5156 results about "Reference image" patented technology

In a measurement processing apparatus for measuring a geometric feature of an object image: a measurement-reference-element setting unit automatically sets at least one first measurement reference element for use in measurement of the geometric feature of the object image, at at least one first position on the object image based on first image data representing the object image and position information indicating at least one second position of at least one second measurement reference element which is set on a measurement reference image corresponding to the object image; and a geometric-feature measurement unit measures the geometric feature of the object image based on the at least one first position of the at least one first measurement reference element.

Disclosed in the present application are a multi-modal data processing method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring a reference image and a reference text; extracting a reference visual feature of the reference image; by means of a multi-modal large language model, determining an embedding of the reference text, an embedding of a start mark of the reference visual feature, an embedding of the reference visual feature, and an embedding of an end mark of the reference visual feature; on the basis of the multi-modal large language model, splicing the embedding of the reference text, the embedding of the start mark, the embedding of the reference visual feature, and the embedding of the end mark into a target embedding sequence, performing attention processing on the basis of the embedding of the start mark, the embedding of the end mark, and an embedding selected by a sliding window in the target embedding sequence, and outputting a predicted sequence; and generating a predicted image and a predicted text on the basis of the predicted sequence.

Processing circuitry may configure a system to implement a CAR-OnMap (“CAROM”) air framework for vehicle localization and traffic scene reconstruction using the aerial video of the traffic scene. Such a system may obtain aerial video of a traffic scene including vehicles that traverse the traffic scene and a satellite map image of the traffic scene as a distinct reference image. In such an example, processing circuitry may determine aerial image reference points within the aerial image which correspond to reference points in the satellite map image of the traffic scene. Processing circuitry may responsively generate calibrated images of the traffic scene from individual frames of the aerial video and determine unique keypoints on the vehicles in the traffic scene. In such an example, processing circuitry may track the vehicles across the individual frames of the aerial video utilizing the unique keypoints. Processing circuitry may output vehicle metrics for the vehicles.

The invention discloses an AOI optical scheme automatic optimization method based on reinforcement learning, and belongs to the technical field of automatic optical detection. According to the method, a reinforcement learning technology is applied to automatic adjustment of optical schemes in a machine vision system, wafer images under different optical schemes are collected by using an AOI system, and scoring is performed by using a plurality of semantic segmentation models; constructing and training a non-reference image quality evaluation network, evaluating the optical imaging quality in real time, and designing a reward function on the basis; by using the Actor-Critic algorithm, the intelligent agent can autonomously learn an optimal parameter adjustment strategy, quickly adapt to different scenes, realize dynamic optimization of light source parameters and remarkably improve image quality, and an efficient and intelligent solution is provided for efficient application of a machine vision system in a complex industrial environment.

The invention relates to a multi-stage filtering road spilled object detection method based on dynamic difference analysis, which is suitable for automatic identification of unstructured foreign matters in video monitoring. The method comprises the following steps: firstly, extracting a reference image road mask, eliminating vehicle and pedestrian interference by using YOLOv8 detection, and extracting a motion candidate area through a frame difference method and background modeling; and then context expansion and super-resolution reconstruction are carried out on the candidate region, the candidate region is converted into an HSV space, multi-dimensional features such as color similarity, structural similarity and shadow determination are synthesized for screening, false detection is further removed in combination with inter-frame time sequence consistency, and finally a stable detection result is output. The method provided by the invention has the advantages of strong anti-interference capability, high adaptability, high detection precision and the like, and is suitable for the intelligent recognition task of the expressway thrown objects in a complex environment.

The invention discloses a metal structural part surface damage identification method based on machine vision, and belongs to the field of machine vision, and the method comprises the steps: obtaining reference image data with known damage features, carrying out the preprocessing, analyzing the change trend of a system detection state, and judging whether there is a deviation correction demand or not. And if the deviation exists, carrying out geometric correction processing on the lens distortion error to obtain a corrected reference image. Further separating the real change of the damage from the system deviation, and combining low-resolution and high-resolution detection to obtain the distribution data of the suspected damage area and the specific characteristic parameter data of the damage. According to the method, quantitative data of damage levels are obtained through automatic classification, detection differences among multiple devices are calibrated, visual presentation information of damage positions and levels is generated, and finally camera parameters and algorithm thresholds for subsequent detection are optimized and adjusted, so that high-precision damage detection and evaluation are realized.

