733 results about "Point pair" patented technology

Disclosed in the present invention is a method for repairing an RPC of a remote-sensing image. The method comprises: S1, acquiring information such as an image to be repaired and a reference image; S2, performing feature extraction and matching on the image to be repaired and the reference image by using an SIFT algorithm, so as to obtain a matching point pair and corresponding first pixel coordinates; S3, acquiring longitude and latitude coordinates; S4, acquiring geodetic coordinates and a control point; S5, constructing an RFM model, performing RPC positive calculation on an original RPC parameter of the image to be repaired and the geodetic coordinates, so as to obtain corresponding second pixel coordinates of the geodetic coordinates on a remote-sensing image, and separately calculating a mean value of error distances between corresponding pixel coordinates; S6, introducing a constraint condition by using an L1 regularization optimization method, so as to obtain an optimized RFM model; and S7, performing determination according to the mean value of the error distances and a preset threshold value, and selecting different repair policies to recalculate or correct the RPC parameter. In the present invention, an RFM model is optimized by using an L1 regularization method, and different repair policies are selected to perform correction or estimation on an RPC parameter, thereby improving the geometric positioning precision of a satellite image.

The invention relates to an image processing technology, and discloses an efficient panoramic image splicing method and system based on multi-view fusion, and the method comprises the steps: collecting a plurality of images from different views; performing multi-scale feature extraction on each image, generating a feature descriptor for each extracted feature point, and matching a corresponding feature point pair; performing multi-view geometric constraint screening on the feature point pairs; according to the screened feature point pairs, estimating a homography matrix between adjacent images, and carrying out global optimization on the homography matrix; aligning all the images into the same coordinate system; determining an overlapping region between adjacent images; and according to the pixel information in the overlapping areas, fusing the overlapping areas by adopting a self-adaptive weighted fusion algorithm so as to splice the plurality of images into a panoramic image. The invention further discloses a control device and a computer readable storage medium. The invention aims to improve the efficiency and accuracy of generating the multi-view fused panoramic image.

The invention provides a camera extrinsic parameter calibration method, an image stitching method and an apparatus thereof. The calibration method can include: acquiring a plurality of images captured by the camera based on a plurality of sets of extrinsic parameters to be calibrated, wherein each of the plurality of sets of extrinsic parameters to be calibrated include a horizontal rotation angle and a vertical rotation angle; obtaining at least one matched image pair based on feature point matching among the plurality of images, wherein each matched image pair includes matched feature point pairs with a quantity satisfying a threshold condition; and calibrating the plurality of sets of extrinsic parameters to be calibrated according to a first difference representation between coordinate representations of each matched feature point pair of each matched image pair in a reference coordinate system.

The invention discloses a three-dimensional point cloud registration method for image pre-registration and multi-criterion mismatching suppression, which relates to the technical field of point cloud registration, and comprises the following steps of: firstly, enhancing surface texture information of a to-be-measured object by using a projection speckle image to perform data acquisition, and then positioning an optimal registration area of the to-be-registered image by using an image partitioning and template matching algorithm, image pre-registration is realized by performing feature point detection and registration on the region, and adverse effects caused by the non-overlapping region of the to-be-registered image are inhibited; thirdly, according to the coordinate transformation relation, obtaining corresponding three-dimensional matching point pairs through the two-dimensional matching point pairs obtained through image pre-registration, and completing point cloud coarse registration; and finally, adopting a classic ICP algorithm to realize point cloud precise registration. In order to improve the precision and efficiency of registration, multiple error matching suppression strategies are integrated in the stages of image pre-registration and point cloud coarse registration. According to the method, high-efficiency and high-precision registration of the point clouds which are limited in overlapping rate and lack of features can be realized.

The invention discloses a cross-source data three-dimensional reconstruction method and system based on improved Gaussian sputtering, and the method comprises the steps: collecting an unmanned plane inclined image and a ground panoramic image of a target region, and constructing a time-space correlation data set; based on multi-view geometric constraints, space-time coding matching point pairs are established through an adaptive feature pyramid, intelligent incremental cross-source data sparse reconstruction is carried out, and point cloud and camera parameters are output; adopting improved Gaussian sputtering, compressing a three-dimensional Gaussian kernel into a two-dimensional Gaussian primitive through double tangent vector constraint, and fitting surface geometry to realize multi-scale reconstruction; and optimizing primitive parameters by using a differentiatable renderer, completing multi-scale fine reconstruction through gradient back propagation, and generating a high-precision three-dimensional model. According to the method, multi-scale accurate geometric prior input and accurate camera poses are provided for three-dimensional reconstruction, the dependence on professional manual operation in a traditional three-dimensional reconstruction method is greatly reduced, and meanwhile, the geometric accuracy and visual fidelity of a reconstruction result are remarkably improved.

