696results about "Still image data querying" patented technology

A method and apparatus for generating photorealistic synthetic images by receiving multiple forms and multiple instances of user input corresponding to a user's visual idea, executing an iterative image search to identify pre-existing images semantically aligned with the user's visual idea, and using an image synthesis deep learning model to generate at least one synthetic image based on the multiple forms and instances of user inputs.

The invention provides a visualization system capable of synchronously displaying multiple types of data according to time. Comprising a distributed service cluster composed of a micro-service, a user management micro-service, a data transmission micro-service, a data storage management micro-service, a data extraction micro-service, a data visualization display micro-service, a data visualization template management micro-service and a resource monitoring micro-service; the micro-services are packaged in a containerized manner and interact by adopting a lightweight communication protocol, and automatic deployment and dynamic expansion are realized through a container arrangement tool; the system is provided with a basic parameter set with customizable micro-service configuration and a graphical configuration interface which are used for cooperatively generating a system operation environment configuration strategy. The user management micro-service establishes a multi-dimensional authority system based on a role access control model, and records an operation log to realize audit tracking; the data transmission micro-service integrates a plurality of heterogeneous data access modes, carries out transmission process verification and carries out secure channel transmission through the service gateway.

The invention discloses a laser point cloud shielded vehicle completion method and device based on a thunder-vision fusion deep learning framework in the technical field of automatic driving environment perception. The method comprises the following steps: acquiring original laser point cloud data and an aerial image; constructing a fan-shaped shielding area based on the original laser point cloud data; identifying two-dimensional bounding boxes, orientations and category labels of all vehicle targets in the image; inputting the fan-shaped occlusion area and the two-dimensional bounding boxes, orientation and category labels of all the vehicle targets into a pre-trained double-branch deep learning network, and predicting whether an occluded vehicle exists or not and the position, orientation and category information of the occluded vehicle; and selecting a vehicle point cloud template based on the category information of the shielded vehicle, and then generating a scene point cloud after vehicle point cloud completion as a final result of vehicle completion in the shielded region. According to the invention, an image-point cloud space mapping mechanism based on the Leiyu fusion deep learning framework is introduced, so that the capability of automatically identifying and positioning the shielded vehicle is remarkably improved.

The invention provides an image data and pattern spot management system and method and electronic equipment, and relates to the technical field of geographic information data processing, and the image data and pattern spot management system comprises an image data indexing module which is used for carrying out three-dimensional indexing on a remote sensing image to obtain a space-time-data source association chain of the remote sensing image, the remote sensing image contains pattern spot data with an identifier; the pattern spot complete cycle construction module is used for performing multi-temporal analysis on the pattern spot data to obtain an analysis result, and constructing a pattern spot change life cycle map of the pattern spot data in combination with the association chain; and the tracing module is used for positioning the target pattern spot when the target pattern spot needs to be traced to obtain a change node of the target pattern spot and a space-time-data source index corresponding to the change node, and searching in the association chain according to the change node and the space-time-data source index to obtain a traceable data chain. According to the invention, the storage and management of the geographic image data and the pattern spot data are more systematized and refined.

Apparatus for visualization within a three-dimensional (3D) model and methods used therein are described, wherein the apparatus includes a processor and a memory communicatively connected to the processor, wherein the memory includes instructions configuring the processor to receive a query image, extract neural network encodings from the received query image, query a synthetic image repository for at least a matching synthetic image, and display an estimated position and orientation within the 3D model, wherein the synthetic image repository includes a plurality of synthetic images and their extracted neural network encodings, each synthetic image therein corresponds to a slice extracted at a specific position and orientation in the 3D model, and querying the synthetic image repository includes comparing the extracted neural network encodings between the query image and synthetic images.

Systems and methods for image search result filtering can include obtaining a search query, determining a plurality of candidate image search results, processing the search query with a generative model to determine a plurality of search result criteria, and refining the plurality of candidate image search results based on determining whether the candidate results satisfy the plurality of search results criteria. The systems and methods can perform a plurality of determinations based on the output of the generative model.

