44 results about "Texture reconstruction" patented technology

The invention relates to the technical field of industrial machine vision detection and image processing, in particular to an automobile part production mold surface smoothness detection system based on image enhancement, which comprises a data acquisition module used for acquiring an original grayscale image of the surface of an automobile part mold; performing low-pass filtering processing on the original grayscale image to eliminate imaging thermal noise; the manifold reconstruction module is used for constructing a structure tensor field; reversely deducing a pseudo-curvature field of the mold surface; the adaptive enhancement module is used for generating a corrected image; constructing a texture orthotropic diffusion model; generating a texture reconstruction reference image; the surface metering module is used for calculating the difference between the corrected image and the texture reconstruction reference image and generating a defect saliency image; calculating the surface roughness value of the mold surface; according to the method, the problem that design textures and abnormal scratches are difficult to distinguish in the prior art is effectively solved, and the technical bottleneck that micro defects are easily missed in a complex geometric structure in traditional visual detection is overcome.

The invention relates to the technical field of image compensation, in particular to a reflection compensation method based on image processing, and provides the following scheme: acquiring an environment panoramic image by using a panoramic camera to establish a scene global coordinate system, and acquiring a multi-view original image in combination with a camera array arranged in the circumferential direction of an object; determining a rotation symmetry axis according to the multi-view contour features, reconstructing a three-dimensional geometric body, and calculating normal distribution and curvature change; generating a prediction image based on diffuse reflection and specular reflection hypothesis in the surface expansion domain through virtual visual angle disturbance, identifying a reflection region according to color and gradient consistency, and generating a reflection mask; and performing texture reconstruction on the reflective area by using geometric registration and multi-view compensation, and finally performing splicing and fusion to obtain a non-reflective high-fidelity panoramic image. The method does not need to change the field illumination condition, and can achieve the precise recognition and compensation of the complex curved surface reflection in the cultural relic in-situ collection environment.

The invention discloses a metal product defect detection method and system based on image recognition. The method comprises the following steps: firstly, executing reflection disturbance digestion processing on a surface image of a to-be-detected metal product to obtain a reflection digestion image; obtaining surface reference texture features of the defect-free metal product, and generating a reference texture model on the basis of a texture distribution rule, a gray average value and texture continuity; performing defect texture gradient separation on the reflection resolution image based on a reference texture model, positioning an abnormal region, and performing segmentation to obtain a suspected defect texture region; performing boundary pixel reconstruction on the suspected defect texture region to obtain a defect texture reconstruction region; obtaining a target defect texture region through local variance enhancement and neighborhood correlation analysis; and finally, the overexposure area is positioned, gray inverse stretching processing is performed, abnormal pixel group feature clustering is performed on the preprocessed defect area, and then a surface defect detection result is output, so that the precision and accuracy of metal product surface defect detection are improved, and the false detection rate is reduced.

The invention belongs to the technical field of image enhancement and recognition, and particularly relates to a radar image intelligent enhancement and recognition method and system based on multi-model fusion, and the method comprises the steps: carrying out the adaptive suppression of speckle noise of an original radar image; feature point detection is carried out, robust transformation matrix estimation and adaptive contrast enhancement are carried out, and a corrected and enhanced image is output; utilizing the generative adversarial network and multi-loss function collaborative constraint to obtain a texture reconstruction image; establishing an image-semantic double-flow network architecture, performing cross-modal attention fusion to obtain a fusion feature map, and outputting a target recognition result; performing time phase division on the texture reconstruction image, judging a change type, and outputting a change detection result; and outputting a processing report including the enhanced image, the target list and change analysis. According to the method, noise suppression, correction enhancement, texture reconstruction, target recognition and change detection are integrated, the defect of fragmentation processing in the traditional technology is overcome, and the overall processing performance and the actual application adaptability are improved.

