236 results about "Geometric transformation" patented technology

The invention discloses an automobile part quality detection method and system based on artificial intelligence visual inspection, and belongs to the field of artificial intelligence machine visual inspection, and the method comprises the steps: firstly, carrying out the registration of a collected RGB image and a depth image, and extracting a part region through a saliency detection network; two-dimensional key points are extracted based on an RGB region image and are matched with key points of a three-dimensional model, an initial three-dimensional attitude is obtained by adopting a PnP algorithm, iterative registration is performed with the three-dimensional model in combination with a point cloud generated by a depth image, and a fine three-dimensional attitude is obtained. And calculating a geometric transformation matrix from the part to a standard front view attitude according to the attitude, and performing attitude correction on the RGB and depth region image. And then matching the corrected image with a standard template image by using a feature detection and matching network so as to correct the position of the detection window. And finally, the three-dimensional size of the part is calculated in the corrected detection window in combination with the depth value, and tolerance judgment is carried out. And the precision, the robustness and the automation level of online detection of the automobile parts can be obviously improved.

The invention relates to a GIS (Gas Insulated Switchgear) equipment mechanical defect diagnosis method based on a Gramb angle field and a dual-channel PCNN-Attention neural network, and belongs to the technical field of gas insulated switchgear mechanical vibration defect diagnosis. The method solves the problems that traditional diagnosis depends on artificial feature extraction, so that subjectivity is high, information mining is insufficient, and defect severity evaluation is missing. According to the technical scheme, the method comprises the steps that a one-dimensional vibration signal is converted into a GASF two-dimensional image and a GADF two-dimensional image through a GASF field so as to completely reserve time sequence topological features; carrying out data enhancement by adopting an image geometric transformation technology so as to improve the generalization ability of the model; and a dual-channel PCNN-Attention model is constructed, and synchronous intelligent identification of defect types and severity is realized through parallel feature extraction and dynamic weight optimization of an attention mechanism. According to the method, the diagnosis accuracy, reliability and adaptive capacity are improved, and support is provided for equipment state operation and maintenance.

The invention discloses a digital pathological section paired image block data set construction method and system, and belongs to the technical field of medical image processing. The method comprises the following steps: carrying out local feature matching on HE and IHC images, and respectively solving a homographic transformation model and an affine transformation model based on a robust estimation algorithm; constructing an objective function preferential geometric model; mapping the HE image block to an original resolution coordinate system of the IHC image, determining a local rotation angle according to a local Jacobian, and executing one-time geometric transformation in a target domain; calculating similarity indexes based on tissue masks to perform quality control screening; hierarchically outputting index files by taking slices or patients as granularity; a verification example mask is obtained through an H-channel enhancement and segmentation process, an organization mask is generated based on a hybrid backspacing mechanism, and an example level label is exported. According to the method, the problems of difficulty in accurate registration and uncontrollable quality of the cross-dyeing image are solved, and a high-quality data basis is provided for subsequent model training.

The invention relates to the technical field of flexible circuit board detection, and provides an intelligent detection method and device for a flexible circuit board, and electronic equipment. The method comprises the following steps: S1, controlling an image acquisition device to obtain at least one target image of a to-be-detected flexible circuit board; s2, the control processing unit identifies a plurality of preset optical positioning reference points from the target image, and obtains actual coordinates of each optical positioning reference point in the current target image; s3, the control processing unit compares the actual coordinates of the optical positioning reference points with the theoretical coordinates of the optical positioning reference points in the standard template image to generate a deformation mapping relation of the to-be-detected flexible circuit board; s4, the control processing unit performs nonlinear geometric transformation on the target image or the to-be-detected region of interest in the target image according to the deformation mapping relation to obtain a corrected image which is spatially aligned with the standard template image; and S5, controlling the processing unit to execute a defect detection algorithm on the corrected image so as to identify defects on the flexible circuit board.