The invention discloses a slope deformation monitoring method and system, a medium and equipment, and relates to the field of slope deformation monitoring, and the method comprises the steps: obtaining a slope image sequence with a fixed time interval; extracting features of the first image, tracking the features of the first image in the to-be-detected image by using a Lucas-Kanade optical flow method, estimating a view field translation amount and a rotation angle of the to-be-detected image relative to the first image, and performing view field motion correction on the to-be-detected image; performing semantic segmentation on the first image and the corrected to-be-detected image to obtain an image pair with a slope region mask; obtaining a feature point matching set of the image pair based on LoFTR; performing feature point mismatching elimination on the feature point matching set by using a two-stage mismatching elimination method to obtain a matching point pair set M [beta]; and calculating the displacement of each point pair in the M [beta], and obtaining a sub-pixel-level slope deformation field through Gaussian interpolation. The scheme is low in cost, small in calculation amount and high in precision.

The invention discloses an image feature matching optimization method based on intra-class space consistency in the technical field of computer vision and image processing. The method comprises the following steps: feature point extraction and preliminary matching: extracting feature points from a query image and a reference image and performing preliminary matching; initialization and transformation model estimation: initializing a matching point set and a residual error, and calculating an initial transformation model; error calculation and matching point set updating: calculating the error of the matching point pair, and updating the matching point set by adopting a dynamic screening method; performing residual optimization: judging whether the optimal condition is reached or not based on the residual, and deciding whether to continue iteration or not; performing intra-class space consistency clustering and isolated cluster elimination: performing clustering analysis after the optimal residual error is obtained, and eliminating isolated clusters based on an intra-class space consistency separation ion structure; and outputting a result: outputting a matching point set after the isolated clusters are removed. The method solves the problem that a traditional feature matching method is difficult to completely remove mismatching in a complex scene and is sensitive to noise.

Provided are a multimodal image matching method and system, terminal device, and storage medium. The method includes: performing self-supervised feature extraction on an optical image and a synthetic aperture radar (SAR) image to obtain a repetitive feature point between the optical image and the SAR image; segmenting the optical image and the SAR image into a first image block sequence based on the repetitive feature point, and performing feature extraction on the first image block sequence through a dual-branch network to obtain feature description vectors of the optical image and the SAR image respectively, where the dual-branch network includes a first branch network for extracting a global feature and a second branch network for extracting a local feature; and performing feature matching on the optical image and the SAR image based on the feature description vectors to obtain a matching point pair between the optical image and the SAR image.

The invention relates to the technical field of image processing, and provides an OCT (Optical Coherence Tomography) image splicing method, which comprises the following steps: acquiring image pairs and matching point pairs corresponding to the image pairs, the image pairs being adjacent OCT images; calculating a homography matrix based on the matching point pairs so as to align the image pairs, and outputting preliminary aligned image pairs; constructing a fusion weight map, wherein the fusion weight map comprises a weight value of a pixel position and a region type; and according to the weight value and the region type, carrying out fusion splicing on the pixel positions so as to output a panoramic OCT image. According to the method, partition fusion is achieved by fusing the weight map, the problems of tissue dislocation and artifacts in OCT splicing are solved, and then the problem that the splicing effect of OCT image splicing is poor is solved.

The invention provides a coal mine underground point cloud accurate registration method based on dynamic weight combination, and relates to the technical field of point cloud registration, and the method comprises the steps: constructing an initial point pair set; calculating a point pair distance weight by adopting a Gaussian kernel function; calculating the shape feature weight of the point pair based on the BSC descriptor; based on the point pair distance weight and the point pair shape feature weight, constructing a point pair reliability weight dynamic combination model, and screening high-reliability point pairs from the initial point pair set; and on the basis of the screened high-reliability point pairs, optimal rigid body transformation is calculated, and point cloud accurate registration is realized. According to the invention, based on the double-weight dynamic combination model of the Gaussian kernel function and the BSC descriptor, the reliability of the point pair is accurately evaluated, and the influence of noise and local feature degradation is effectively inhibited. The adaptive weight adjustment strategy dynamically adjusts the distance weight and the shape feature weight in different registration stages, and optimizes the registration process. And an efficient point pair screening and optimization mechanism is combined with KD-tree accelerated search and Gaussian Newton method optimization, so that the registration speed and precision are improved.