The invention relates to the technical field of image processing and cultural relic protection, in particular to a cultural relic image virtual restoration method based on texture reconstruction and color correction, and the method comprises the following steps: S1, obtaining a digital image of the surface of a to-be-restored cultural relic, and carrying out the denoising and brightness equalization processing of the digital image; s2, identifying and segmenting a damaged area in the image; s3, selecting an optimal sample block which is most matched with the structure of the region to be filled; s4, performing adaptive affine transformation on the optimal sample block to generate a reconstructed texture block; s5, carrying out linear transformation to obtain a repaired texture block after color correction; and S6, seamlessly embedding the repaired texture block after color correction into the damaged area. According to the method, the texture direction alignment and the color distribution correction are combined, so that the consistency of the damaged area and the surrounding image in structure and color is realized, and the naturalness and integrity of cultural relic image restoration are remarkably improved.

The invention provides a method for rapidly detecting the processing degree of rhizoma pinellinae praeparata, and the method comprises the steps: calculating a wrinkle intensity feature from a preprocessed image based on a gray-level co-occurrence matrix, and determining the type of the processing degree of rhizoma pinellinae praeparata by analyzing the wrinkle intensity change of texture distribution in an evolution process from disorder to order; the method comprises the following steps: acquiring surface texture reconstruction data of a plurality of rhizoma pinellinae praeparata samples at each time node under different processing conditions, and establishing a corresponding relationship between image features and processing degree categories; according to the rhizoma pinellinae praeparata processing degree evaluation result, the temperature condition is adjusted, rhizoma pinellinae praeparata image data are collected again, the adjusted wrinkle density feature is extracted, and the rhizoma pinellinae praeparata dynamic change trend is obtained; and by comparing the adjusted rhizoma pinellinae praeparata dynamic change trend with the initial rhizoma pinellinae praeparata dynamic change trend, the processing quality control consistency is judged, and rapid detection of the rhizoma pinellinae praeparata processing degree is completed.

The invention relates to the technical field of video generation, in particular to a video frame generation system and display equipment based on texture reconstruction and trajectory optimization, and the system comprises a motion breakpoint detection module, a trajectory interpolation frame generation module, a texture anomaly positioning module, a texture interpolation reconstruction module and a video frame synthesis module. According to the method, an edge feature map is generated through edge detection and non-maximum suppression, the boundary recognition precision is improved, noise is suppressed, candidate regions are divided through region growth, the local feature extraction efficiency is enhanced, global redundancy is reduced, three-frame optical flow analysis captures trajectory breakpoints, and motion vector correction path deviation is predicted in combination with a Lucas-Kanade method. Color consistency verification optimizes interpolation to reduce cross-frame abrupt change; 64 * 64 grids and a gray level co-occurrence matrix locate texture abnormity; five-frame similarity strengthens time sequence stability; Gabor filtering extracts a main direction and combines an adjacent frame reconstruction texture direction to ensure consistency; and trajectory smoothness and visual consistency are optimized through multi-frame cooperation and layered detection.

The invention discloses a camera image acquisition parameter verification method and system based on big data analysis, and relates to the technical field of image data processing. The camera image acquisition parameter verification method and system based on big data analysis comprises the following steps: S1, preprocessing image equipment data and statistical prior data; s2, completing re-parameterization sampling of potential variables through joint coding of an attention fusion mechanism and a variational auto-encoder; s3, constructing a de-noising diffusion probability model, establishing a forward diffusion sequence and reverse de-noising, and forming a reverse generated image sequence and a generated feature map; s4, discriminating and evaluating the domain consistency of the generated image and the target quality image through an adversarial discrimination network; and S5, uniformly updating the network parameters. The problems that the calculation load is too heavy and the imaging speed is low due to the fact that an existing single-image super-resolution technology is insufficient in high-frequency detail recovery, unreal in texture reconstruction and low in diffusion sampling efficiency are solved.