The invention relates to an image frame insertion method and device in virtual shooting and a storage medium. The method comprises the following steps: acquiring at least two frames of reference images generated by a rendering engine; obtaining motion information and depth information of at least two frames of reference images generated by a rendering engine; and based on the motion information and the depth information of the at least two frames of reference images, determining a pixel value of a frame insertion image between the at least two frames of reference images, the frame insertion image and the at least two frames of reference images being used for sending to a display screen for display, and the display screen serving as a shooting background in virtual shooting. According to the embodiment of the invention, on-screen content can be smoothly played without improving the performance of a rendering end, the picture quality of a picture is remarkably improved, the data output capability of a rendering engine is fully played, redundant calculation is avoided, the computing power is saved, the remarkable frame rate improvement can be realized at relatively low cost, and the user experience is improved. The method meets the requirements of a virtual shooting scene, and has good stability and robustness.

The invention relates to the technical field of image processing, and discloses a packaging material printing quality detection method and system based on machine vision. The method comprises the following steps: acquiring a multispectral image sequence and three-dimensional shape data of a moving packaging and printing material under different illumination, and constructing a dynamic three-dimensional physical attribute field; generating a virtual reference image and a dynamic reference image, constructing a multi-modal reference image, carrying out space-time registration on the multi-modal reference image and the dynamic three-dimensional physical attribute field, and calculating the difference between the multi-modal reference image and the dynamic three-dimensional physical attribute field in different dimensions to generate a multi-dimensional difference quality field; each dimension difference is enhanced through local statistics, and the comprehensive defect confidence coefficient is calculated based on the enhanced dimension difference; and extracting a defect region based on the comprehensive defect confidence, generating a defect evolution sequence and a defect track, analyzing defect track characteristics, constructing a correlation model in combination with process parameter time sequence data of the printing equipment, and positioning a defect reason. According to the invention, high-precision, multi-dimensional and self-adaptive printing defect detection and traceability can be realized.

The present invention belongs to the field of medical image registration, and more specifically, relates to a building method of a multi-modal three-dimensional medical image segmentation and registration model, and an application thereof. The method includes: acquiring medical images of two modalities of each target, and respectively using the images as a reference image and a floating image to acquire a training sample; and using the training sample to simultaneously optimize three network parameters, so as to acquire a segmentation and registration model formed by a reference image segmentation model, a floating image segmentation model, and a registration model. The reference image and floating image segmentation models are respectively used to perform multi-scale segmentation on corresponding images to acquire multi-scale segmentation results having the same maximum scale as the original images. The registration model are used to acquire a multi-scale deformation field on the basis of the reference image, the floating image, a maximum scale reference image segmentation result, and a maximum scale floating image segmentation result. Each of a segmentation loss and a registration loss are the sum of segmentation and registration losses in each scale, and the segmentation loss includes a first-order gradient loss and / or a level set energy function loss. The present invention can improve registration accuracy.

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.

The invention relates to the technical field of engineering materials, in particular to an engineering material quality detection method and system based on image recognition, and the method comprises the steps: reference image acquisition, sampling point selection and marking, image acquisition, image comparison and positioning, secondary acquisition and anomaly analysis. Compared with the defects that a detection system in the prior art is rigid in process, poor in adaptability and difficult to cope with a complex and changeable engineering field environment, the scheme constructs a full-process automatic system from intelligent sampling, self-adaptive image acquisition, precise registration and semantic level difference detection to intelligent post-processing and analysis; the method has high intelligence, adaptivity and robustness, and can stably and efficiently complete quality detection tasks in a complex engineering environment.