The invention relates to the technical field of intelligent information retrieval, in particular to an image-text retrieval generation method and device based on reference semantics and electronic equipment. The method comprises the steps of performing semantic segmentation on a document in a document knowledge base to obtain a plurality of paragraphs, performing semantic similarity judgment, and merging similar paragraphs; extracting semantic features of the merged paragraphs to form semantic features of lower-layer paragraphs; abstract description is carried out on the merged paragraphs, semantic features are extracted from abstract description, upper layer description semantic features are formed, and text level semantic features are constructed; image semantic features in the image knowledge base are extracted, normalization processing is carried out on the text level semantic features and the image semantic features, an inverted product quantitative index is constructed, and construction of an image-text reference semantic feature index is achieved; and processing the input text based on the image-text reference semantic feature index to obtain a retrieval result. According to the method, the problems of lack of previous knowledge, insufficient detail information and poor image-text relevance in image-text retrieval are solved.

The invention discloses a professional knowledge domain data processing method based on a large language model, and relates to the technical field of natural language processing, and the method comprises the following specific steps: knowledge graph-driven multi-modal preprocessing: collecting professional domain knowledge graph, text, image and audio data, according to the method, the data quality is effectively improved through multi-modal preprocessing driven by the knowledge graph, a solid foundation is laid for subsequent processing, the attention regulation and control algorithm of multi-modal perception is combined, a large language model can dynamically adjust attention according to modal features such as text context, images and audios, key information is accurately captured, and the method is suitable for popularization and application. The comprehensive understanding and processing capability of professional knowledge data is remarkably improved, and in addition, the generalization capability of the model is further enhanced through the modal self-adaptive data enhancement method, so that the model can better deal with diversity and complexity in the professional field.

The invention discloses a multi-mode convergence media content auxiliary creation method based on an AI technology, and the method comprises the steps: extracting key features according to a creation demand text inputted by a user, carrying out the retrieval in a knowledge base through employing a knowledge graph retrieval mode according to the key features, obtaining a creation material, and generating a first draft; carrying out cross-modal feature mapping on the first draft by adopting a multi-modal alignment model, aligning text-image-video embedded vectors through contrastive learning, and dynamically adjusting the correlation of multi-modal contents by utilizing an attention mechanism to obtain a multi-modal content packet; duplicate checking is carried out on the multi-modal content packet in multiple modes, and the multi-modal content packet after duplicate checking is sent to a user for manual editing. Through multi-mode processing methods such as AI auxiliary writing, AI illustration and video generation and whole-network duplicate checking and propagation value evaluation, the content production efficiency and quality are improved, the propagation effect is optimized, and the original content is protected.

The invention discloses a medical image report generation method based on multi-modal large model retrieval enhancement, which relates to the technical field of medical image processing and comprises an image vector model module, a vector database and similarity detection module, a multi-modal large model module, a dynamic retrieval module and a retrieval enhancement generation prompt project module. The multi-modal large model module comprises a multi-modal input splicing unit, a reasoning information processing unit and a diagnosis report set generation unit, the dynamic retrieval module comprises a similarity threshold value analysis unit and a retrieval quantity analysis unit, and the similarity threshold value analysis unit is used for analyzing a maximum similarity value between a new image and a database. According to the invention, an image vectorization processing technology based on a CLIP-ViT model is adopted, so that the system can accurately capture fine features of a focus, and the risk of key information omission is reduced; a dynamic threshold adjustment algorithm is introduced, and the rigidity defect of a traditional fixed retrieval strategy is overcome.