The application relates to a complex texture textile defect recognition method and system based on feature decoupling, and relates to the field of computer technology, which comprises the following steps: obtaining a multi-scale feature set of an original textile image to obtain a complex texture fusion feature; projecting the complex texture fusion feature to two mutually orthogonal hidden subspaces to obtain a reference texture component and an abnormal disturbance component; performing manifold alignment processing on the reference texture component based on a preset texture library to obtain a texture reconstruction feature; performing feature fusion on the texture reconstruction feature and the abnormal disturbance component to obtain a texture residual feature; performing adaptive threshold segmentation on the texture residual feature to obtain a defect feature map of the original textile; and performing connected domain analysis processing on the defect feature map to output a defect detection result. The application has the effects of improving the robustness of textile detection, meeting the needs of real-time detection in a pipeline, and reducing the computing resources and labor costs.

The application discloses an image compression sensing method of domain sampling and mixed transformer, comprising the following steps: a sampling recovery stage: learning the deep representation of the input image through multi-layer progressive 5*5 and 7*7 convolution and nonlinear activation function, and fully interacting the fragmented window information, and then generating the fine reconstruction iteration stage containing low and high level aggregation features at the same time through the jump connection; a fine reconstruction iteration stage: using a deep gradient descent module to perform optimization update of the reconstruction feature, and the deep gradient descent module expands the calculation of the update fidelity term to the neural network. Through the innovative network architecture and training strategy, the application realizes excellent image reconstruction performance, especially at a low sampling rate, and the method exhibits significant advantages and positive gain effects in detail preservation, texture reconstruction, robustness and universality compared with existing methods, thereby providing strong technical support for research and application in the field of image reconstruction.

This application relates to the field of tunnel construction safety monitoring technology, and discloses an intelligent identification method for water seepage risk at the tunnel face in water-rich clay layers. This method controls an active infrared excitation module to project radiation in an oblique incidence manner, uses polarization imaging to acquire sequences and calculates Stokes vectors; calculates the degree of linear polarization based on the Stokes vectors and performs threshold segmentation to generate a water film distribution mask; uses the Stokes vectors to construct a polarization angle field reflecting local normal changes as texture features, solves the optical flow constraint equation to obtain the instantaneous velocity field; performs frequency domain transformation on the velocity field, extracts the proportion of low-frequency creep energy through power spectral density analysis, and determines the soil rheological softening factor; finally, combines the water film distribution, rheological softening factor, and instantaneous velocity field to construct a mudslide risk index. This invention utilizes polarization texture reconstruction to solve the problem of weak texture tracking and eliminates elastic vibration interference through frequency domain energy decoupling, effectively improving the accuracy of mudslide risk identification.

The invention relates to the technical field of three-dimensional reconstruction, and discloses a face three-dimensional reconstruction method, system and device based on a portable device and a medium, and the method comprises the steps: collecting a face image frame sequence of a target user through the portable device; performing face key point detection on each frame of face image in the face image frame sequence, and performing face geometric reconstruction based on a face key point result in combination with a multi-stage fusion algorithm to obtain a face geometric reconstruction model; determining a plurality of key face images in the face image frame sequence based on a frame selection strategy, performing de-illumination processing on each key face image, and fusing each de-illuminated face texture image through a Laplacian pyramid network to generate a face texture reconstruction model; and mapping the face texture reconstruction model to the face geometric reconstruction model to obtain a complete face three-dimensional reconstruction result. According to the invention, the hardware cost can be reduced, the convenience is improved, remote medical treatment is realized, and the face three-dimensional reconstruction precision and quality are improved.

This application discloses a method and system for detecting defects in metal products based on image recognition. The method first performs reflection perturbation elimination processing on the surface image of the metal product to be detected to obtain a reflection elimination image; then, it acquires the surface reference texture features of the defect-free metal product, and generates a reference texture model based on texture distribution patterns, gray-level mean, and texture continuity; next, it performs defect texture gradient separation on the reflection elimination image based on the reference texture model, locates abnormal regions, and segments them to obtain suspected defect texture regions; then, it performs boundary pixel reconstruction on the suspected defect texture regions to obtain defect texture reconstruction regions; the target defect texture region is obtained through local variance enhancement and neighborhood correlation analysis; finally, it locates overexposed regions and performs gray-level inverse stretching processing, and outputs the surface defect detection results after clustering abnormal pixel group features of the preprocessed defect regions, thereby improving the accuracy and precision of surface defect detection of metal products and reducing the false detection rate.

