58 results about "Image registration algorithm" patented technology

The invention relates to the technical field of historical building protection, and discloses an intelligent identification and diagnosis method for historical building brick wall surface damage, which breaks through the limitations of low efficiency, strong subjectivity and easy detail omission of traditional manual exploration by fusing unmanned aerial vehicle high-precision image acquisition, deep learning semantic segmentation and multi-modal feature analysis technologies. And automatic rapid positioning and accurate classification of large-range wall surface damage are realized. Environmental distortion is eliminated by using a self-adaptive image registration algorithm, fine texture features are extracted in combination with a damage probability prediction model, and complex damage forms such as salting-out crystallization, plant root erosion and weathering spalling are effectively distinguished; through three-dimensional space clustering and visual marking technologies, the damage distribution density and the evolution trend are visually presented, and a reliable basis is provided for scientifically formulating a grading repair strategy. Besides, through establishment of a damage database and iterative optimization of an intelligent diagnosis model, the building health condition can be tracked for a long time, and technical support is provided for preventive protection and sustainable management of cultural heritage.

The invention relates to the technical field of computer vision, and discloses a jade defect intelligent detection method and system based on machine vision and deep learning, and the method comprises the following steps: S1, based on a high-resolution industrial camera and a laser three-dimensional scanner, adopting a multi-mode synchronous collection strategy, and rotating a jade sample through a precise motion control system, a jade surface high-resolution two-dimensional color image and high-precision three-dimensional point cloud data are respectively obtained, and a jade multi-mode original data set is generated. A high-resolution two-dimensional color image and high-precision three-dimensional point cloud data are integrated through a multi-modal synchronous acquisition strategy, and multi-dimensional feature expression under unified coordinates is constructed, so that the limitation of a single data source is effectively overcome; an image registration algorithm and a feature pyramid network are combined with a point cloud network to perform multi-modal feature fusion, complementarity of color texture and geometric morphology information is enhanced, and image quality is optimized based on adaptive histogram equalization and non-local mean filtering.

Systems, devices, and methods are disclosed to correct aimpoint of a system of a weapon and affixed digital weapon sight. The method employs the components of a digital weapon sight configured together for a process of sensing of a ballistic event, storing of digital imagery data before and after a shot or series of shots, and then the performing of an image registration algorithm, via a cross-correlation type function. The image registration determines the misalignment between the images as a Cartesian shift, and aimpoint of subsequent shooting is corrected through application of adjusted reticle symbology or adjusted image sensor windowing. Preprocessing methods for enhancing image registration algorithm accuracy are presented.

The invention relates to a multi-modal registration method and device based on medical images, and the method comprises the steps: obtaining a brain registration data set, and dividing the brain registration data set into a training set and a test set; and constructing a registration network based on a UNet network structure. The method comprises the following steps: selecting an input image, inputting the input image into a dual framework, performing bidirectional primary registration on the input image to obtain forward and reverse deformation fields and a primary registration image, and applying the dual two-party exchange deformation field to the primary registration image to perform secondary registration to obtain a secondary registration image. And calling a Laplace operator to extract structural features from the input image, the primary registration image and the secondary registration image, and constraining the registration network through structural similarity measurement. And training an end-to-end unsupervised image registration algorithm through the training set and the test set, and optimizing the algorithm according to loss constraints. And inputting a to-be-detected registration image into the registration network, applying the optimal model weight, outputting a registration result, and ensuring the uniformity and accuracy of the result.

The invention discloses an automatic system for packaging substrate detection, and relates to the technical field of data encryption, and the system comprises a data collection module which is used for collecting multi-view image data and carrying out the preprocessing of the multi-view image data; the feature extraction module is used for performing feature extraction on the preprocessed multi-view image data; the feature map fusion module is used for carrying out registration fusion on the feature maps through an image registration algorithm based on the extracted feature maps to form a three-dimensional feature map of the substrate; the defect probability prediction module is used for constructing a defect identification model and predicting the defect probability of the substrate based on the three-dimensional feature map of the substrate; and the defect grade evaluation module is used for predicting a substrate defect degree score according to the substrate defect probability, evaluating a substrate defect grade according to the substrate defect degree score, and generating a substrate detection report. According to the method, intelligent identification and evaluation of multiple defect types are realized, and the detection precision and the automation level are remarkably improved.

