629 results about "Information capture" patented technology

The present invention relates to the technical field of image fusion. Disclosed is a method for fusing infrared light and visible light images. According to the present invention, design is carried out on the basis of a spatial channel attention mechanism and a gradient aggregation residual dense block, a strong texture and weak texture of a feature are retained by integrating Sobel and Laplacian operators while combining the advantages of ResNeXt and DenseNet, and channel information and spatial information of a feature map are refined by means of introducing a spatial and channel attention mechanism, thus the information capture capability of the feature map is increased, and refined spatial and channel feature maps are fused by using a pooled fusion block, to obtain a high-quality fusion feature.

Approaches presented herein provide for the generation of a tokenized description of an environment for use in making decisions with respect to the environment. In particular, a large language model (LLM) can be used to generate a tokenized text string representation of an environment using sensor information captured at a specific location, as well as information about the semantics, topology, and geometry of the environment. A similarity-based search can be performed against tokenized descriptions for various locations until a single high-quality match is identified, and the geographic position of the match can be inferred to correspond to the current position of a vehicle that captured the sensor data. The current location and tokenized description can also be provided to a language model, along with a road-level route plan, in order to generate more detailed routing information that is optimized based on the additional information available in the tokenized description for a sequence of goals corresponding to the route plan.

The invention relates to the field of computer vision, and discloses a photovoltaic panel defect category detection algorithm based on feature pyramid and cascade group attention, comprising the following steps: S1, data acquisition, labeling and preprocessing; s2, carrying out model training by using an improved YOLOv11 algorithm; and S3, predicting the input infrared picture, accurately positioning the defect and marking the category. According to the photovoltaic panel defect category detection algorithm based on the feature pyramid and the cascading group attention, the feature pyramid and the cascading group attention can be detected according to the internal circuit structure of the photovoltaic panel and an infrared imaging picture; accurately positioning, marking and classifying the defects on the photovoltaic panel; a newest YOLOv11 target detection algorithm is adopted and improved, and part of C3k2 modules are replaced by SCC3k2 modules, so that information capture on space and channels is more accurate, and adverse effects caused by redundant information extraction are reduced; and meanwhile, different input segmentation is provided for each attention head in the attention module, and the diversity of the characteristics input to the attention heads is enhanced by cross-head cascade output characteristics.

The invention discloses an ultrasonic image segmentation method and system based on multistage feature extraction, and the method comprises the steps: carrying out the ultrasonic image segmentation of an input ultrasonic image through an ultrasonic image segmentation network model, the ultrasonic image segmentation network model comprises a double-branch encoder, a multi-scale feature fusion module, a multi-scale feature attention module and a decoder, and the double-branch encoder is used for extracting small detail features, large-scale context features and global features of different scales; the multi-scale feature fusion module fuses features and then inputs the fused features into the decoder, the multi-scale feature attention module enhances each layer of features of the CNN encoder and then inputs the enhanced features into the decoder, and a segmentation prediction map is obtained through decoding of the decoder. The method aims at solving the problem that most of existing ultrasonic image segmentation methods based on deep learning only pay attention to capturing local details and global correlation and ignore large-scale context information, the information capturing efficiency of an input image is improved, and the segmentation performance of a network is improved.

The invention relates to a polyp image segmentation method based on pyramid vision Transform, and belongs to the technical field of digital medical treatment. The method comprises the following steps: capturing global context information through a pyramid vision Transform module, and obtaining feature maps with different resolutions from a plurality of extraction stages; detail information is extracted from the shallow feature map of the first stage through a cyclic cross attention module, and shallow features are obtained; a multi-scale feature fusion sensing module is used for carrying out fusion processing on the feature maps extracted in multiple stages, deep features are extracted, and the deep features and shallow features are fused and then used for image segmentation; and designing weighted binary cross entropy loss and weighted IoU loss to train the above process, and segmenting the polyp image after training is completed. According to the invention, through the pyramid vision Transform module, the cyclic cross attention module and the multi-scale feature fusion perception module, the global information learning ability, the detail information capturing ability and the segmentation performance are significantly improved.