The invention discloses a road modeling system, a repairing spraying action adjusting method and a road repairing robotic.The road modeling system conducts digital modeling on a road environment and crack details by collecting multi-view multi-mode image data of a designated area and combining a collaborative perception mechanism, and the method comprises the steps that S1, quality optimization is conducted on the image data; s2, performing dense three-dimensional texture reconstruction on the image to form a preliminary earth surface model, S3, realizing spatial registration of ground point cloud and aerial survey point cloud for the model, and generating high-density point cloud; and S4, constructing an image-point cloud double-flow feature coding network, and reconstructing to obtain a three-dimensional road crack model. According to the method, road infrastructures can be converted into predictable and controllable digital objects from physical static assets, accurate mapping and virtual-real synchronization of road damage states and robot behaviors are achieved, and the cognitive precision, virtual-real consistency and feedforward decision-making ability of a repair system to complex operation scenes are remarkably improved.

A facial texture reconstruction unit reconstructs a texture of a face from a 2D video of a person. A facial shape reconstruction unit reconstructs a 3D shape of the face from the 2D video. A pose estimation unit estimates a pose of the person from the 2D video. A shape integration unit reconstructs a 3D shape of the body corresponding to the estimated pose based on the 3D shape data, and integrates the reconstructed 3D shape of the body and the reconstructed 3D shape of the face to reconstruct a 3D shape of the person. A texture reconstruction unit reconstructs a texture image of the person by blending, with an image of the reconstructed texture of the face, a texture image included in the texture data and a model generation unit generates a 3D model of the person based on the 3D shape and the texture image of the person.

The invention provides an image texture defect repairing method, a segmentation method and a program product, and provides a newly designed normal texture reconstruction network for repairing and reconstructing the texture defect of an image, the reconstruction network comprises an encoder, a multi-scale median filtering module and a decoder, the multi-scale median filtering module realizes refined reconstruction and restoration of image texture details through multi-stage feature processing, abnormal information of a defect area can be effectively eliminated, the performance is excellent in normal texture detail restoration, and texture structure continuity, color consistency and marginal definition are greatly improved; and based on the reconstructed image, generating a segmented image by using a comparison network which is newly designed, so that pixel-level detection of the surface texture defects of the industrial product is realized, the defect detection precision is as high as 100%, and the defect positioning precision is not lower than 97.6%.

The invention discloses a human body reconstruction method and system based on a single RGB-D image and side edge optimization, and relates to the field of digital human reconstruction processing. According to the invention, a point cloud initialization module fully utilizes depth conditions to optimize an SMPL-X model so as to construct a back surface depth map and a human body point cloud model, and then a side surface hybrid optimization module combines a front surface RGB image with the optimized SMPL-X model to carry out geometric detail optimization on a side surface so as to obtain a left side depth map and a right side depth map. And finally, a texture generation module is used for realizing high-fidelity texture estimation from the aspects of text and vision through multi-network combination, and then the texture is mapped to the texture-free human body geometric model through UV to obtain a human body geometric model with complete texture. According to the method, high-performance geometric and texture reconstruction of the complete human body geometric model can be realized, and the reconstruction effect is improved.