The invention belongs to the technical field of artificial intelligence image generation, and particularly relates to an image generation method and system based on style feature injection, and the method comprises the steps: carrying out the multi-dimensional feature analysis of a reference image specified by a user side through a pre-trained multi-level style extraction model, extracting a style feature vector, and carrying out the feature extraction of the style feature vector; the style feature vector comprises a color feature vector, a texture feature vector, a composition feature vector and an illumination feature vector; obtaining a text description input by a user side, and outputting triple information including a scene entity, an entity attribute and a spatial relationship; performing weighted fusion on the triple information and the style feature vector to obtain a style enhanced semantic embedding vector; and inputting the style-enhanced semantic embedding vector into a generative adversarial network for splicing, and outputting an image. The method has the effect of remarkably improving the similarity between the generated image and the reference style.

The invention discloses an intelligent manufacturing system and method based on an industrial robot, and relates to the technical field of industrial robot control, and the method comprises the steps: constructing a workpiece posture-space structure topological graph according to a cross-scale visual recognition result, carrying out the space comparison with an original trajectory planning graph, outputting a space deviation mapping relation, and carrying out the calculation of a spatial deviation mapping relation; performing spatial correlation analysis and path reachability evaluation on the workpiece attitude-spatial structure topological graph by using a graph neural network to obtain an end execution path instruction; driving the industrial robot to perform intelligent manufacturing operation through the tail end execution path instruction, and obtaining an actual operation result image; and performing feature alignment and difference comparison processing on the actual operation result image and the process reference image to obtain an operation deviation feature mapping relation, performing operation quality evaluation, and outputting an operation result visual detection label. According to the method, the adaptability and the manufacturing precision of the operation path of the industrial robot are effectively improved.

The invention relates to the technical field of goods shelf detection, in particular to a self-detection method and device for goods shelf settlement, and provides the following scheme: obtaining a top view image through an image sensor arranged right above the top of a goods shelf, dividing the image into a plurality of grid units, and positioning a rectangular geometric shape by utilizing Hough transform; and screening a plurality of to-be-detected areas in combination with the edge features. For an area to be measured, homographic registration and ortho-rectification are carried out based on a reference image, a displacement field is obtained by adopting sub-pixel-level dense registration, and a geometric parallax component field corresponding to imaging parameters is obtained through robust estimation. And under the hypothesis of small deformation, inverting the parallax into a pixel normal distance, and carrying out weighted aggregation on the local region to obtain a local distance measurement result. And by iteratively combining adjacent grids, determining a settlement area boundary, and finally outputting a settlement detection result. Millimeter-level settlement quantification can be realized under a single-frame image, hardware transformation is avoided, and the method is suitable for automatic detection and long-term monitoring of multi-specification goods shelves.

The invention relates to the technical field of image processing, in particular to an unmanned aerial vehicle positioning method and system based on machine vision, and the method comprises the steps: obtaining a current frame image and a reference image in a real-time video stream of an unmanned aerial vehicle, generating an initial matching pair set, and calculating the structural consistency of each matching pair, the method comprises the steps of adaptively determining a screening threshold value of a current frame image based on structural consistency, determining a screening matching pair set by utilizing the screening threshold value, evaluating a positioning contribution weight of each matching pair of the screening matching pair set, executing weighted pose calculation based on the positioning contribution weights, and obtaining an instantaneous pose of an unmanned aerial vehicle in the current frame image. And inputting the instantaneous pose as an observation value into a time sequence filtering model, performing time sequence fusion in combination with a motion model of the unmanned aerial vehicle, and outputting the final pose estimation of the unmanned aerial vehicle in the current frame image so as to complete the accurate positioning of the unmanned aerial vehicle. The method improves the accuracy of unmanned aerial vehicle positioning.

The invention relates to the technical field of power equipment state monitoring, and particularly discloses a transformer fault diagnosis method and system based on image recognition, and the method comprises the steps: collecting a transformer multi-mode image sequence in real time, and carrying out the definition and part integrity evaluation and screening to form an initial image set; performing multi-scale space registration on the initial image set and a transformer normal state standard template to generate a reference image, and reversely deriving a displacement vector field based on pixel-level difference; carrying out smooth optimization and geometric reconstruction on the displacement vector field under the geometric constraint of the transformer structure, and generating a correction image with a real structure; fault feature enhancement is carried out in a gradient domain of the corrected image, a fault area is identified through matching of multichannel feature extraction and a transformer typical fault feature library, and a diagnosis report integrating fault types, confidence coefficients and geometric parameters is generated; according to the method, the problem of image geometric deformation caused by shooting condition differences is effectively solved, and the accuracy and reliability of fault identification are improved.