A system and method for implementing experiential manifold cognition that extends persistent cognitive machines beyond discrete thought caching to continuous geometric representation of experience. The system maintains an experiential manifold comprising a differentiable manifold with Riemannian metric tensor encoding semantic relationships, compression pressure field governing memory consolidation, and potential field encoding goals and attention. Input data is projected onto the manifold through adaptive geometric diffusion preserving semantic structure. The system executes geometric transformations including metric evolution, geodesic computation, and curvature estimation. During non-interactive periods, autonomous evolution occurs through trajectory recombination and selective pruning. A user interface enables visualization and direct manipulation of manifold geometry, translating navigation into geodesic traversal and edits into metric modifications. The system maintains persistence across sessions and enables controlled federation between multiple manifolds through consent-bounded synchronization. Applications include persistent narrative worlds, collaborative cognitive spaces, and experiential intelligence systems that learn through geometric evolution.

The embodiment of the specification provides a copper foil defect detection system, comprising: a data acquisition module configured to acquire a copper foil surface image through a multi-spectral line-scan digital camera and output original image data; the preprocessing module is configured to perform dynamic denoising and partition contrast enhancement on the original image data to generate a preprocessed image; the frequency domain processing module is configured to perform Fourier transform on the preprocessed image to obtain a frequency domain feature map, separate a low-frequency contour and a high-frequency texture component through a band-pass filter bank, and generate a composite feature map through inverse transformation after frequency domain mask enhancement; the data enhancement module is configured to implement geometric transformation enhancement and frequency domain noise injection on the composite feature map and output an enhanced sample set; and the multi-scale detection network is configured to extract hierarchical features from the enhanced sample set, fuse the hierarchical features through a gating mechanism and output defect positioning and classification results. According to the scheme, the frequency domain image processing technology is combined with the CNN, and the detection effect of the weak contrast defect is improved.

The invention discloses a multi-layer semantic perception, distillation and semi-supervised cooperative training target detection method, and the method specifically comprises the following steps: constructing a data set: extracting a first part of images from image data, marking the first part of images to construct a supervised target detection data set, and taking the remaining images as an unmarked image data set, the data volume of the unlabeled image data set is greater than that of the supervised target detection data set; teacher model optimization: performing supervision training on the teacher model on the supervised target detection data set; constructing a teacher model, and executing self-distillation training on the teacher model; pseudo labels are generated for the unlabeled images through a teacher model, and adaptive screening is carried out based on confidence distribution; mapping a pseudo label to a strong enhanced sample through enhanced geometric transformation, carrying out semi-supervised training by using the strong enhanced sample and the pseudo label, and introducing a feature layer distillation constraint at the same time; optimizing a student model; and outputting the target detection model obtained through training.

The invention relates to the technical field of equipment operation tests, particularly discloses a simple scene equipment operation action rapid processing method based on a test video, and is used for solving the problems of low action recognition precision, insufficient spatial-temporal feature fusion, low detection speed and more redundant data in the prior art. Comprising the following steps: accurately intercepting motion start-stop frames, extracting the frames according to a preset frame rate, implementing geometric transformation and color augmentation on the frame-extracted images, respectively extracting spatio-temporal dynamic features and static spatial features by adopting a 3D convolutional network and a 2D convolutional network in parallel, integrating the spatio-temporal features by a channel fusion attention module based on a Gram matrix, and extracting the spatial and temporal dynamic features and the static spatial features by adopting the channel fusion attention module based on the Gram matrix. A thermodynamic diagram is generated based on Grad-CAM to assist in key area positioning, a RefineDet network is input to generate a detection result through ARM coarse regression and negative anchor filtering, ODM fine regression and non-maximum suppression in sequence, and efficient and accurate positioning and classification of operation actions are carried out with assistance of a dynamic frame abandoning and time sequence correction strategy; according to the invention, through the multi-scale residual error convolution and the anchor frame network, accurate positioning of slow action of equipment is realized.