The invention discloses a power line identification method, device and equipment based on image fusion and a medium, and the method comprises the steps: obtaining an infrared image and a visible light image of a power line of a power distribution network, and carrying out the registration of the infrared image and the visible light image through a preset image registration algorithm, and generating a first image; wherein the infrared image and the visible light image are derived from the same picture; performing feature extraction and feature fusion on the first image and the visible light image through a preset image fusion algorithm to generate a second image; and performing power line identification on the second image through a preset power line identification algorithm. According to the method, the infrared image and the visible light image which are derived from the same power line picture are fused to obtain the fused image which contains more source information and has more obvious power line characteristics, so that power line recognition is performed, the difficulty of power line recognition is greatly reduced, and the accuracy of power line recognition of the power distribution network is further improved.

The application relates to an airplane change detection method based on a deep learning and an image registration algorithm, and the method comprises the following steps: acquiring a first remote sensing image and a second remote sensing image of the same region at different time points; performing airport detection on the first remote sensing image and the second remote sensing image to obtain an image of a first airport region in the first remote sensing image, a first offset of the first airport region, an image of a second airport region in the second remote sensing image and a second offset of the second airport region; performing image registration on the image of the first airport region and the image of the second airport region according to a surf image registration algorithm to obtain a registration image; performing airplane detection on the registration image to obtain an airplane target; performing change detection on the result obtained by the airplane detection; and restoring a target frame corresponding to the airplane target to the first remote sensing image and the second remote sensing image. The application can solve the problems of low detection precision, slow detection process running speed and large hardware resource occupation in the prior art.

Systems and methods are disclosed to correct aimpoint of digital weapon sight. The method employs the components of a digital weapon sight configured together for a process of sensing of a ballistic event, storing of orientation data and digital imagery data before and after a shot or series of shots, and then performing an image registration algorithm using the imagery data stored. The image registration determines the translational offset between the images, and aimpoint of subsequent shooting is corrected through application of adjusted reticle symbology or adjusted image sensor windowing.

The invention provides a temporal-mandibular joint deflection determination method and system based on deep learning, and the method comprises the steps: obtaining a multi-view two-dimensional image and surface scanning data of a user; performing three-dimensional reconstruction on the multi-view two-dimensional image of the user by adopting a preset multi-view photo reconstruction algorithm, and determining a three-dimensional face model of the user; adopting a preset point cloud feature extraction network to determine a three-dimensional face model of the user and key feature points of the face scanning data; inputting the three-dimensional face model of the user and the key feature points of the face scanning data into a preset multi-modal image registration algorithm, and determining multi-modal data of the same three-dimensional space; inputting the multi-modal data into a preset deep neural network for diagnosis, and determining a diagnosis result of the user; and according to the multi-modal data, determining a facial index of temporal-mandibular joint deflection corresponding to the user. According to the method and the device, early screening of temporomandibular joint deflection is realized by adopting the two-dimensional image, the data acquisition cost is reduced, and the efficiency and the precision of medical diagnosis are improved.

The present description relates to an image sequence motion correction method and apparatus based on intensity correction optical flow registration. The method comprises: determining a reference image of each deformed image in a deformed-image sequence, and performing motion correction on the deformed image by means of adjusting the weight of a mechanical regularization term between the reference image and the deformed image, so as to obtain a displacement field of the deformed image relative to the reference image; on the basis of the displacement field and an intensity correction value of a finite element node, performing intensity correction on the reference image; adjusting the weight of the mechanical regularization term, performing motion correction on the deformed image, performing intensity correction on a first corrected reference image on the basis of an optimized displacement field, repeatedly executing the process until an image residual function converges, determining that the deformed image has been corrected, and recording the optimal solution of a weight value of the mechanical regularization term of the deformed image; and on the basis of the optimal solution of the weight value, determining the actual displacement of the deformed image. In the present description, the mechanical model behind physiological motion and an intensity correction technique are integrated into an image registration algorithm to reduce image noise, thereby improving the algorithm accuracy.