Methods and systems for training a prediction model to predict a mask image in which mask rule check (MRC) violations or process violations (e.g., edge placement error, sub-resolution assist feature (SRAF) printing) are minimized or eliminated. The prediction model is trained based on a loss function that is indicative of (a) a difference between the predicted mask image and a reference image, and (b) at least one selected from: an MRC evaluation of the predicted mask image or an evaluation of a simulated image of the predicted mask image.

The invention belongs to the technical field of visual identification, and discloses a board surface defect detection method and system based on industrial vision, and the method comprises the steps: constructing a standard board reference library; acquiring raw material information and visual data of a to-be-detected wood board; selecting a plurality of board images from the reference library according to the to-be-detected board information to form a contrast image set; performing comparative analysis on the to-be-detected wood board image and the contrast image set to obtain an abnormal region; and monitoring an abnormal region, if the abnormal region is empty, judging that no defect exists, otherwise, extracting an abnormal region image and inputting the abnormal region image into a pre-trained classification model to identify a defect type. According to the method, a two-stage strategy of firstly positioning the abnormal area and then identifying the defect type is adopted, the abnormal area is positioned by comparing with a defect-free sample, and only defect identification is performed on the abnormal area, so that the problem that defect features are diluted in the whole image is avoided; the problems of high identification difficulty, low accuracy and the like caused by overlarge information amount of the whole image in the prior art are solved.

The invention relates to the technical field of printed matter quality detection and computer vision and the technical field of artificial intelligence systems in the production field, in particular to a color box printed matter printed pattern visual detection algorithm. The invention discloses a visual detection algorithm for a printing pattern of a color box printed matter. The visual detection algorithm comprises the following steps of image acquisition, preprocessing, feature extraction, reference comparison, defect evaluation and defect classification. According to the scheme, the accuracy and the real-time performance of complex printing pattern defect detection are improved. A light-weight multi-scale attention convolutional neural network and a self-learning mechanism are combined, defects in various printing patterns such as block colors, fine characters and graph gradient are effectively detected, and human intervention and misjudgment are reduced. A defect saliency map is generated through color normalization, geometric correction preprocessing and reference map comparison, an online misjudgment cache and incremental learning strategy is introduced, self-adaptive optimization of a model along with time is kept, and real-time high-precision quality monitoring of an offset printing color box production line is achieved.

The invention provides a novel three-dimensional reconstruction method for an interested target in a complex environment. The method comprises the following steps: firstly, constructing a data set for personalized segmentation and reconstruction, wherein the data set comprises a reference image and a mask thereof; then, extracting features through an SAM image encoder, and fusing multi-view features to construct a cross-view position similar graph; then, positive and negative prompt points are selected from the image, multi-view consistent prompt features are generated by means of an SAM prompt encoder, and mask decoder adjustment is carried out in combination with self-adaptive attention of a local area; thirdly, fusing masks with different scales by utilizing the learnable weight, and finely adjusting and generating an accurate mask of the interested target by taking the reference mask as supervision; and finally, acquiring a clean foreground image based on the mask, extracting sparse point clouds and camera parameters by means of COLMAP, and inputting the point clouds into a 3DGS pipeline to generate a high-quality three-dimensional reconstruction model. According to the method, the high-quality three-dimensional model of the interested target is reconstructed from the multi-view image, and the method has high practical application value.

Methods, systems, and computer-readable storage media for receiving a product image depicting a product that is to-be-inspected for defects, transmitting a request to a LLM system, the request including the product image and a reference image, receiving, from the LLM system, a textual response, the textual response being generated by the LLM system at least partially by processing the product image and the reference image, processing the textual response and the product image through a RIS model to provide an output image that includes one or more masks, each mask indicating a defect in a product depicted in the product image, and providing the output image with an indication that the product is defective.