The invention discloses a refraction distortion automatic correction method and system for an SPIV experiment, and belongs to the technical field of fluid mechanics experiment measurement, and the method comprises the following steps: obtaining a camera shooting posture and medium physical parameters; constructing a multi-layer medium forward refraction model; iteratively adjusting the assumed real angle and repeatedly calling the forward model by taking the measured distortion angle as a target through reverse iterative calculation until the predicted angle of the model is matched with the measured angle, and solving the corrected actual camera angle; constructing a nonlinear mapping relation from a distorted image coordinate to a non-refraction ideal image coordinate according to the difference between an actual angle and a measurement angle; performing reverse geometric transformation and interpolation on the original SPIV image by using the mapping relation to generate a correction image for eliminating the refraction effect; according to the invention, a software algorithm is used for replacing a traditional water prism physical correction device, so that the cost and complexity are reduced, and the adaptability to different experimental conditions and the correction precision are improved.

The invention belongs to the technical field of crossing of rock soil, geological engineering and computer modeling, and discloses a three-dimensional fractured rock anisotropic fragmentation and expansion structure generation method and system, and the method comprises the following steps: generating tightly embedded initial blocks in an expansion domain according to the number of control blocks and the initial equivalent size of the blocks; on the basis of the node information of the initial block, anisotropic fragmentation and expansion mapping geometric transformation is carried out on the cell elements, and node coordinate information after fragmentation and expansion and form control is carried out is obtained; calculating the volume ratio of blocks in the target area to obtain a current volume fraction; extracting a target domain in the extended domain, performing constraint smoothing, abandoning an external block, and retaining node coordinate information in the target domain; and exporting the reserved node coordinate information, the current volume fraction and the geometric structure to obtain the fragmentation and expansion structure.

A technology capable of suitably correcting a geometric distortion caused by a shape of a curved surface of a screen or the like and obtaining a suitable image easily viewable for a user is provided. A projector is an image display apparatus configured to project an image onto a screen and includes a projection lens arranged at a first position and a camera arranged at a second position. When the screen has a curved surface, a camera image obtained by capturing a first image projected on the screen by the camera is acquired, and a geometric transformation for correcting a geometric distortion caused by the curved surface seen from a first virtual viewpoint position (virtual viewpoint) is performed for an image to be displayed based on information of the camera image, the first position, and the second position, and a post-transformation image is projected onto the screen.

The invention discloses a method and system for outputting a two-dimensional plane based on a three-dimensional scene, and relates to the technical field of three-dimensional visualization, and the method comprises the steps: carrying out the precise mapping and spatial restoration of a three-dimensional scene component to a CAD (Computer Aided Design) primitive through a type field driven primitive matching mechanism and a component attribute data driven parameterized geometric transformation method, and obtaining a three-dimensional scene component; one-to-one correspondence from component types to graphic components is supported, automatic insertion, zooming and labeling are carried out in combination with spatial attributes such as positions, sizes and directions, and finally an editable two-dimensional plane CAD drawing is output in a standard DXF format, so that the reusability and engineering suitability of a three-dimensional modeling result in design iteration, engineering collaboration and multi-platform integration are remarkably improved, and the construction efficiency is improved. And the core technical defects of non-editability and the like caused by traditional engine image output are overcome.

A classification model generating system includes: an obtainer that obtains a good product image group including a plurality of good product images; a defective portion image generator that generates a plurality of defective portion images, based on a seed image group obtained by geometrically transforming a seed image simulating a defective portion, the seed image being an artificially drawn image; a combination processing unit that combines each of the plurality of defective portion images with the good product image group to generate a defective product image group; and a classification model generator that performs classification training by using a part of the good product image group and a part of the defective product image group as a training image group to generate a classification model.