The invention discloses a pose estimation method and device based on point pair feature matching, a medium and a product. The method comprises the following steps: performing coarse registration on a fusion scene point cloud and each template point cloud, and calculating point pair features; according to the corresponding hash key values, retrieving from each hash table to establish registration point pairs; calculating a translation vector and a rotation quaternion matched with each registration point pair according to the reference point coordinate system and the template coordinate system, and performing clustering processing on each registration point pair to obtain each initial corresponding set; screening out a target pose candidate transformation matrix and a matched target template point cloud from the pose candidate transformation matrixes matched with the initial corresponding sets respectively; a target optimization function between the fusion scene point cloud and the target template point cloud is constructed, iterative optimization is performed on parameters in the target pose candidate transformation matrix, and the target pose of the fusion scene point cloud is obtained at the end of iteration, so that the precision, real-time performance and reliability of six-dimensional pose estimation are improved.

The invention relates to the technical field of camera measurement, and discloses a target positioning method and device, computer equipment and a storage medium, and the method comprises the steps: determining a model point and candidate feature points corresponding to a target point on a current frame image; determining a reference feature point according to the distance between the model point and the candidate feature point; determining matching point pairs according to the reference feature points; constructing a similar transformation matrix according to the matching point pairs, and determining a registration error corresponding to the similar transformation matrix; when the registration error is smaller than a preset threshold value, determining the similar transformation matrix as a target transformation matrix; determining a search area on the next frame of image through the covariance matrix; fitting a plurality of prediction points in the search area by using a least square method to obtain a fitting function, and solving an extreme point of the fitting function; and correcting the extreme point according to the target transformation matrix to obtain the position and speed of the target point on the next frame of image. Based on the technical scheme of the invention, the precision and efficiency of target point positioning can be improved.

The invention discloses an IMU (Inertial Measurement Unit)-assisted moving target detection method under a dynamic condition, which comprises the following steps of: firstly, extracting feature points of a target image for matching to obtain feature point pairs; then, relative coordinate conversion is carried out on IMU sensor data, a corresponding basic matrix or homography matrix is solved, and then corresponding polar lines or mapping projection feature points are obtained; classifying the extracted feature points into two parts, namely static background feature points and dynamic target feature points; an affine transformation matrix is solved according to the corresponding relation of the static background feature points of the two adjacent frames of images and the motion parameter model, an inter-frame difference method is used for carrying out difference on the two frames of images and carrying out image binarization and morphological processing, and a corresponding motion target frame is obtained; and finally, traversing the moving target frame to carry out overlap ratio matching, and screening out a detection object of which the overlap ratio is greater than a set threshold value, namely an actual moving target in the current image. The method provided by the invention can effectively improve the precision and accuracy of moving target identification in a dynamic background.

The invention discloses an image registration method based on improved ORB feature extraction and grid feature matching. The method comprises the following steps: inputting an image to be extracted; using an improved FAST algorithm to extract feature points of the to-be-spliced image; establishing a BRIEF descriptor, and obtaining a BRIEF descriptor with a direction; according to the feature point set of the to-be-spliced image, establishing a Delaunay triangular grid taking the feature points as vertexes; judging the similarity of triangles, and obtaining similar triangles formed by the feature points; matching the similar triangle vertexes by using a Hamming distance to obtain an optimal matching feature point pair; obtaining affine matrix parameters by using an SVD method; according to the image registration method provided by the invention, the image quality is ensured, the feature extraction efficiency and the extraction precision can be improved, wrong matching is reduced, the stability is improved, the real-time performance of video stitching is improved, the waste of memory resources is reduced, the equipment cost is reduced, the working efficiency is greatly improved, and the method is suitable for popularization and application. And a better method is provided for image splicing.