The invention relates to the technical field of image recognition, in particular to an agricultural crop disease and pest detection method and system based on image segmentation, and the method comprises the steps: collecting a vertical view angle image and an inclined view angle image of a tea garden through an unmanned aerial vehicle, carrying out the image registration through SIFT feature extraction, KNN matching and RANSAC filtering, and carrying out the alignment to a reference image coordinate system. And segmenting the foreground region by adopting a U-Net algorithm, and performing post-processing optimization. Positioning a disease area through a color detection method, extracting disease features, and identifying a disease stage by using a CNN algorithm; and using a YOLOv3 algorithm to identify insect body areas, extracting insect pest features, and evaluating insect pest degrees. And finally, based on the disease stage and the pest degree, using an LSTM algorithm to predict the pest diffusion trend, and generating a space thermodynamic diagram according to the reference image coordinate system, thereby improving the detection precision and timeliness, and providing technical support for intelligent agricultural prevention and control.

The invention belongs to the technical field of artificial intelligence generation, and particularly relates to a Chinese painting line draft coloring method based on time sequence modeling and cross-modal fusion, which comprises the following steps of: acquiring a multi-modal Chinese painting data set, and taking a line draft image, text description and a reference image in the image data set as original input; after preprocessing, dividing into a training set and a test set; the line draft image, the text description and the reference image serve as input, a Chinese line draft coloring network model is trained, and a training model is obtained; the Chinese line drawing draft coloring network structure comprises a text time sequence modeling module and a multi-modal feature fusion module, the text time sequence modeling module extracts semantic features through a text encoder and introduces position coding and bidirectional LSTM to construct a time sequence relation between words, the multi-modal feature fusion module fuses text and image features, and the text and image features are integrated to form a multi-modal feature fusion model. Detail optimization and feature enhancement are carried out; through the multi-modal data set, time sequence modeling and cross-modal fusion, automatic high-quality coloring of the Chinese drawing draft is achieved.

The invention belongs to the technical field of image data processing, and discloses a beverage package defect visual detection method and system, and the method comprises the steps: firstly, shooting a defect-free beverage package sample under a preset scene, and building a standard image library; then collecting and preprocessing a to-be-detected package image, obtaining a package model, and selecting a corresponding reference image from the standard image library; the detection image and the reference image are registered, difference is carried out to obtain a difference image, and enhancement processing is carried out on the difference image; and performing threshold processing on the enhanced image to extract an abnormal region, analyzing features of the abnormal region to determine the position and size of a defect, and generating a detection result report. According to the method, the optical distortion effect of the transparent package on the background pattern is analyzed, invisible defects are converted into detectable background changes, different enhancement strategies are adopted for different types of areas, the defect detection problem of the transparent package is effectively solved, and the detection sensitivity and accuracy are improved.

The invention belongs to the technical field of image processing, and discloses a maskless image synthesis method and system based on a diffusion model, and the method comprises the steps: inputting a background image and a noise image containing a target object into a pre-trained potential diffusion model, and enabling the potential diffusion model to execute a reverse denoising process under the guidance of a condition vector, the target object is synthesized in a self-adaptive mode, and a synthesized image is obtained; wherein the condition vector acquisition mode comprises the following steps: encoding a reference image containing a target object into an object embedding vector, and generating a group of learnable background cue words according to the object embedding vector; splicing with the background prompt word; and performing spatial mapping on the spliced feature representation to obtain a condition vector. The method can overcome the defects that in an existing image synthesis technology, the process is tedious, the efficiency is low, a large amount of manual intervention is needed, the synthesis result lacks the sense of reality and harmony, and especially the foreground object cannot be adaptively adjusted according to the background environment.