A method and apparatus of ALF classification and / or geometric transformation for the chroma component. According to the method, reconstructed pixels are received, where the reconstructed pixels comprise a current colour block and the current colour block comprises a current luma block and a current chroma block. A transpose index for the current chroma block is determined. A filtered chroma output is derived by applying a target chroma ALF to the current chroma block, where the transpose index is included in information used for selecting the target chroma ALF from a set of chroma ALFs, or the transpose index is used to select a target geometric transformation for generating the target chroma ALF, or both. Filtered-reconstructed pixels are provided, where the filtered-reconstructed pixels comprise the filtered chroma output.

The application provides a real-time conversion method for pixels and geographic latitude and longitude in low-altitude photogrammetry, which comprises the following three parts: unmanned aerial vehicle capability confirmation, real-time conversion service implementation deployment for pixels and geographic latitude and longitude in low-altitude photogrammetry, and GIS geographic information platform integration docking. Through real-time data collected by an unmanned aerial vehicle, combined with a computer vision algorithm and a spatial geometric transformation model, the specific pixel points in image data are associated with real geographic coordinates, so that accurate positioning and measurement of ground objects are realized. The application relates to the technical field of low-altitude photogrammetry, and through the cooperative work of real-time data collection by an unmanned aerial vehicle, real-time conversion service for pixels and geographic latitude and longitude in low-altitude photogrammetry, and a GIS geographic information platform, efficient mapping from a photographed image to a geographic coordinate is realized, and accurate and rapid technical support is provided for low-altitude photogrammetry.

The invention provides an automatic recording method, device and equipment, a storage medium and an automatic recording system, and relates to the technical field of computers, in particular to the technical field of sports science and technology and computer vision. According to the specific implementation scheme, the method comprises the steps of obtaining a current video stream collected by a visual collection device for a monitoring scene, and loading initial region configuration information of the monitoring scene; determining geometric transformation parameters according to the characteristic difference between the standard reference image of the monitoring scene and the current calibration image; calibrating coordinates of a functional region frame contained in the initial region configuration information by using the geometric transformation parameters to obtain a calibrated functional region frame; and based on the calibrated functional area frame, performing target activity detection on the current video stream, and generating a recording record when a detection result meets a preset triggering condition. According to the technical scheme, the frequency of mechanical calibration can be reduced, the operation and maintenance cost is reduced, and the long-term stability and accuracy of the recording system are ensured.

The application relates to a remote sensing image generation online map method, device, equipment and medium, a plurality of different transformed sample images are obtained by performing geometric transformation on remote sensing sample images in each group of sample image pairs, the plurality of transformed sample images are added to the corresponding sample image pairs to obtain a training data set, each training data set is used to train an online map generation model to obtain a trained online map generation model, an encoder in a perception image compression network is used to map remote sensing sample images and corresponding transformed sample images from a pixel space to a feature space, a forward diffusion and reverse denoising are performed on the feature space by a denoising diffusion bridge network, and then an output of the denoising diffusion bridge network is mapped from the feature space to the pixel space by a decoder in the perception image compression network, and a real-time remote sensing image is input into the trained online map generation model to obtain a real-time network map. By adopting the method, a map with clearer boundaries and brighter colors can be generated in real time.

The application discloses a kind of dynamic ring vision splicing method and system based on image overlap area feature perception, method includes based on the depth information and the feature information dynamic planning splicing path;According to the splicing path of planning, image splicing is executed, including the multi-band image fusion based on depth perception.The present application extracts local and global features of the overlapping area and calculates pixel-level depth information, constructs a geometric transformation model optimized by feature-depth combination, so that panoramic stitching can accurately identify the outline of close-range objects, and dynamically plan the optimal stitching line to bypass prominent objects;By searching the distance splicing template based on the real distance and automatically unifying the focal length of each camera, the field of view range is kept consistent;Through the multi-scale depth estimation network guided by features and joint reprojection error optimization, high-precision registration can still be maintained in scenes with few feature points or low overlap areas.

