122 results about "Image reference" patented technology

The invention aims to disclose an image anaphora segmentation method based on multilevel feature fusion and dual-channel information enhancement. The method comprises the following steps: obtaining and extracting visual features to be segmented and language features in an anaphora text; self-adaptively matching visual features of different levels by using language features, and performing spectrum enhancement on the visual features by using Fourier transform; through cross-modal fusion of visual and language features of different hierarchies, multi-level visual features with language perception are constructed; constructing visual language fusion features by using dual-channel information enhancement; and generating a segmentation mask. According to the method, the advantages of a large model, adaptive dynamic matching and feature enhancement are fused, automatic generation of the segmentation mask is realized, the efficiency and accuracy are improved, and the method has wide application and popularization values.

The invention discloses a feature extraction method and system based on heterogeneous multi-modal information fusion, and the method comprises the steps: constructing a spectrum reference system through synchronously collecting the data of an image sensor, a laser radar and an infrared spectrometer carried by an unmanned plane, achieving the unified calibration of image data, and generating a unified image reference through employing a feature field fusion technology; extracting multi-modal characteristic spectral lines, performing complementary analysis to confirm fusion characteristics, and establishing a dynamic weight table by matching working frequency bands; a separation factor is generated based on correlation analysis of a point cloud density field and a modal characteristic spectral line, a correction coefficient is generated in combination with characteristic fluctuation analysis, and a pure visual characteristic signal is identified; a mapping transformation kernel is constructed to realize standardized conversion of feature data, a migration coefficient is generated through spatial positioning analysis and feature intensity analysis, a regulation and control instruction is generated through multi-level feature processing, a weight table is adjusted based on the regulation and control instruction to form closed-loop optimization, a hierarchical feature extraction signal is generated, and deep fusion and intelligent extraction of features are realized.

The invention provides a video reference frame management method applying a real-time scene. The method comprises the following steps: updating a reference frame queue: (1) inputting an image Fn to be compressed; (2) generating a reconstructed image F'n from the to-be-compressed image Fn through a coding inverse process; (3) sending the reconstructed image F'n into an image reference frame queue and a traditional reference frame queue at the same time for respective update processing; comprising the following steps of: (1) inputting an image Fn to be compressed; (2) generating a scene ID of the image; (3) comparing the scene ID of the generated image with the scene ID of the scene reference frame queue; (4) judging whether the scene ID of the to-be-compressed image Fn is the same as the scene ID in the scene reference frame queue or not; (5) if yes, taking the scene reference frame images with the same scene ID as reference frames of the to-be-compressed image; and (6) if not, obtaining the reference frame from the traditional reference frame queue. According to the method, the video compression efficiency can be remarkably improved.

The invention belongs to the technical field of computer vision, and discloses an interactive semi-automatic anomaly detection labeling method, system and device and a medium, and the method comprises the steps: obtaining a to-be-detected image of an industrial product, manual click input representing an abnormal region position, and natural language description of a defect type; based on the defect-free image reference set, extracting position constraint features of each image patch of the to-be-detected image, and calculating pixel-level position rapid abnormal residual features; converting the natural language description into a discriminant language feature vector by using a pre-training language model and a discriminant encoder; processing the residual feature through a residual feature branch, and generating a first fusion feature through a cross-modal attention mechanism under the guidance of a language feature vector; processing the original pixel information by combining the pixel information branch with click input to generate a second fusion feature; and fusing the two features and decoding to obtain a pixel-level abnormal annotation mask, thereby realizing high-precision semi-automatic annotation of the abnormal region in the industrial product image.

The invention relates to a remote sensing image anaphora segmentation method and system based on multi-mode prompt, and belongs to the technical field of computer vision and remote sensing intelligent interpretation. The method comprises the following steps: S1, data preprocessing: dividing a remote sensing image anaphora segmentation data set; s2, constructing a remote sensing image anaphora segmentation model based on multi-modal prompt, wherein the remote sensing image anaphora segmentation model comprises an image encoder, a space prior module, a text encoder, a fine-grained visual language interaction device and a multi-modal prompt encoder; s3, training a remote sensing image anaphora segmentation model based on multi-modal prompt: for the training of the remote sensing image anaphora segmentation model, performing optimization training on the model by using a loss function combining Focal loss, cross entropy loss and Dice loss; and S4, outputting a segmentation result: inputting a remote sensing image to be segmented into the trained model, and then inputting a model output result into a mask decoder to complete anaphora segmentation of the target object. According to the invention, the interpretation efficiency is improved.