The invention discloses a three-dimensional point cloud registration method and system based on multi-feature dynamic weighting. The method comprises the following steps: firstly, acquiring a source point cloud and a target point cloud to be registered and performing down-sampling; secondly, extracting geometric features of the source point cloud and the target point cloud, including curvatures and normal angles of all points; extracting a target point from the target point cloud, performing point pair matching by using a multi-constraint weighted scoring mechanism and a dynamic weight optimization strategy, and taking a point pair with a minimum dynamic weighted difference function value as a matching point pair; screening the matching point pairs according to the normal angle difference threshold value and the curvature difference threshold value, if the normal angle difference score is smaller than or equal to the normal angle difference threshold value and the curvature difference score is smaller than or equal to the curvature difference threshold value, reserving the matching point pairs, and otherwise, rejecting the matching point pairs; and finally, solving a rotation matrix and a translation vector according to the reserved matching point pairs to realize point cloud registration. The problems that a traditional ICP algorithm is sensitive to the initial attitude of the point cloud, the anti-noise capability is weak, and feature utilization is insufficient are solved.

The invention discloses a registration method and system for an optical image and an SAR image of the moon, and relates to the technical field of image registration, and the method comprises the steps: firstly determining the same typical moon appearance object in an image to be registered, and enabling the corresponding optical and SAR region images to form a region image pair; performing feature extraction and matching on each regional image pair by using a feature-based registration algorithm to obtain a preliminary matching point pair, and screening out a high-confidence matching point pair; and calculating a region affine transformation matrix of each region image pair based on the high-confidence matching point pairs, constructing a global optimization objective function according to all region affine transformation matrixes, solving an optimal affine transformation matrix, and finally realizing accurate registration of the to-be-registered image.

The invention relates to an image registration method and a real-time tracking method, and the method comprises the steps: dividing a reference frame and a subsequent frame into a plurality of regions according to the same rule, carrying out the registration of the reference frame and the subsequent frame, and obtaining a region combination (a reference frame region and a subsequent frame region) where each pair of registration points are located; screening out matching point pairs according to the distribution condition of the registration point pairs in all region combinations; and calculating a transformation matrix according to the matching point pairs. As the change of the images between the continuous frames is not large, the method calculates the transformation matrix for registration by using the most representative local area, can avoid interference information brought by the influence of the environment and noise on the partial area in the image, can ensure that the screened matching point pair for registration has high reliability, and can improve the registration accuracy. In addition, calculation is simple and convenient, the rapid processing requirement of real-time registration can be met, and the method has wide application scenes and value.

The invention relates to a multi-modal image matching method and system based on learning features and epipolar geometric constraints. The method comprises the following steps: carrying out edge enhancement processing on an input image through wavelet transform; extracting a multi-scale dense feature map based on the transformed convolutional neural network, and generating a feature descriptor with rotation and scale invariance in combination with principal direction normalization; adopting an FLANN algorithm and dynamic distance constraint to realize preliminary feature matching; and introducing a basic matrix construction and epipolar geometric consistency verification mechanism, and eliminating mismatching point pairs in combination with an RANSAC affine constraint model. According to the method, image enhancement, deep learning and geometric verification strategies are fused, the problems of radiation nonlinearity and geometric distortion caused by imaging mechanism differences among multi-modal images are effectively solved, the matching precision and robustness are improved, and the method is suitable for remote sensing application scenes such as optical-SAR registration, multi-source image fusion and earth surface change detection.

The invention discloses a camera offset detection and dynamic labeling method based on feature point matching. The method comprises the following steps: constructing a target object feature point data model; acquiring a camera monitoring picture image in real time, performing feature point extraction on the picture and the video frame of the target object, and performing matching with the target object feature point data model by using a feature point matching algorithm to obtain a matched feature point pair; calculating the offset of the camera according to the matched feature point pairs, including the translation amount and the rotation amount; correcting the video frame according to the offset of the camera, and identifying and positioning a target object in the corrected video frame; and generating a corresponding label according to the identification and positioning result of the target object, and dynamically displaying the label in the video frame. The method can effectively solve the problems of poor real-time performance, low accuracy, poor robustness and the like in the prior art, and has a wide application prospect.

The invention discloses a satellite angular rate identification method and related equipment, and relates to the technical field of rocket launching, and the method comprises the steps: obtaining a rocket telemetry video frame sequence after satellite-rocket separation; for each frame of image of the rocket telemetry video frame sequence, determining a dynamic image area of the target satellite based on the static area mask; based on a feature detection algorithm, binary descriptors are extracted from dynamic image areas of two adjacent frames of images; based on the binary descriptor, matching corresponding feature point pairs between two adjacent frames of images; estimating a rotation matrix between two adjacent frames of images through an iterative optimization algorithm based on the corresponding feature point pairs; and determining the angular rate of the target satellite according to the rotation matrix and the time interval between the two adjacent frames of images. According to the method, rapid and high-precision identification of the satellite angular rate is realized, the problem that the traditional technology depends on indirect data and is high in delay is solved, task success or failure can be judged in real time, and the launching task evaluation efficiency is improved.