The application discloses a mesh texture simplification algorithm suitable for three-dimensional reconstruction, and comprises the following steps: S1, reference three-dimensional model scene construction; using the recovered scene structure in three-dimensional reconstruction and the calibrated image, performing texture mapping on the original fine three-dimensional mesh to complete the reconstruction of the reference three-dimensional model scene; S2, reference three-dimensional model scene image acquisition; according to the three-dimensional space relative attitude relationship between the reference three-dimensional model scene and the view internal and external parameters, using the inverse projection principle to perform three-dimensional mesh to two-dimensional image rasterization calculation pixel by pixel and view by view, and completing the acquisition of the reference image set; S3, mesh and texture simplification; using the QEM algorithm to simplify the mesh, using the reference image set as a data source and using the texture reconstruction algorithm to perform texture remapping and simplification. The application has the advantages that the algorithm can support mesh and texture simplification together, under different texture simplification parameters, the texture almost has no distortion and can significantly reduce the texture data amount.

This invention relates to the field of industrial machine vision inspection and image processing technology, specifically to an image enhancement-based system for inspecting the surface finish of automotive component production molds. The system includes a data acquisition module for acquiring the original grayscale image of the automotive component mold surface; performing low-pass filtering on the original grayscale image to eliminate imaging thermal noise; a manifold reconstruction module for constructing a structure tensor field; inversely inferring the pseudo-curvature field of the mold surface; an adaptive enhancement module for generating a correction image; constructing a texture orthogonal anisotropic diffusion model; generating a texture reconstruction reference image; and a surface metrology module for calculating the difference between the correction image and the texture reconstruction reference image, generating a defect saliency map; and calculating the surface roughness value of the mold surface. This invention effectively solves the problem of existing technologies struggling to distinguish between designed textures and abnormal scratches, overcoming the technical bottleneck of traditional visual inspection easily missing minute defects in complex geometric structures.

This invention discloses a reinforcement learning-based underwater image enhancement training optimization method, belonging to the field of underwater image enhancement technology. Addressing the problems existing in current technologies, this method treats low-frequency color correction and high-frequency texture reconstruction in underwater image enhancement as two enhancement objectives with different optimization focuses. It utilizes a reinforcement learning mechanism to dynamically adjust the training strategies for both, solving the problem that existing fixed training strategies are difficult to adapt to changes in training states. A frequency-domain perceptual state representation is constructed by combining low-pass filtering and residual decomposition to explicitly describe the relative optimization state between low-frequency color restoration and high-frequency texture restoration during the current training process, providing a decision-making basis for the policy controller. An adaptive training optimization mechanism based on frequency-domain state feedback is built, automatically completing policy scheduling according to the actual restoration state during training, reducing the reliance on manually designed training strategies and improving the adaptability, generalization, and scalability of the method in complex underwater degradation scenarios.

The application relates to the technical field of image compensation, in particular to a reflection compensation method based on image processing. The application proposes the following scheme: an environmental panoramic image is acquired by using a panoramic camera to establish a global coordinate system of a scene, and a camera array arranged along the circumference of an object is used to acquire multi-view original images; a rotationally symmetrical axis is determined according to multi-view contour features, a three-dimensional geometric body is reconstructed, and a normal distribution and a curvature variation are calculated; a predicted image based on diffuse reflection and mirror reflection assumptions is generated in a surface development domain through virtual view angle disturbance; a reflection area is identified and a reflection mask is generated according to color and gradient consistency; texture reconstruction is performed on the reflection area by using geometric registration and multi-view compensation; and finally, a high-fidelity panoramic image without reflection is obtained by splicing and fusing. The application can realize accurate identification and compensation of complex curved surface reflection under the condition that the original environment of cultural relics is collected without changing the on-site lighting conditions.

The invention relates to an underground garage mirror surface highlight removal method based on a multi-network model, and belongs to the technical field of image processing, and the method comprises the following steps: inputting an original image into an MM-SHR; performing feature extraction on an input image by using a shallow CNN network, including capturing medium-range and remote context information from high-resolution features by using an OAIBlock module, and improving local detail extraction and feature fusion; an HDDAConv module is utilized to perform self-adaptive decoupling and fine-grained texture reconstruction on the highlight area of the mirror surface; extracting long-distance information by using an HDCTransform, and repairing damaged features of the highlight area by using features around the highlight area; introducing a cross-domain attention mechanism, and fusing frequency domain and spatial domain information; and simultaneously outputting a highlight-free image and a highlight residual image, adding the two output images according to pixels, reconstructing the input original image, and removing mirror highlight.