The invention relates to the field of image data processing, and provides a steam boiler gas leakage detection method based on image processing, which comprises the following steps: setting an image acquisition unit, covering a predetermined leakage risk area together, acquiring corresponding reference images under different production working conditions, and establishing an image reference library covering a target area; the method comprises the following steps: dividing a boiler operation time axis into a plurality of production states, calling corresponding reference images according to different states, and carrying out difference, partition comparison and motion detection on the real-time acquired images to obtain suspected leakage cloud cluster areas in the corresponding states; arranging a condensate water indication patch, collecting a patch image, extracting through color, brightness and texture features to form a patch humidity change curve, carrying out multi-source information fusion on the patch humidity change curve, time sequence features and production time states, and outputting a corresponding steam leakage risk level; and generating alarm information according to the steam leakage risk level, and recording and archiving the alarm information in a monitoring and management system for energy consumption analysis and risk tracing.

The invention discloses an RAG document splitting optimization method and system in the operator field, and belongs to the technical field of large model optimizing.The method comprises the steps that a document is uploaded, and source files and file information are stored through minio and paradeDB respectively; constructing a document loader, automatically selecting a corresponding loader according to a file type to carry out file processing, converting the file into a uniform Markdown text, analyzing a picture in the document, and converting the picture into a base64 format; constructing a picture processor, extracting a picture base64 character string in the text, processing a bitmap and a vector diagram, and converting the bitmap and the vector diagram into a Markdown picture reference format; constructing a document divider; vector conversion; and recalling the text. According to the method, the problem that picture extraction, conversion and processing are complex in the current RAG is solved, vector retrieval, full-text retrieval and mixed retrieval functions can be achieved through one database, and the operation and maintenance cost is reduced.

The embodiment of the invention provides a video image component prediction method and device, and a computer storage medium. The method can comprise the following steps: acquiring a reference value set of a first image component of a current block; determining a plurality of first image component reference values from a reference value set of the first image component; performing first filtering processing on the sample values of the pixel points corresponding to the plurality of first image component reference values to obtain a plurality of filtered first image reference sample values; determining to-be-predicted image component reference values corresponding to the plurality of filtered first image reference sample values; determining parameters of a component linear model according to the plurality of filtered first image reference sample values and the to-be-predicted image component reference value; according to the component linear model, mapping the reconstruction value of the first image component of the current block to obtain a mapping value; and determining a predicted value of the to-be-predicted image component of the current block according to the mapping value.

This application provides a video image component prediction method and apparatus, and a computer storage medium. The method may include: acquiring a reference value set of a first image component of the current block; determining multiple first image component reference values ​​from the reference value set of the first image component; performing a first filtering process on the sample values ​​of the pixels corresponding to the multiple first image component reference values ​​respectively to obtain multiple filtered first image reference sample values; determining the image component reference value to be predicted corresponding to the multiple filtered first image reference sample values; determining the parameters of a component linear model based on the multiple filtered first image reference sample values ​​and the image component reference value to be predicted; performing a mapping process on the reconstructed value of the first image component of the current block according to the component linear model to obtain a mapping value; and determining the predicted value of the image component to be predicted of the current block based on the mapping value.

Techniques for video processing including video coding, video decoding, and video transcoding are described. One example method includes performing a conversion between a video comprising a video picture and a bitstream of the video, the video picture comprising one or more slices. The video picture refers to a picture parameter set, and the picture parameter set conforms to a format rule that specifies that the picture parameter set includes a column width list of N slice columns, where N is an integer. The (N-1) th slice column is present in the video picture, and the width of the (N-1) th slice column is equal to the (N-1) th entry in the explicitly included slice column width list plus a number of codec tree blocks.

The invention discloses a video generation method and device, a model training method and device and a computer program product, and the video generation method comprises the steps: obtaining a target audio and a reference picture used for generating a video, and the reference picture comprises a sound production object; determining a global visual feature of each to-be-generated video frame corresponding to the audio clip according to the clip features of one or more audio clips corresponding to the target audio and the reference image; according to the pronunciation feature of each audio frame of the target audio and the lip feature of the sounding object in the reference picture, determining the lip feature of the sounding object in a to-be-generated video frame corresponding to the audio frame; and generating each video frame according to the lip feature and the global visual feature corresponding to the to-be-generated video frame. Through the scheme provided by the invention, the expression of characters in the generated video is more vivid and natural, the lip action and the audio can be accurately synchronized, and the visual experience of a user is improved.