Disclosed in the present invention are a multi-modal image matching method and system, and a terminal device and a storage medium. The method comprises: performing self-supervised feature extraction on an optical image and an SAR image, so as to obtain repeatable feature points between the optical image and the SAR image; on the basis of the repeatable feature points, segmenting the optical image and the SAR image into a first image block sequence, and performing feature extraction on the first image block sequence by means of a double-branch network, so as to respectively obtain a feature description vector of the optical image and a feature description vector of the SAR image, wherein the double-branch network comprises a first branch network used for extracting global features and a second branch network used for extracting local features; and on the basis of the feature description vectors, performing feature matching on the optical image and the SAR image, so as to obtain matching point pairs between the optical image and the SAR image. In the present invention, a two-stage training method is used, in which method training is performed first so as to obtain robust SAR-optical image feature description vectors, and learning is then performed in view of the feature description vectors so as to obtain feature points having high matching performance.

The invention relates to the technical field of remote sensing surveying and mapping, in particular to a multi-frame wide-area InSAR deformation result fusion method, which aims at the splicing problem of multi-frame InSAR deformation under a large spatial scale, performs optimization on the basis of a double-layer triangulation network and a local extraction method, and performs splicing according to dot-shaped and planar deformation storage characteristics. LOS deformation of each frame of image is converted into a vertical direction; and then on the basis of the double-layer triangulation network model, a genetic algorithm and PSO optimization are used as an improved algorithm for dotted deformation data homonymy point pairing to solve the many-for-one condition during registration. And under the condition of ensuring that the space position offset of the overlapping area is small, the offset of adjacent planar data is calculated by utilizing an optimized local extraction method, so that the deviation of adjacent deformation results in a large range is solved. And finally, generating a wide-area InSAR deformation product with consistent space reference and high availability based on two optimization algorithms.

The invention discloses a method for point cloud data registration, and relates to the technical field of point cloud data processing. In order to solve the technical problems that in the prior art, a traditional ICP algorithm is sensitive to an initial position, prone to falling into a local optimal solution, large in calculation amount, insufficient in feature extraction, low in precision and long in consumed time, the technical scheme provided by the invention is that the method for point cloud data registration comprises the steps of extracting feature points of point cloud data; a step of describing the feature points; performing coarse registration on the point cloud data according to the description result; and a step of performing accurate alignment on the coarse registration result. Wherein the feature points are subjected to coarse registration through an SAC-IA algorithm, and an initial alignment position between the point cloud data is obtained. And accurate alignment is carried out through an ICP algorithm. And searching corresponding point pairs through a k-d tree algorithm. The method is suitable for point cloud data registration.

The invention belongs to the technical field of computer vision, and particularly relates to a camera external parameter calibration method, device and equipment. The camera extrinsic parameter calibration method comprises the steps of determining initial extrinsic parameters of a camera, constructing 2D-3D matching feature point pairs in 2D pixel points in a 2D image and 3D points in a 3D point cloud for edge lines of a static target in a target area based on each initial extrinsic parameter in an initial extrinsic parameter set, and determining final extrinsic parameters based on the 2D-3D matching feature point pairs, the 2D image is acquired by the camera; and determining a re-projection error of projecting 3D feature points in the 2D-3D matching feature point pair to the 2D image based on the final external parameter, when the re-projection error meets a preset standard, taking the final external parameter as a calibration external parameter of the camera, otherwise, taking the final external parameter as an initial external parameter and adding the initial external parameter into the initial external parameter set, and repeating the steps until the calibration external parameters are obtained.

The invention provides a panoramic image intelligent splicing method based on context semantics. The method comprises the following steps: firstly, obtaining and preprocessing a sequence image; extracting a depth feature map of the image by using a pre-trained depth network; performing semantic-guided feature matching and image alignment based on the feature map; an optimal suture line is generated according to the semantic region boundary, and fusion is carried out by adopting a semantic weighted multi-band fusion algorithm; and finally, detecting and repairing the semantic inconsistent region to ensure the semantic coherence of the panoramic image. According to the method, matching is carried out by using the high-dimensional feature tensor rich in semantic information extracted by the deep neural network, the problem of feature matching ambiguity caused by repeated textures and weak texture regions such as sky or white walls is solved, the semantic information is used as a strong constraint, regions with similar appearances but different semantics can be effectively distinguished, and the accuracy of feature matching is improved. Therefore, correct matching point pairs with consistent semantics are screened out from massive candidates, and the matching accuracy is greatly improved.