A cross-view-angle image retrieval method for unmanned aerial vehicle navigation comprises the following steps: step 1, enhancing an image, step 2, based on a ConvNeXt network for cross-view-angle image retrieval for unmanned aerial vehicle navigation, performing multi-scale feature extraction on the enhanced image, and step 3, performing multi-scale feature extraction on the enhanced image based on a ConvNeXt network for cross-view-angle image retrieval for unmanned aerial vehicle navigation. 3, performing multi-dimensional feature fusion based on an attention mechanism; 4, after multi-dimensional feature fusion, calculating a loss value, and based on a determined weight, obtaining a detection model for image retrieval; through the multi-scale feature convolution and multi-dimensional feature fusion technology, the technical problems of insufficient matching precision, poor retrieval robustness and the like caused by view angle, scale and structure differences between the satellite image and the unmanned aerial vehicle image are solved; the invention further comprises a system, equipment and a medium for implementing the method.

The invention discloses a multi-modal data retrieval method and device under dynamic collaboration and a medium, belongs to the technical field of information retrieval and natural language processing, and is used for solving the problems that unstructured data is difficult to process efficiently in traditional data retrieval, an information island phenomenon exists, and the data retrieval efficiency is low. And an effective connection and integration mechanism is lacked between data from different sources. The method comprises the following steps: performing task allocation processing on a corresponding Agent cluster on a question type to be queried to obtain an Agent task list; performing data query processing on the Agent task list under different data sources, and obtaining query result data; performing data primary processing on the query result data to determine initial retrieval data; performing multi-modal consistency check on the initial retrieval data, and integrating verified integrated retrieval data; and performing information strategy generation processing based on a fact verification mode and an explanation enhancement mode on the integrated retrieval data to obtain final answer information.

The embodiment of the invention discloses a building engineering crack detection method and system based on image recognition, and the method comprises the steps: obtaining a building surface image, carrying out the preprocessing of the image, obtaining a standardized image, and carrying out the multi-scale decomposition extraction and integration of various features, and forming a multi-dimensional feature descriptor set; after feature importance is evaluated, a compact feature vector is generated through dimension reduction, quantization coding and compression, and then a multi-level feature index mechanism for optimized compression is constructed. A query feature vector is extracted from a newly collected image, searching and screening are completed by means of an index mechanism and a tolerance threshold, and a crack matching result is obtained; and based on the result, positioning cracks, classifying types, measuring parameters and evaluating severity, and generating a crack state report. The crack trend is analyzed in combination with the historical data time sequence, a multi-stage early warning mechanism is designed, maintenance suggestions are provided, and a real-time monitoring and early warning system is formed. According to the embodiment of the invention, the technical problems of high storage pressure and low real-time detection efficiency in the prior art can be effectively solved.

The invention belongs to the computer vision technology, and particularly relates to a small sample multi-modal prototype learning-oriented remote sensing scene classification method, which comprises the following steps of: acquiring RGB (Red, Green and Blue) images with category labels and text prompts of the RGB images as a support set; establishing a text prototype, an RGB prototype and a hyperspectral prototype of each category according to the support set; and extracting to-be-classified query set image features by using a pre-trained CLIP image encoder, calculating cosine similarities between the query set image features and the text prototype, the RGB prototype and the hyperspectral prototype of each category of the support set, taking the cosine similarities as input of a multi-layer perceptron, and obtaining the category of the to-be-classified RGB image through classification of the multi-layer perceptron. High-precision and high-robustness remote sensing scene classification is realized under the small sample condition, only prototype and similarity calculation is needed in the reasoning stage, and deployment and expansion are easy.

The invention relates to a crystal pixel lookup table generation method and device, computer equipment and a storage medium. Determining a preset number of first pixel peak points from the first crystal pixel lookup table, performing data enhancement processing on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table, and performing data enhancement processing on the first pixel peak points in the first crystal pixel lookup table to obtain a second crystal pixel lookup table, and obtaining a target crystal pixel lookup table based on the first crystal pixel lookup table and the second crystal pixel lookup table. According to the embodiment of the invention, the second crystal pixel lookup table is obtained by performing data enhancement processing on the first pixel peak point, and the phenomenon that the crystal of the medical equipment disappears along with the use time is simulated, so that the target crystal pixel lookup table is obtained based on the first crystal pixel lookup table and the second crystal pixel lookup table; the number and diversity of crystal pixel lookup table data sets are improved, and the complexity of crystal pixel lookup table generation is reduced.