The invention provides an unmanned aerial vehicle image anaphora detection method based on a mixed granularity expert, and belongs to the field of unmanned aerial vehicle image anaphora detection. The cross-modal sequence is input into multiple layers of stacked coding blocks, each layer of coding block comprises an MHSA layer, an MoG layer and an FFN layer which are connected in sequence, and after multi-layer iteration, a cross-modal scale comprehensive memory is output; the cross-modal scale comprehensive memory and the target query are input into a multi-layer stacked scale comprehensive decoder, each layer of decoder comprises an MHSA layer, an MHCA layer, an MoG layer and an FFN layer which are connected in sequence, and coarse query representation is output; the coarse query representation and the cross-modal scale comprehensive memory are input into a multi-layer stacked scale sensitive decoder, each layer of decoder comprises an MHSA layer, an MMCA layer and an FFN layer which are connected in sequence, after multi-layer iteration, the output fine-grained query representation enters a regression prediction head, and an anaphora detection result is obtained; the invention further provides a detection system. The problem that an existing method is low in detection precision in an aerial photography scene is solved.

The invention relates to an image generation method and device, electronic equipment and a storage medium. The method comprises the steps that a preset page comprising at least one kind of image reference information is displayed; in response to a reference image selection operation for first image reference information, determining at least one reference image corresponding to the first image reference information, the first image reference information being any one piece of image reference information in the at least one piece of image reference information; in response to the image generation operation, displaying at least one generated image, the at least one generated image being generated based on target reference information corresponding to each of a plurality of target reference images, the plurality of target reference images being reference images determined when the image generation operation is triggered, the plurality of target reference images correspond to one or more pieces of image reference information in the at least one piece of image reference information. According to the embodiment of the invention, a user can flexibly and conveniently select the image reference information and the corresponding reference image, so that the image generation effect is improved.

Arrangements are disclosed that enable reliable and accurate referencing of image distance, orientation, and / or color. According to exemplary embodiments, an image reference marker is arranged on or near an area to be imaged. A display shows a live view of the area with a superimposed alignment pattern, while a user positions the image capture device so that the image of the marker is aligned with the alignment pattern. Once satisfactory alignment is achieved, an image of the area can be captured manually or automatically.

Arrangements are disclosed which provide reliable and accurate image ranging, orientation, and / or color referencing. In exemplary implementations, an image reference marker is arranged at or proximate to an area to be imaged. A display shows a live view of the area with a matching pattern superimposed thereon as a user positions the image capture device to align the image of the marker with the matching pattern. Once satisfactory alignment is achieved, an image of the area can be captured manually or automatically.

A video encoding method using a plurality of reference pictures includes: selecting whether or not a resilient picture referencing scheme is to be used for encoding video; writing a parameter indicating the selection into a header of an encoded video bitstream; and encoding a picture using inter-picture prediction using a result of the selection.

A data platform having an anti-abuse analysis pipeline is provided. The anti-abuse analysis pipeline detects an image referenced in an application package and schedules an application scan to scan application source files and generate application scan results. The anti-abuse analysis pipeline also schedules an image scan to scan the image and generate image scan results. The anti-abuse analysis pipeline extracts application source files from the application package and executes an application scan using the extracted application source files to generate application scan results. The anti-abuse analysis pipeline extracts artifacts from the referenced image and executes an image scan using the artifacts to generate image scan results. The anti-abuse analysis pipeline determines a completion of the application scan and the image scan and generates a scan result using the application scan results and image scan results.

The present application relates to a task decomposition-based scene consistency image instruction generation method, and the generation method comprises the following steps: step S1, image analysis, object recognition, position and state recognition are performed; step S2, instruction understanding is performed, and set key information is extracted; step S3, feature extraction of a pre-scene image in a latent space is realized through a VAE encoder; step S4, a task decomposition generation step sequence is generated, and step-by-step description is performed; step S5, based on the step sequence, an instruction weight matrix with front and rear correlations is generated; the instruction weight matrix with front and rear correlations is designed based on the step sequence of step S4; step S6, based on the image reference of the pre-scene and the instruction weight, a visual instruction of the current scene is generated; the present application is reasonable in design, compact in structure and convenient to use.