The invention discloses an engineering building deformation monitoring method and system, and the method comprises the steps: obtaining a texture target image on a building, carrying out the preprocessing of the texture target image through employing a self-adaptive illumination compensation algorithm, and adjusting the brightness and contrast of the texture target image if the illumination change is detected, and obtaining a first image; performing denoising processing on the first image, removing noise in the first image by using a Gaussian filtering algorithm, and if rain and fog weather is detected, enhancing the definition of the first image by using a haze removal algorithm to obtain a second image; and carrying out displacement calculation on the fifth image, calculating the displacement amount of the feature points in the fifth image by adopting an optical flow method, and if image drift is detected, correcting the position of the fifth image by using an image registration algorithm to obtain the final deformation displacement amount of the building.

The invention relates to the technical field of textile double-sided printing, in particular to a high-permeability and double-sided positioning printing method for all-cotton towel products, which comprises the following steps: pre-treating all-cotton towel gray cloth, including desizing, scouring and bleaching procedures; padding the treated gray cloth in slurry containing urea, sodium bicarbonate, anhydrous sodium sulphate and a penetrant, and then drying and sizing; printing on the front surface of the towel by adopting a digital printing machine, and spraying a penetrating agent with the surface tension of 25-35mN / m to a printing area through an independent jet printing channel, so as to promote the dye to fully permeate to the back surface of the fabric and form a clear pattern outline; according to the invention, an image acquisition system composed of an industrial camera, an annular LED coaxial light source and a polarization filter captures fabric back pattern contour features in real time, and generates a translation, rotation and zooming transformation matrix based on an image registration algorithm; in combination with closed-loop feedback control of the digital printing machine, the positioning precision is improved by more than 75% compared with a traditional method.

The invention discloses a cutting path planning method and system for ultrasonic knife equipment, and relates to the technical field of medical treatment. The invention discloses a cutting path planning system of ultrasonic knife equipment. The cutting path planning system comprises a cutting path planning module and a cutting path calibration module, according to the method, image recognition is carried out by inputting the cut image annotation model, the cut object feature map is obtained, and the improved space trajectory planning algorithm and the image registration algorithm are utilized, so that the initial cutting path can be efficiently predicted and optimized, and the accuracy of the cutting path is ensured; according to the method, the image of the simulated cutting object is registered, analysis is carried out based on the cutting error judgment model, potential cutting errors can be recognized before an operation, a cutting path is adjusted in advance, and therefore the influence caused by the errors is reduced. And the initial cutting path is updated by using the error judgment result, so that the path deviation caused by the error is effectively prevented.

The present invention discloses a deep learning SAR image registration algorithm based on a dual transformation network, which mainly solves the problems of difficult acquisition of matching image pairs, low matching accuracy, too high cost of manually labeled data sets and class imbalance in existing deep learning SAR registration methods. The implementation scheme is as follows: 1) Generate training and test data sets. 2) Set the number of categories of the classification head of the deep image classification network and construct two branches of the dual transformation network; 3) Train the two branches of the dual transformation network and perform preliminary matching using the trained dual transformation network, 4) Perform fine matching on the basis of the preliminary matching; 5) Take the point pairs jointly recognized by the two branches and update the point pairs according to the results of the fine matching to obtain the final matching result. The present invention is simple in obtaining image pairs and does not require manual annotation, the data set has balanced categories, and has high matching accuracy, and can be used for geological mineral resource detection and digital terrain model extraction.

The application provides a pinhole image splicing true value acquisition and splicing method based on a heterogeneous camera combination. The acquisition method first symmetrically installs two pinhole cameras on a support, and installs an fisheye camera between the two pinhole cameras. Based on a double spherical camera model, the three cameras are calibrated to obtain the internal parameters and external parameters of the three cameras. The left eye pinhole view, the right eye pinhole view and the middle eye fisheye view of the target scene are simultaneously acquired by using the three cameras. The middle eye fisheye view is subjected to equirectangular projection. According to the internal parameters and external parameters of the three cameras, the left eye pinhole view and the right eye pinhole view are projected to the equirectangular projection view plane respectively, multi-camera coordinate system one is completed, and the splicing true value is obtained. The application has the core advantages of the hardware structure design and the heterogeneous camera image registration algorithm, can stably acquire images without seams and time sequence consistency, and provides strong support for the true value reference of the precision verification and model training of subsequent panoramic video splicing.