The present disclosure provides a character recognition model training method and apparatus, a character recognition method and apparatus, a device and a medium, relating to the technical field of artificial intelligence, and specifically to the technical fields of deep learning, image processing and computer vision, which can be applied to scenarios such as character detection and recognition technology. The specific implementing solution is: partitioning an untagged training sample into at least two sub-sample images; dividing the at least two sub-sample images into a first training set and a second training set; where the first training set includes a first sub-sample image with a visible attribute, and the second training set includes a second sub-sample image with an invisible attribute; performing self-supervised training on a to-be-trained encoder by taking the second training set as a tag of the first training set, to obtain a target encoder.

The invention relates to an unmanned aerial vehicle scheduling method and system for emergency rescue, a terminal and a storage medium, and belongs to the technical field of emergency rescue, the unmanned aerial vehicle scheduling method comprises the following steps: sending an inspection instruction to a front-end unmanned aerial vehicle cluster, and the front-end unmanned aerial vehicle cluster performing inspection according to a preset inspection path; after the front-end unmanned aerial vehicle cluster finds the disaster site, receiving a preliminary assessment report of the disaster site sent by the front-end unmanned aerial vehicle cluster; the front-end unmanned aerial vehicle cluster generates and uploads a preliminary evaluation report after discovering a disaster site; inputting the preliminary evaluation report into a pre-constructed scoring model to obtain a score value of the preliminary evaluation report; calling a current dispatching scheme matched with the score value from a historical dispatching database; and sending a rescue instruction to the standby unmanned aerial vehicle cluster and the rescue terminal according to the current dispatch scheme. The method has the beneficial effects that the response time of the rescue unmanned aerial vehicle is shortened, so that the search and rescue efficiency is improved.

The invention discloses a multi-model reasoning method and device based on a graph structure, a medium and a program product, and the method comprises the steps: querying a task target node in a graph database, starting from the task target node, traversing the graph database according to a corresponding driving model, and carrying out reasoning path extension, each directed acyclic graph is obtained by mapping metadata of the registered analysis model; generating a task topology execution graph according to the model nodes involved in the expanded reasoning path and the corresponding driving model; and according to the task topology execution graph, actual execution of each model node is scheduled in sequence, and an interpretation result corresponding to the task target node is obtained. According to the method, the model attribution relation is explicitly analyzed, and the reasoning path is optimized by utilizing graph calculation, so that the reasoning execution efficiency is improved, and the intelligence, performance and interpretability of multi-model collaborative analysis are improved.

The invention discloses a celestial body data retrieval method and device, a storage medium and electronic equipment, and the method comprises the steps: matching the coordinate information of each celestial body image in a celestial body image header file with the coordinate information contained in each celestial body star catalogue record in a star catalogue database of each different data source according to the coordinate similarity; and determining each celestial body data pair formed by the celestial body image and the celestial body star catalogue record which have a matching relationship, and for each celestial body data pair, carrying out feature coding on the celestial body image and the celestial body star catalogue record in the celestial body data pair to obtain the multi-modal features of the celestial body data pair. A multi-modal feature is constructed by associating a celestial body image in a celestial body image header file with celestial body star catalog records in a star catalog database. And when celestial body data retrieval needs to be carried out, obtaining a retrieval result according to the multi-modal features. According to the method, the similarity of data features in the celestial body image and the celestial body star catalogue record is considered at the same time, and more accurate retrieval precision can be achieved.