This invention provides a method, apparatus, device, and storage medium for generating digital life forms from multiple reference images. The method includes: acquiring multiple target reference images corresponding to different attributes such as appearance, clothing, and scene; extracting features from each of the multiple target reference images to determine multiple target feature vectors; determining comprehensive constraints, which at least include a comprehensive condition vector and condition injection parameters; inputting the comprehensive constraints into a target generation model to generate an image, determining an initial generated image corresponding to the digital life form; and optimizing the quality of the initial generated image corresponding to the digital life form to determine the target generated image corresponding to the digital life form after quality optimization. The character generated by this invention is highly consistent with each reference image in appearance, clothing, and background, achieving a realism close to that of a photograph, and the implementation process is simple and low-cost.

Techniques for video processing including video coding, video decoding, and video transcoding are described. One example method includes performing a conversion between a video and a bitstream of the video, the video comprising a video picture comprising one or more slices. The video picture references a picture parameter set, and the picture parameter set conforms to a format rule, the format rule specifying that the picture parameter set comprises a list of column widths for N slice columns, where N is an integer. An (N-1)th slice column is present in the video picture, and a width of the (N-1)th slice column is equal to an (N-1)th entry in the explicitly included list of slice column widths plus a number of coding tree blocks.

This application provides a video image component prediction method and apparatus, and a computer storage medium. The method may include: acquiring a reference value set of a first image component of the current block; determining multiple first image component reference values ​​from the reference value set of the first image component; performing a first filtering process on the sample values ​​of the pixels corresponding to the multiple first image component reference values ​​to obtain multiple filtered first image reference sample values; determining the image component reference value to be predicted corresponding to the multiple filtered first image reference sample values; determining the parameters of a component linear model based on the multiple filtered first image reference sample values ​​and the image component reference value to be predicted; performing a mapping process on the reconstructed value of the first image component of the current block according to the component linear model to obtain a mapping value; and determining the predicted value of the image component to be predicted of the current block based on the mapping value.

The invention relates to a PIS distributed automatic energy-saving electronic screen, and provides a method for performing histogram equalization on reference values of original image (white, red, blue and green) color values on the basis of image pulses on the basis of power supplied to an LED module, setting the value of current (If) flowing in an LED, and adjusting the brightness of the LED module. And then comparing the difference between the image reference value of the gamma controller and the image correction value equalized by the histogram at a gain controller, considering the image quality, the brightness and the image size, and identifying the change of the loss value of the difference subtraction by using the power consumption difference of the display image, thereby automatically reducing the loss and realizing the energy-saving PIS distributed automatic energy-saving electronic screen.

A system and method for software container remediation. A method includes determining that a vulnerability of a software container resides in a first origin image of the software container at least partially by identifying a plurality of derived container images referencing the origin image which have the vulnerability, wherein a first derived container image of the plurality of derived container images is used to run the software container; and rebuilding the first derived container image using contents of a second origin image, wherein the second origin image avoids the vulnerability.

A decoding method is disclosed. A first motion compensation filter is selected in a case where a condition is true and a second motion compensation filter is selected otherwise. A current block is reconstructed based on an inter prediction obtained using the selected motion compensation filter. The condition is true in a case where any one of the following conditions is true: the current block is predicted using CIIP, the current block is predicted using MHP, at least one motion vector component is below a value or has a given pel-accuracy, a picture reference index is equal to a given value, a temporal index is among a given set of temporal indices.

Provided are a video image component prediction method and apparatus, and a computer storage medium. The method may comprise: acquiring a reference value set of a first image component of a current block; determining, from the reference value set of the first image component, multiple first image component reference values; respectively carrying out first filtering processing on a sample value of a pixel point corresponding to each of the multiple first image component reference values to obtain multiple filtered first image reference sample values; determining reference values, corresponding to the multiple filtered first image reference sample values, of an image component to be predicted; according to the multiple filtered first image reference sample values and the reference values of the image component to be predicted, determining a parameter of a component linear model; according to the component linear model, carrying out mapping processing on a reconstruction value of the first image component of the current block to obtain a mapping value; and according to the mapping value, determining a prediction value of the image component to be predicted of the current block. 20 24 28 72 36 27 D ec 2 02 4 A B S T R A C T 2 0 2 4 2 8 7 2 3 6 2 7 D e c 2 0 2 4