The invention discloses a traffic abnormal event detection method and system based on multi-mode intelligent perception, and the method comprises the steps: deploying an infrared and visible light dual-mode camera device at a key position of a road, and obtaining a synchronous image sequence of infrared and visible light mode images through a timestamp; performing spatial alignment and noise suppression on the infrared and visible light modal images by adopting lightweight geometric transformation, normalization and fast filtering algorithms, and outputting a preprocessing result of a synchronous image sequence; feature fusion of infrared contours and visible light textures is realized through an infrared attention guiding mechanism and a low-complexity convolution structure, and a multi-modal time sequence feature sequence is generated; a lightweight time sequence modeling and reconstruction error discrimination method is adopted to carry out space-time analysis on the fused features, and rapid similarity comparison and threshold discrimination are adopted to complete identification of traffic anomalous events, so that traffic anomalous event detection based on multi-modal intelligent perception is realized. According to the invention, a multi-mode cooperative enhancement network and an anomaly detection and early warning mechanism are realized.

The invention relates to the technical field of computer vision and video image processing, and discloses a video picture intelligent frame supplementing method and system based on deep learning, and the method comprises the steps: carrying out the feature coding and semantic segmentation of front and rear frames of a video sequence, and dividing an image into a rigid body instance region and a non-rigid body region; constructing a parameterized rigid body reference flow field by predicting geometric transformation parameters of the rigid body instance; calculating a space gradient and a semantic edge weight of the reference flow field; a motion field gradient consistency constraint is introduced when a residual optical flow is predicted, and a semantic edge weight is used for forcibly synthesizing a space gradient of an optical flow field to keep consistent with a reference flow field at the edge; and determining a pseudo depth sequence according to the semantic category, and executing hierarchical forward transformation and hole filling by using the synthetic optical flow to generate a target intermediate frame. According to the method, parameterized modeling and a gradient constraint mechanism are combined, the problems of structural deformation and obscured shielding edges in a rigid body large-displacement scene are solved, and the definition and structural integrity of a complementary frame picture are improved.

Aspects of the disclosure for reducing a qubit count employed by a quantum circuit include performing a geometric transformation to boundaries of a three-dimensional (3D) toric code, wherein a Hermite normal form is utilized to parameterize the geometric transformation. Aspects include transforming the 3D toric code to a two-dimensional (2D) toric code for the quantum circuit and causing the quantum circuit to execute the 2D toric code.

A method implemented by a data-processing device for aligning a face of an individual in an image. The method includes detecting, in an image of the face of an individual, positions of a left eye, of a right eye, of a midpoint between the right eye and left eye, and of a midpoint of a mouth, applying a first geometric transformation so that the positions of the midpoint between the left eye and right eye and of the midpoint of the mouth coincide with reference points, and applying a second geometric transformation so that the position of a closest eye in a depth of the image coincides with the position of a vertical reference line.

The present disclosure relates to intra prediction of a target block of a video picture based on template matching that compares a target template patch to a candidate reference template patch. The intra prediction includes identifying a candidate reference block neighborhood from a target block neighborhood and from a geometric transform type; obtaining the candidate reference template patch by applying a geometric transform identified by the geometric transform type to the candidate reference block neighborhood; selecting a candidate reference block having a minimum cost obtained by comparing the candidate reference template patch to the target template patch; and generating an intra prediction block for the target block by applying a geometric transform identified by the geometric transform type associated with the selected candidate reference block to the selected candidate reference block.

The invention relates to the technical field of assembly precision detection, in particular to an assembly precision detection system for a bearing copper retainer. The system comprises an image acquisition module used for acquiring a top view image and a side view image of each rolling bearing; the image correction module is used for performing geometric transformation correction on each top view image; the deviation analysis module is used for acquiring a position dislocation index of each rolling bearing according to the distance dispersion degree between the retainer and the outer ring and the distance dispersion degree between the retainer and the inner ring in the corrected top view image and the height dispersion degree of the upper edge of the bearing in the side view image; and the assembly precision detection module is used for judging whether the assembly precision of the bearing copper retainer in each rolling bearing is qualified or not according to the distribution uniformity among the rolling bodies in the corrected top view image and the position dislocation index of each rolling bearing. According to the method, the top view image is corrected, the image features during assembly dislocation are analyzed, and the detection precision of the assembly precision of the bearing copper retainer is improved.