The invention provides a 6D pose estimation method. The estimation method comprises the following steps: acquiring an RGB image and depth data; extracting a depth region of interest of the target object; and constructing a first point pair feature descriptor based on the depth region of interest, and matching the first point pair feature descriptor with a pre-acquired second point pair feature descriptor to determine an estimated pose of the target object. According to the pose estimation method provided by the invention, a final result can reach millimeter-level precision, and particularly, stronger robustness can be shown in an object scene with a complex shape or occlusion. In addition, the invention further provides a grabbing method based on the 6D pose estimation method, electronic equipment and a robot.

An image splicing method, comprising: (1) extracting any two images, having an overlapping area, to a canvas; (2) respectively identifying feature points in the two images extracted in step (1) and the features of the feature points; (3) on the basis of the similarity of the feature of each feature point, carrying out matching on the feature points in the two images to obtain all feature point pairs that are successfully matched, and extracting the feature point pairs; (4) on the basis of the feature point pairs extracted in step (3), acquiring a matching relationship between the two images, and on the basis of the matching relationship, splicing the two images; and (5) repeating steps (1)-(4), and extracting two images different from the previous two images each time for processing until all the images are spliced.

The invention relates to a pathological section splicing method, system and device and a storage medium, and the method comprises the steps: collecting a pathological section image, converting the pathological section image into a plurality of modes, and carrying out the histogram equalization and denoising processing; calculating an entropy value of each pixel point region in the image, and extracting pixel points with high entropy values as feature points; carrying out preliminary matching on the image under different scales, and carrying out bidirectional matching operation in a matching region to obtain a feature point pair; constructing a deformation model according to the feature point pairs, calculating parameters of the deformation model, and enabling the to-be-registered image to deform based on the deformation model through minimizing deformation energy; gradient information of an image overlapping region is calculated, a weight is allocated to each pixel point in the overlapping region according to a weight allocation rule, and the edge of the image overlapping region is processed to obtain a spliced image; and carrying out quantitative evaluation on the spliced image. According to the method, the problems of low registration precision, large calculation amount and poor adaptability to complex backgrounds in the prior art can be solved.

The invention discloses a point cloud semantic segmentation method based on two-dimensional and three-dimensional convolution. Aiming at the problem that the dependency relationship between pixels or points is explored and the relationship between objects is neglected in the existing method, and considering that the variance of ALS point cloud coordinates on an XY plane is greater than the variance along a Z-axis direction, firstly, the representativeness of features obtained by 3D convolution is enhanced by adding 2D convolution; in this way, the distribution of points on the XY plane can be more concerned. In the feature extraction module, the original single 3D KPConv operator in the KPConv is replaced by 2D KPConv and 3D KPConv, and features of more representative points are extracted by two-dimensional and three-dimensional convolution information; at the object level, a spatial channel attention mechanism is applied to account for global information. According to the method, information among all point pairs is obtained by applying a space attention matrix, and the output of two-dimensional and three-dimensional convolution is embedded among the point pairs, so that information gain is carried out, the relation between points and objects is improved, and semantic consistency is enhanced.

The invention relates to the technical field of multi-view three-dimensional reconstruction, and discloses a multi-view three-dimensional reconstruction method, device and equipment and a storage medium, and the method comprises the steps: obtaining a multi-view image, generating a diffusion feature map for the multi-view image through a diffusion model, carrying out the feature matching according to the diffusion feature map, and generating a matching point pair; calculating the pose of a camera through a Colmap algorithm according to the matching point pairs, extracting the deep features of the multi-view image by using a convolutional neural network to obtain a deep feature map, projecting the deep feature map to a three-dimensional space according to the pose of the camera to generate a preliminary three-dimensional feature map, and extracting the preliminary three-dimensional feature map according to the preliminary three-dimensional feature map. Fusing the preliminary three-dimensional feature map by adopting a U-Net network model to obtain a fused three-dimensional feature map, generating a three-dimensional voxel grid according to the fused three-dimensional feature map, generating a three-dimensional model according to the three-dimensional voxel grid, and finally outputting a globally optimal solution to improve generalization ability and precision.