Some embodiments of the present disclosure provide a method, device and computer readable medium for identifying an analog instrument, the method comprising: inputting a first instrument panel image to be tested into a first neural network model, and outputting the first instrument panel image; extracting feature points of the first instrument panel image, and performing feature point registration on the first instrument panel and a standard instrument panel based on an image registration algorithm, and outputting a second instrument panel image after registration; inputting the second instrument panel image into a second neural network model, and outputting pointer position information on the second instrument panel image; and calculating a reading of the analog instrument based on the pointer position information. Embodiments of the present disclosure achieve identification and reading of the analog instrument based on an improved neural network model.

This invention discloses a multimodal image real-time registration and fusion system and method for cardiac interventional surgery, comprising: a multimodal image acquisition module, an image data transmission module, an intraoperative twin image registration and analysis platform, an algorithm calculation module, a parameter adjustment module, and an image fusion output module. After acquiring image data, the multimodal image acquisition module sends it to the intraoperative twin image registration and analysis platform via the image data transmission module. The platform incorporates a cardiac deformation adaptive optical flow algorithm, a multi-resolution hierarchical mapping algorithm, and a large-deformation cardiac image registration algorithm. The algorithm calculation module performs registration calculations, and the parameter adjustment module optimizes the fusion parameters based on the calculation results. Finally, the image fusion output module generates and outputs the fused image. This invention achieves real-time and accurate multimodal image registration and fusion, providing reliable image support for cardiac interventional surgery and improving surgical accuracy and safety.

The invention relates to the field of image recognition, in particular to an in-transit transportation abnormity intelligent early warning system for an intelligent supply chain. The visual information acquisition module is used for acquiring land visual representation, vehicle motion time sequence signals, operation flow time sequence and intersection point visual representation; the morphological correlation model construction module is used for outputting seaport scene visual representation through semantic segmentation; outputting a sea-land intersection point form correlation model through an image registration algorithm; the event attribution module is used for adding the vehicle motion time sequence signal and the sea transportation environment data to the sea-land intersection point form correlation model to obtain sea-land visual time sequence representation; performing feature analysis to obtain attribution judgment; generating a transportation event attribution heat map through a feature attribution algorithm; and the risk judgment module is used for generating an early warning signal when the cause is judged to be damage and the visual activation degree is lower than a threshold value. According to the method, end-to-end multi-dimensional coupling from geometric modeling to space-time attribution to risk decision is carried out, so that the logicality and credibility during damage distinguishing are improved.

The invention relates to the field of medical image processing, and aims to provide a DSA image registration method fusing moving target features. Comprising the steps that a DSA image registration model fusing blood vessel information is established, and the model comprises a similarity measurement item, a regularization item of a displacement field and a regularization item of the blood vessel information; taking the DSA angiography image and the background image as the input of a model, and discretizing on a node grid; discretizing the model by using a difference operator to obtain an optimization model; decomposing and optimizing the model through an alternating direction algorithm, iteratively solving a displacement field and updating blood vessel information, and outputting a DSA subtraction image after a stop condition is met. The registration model provided by the invention can effectively cope with artifacts caused by rigid and non-rigid image deformation, more accurately estimate a displacement field, extract a vascular structure and improve the image registration accuracy; the alternating direction algorithm framework enables the solution of the displacement field to utilize the newest image registration algorithm, so that the optimization problem of blood vessel image updating has a closed-form solution, and the solution can be efficiently solved.