A video bitstream comprising a current picture of a video is received. A first group of samples and a second group of samples in the current picture are determined. A first geometric transform is determined for the first group of samples in the current picture and a second geometric transform is determined for the second group of samples in the current picture. The first geometric transform is configured to adjust an orientation of the first group of samples in the current picture. The second geometric transform is different from the first geometric transform and configured to adjust an orientation of the second group of samples in the current picture. The picture is reconstructed, where the first group of samples is reconstructed based on the determined first geometric transform and the second group of samples is reconstructed based on the determined second geometric transform.

This invention belongs to the field of image processing technology, specifically relating to an image stitching method for a low-altitude unmanned aerial vehicle (UAV) monitoring network. The method includes: acquiring a reference image and an image to be stitched; extracting matching point pairs between the two images; determining the static confidence level of the matching point pairs based on their disparity changes; extracting the static matching point pairs and performing multiple linear transformations to obtain multiple static projection matrices; selecting the optimal static projection matrix for image transformation; and extracting dynamic targets within the overlapping area. When generating the stitched image, the gray values ​​of the regions identified as dynamic targets in the reference image are replaced with the gray values ​​of the same regions in the image to be stitched, thus completing the image stitching. This invention, through a dynamic-static separation strategy, effectively avoids the contamination of geometric transformation calculations by dynamic targets, significantly improving stitching accuracy and visual quality.

The invention belongs to the technical field of image processing, and particularly discloses an image restoration method and device based on deep learning and electronic equipment, and the method comprises the steps: obtaining a training data set which comprises an isotropic low-quality image and a directional high-quality image in pairs; training a neural network model based on the data set to enable the neural network model to learn a feature mapping relation from an isotropic low-quality image to a directional high-quality image; obtaining an isotropic low-quality image of a to-be-detected sample, and performing geometric transformation on the isotropic low-quality image to enable a to-be-restored target direction to be aligned with a high-quality direction obtained by the model; inputting the transformed image into a model to obtain a predicted image, and restoring the high-quality direction to a target direction through inverse geometric transformation; and finally, fusing the original directional high-quality image of the to-be-detected sample with the recovered target direction high-quality image.

The application discloses a thermal superstructure manufacturing method, device and system based on discrete transformation thermology, and belongs to the technical field of heat conduction and heat flow regulation. The method comprises the following steps: carrying out discrete simplex grid dissection on a design domain to obtain a grid, and specifying a hard constraint for an internal function boundary according to a regulation function; defining a piecewise linear mapping on the grid and solving by two-stage optimization, wherein a negative Jacobian determinant is punished in the first stage to eliminate folding to obtain a bijective mapping, and anisotropy is inhibited by minimizing conformal distortion in the second stage; and finally, the thermal conductivity tensor field of the physical domain is derived by using a Jacobian matrix J, microstructure matching and filling are carried out, and additive manufacturing is adopted. The application solves the problems of folding and extreme parameters which are prone to occur in complex geometric transformation thermology design, can realize efficient heat management and omnidirectional heat regulation under any complex shape, and the error of experimental verification is less than 5 percent.

A computer-implemented method and a system for temporal damage consistency validation, comprising receiving, at one or more processors, a current vehicle scan containing image data and damage detections for a vehicle, retrieving historical damage data for the vehicle from previous scans;, projecting geometric positions of the previously detected damage regions onto corresponding locations in the current vehicle scan using a geometric transformation that accounts for vehicle positioning differences between inspection sessions, matching the projected damage positions with current scan detections using feature vector similarity scoring by computing similarity measures between deep learning feature vectors of projected damage regions and deep learning feature vectors of damage detections found in corresponding areas of the current vehicle scan and classifying damage states based on results of the matching operation.