This application relates to a method, apparatus, computer device, and storage medium for remediating image vulnerabilities. The method obtains a hash fingerprint of the image layer marked as vulnerable, generated based on the image file change record and a timestamped salt value. Based on this hash fingerprint and the hierarchical dependencies encompassing the build relationships and version evolution relationships between image layers, candidate business images referencing the vulnerable layer are traced upwards, and related candidate newly built images and derived image layers are analyzed downwards. By comparing with currently running instances in the container cluster, the target image and image layer actually running are selected from the candidate objects. The target object is input into a preset remediation priority evaluation model to obtain a quantified remediation priority evaluation value, based on which a vulnerability remediation plan is determined. This method achieves accurate source tracing and dynamic convergence of the vulnerability's impact scope, and optimizes remediation decisions through priority evaluation, effectively improving the efficiency and targeting of vulnerability remediation.

The invention discloses an SAR (Synthetic Aperture Radar) image interpretation method, device and equipment and a storage medium, and relates to the technical field of image data processing. The method comprises the following steps: acquiring an SAR image of a disaster area and imaging information of the SAR image, wherein the imaging information at least indicates imaging time, data resolution, a lifting track, a side view direction and an incident angle; processing the SAR image by using image processing software to obtain a corrected image of the SAR image; on the basis of image features associated with image reference features in the corrected image, the corrected image is interpreted according to the imaging information, an interpretation result is obtained, and the image reference features indicate common image features convenient to interpret in the SAR image; the interpretation result is used for identifying the SAR image so as to draw a plotted image, the plotted image indicates the disaster situation of the disaster area, and the disaster situation at least comprises the specific position of the disaster area, the disaster range, the position and size of disaster facilities and multiple pieces of information of the surrounding mountain, river and road positions. According to the embodiment of the invention, the interpretation difficulty of the SAR image can be reduced.

This application relates to a method and system for detecting fabric defects, specifically in the field of fabric defect detection. The method includes: receiving several actual images of fabric areas from an image acquisition device group, along with the identification codes of the image acquisition devices corresponding to the target actual images; retrieving a standard image corresponding to the identification code from a preset fabric image reference database; if the actual similarity value obtained by comparing the actual image and the standard image is less than a preset similarity standard value, then determining that the fabric area in the actual image has a defect; and sending a warning message related to the presence of a defect in the fabric area of ​​the actual image to the user terminal. The technical advantage of this application is that it automatically detects fabric defects during the fabric production process, resulting in high detection efficiency.

The application relates to a minimum spanning tree-based SAR tomography reference net generation method and device. The method comprises the following steps: calculating amplitude deviation index values of all PS points in a remote sensing imaging area constituting an imaging reference net, selecting a PS point with the minimum amplitude deviation index value from all PS points as a starting reference point according to the amplitude deviation index values of all PS points, adding the starting reference point into an SPS point set, and initializing an SPS edge set as an empty set; the imaging reference net comprises a PS point set; according to a pre-set distance threshold, PS edges meeting the distance threshold are sequentially found in the SPS point set and the PS point set, and a candidate SPS edge set is set; the highest-quality edge is selected from the candidate SPS edge set and added into the SPS edge set, and the end points corresponding to the highest-quality edge are moved from the PS point set to the SPS point set, and finally, an SPS edge set and an SPS point set are output; and a SAR tomography reference net is constructed according to the final SPS edge set and the SPS point set. The method can generate a reference net which maximally covers a full scene.

This application provides an image classification method, apparatus, electronic device, and storage medium, belonging to the fields of artificial intelligence and digital healthcare technology. The method includes: acquiring and inputting training image features into an original image classification model including an original encoder and an original decoder; encoding the training image features using the original encoder to obtain training image vectors, the training image vectors including: image domain vectors, image semantic vectors, and image instance vectors; decoding the training image vectors using the original decoder to obtain image prediction categories; decoupling the training image vectors into a decoupling model to obtain image decoupling information; adjusting the parameters of the original image classification model according to preset image reference categories, image prediction categories, and image decoupling information to obtain a target image classification model; and inputting target image features into the target image classification model to perform image classification to obtain the target image category. This application can improve the accuracy of image classification.