The invention relates to the technical field of channel monitoring and underwater topography analysis, in particular to a multi-beam sounding data driven underwater topography profile extraction method and device and a medium, and the method comprises the steps: obtaining channel region multi-beam sounding original data, carrying out the standardized preprocessing, and outputting a sounding data set; performing spatial interpolation and vectorization processing on the sounding data set to generate channel geological data, and issuing the channel geological data as a similar three-dimensional channel bottom graph through a geographic information service platform; generating a profile path, and generating interpolation points according to a preset interval; constructing a spatial index structure based on the sounding data set, and establishing an adjacent sounding point retrieval channel for each interpolation point; and in allusion to the same profile path, acquiring multiple periods of sounding data, calculating water depth difference, and dynamically and visually displaying an abnormal movement phenomenon by using a broken line graph. According to the method, efficient extraction, dynamic comparison and automatic early warning of the multi-period sounding data can be realized, and the analysis efficiency and accuracy of the channel topographic change are remarkably improved.

The present application relates to the technical field of computers. Disclosed are an image retrieval method and apparatus, and a storage medium and an electronic device. The method comprises: using a preset deep hashing model to process an image to be retrieved, so as to obtain an image hash code, wherein the preset deep hashing model is obtained by means of performing incremental learning training on the basis of a plurality of preset class centers and query data; and on the basis of a preset image corresponding to a preset hash code matching the image hash code, obtaining a matched image. The present application effectively improves the accuracy of image retrieval.

The invention relates to the technical field of computer vision processing, in particular to an automatic defect positioning method based on a BIM virtual image. The method comprises the following steps: establishing a high-rise building model, and making a data set integrating an illumination condition and a full view angle; calculating camera parameters; performing cross-modal image retrieval: performing targeted optimization on the basis of a classical ResNet architecture, and constructing a backbone network structure suitable for a building image retrieval task; initializing position attitude estimation based on matching; and correcting the camera position posture. According to the method, a defect fixed frame based on a building BIM virtual image is provided, a building image data set BIM-Vision based on Revit is constructed, rich visual angles and illumination condition setting are achieved, accurate camera position postures and 3D labels between beam columns are provided, high-quality basic data support is provided for building visual research, and the method has the advantages of being high in practicability and high in practicability. And during inspection, accurate positioning of defect positions and component association can be completed only by shooting a field image, so that the field operation process is greatly simplified.

The invention discloses a building indoor positioning method and system based on AI image retrieval, and relates to the technical field of indoor positioning, and the method comprises the steps: constructing an environment prior knowledge base, obtaining a real-time image for positioning, and generating an image comprehensive quality score; processing the real-time image to obtain a candidate positioning result set; calculating spatial dispersion according to the candidate positioning result set; according to the initial positioning result, determining a target logic area, extracting a corresponding scene visual ambiguity index, and generating a mismatch diagnosis index; according to the mismatch diagnosis index, the image comprehensive quality score and the spatial dispersion, a final positioning state is generated, and a calibration positioning result or a user instruction is output. Through a multi-module cooperation and innovation algorithm, scene difficulty is quantified, a positioning problem root is diagnosed, a closed-loop decision process is formed, the positioning reliability is improved, and the positioning accuracy is improved. And mismatching between the original confidence and the scene positioning difficulty is avoided.

The invention discloses a distributed medical image retrieval and hierarchical storage management system and method. The system comprises an interface processing module, a distributed image storage cluster, a routing forwarding module, a metadata management module and a storage management module. The interface processing module receives the image retrieval request, generates a routing identifier for positioning the storage position of a target medical image file and sends the routing identifier to the routing forwarding module; and the routing forwarding module queries a mapping relationship between the medical image file and the storage node and / or the storage hierarchy based on the routing identifier, determines a first storage node and forwards the request, so that the first storage node returns a target medical image file. And the storage management module obtains the access statistical information, determines a target storage level and / or a target storage node, migrates the medical image file, and triggers updating of the mapping relation after migration is completed. Therefore, cross-node accurate positioning and unified retrieval are realized, positioning consistency is kept after file migration, and hierarchical storage management based on access conditions is supported.

