamic map registration method based on template matching and tracking algorithms. The method divides the dynamic registration problem into two parallel tasks, matching and tracking, and realizes the dynamic registration of optoelectronic images and maps through the collaborative constraints of the two. Compared with the prior art, the present invention proposes a real-time heterogeneous dynamic map registration method, which can realize real-time registration of images or videos with map data, has low time complexity, and a processing speed of more than 60fps on a computer. The algorithm is simple and easy to transplant on an embedded platform. The present invention adopts template matching and feature point tracking to dynamically adjust the search area through matching accuracy, which can reduce the search difficulty and time and improve the robustness of the algorithm.

The application discloses a kind of dynamic phase shift interferometry system and method thereof, including first depolarization beam splitter, first depolarization beam splitter side is sequentially spaced with first polarizer, collimating lens, pinhole filter, first attenuator and laser, the other side is sequentially spaced with third polarizer and object, the upside of first depolarization beam splitter is sequentially spaced with second polarizer, second attenuator and first mirror, the downside of first depolarization beam splitter is sequentially spaced with imaging lens, second depolarization beam splitter, polarization grating and second mirror, the side of second depolarization beam splitter is provided with camera;Polarization grating is liquid crystal circular polarization grating, liquid crystal molecule fast axis orientation is periodic continuous gradual change along x direction, overall has λ / 2 phase delay amount.The application can ensure high-precision phase measurement results while meeting the demand of dynamic measurement.

The present invention discloses a registration method based on rib curvature change, comprising: step 1, ultrasonic probe coordinate acquisition, using the position information of the end joint of the mechanical arm to obtain the coordinates of the ultrasonic probe in the mechanical arm coordinate system in real time; step 2, curvature change measurement, in the process of the ultrasonic probe moving along the rib direction, through the curvature sensor or the curvature calculation module, the curvature change of the ultrasonic probe is measured in real time; step 3, rib curvature distribution function analysis, using CT imaging technology to obtain a three-dimensional model of the rib in advance, and calculating the curvature distribution function of the rib along different directions; step 4, scanning section determination, according to the measured ultrasonic probe curvature change and the rib curvature distribution function, determine the specific rib section to be scanned; step 5, coordinate system registration, using the rib section information obtained by scanning to perform registration with the rib model in the CT coordinate system, so as to achieve high-precision registration between the mechanical arm coordinate system and the CT coordinate system.

The invention provides a time-space domain combined space detection image dark and weak target detection method and system. The method comprises the following steps: slicing an original space target detection image; key points are extracted from each image slice; constructing topological space description features of the key points, and performing inter-frame registration of adjacent frame images; calculating the inter-frame difference of adjacent frames after registration; the inter-frame difference results are superposed; space target training and detection are carried out through a Yolov5 deep learning network; and screening and combining the detection results, and outputting a final detection result. According to the method, the fixed star residual error after inter-frame difference is effectively reduced under the condition of a relatively large detection field of view, the detection performance of a detected image space target is improved, and the method has universality for working modes of staring targets and staring fixed stars in space detection.

The present invention relates to a method and apparatus for the adhesive fixation of battery covers and protective plies, comprising: a protective ply placement step in which all discrete protective plies for one battery cover are picked up together from a pick-up position by a first single robotic arm and transferred together and placed on corresponding receiving tables of a support tool; a protective layer sheet alignment step in which the movable stopper is actuated to move from the rest position to the stop position; a protective layer sheet gluing step, wherein the upper surface of the protective layer sheet placed on the receiving table top is sprayed with a binder by a borne spraying device through a second single robot arm; a battery cover body pressing step: transferring and placing the received battery cover body on a supporting tool on which the glued protective layer sheet is placed, and actuating a movable tool to move from the upper part to the supporting tool and apply pressure to the upper surface of the battery cover body, and the lower surface of the battery cover body and the upper surfaces of the plurality of protective layer sheets are contacted together and are bonded and fixed.

The invention discloses a visible light image-thermal infrared image matching method and system for rice phenotypes. The method comprises the following steps: acquiring a plurality of visible light images and thermal infrared images of rice; determining fuzzy areas and non-mask areas of the visible light image and the thermal infrared image; extracting feature points and descriptors of a non-mask area, obtaining matched feature point pairs on the visible light image and the thermal infrared image, and connecting the matched feature point pairs to obtain a connecting line; screening out connecting lines which simultaneously meet the length and angle threshold intervals of the connecting lines; according to fitting points of the feature points of the visible light image and the thermal infrared image mapped to the visible light image after passing through a homography matrix, generating a residual error to screen the feature points of the visible light image close to a correct position; and finally, connecting the feature points on the visible light image with the corresponding feature points on the thermal infrared image to obtain a connecting line which is a final matching result. According to the invention, the problem of mismatching caused by blurring of a part of thermal infrared images due to insufficient illumination can be avoided.

The present invention application provides a method, device, terminal and medium for registration of a three-dimensional model of a guide plate and a structure of a maxillary sinus. The method includes: obtaining the three-dimensional model of the guide plate and the scanning data of the structure of the maxillary sinus; extracting the curvature distribution; densely sampling the area where the curvature is greater than a threshold, and sparsely sampling the area where the curvature is less than or equal to the threshold, to obtain a feature point set; extracting local geometric information and local texture features to obtain a composite feature vector; and performing feature matching using the first composite feature vector and the second composite feature vector to obtain a registration result. The present invention application samples the three-dimensional model of the guide plate and the scanning data of the structure of the maxillary sinus, respectively, to obtain a feature point set, extracts local geometric information and local texture features, and then obtains a registration result using the obtained composite feature vector. The composite feature vector contains comprehensive information from geometric morphology to texture changes, realizes registration at details, and effectively improves the registration accuracy.