The embodiment of the invention discloses a remote sensing image cloud removal method based on multi-source remote sensing data fusion, and relates to the technical field of remote sensing image intelligent processing, and the method comprises the steps: obtaining a cloud coverage image and an SAR image of a target region, and inputting the cloud coverage image and the SAR image into a cloud removal model; extracting optical features and SAR features through a generator of a cloud removal model; an optical-SAR fusion feature is obtained through a feature fusion module, and a cloud removal image is generated; and determining the confidence coefficient of the cloud-removed image through a discriminator in combination with the SAR image, and if the confidence coefficient is greater than a preset confidence coefficient threshold value, outputting the cloud-removed image. According to the method, the problem that a time-phase domain method depends on high-quality time sequence data is solved, the limitation of a spectral domain method in a thick cloud region is overcome by utilizing the penetrability of the SAR to the cloud, the direct fusion difficulty caused by the difference of imaging mechanisms in related technologies is avoided, and the defect that a spatial domain method is insufficient in complex earth surface and high-frequency texture reconstruction precision can be overcome.

This invention discloses a method for the collaborative restoration of structure and texture in Dunhuang murals based on structural uncertainty, belonging to the field of image restoration technology. The method includes: a structure prediction step, which generates a structure reconstruction result through an encoder-decoder architecture based on codebook quantization and simultaneously outputs pixel-level structural uncertainty parameters; a texture reconstruction step, which models the texture completion process as texture flow propagation on a graph structure and adaptively adjusts the propagation range and constraint strength according to the structural uncertainty parameters; and a fusion step, which fuses structural features and texture features at multiple scales and dynamically adjusts the fusion strength according to the structural uncertainty parameters to generate the final restoration result. This invention achieves effective linkage between structure prediction and texture reconstruction through structural uncertainty parameters, suppressing the transmission of structural errors to the texture generation process when there is large-area damage or severe information loss, while maintaining overall consistency and natural detail, making it suitable for the digital restoration of Dunhuang murals.

The application discloses a non-contact pavement friction coefficient detection method, which comprises the following steps: obtaining a plurality of pavement point clouds by performing three-dimensional texture scanning on a pavement through a laser profilometer and a visible light camera; performing three-dimensional texture reconstruction on the pavement point clouds to obtain a space curve; extracting an index set of apparent texture features from the space curve; collecting friction data through a pavement friction test vehicle; and establishing a mapping relationship between the index set and the friction coefficient. The detection method realizes three-dimensional reconstruction of pavement micro-texture and macro-texture through two non-contact detection methods of a laser profilometer and a visible light camera, and then establishes a mapping relationship between a friction coefficient value collected by a traditional pavement friction test vehicle and the index set. The index set and the mapping relationship obtained through the method can be used to directly obtain the friction coefficient of the pavement.

This invention discloses a method for 3D reconstruction of asphalt pavement texture, belonging to the fields of road detection and computer vision technology. The method first calibrates an industrial camera to obtain intrinsic parameter matrices and distortion coefficients, and then continuously acquires pavement images at short intervals of 1 to 2 centimeters on a moving vehicle. Next, the images undergo preprocessing including cropping, Gaussian kernel convolution for noise reduction, and 8 to 12 low-pass filtering convolution enhancements. Feature points are matched using the SIFT algorithm combined with a limited neighborhood range strategy of 80 to 120 pixels. Subsequently, based on the matched points, the fundamental and essential matrices are solved using the RANSAC algorithm and the 8-point method. The camera pose is optimized using bundle adjustment to obtain an initial point cloud, followed by kdtree clustering and statistical filtering for dual noise reduction. Finally, bending deformation is corrected through quadratic polynomial surface fitting, tilt is corrected using projection transformation, and the model scale is adjusted according to the scaling factor to obtain a standardized 3D model. This method effectively solves the problem of weak asphalt texture matching and achieves efficient and high-precision pavement texture reconstruction.