In an image processing method, a reference library and a query library are obtained; a reference image in the reference library and a prompt are inputted into a diffusion model to obtain estimated noise; the estimated noise is merged to obtain a reference noise feature; a plurality of query noise features corresponding to a query image are determined; and a target label corresponding to the query image is determined based on feature similarities between the plurality of query noise features and the reference noise features.

The present invention discloses an image retrieval method based on hyperdimensional vector calculation, comprising: preprocessing a collected image data set; dividing the preprocessed data set into a training set and a test set; based on the training set, training a ResNet18 network using a small sample learning method to obtain m+1 feature extraction networks; using the trained ResNet18 network to extract features from each image in the test set, generating a hyperdimensional vector of the test set image, and obtaining a hyperdimensional vector library; using the trained ResNet18 network to extract features from an input query image, generating a hyperdimensional vector corresponding to the query image; matching the hyperdimensional vector corresponding to the query image with all vectors in the hyperdimensional vector library, and outputting the vector with the highest matching degree. The present invention realizes image retrieval with low resource consumption and high robustness, can effectively complete image matching tasks in the field of the Internet of Things, and meets the demand for high robustness image retrieval in scenarios with limited hardware resources.

To provide an information processing device which acquires a screenshot posted by a user, so as to offer complementary information for complementing a content of the screenshot to viewers of the screenshot.SOLUTION: An information processing device includes an acquisition section, a generation section, and a provision section. The acquisition section acquires a screenshot posted by a user. The generation section generates complementary information for complementing a content of the screenshot on the basis of information on the screenshot and attribute information on viewers of the screenshot. The provision section provides the complementary information together with the screenshot to the viewers.SELECTED DRAWING: Figure 1

This document describes techniques and systems that enable privacy controls for sharing embeddings for searching and indexing media content. A set of images of a user's face are obtained and a machine-learned model is applied to the set of images to generate a user-specific dataset of face embeddings for the user. Media content stored in a media storage is indexed by applying the machine-learned model to the media content to provide indexed media information identifying one or more faces shown in the media content. Access to the indexed media information by another user querying the media content for images or videos depicting the user is controlled based on a digital key shared by the user with the other user, where the digital key is associated with the user-specific dataset and the user-specific dataset is usable to identify the images or videos depicting the user.

Systems and methods for image retrieval are disclosed. In an example, sets of catalog images are received, wherein each set of catalog images is associated with a catalog item of a plurality of catalog items. Respective catalog embeddings representing each set of catalog images are generated. Query images associated with a query item are received. Query embeddings representing the query images are generated. Based on comparisons of the query images and the catalog images, select a candidate set of catalog items from the plurality of catalog items. Based on a comparison of the query embeddings and respective catalog embeddings associated with respective catalog items of the candidate set, generate respective similarity scores. Based on the similarity scores, determine that the query item is similar to a candidate catalog item, and in response identify the query item for review.

The invention belongs to the technical field of medical image cross-domain retrieval, and provides a medical image cross-domain retrieval method and system based on a generative adversarial network, and the method comprises the steps: obtaining an MRI image and a CT image; performing unsupervised cross-domain mapping of the acquired image based on the bidirectional generative adversarial network, and calculating an adversarial loss function of the cross-domain mapping; calculating a gradient consistency loss function and a feature comparison loss function based on a multi-level cyclic consistency constraint mechanism; carrying out adaptive dynamic adjustment on the obtained loss function to obtain a medical image cross-domain retrieval loss function, training a medical image cross-domain retrieval model, and carrying out similarity retrieval based on the trained medical image cross-domain retrieval model to complete medical image cross-domain retrieval based on the generative adversarial network. According to the method, the dependence on paired MRI / CT image samples is eliminated, high-quality image domain conversion is realized through integrated level supervision, and feasible cross-domain retrieval in a real non-paired medical image environment is realized.