The invention relates to the technical field of industrial machine vision detection, in particular to an intelligent grading and feedback system based on image recognition. Comprising a multi-modal image acquisition unit used for synchronously acquiring a visible light image, an infrared thermal imaging image and a hyperspectral image of a target object; the dynamic self-adaptive preprocessing unit is in communication connection with the multi-modal image acquisition unit, performs combined preprocessing on the acquired multi-modal image, and comprises a dynamic noise reduction algorithm based on target edge features, a self-adaptive contrast enhancement algorithm and a multi-modal image registration algorithm; and the closed-loop feedback unit is respectively in communication connection with the multi-modal image acquisition unit and the multi-dimensional dynamic threshold grading unit. Through multi-modal image acquisition and attention-multi-scale feature fusion design, the limitation of traditional single-modal detection is effectively broken through, the recognition capability of micro bubbles and hidden cracks of the quartz crucible is remarkably improved, surface stains and internal impurities are accurately distinguished, and the problem of subjective difference of manual visual detection is solved.

The invention relates to the technical field of biological imaging, and discloses a macromolecular morphology restoration method based on microscopic imaging, which can achieve accurate restoration of macromolecular morphology more simply and conveniently. The method comprises the following steps: generating a grey-scale map according to atomic force microscopic imaging data, wherein the grey-scale map comprises a plurality of macromolecules; applying a migration model to the grey-scale map, performing image detection, extracting an image of macromolecular single particles, filtering defective particles, and retaining conventional particles; wherein the migration model is obtained based on a segmentation model by training data sets in different view ranges to perform multiple rounds of learning; and aligning the images of the conventional particles through an image registration algorithm and averaging to obtain a macromolecule morphology restored image.

A mosaic dislocation repair method and device based on a high-precision image registration algorithm and a medium. It belongs to the technical field of satellite remote sensing, and specifically relates to the technical field of image mosaic dislocation repair. The method comprises the following steps: S1, inputting the dislocated area in the mosaic process in the form of vector data, determining the area to be repaired, and obtaining the local area image to be registered; S2, performing feature point matching on the local area image to be registered; S3, adding fixed points to the buffer area outside the area to be repaired; S4, transforming the local area image to be registered through a thin plate spline function to obtain a final registration image; and S5, replacing the final registration image into the original image for re-mosaic. The method is suitable for dislocation repair requirements in different scenes, significantly reduces the manual repair cost while improving the image product quality, and has important practical value.

The invention relates to the field of railway assistance, in particular to a railway line information acquisition device and method based on deep learning, and the device comprises a motion structure which comprises a small rail car which is a core bearing part of the device and is internally integrated with an intelligent acquisition module to realize data acquisition, processing and storage, and an information acquisition component which is used for acquiring information of the small rail car. Data acquired by the information acquisition component are uploaded to the data processing system through an RTSP protocol, real-time video streams of all the cameras are received, timestamp marking is carried out on the acquired data, and time sequence synchronism of data of different visual angles is ensured. And performing preprocessing steps of distortion removal, geometric correction and the like, and performing feature matching and alignment by using an image registration algorithm. A complete track section image is generated based on an image splicing technology, and a trackside three-dimensional reconstruction model is generated in combination with 3D point cloud data.

The present application relates to a medical image-based multi-modal registration method and device, the method comprising: obtaining a brain registration dataset and dividing it into a training set and a test set. A registration network is constructed based on a UNet network structure. An input image is selected and input into a dual architecture. The input image is subjected to one-way registration in both directions to obtain forward and reverse deformation fields and a one-way registration image. The deformation fields of the two dual parties are exchanged and applied to the one-way registration image for secondary registration to obtain a secondary registration image. A Laplace operator is called to extract structural features from the input image, the one-way registration image and the secondary registration image, respectively, and the registration network is constrained by structural similarity measurement. An end-to-end unsupervised image registration algorithm is trained by the training set and the test set, and is optimized according to the loss constraint. The registration image to be detected is input into the registration network, the optimal model weight is applied, and the registration result is output to ensure the uniformity and accuracy of the result.

The application provides a kind of measurement method, device and system, the method includes: the initial function of the outgoing wave of the first part and the second part of the object to be measured is obtained respectively, at least once the i iteration is executed respectively, in each iteration: by reciprocating propagation between object plane, modulator plane and detector plane to the outgoing wave of the i part, and the amplitude of the outgoing wave of the i part is constrained according to the actual diffraction intensity of the outgoing wave of the i part in the detector plane;Obtain the reconstruction function of the outgoing wave of the i part on the object plane;According to the reconstruction function of the outgoing wave of the first part and the second part, the displacement vector between the first part and the second part is calculated using image registration algorithm.The application can obtain the relative displacement of scanning position without positioning system, further, the relative displacement can also be used to complete diffraction imaging.