The application discloses a road modeling system, a repair spraying action adjusting method and a road repair robot, the road modeling system collects multi-view multi-modal image data of a specified area, and combines a cooperative perception mechanism to perform digital modeling on a road environment and crack details, S1. image data is optimized in quality, S2. dense three-dimensional texture reconstruction is performed on the image to form a preliminary ground surface model, S3. spatial registration of ground point cloud and aerial survey point cloud is realized on the model to generate high-density point cloud, S4. an image-point cloud double-flow feature coding network is constructed, and a three-dimensional road crack model is reconstructed. The application can change road infrastructure from a physical static asset into a predictable and controllable digital object, realize accurate mapping and virtual-real synchronization of road damage state and robot behavior, and significantly improve the cognition accuracy, virtual-real consistency and feedforward decision-making ability of the repair system on a complex operation scene.

The invention provides a picture texture compression method and system, a computer and a storage medium, and the method comprises the following steps: building a canvas with a preset pixel size, traversing a picture set, carrying out the boxing operation of each picture, and obtaining a canvas set with a specified size; training an auto-encoder neural network, and guiding overfitting through a multi-target mixed loss function based on a canvas set to optimize texture reconstruction quality; inputting the texture pictures with the unified size into an asymmetric depth encoder to generate an encoding vector, and performing quantization compression processing on the encoding vector; and inputting the quantized coding vector into a lightweight decoder according to the index, and outputting a restored texture picture. By using an active over-fitting design and a multi-objective loss function, the reduction degree of texture image quality is remarkably improved while the data volume is reduced; the hardware acceleration capability of the modern GPU on convolution operation is fully utilized, so that the compression and decompression efficiency is high, and the method has remarkable practical value and performance advantages.

The invention provides a three-dimensional rock core texture reconstruction method based on a multi-view image, and the method comprises the steps: continuously obtaining a plurality of rock core images of a rock core sample at a plurality of views in a constant-speed rotation process of the rock core sample; according to the obtained multiple rock core images, correspondingly generating a rock core texture image for describing the surface appearance and a three-dimensional point cloud model for describing the geometric morphology corresponding to the rock core sample; a rock core texture image with clear two-dimensional textures is precisely attached to the surface of the three-dimensional point cloud model through a texture mapping technology, and a one-to-one restored three-dimensional rock core model with textures is generated; and comparing the three-dimensional rock core model with a plurality of rock core images obtained by initially shooting the rock core sample, comparing the texture of the three-dimensional rock core model with the texture in the original rock core image to obtain texture reduction precision, evaluating the texture reduction precision, and if the reduction precision meets an output condition, outputting and storing the three-dimensional rock core model.

The invention discloses a pipeline construction monitoring method and system based on image recognition, and belongs to the technical field of pipeline construction, and the method comprises the steps: projecting a light spot array to a monitoring scene containing a welding seam, analyzing the displacement of the light spot array in an image sequence to analyze affine transformation parameters, and generating a global motion flow field; performing reverse compensation on the image sequence by using the global motion flow field to generate a physical calibration sequence; performing signal analysis of each pixel on a time dimension on the physical calibration sequence, generating a time domain modulation intensity graph, and performing morphological expansion and connected domain analysis on the time domain modulation intensity graph; dual interference of high-concentration metal dust and equipment high-frequency vibration in underground shield tunnel construction can be suppressed, motion parameters are analyzed through a light spot array to achieve jitter reverse compensation, the dust shielding influence is eliminated in combination with the time domain analysis and texture reconstruction technology, and the problem that defect features are mistakenly erased in the denoising process in a traditional method is solved.