The invention discloses a rail transit fastener model identification system and method, and relates to the technical field of fastener overhaul, an initial image of a rail is acquired through an image acquisition module, and an image preprocessing module is used for preprocessing to obtain a reference image; the image analysis module inputs the reference image into a preset model for processing, completes segmentation of the fastener assembly and the steel rail assembly, and obtains segmented images; the positioning module is used for screening the images of part of fastener assemblies and the images of the rail bottom of the steel rail and restoring the images to the reference images; the feature acquisition module is used for acquiring a reference adjustment line based on the segmented image of the rail bottom, acquiring feature parameters of the partial components based on the segmented images of the partial components, and correcting by using the reference adjustment line to obtain reference feature parameters; and the model identification module is used for matching the reference characteristic parameters of the screening component with the data in the constructed database and outputting a corresponding fastener model. According to the invention, efficient identification of the models of the fasteners can be realized, and the identification accuracy is also guaranteed.

The invention relates to the technical field of artificial intelligence and industrial visual inspection, and discloses a Dinov3 and SAM-based few-sample industrial defect target detection method and system, and the method comprises the steps: building a reference feature library: extracting the features of a few defect reference images through a Dinov3 model, and generating a category prototype through weighted aggregation; generating a similarity response diagram: calculating the pixel-by-pixel similarity of the image to be detected and the reference prototype, and performing context enhancement filtering; generating a segmentation prompt: screening a salient region in combination with a space attention mechanism, and generating a geometric prompt required by the SAM model; fine segmentation is executed; an accurate mask of the defect instance is generated by using an SAM model; and confidence evaluation: multi-dimensional scoring is carried out, and a dynamic threshold value is adopted to screen results. Rapid deployment can be realized without fine adjustment of the model, the problem of data shortage in the initial stage is effectively solved, data is continuously accumulated through automatic detection, a foundation is laid for training a better special model, and the method is suitable for scenes such as new product import or new defect discovery.

The invention belongs to the technical field of artificial intelligence, and relates to a multimodal model semantic enhancement and comparative learning method based on a colored lamp knowledge graph, which comprises the following steps: associating an original text with a knowledge graph to generate a structured sentence tree, and carrying out embedded coding to obtain an embedded matrix; inputting the embedded matrix and the visibility matrix into a stacked Mask-Transform encoder to obtain a structured semantic feature, and carrying out modeling through a stacked self-attention block to obtain structured knowledge; respectively inputting the original text into a text encoder and a visual encoder of the multi-modal model, obtaining a reference text feature and a reference image feature, and carrying out dynamic gating weighted fusion to obtain a fusion vector; and obtaining a positive sample text, obtaining a high-quality negative set according to the positive sample text, inputting the fusion vector, the reference image features and difficult negative samples in the corresponding high-quality negative set into a contrast learning module, and obtaining symmetric contrast learning loss for training a multi-modal model.

A method for detecting printing defects in a photolithography mask that will print on a wafer when using the photolithography mask in a specific photolithography system to print semiconductor structures on the wafer, the method comprising: acquiring a first aerial image of the photolithography mask using a mask inspection system; generating a second aerial image of the photolithography mask by applying a machine learning model (26) to the first aerial image, wherein the machine learning model is trained to map a first aerial image acquired by a mask inspection system to a second aerial image that emulates the application of the specific photolithography system to the photolithography mask; and detecting printing defects in the photolithography mask by comparing the second aerial image to a reference image.

The invention discloses a dynamic split mirror generation system and method based on a controllable diffusion model, and belongs to the technical field of film and television production. The implementation method comprises the following steps of: 1, setting a keyword text by a user, and inputting the keyword text into ChatGPT to generate a script; 2, converting the script into a scene category, a camera motion mode, a character role position and action and image description in a shot language by utilizing ChatGPT; 3, using a CLIP model to carry out contrast training on the image encoder and the text encoder; 4, performing an OpenPose model on the action reference image to obtain skeleton key points of the character role, and converting the skeleton key points into image character actions; 5, performing action fine-grained control on the character action of the image by using a Stable Diffusion model and a ControlNet model, and generating a split image; 6, utilizing a Pika Labs model to generate a dynamic video from the split image; compared with the prior art, the accuracy of user role action matching under the scene based on multi-text and high-complexity actions is improved.