The present invention discloses a cutting path planning method and system for an ultrasonic scalpel device, and relates to the field of medical technology. A cutting path planning system for an ultrasonic scalpel device includes: a cutting path planning module and a cutting path calibration module. The present invention performs image recognition by inputting a cutting image annotation model to obtain a cutting object feature map, and utilizes an improved spatial trajectory planning algorithm and image registration algorithm to efficiently predict and optimize the initial cutting path and ensure the accuracy of the cutting path; by registering the simulated cutting object image and analyzing it based on a cutting error judgment model, potential cutting errors can be identified before surgery, and the cutting path can be adjusted in advance, thereby reducing the impact of the error. The initial cutting path is updated using the error judgment result, effectively preventing path deviations caused by errors.

The invention belongs to the technical field of medical image registration, and relates to an algorithm based on dynamic programming, which is suitable for registration of brain three-dimensional images. The method comprises the following steps: firstly, calculating the maximum similarity between a three-dimensional brain image to be registered and a template image by adopting a dynamic programming algorithm, and obtaining an index matrix of the maximum similarity; and then converting the to-be-registered image to the structural framework of the template image based on the index matrix. And finally, respectively generating a registration image from the X-axis direction, the Y-axis direction and the Z-axis direction, and taking the average value of the three images as a final registration image. According to the method, image information of the whole row and the whole column is comprehensively considered, and the problems of many registration parameters, long training time and large GPU resource consumption of an image registration algorithm based on deep learning are solved.

A visible-light SAR image registration algorithm based on OS-SIFT computes the consistent gradient of the SAR image, the gradient magnitude image of the visible image, and the consistent gradient for each visible-light SAR image pair. Two Harris scale spaces are then constructed, and local maxima are searched in each Harris scale space to detect repeatable keypoints. Gradient position and orientation histogram descriptors are extracted from multiple image blocks to improve image saliency. Keypoint pairs are obtained using the NNDR method and further filtered using FSC. More accurate keypoint pairs are then filtered using translation, scale, and orientation constraints. FSC is then used again to remove outliers and identify the correct matching pairs. Finally, the transformation parameters between the SAR and visible images are calculated to register the visible-light SAR image pairs.

The invention discloses a pathological section diagnosis area marking and archiving method, which comprises the following steps: acquiring multi-temporal pathological section image data of a target tissue area, the multi-temporal pathological section image data comprising section images of the target tissue area collected at different time points; based on the multi-temporal pathological section image data, constructing a cable pipeline topology network in the target organization area through an image registration algorithm and a topology refinement algorithm; for the pathological section image data of each time phase, identifying an abnormal diagnosis area in the pathological section image data through an image identification algorithm; calculating geometric topological relation data between the spatial position of the abnormal diagnosis area identified in each time phase and the nearest branch node in the cable pipeline topological network; and based on the geometric topological relation data, generating fault source coordinate data in one-to-one correspondence with the abnormal diagnosis areas, and storing the fault source coordinate data into a diagnosis area coordinate database.

This invention discloses a multi-directional differential phase reconstruction method. For synchronous phase-shifted transverse shearing interferograms in two directions, a phase-correlated image registration algorithm is used to match the positions of the shearing interferograms in both directions. A four-step phase-shifting algorithm is used to obtain the wrapped phase in both directions. An optimized DCT-based least-squares phase unwrapping algorithm is used to unwrap the wrapped phase. The shearing amount of the shearing interferogram is calculated through edge detection and fitting. The wavefront to be measured is reconstructed using a least-squares method based on differential Zernike polynomials. An anti-tilt algorithm eliminates the introduced tilt error, completing the differential phase reconstruction. This invention utilizes an optimized unwrapping algorithm to overcome the unwrapping failure problem caused by noise, making the unfolded phase smoother, more continuous, and closer to the true phase. Furthermore, data is processed in the circular domain, eliminating the need for Zernike polynomial orthogonalization. This invention can be applied to processing multi-directional transverse shearing interferometry.