The invention relates to a multi-modal implicit sentiment analysis method based on a multi-granularity attention mechanism, which belongs to the field of artificial intelligence, and comprises the following steps: S1, extracting visual features in image information by using a visual feature extraction strategy of multi-scale attention fusion; s2, generating a text description of the image information by adopting an image translation engine, splicing the text description with an original text, and extracting text features through a hierarchical attention mechanism; s3, carrying out normalization processing; s4, performing multi-modal fine-grained correlation fusion on the visual features and the text features by adopting a bidirectional cross attention mechanism, and extracting fine-grained features in the visual features and the text features through a multi-head attention mechanism and residual connection; and S5, fusing the fine-grained features by using an adaptive multi-modal classification module to complete sentiment classification. The multi-modal sentiment analysis method solves the problems that multi-modal sentiment analysis is insufficient in inter-modal correlation mining, insufficient in fine-grained information capture and large in noise interference.

The invention belongs to the technical field of new energy and power systems, and discloses a photovoltaic generation power prediction method and device, and the method comprises the steps: collecting the historical meteorological data and generation power data of a photovoltaic power station according to a preset sampling interval; constructing a photovoltaic power generation prediction model based on the bidirectional deep network; training the training set through the constructed photovoltaic power generation prediction model; performing photovoltaic power generation prediction by adopting a single-step prediction or multi-step prediction mode to generate a continuous photovoltaic power generation power sequence; and predicting the photovoltaic power generation power through the generated photovoltaic power generation power prediction sequence. According to the method, the problems of insufficient real-time data processing and model adaptive adjustment and low prediction precision of photovoltaic power generation prediction are overcome, and the method does not depend on a large amount of historical data and high-performance computing resources. When the photovoltaic data information is captured, bidirectional information capture is considered, and more accurate prediction can be carried out when complex and sudden environmental factors are processed in practical application.

The invention discloses a digital twin-driven photovoltaic module monitoring and self-purification system, belongs to the technical field of photovoltaic module cleaning, and realizes intelligent management and maintenance of a photovoltaic system through mutual cooperation of a sensing layer, an information capturing layer, an information transfer layer, an intelligent analysis layer, a decision support layer and an interactive experience layer. The sensing layer deploys various sensors to collect key data of the photovoltaic module; the information capturing layer transmits the data to a back-end processing system in real time; the information transfer layer ensures efficient transmission of data in the system; the intelligent analysis layer predicts a maintenance demand by using a machine learning algorithm, realizes predictive maintenance, and maintains the optimal working state of the component through an intelligent cleaning mechanism; the decision support layer provides decision support based on data analysis for an operator of the photovoltaic power station, and optimizes a maintenance plan and a productivity plan; and the interactive experience layer provides a visual management interface, so that the component state can be remotely monitored conveniently.

The invention provides a multi-modal emotion recognition software development method for voice interaction of an intelligent robot, and the method achieves the synchronous collection and fusion of multi-modal data through the weighted fusion preprocessing of voice signals, facial expression video streams and text contents. A DCNN and LSTM combined model is adopted to deeply extract emotional features, and an attention mechanism is introduced to strengthen key information capture. And a comprehensive emotion representation vector is calculated by using a cross-modal emotion association network CMAN, so that the emotion distinguishing capability is improved. An emotion classifier combining an SVM and a neural network is constructed, and refined output of emotion categories and intensity is achieved. Through real-time feedback and adaptive optimization steps, the model can continuously learn and adapt to user emotion expression habits, and accuracy and user satisfaction are improved. According to the invention, more humanized and accurate multi-modal emotion recognition technical support is provided for voice interaction of the intelligent robot.

The invention discloses a multi-mode sensing fire detection method based on a Transform time sequence feature fusion model, and relates to the technical field of fire safety monitoring, the method comprises a flame detector combining video, multi-band infrared and ultraviolet sensing technologies, the detector is mainly composed of an image sensor, four infrared sensors and one ultraviolet sensor, the image sensor is mainly used for sensing wavelength information within the range of 400 nm to 800 nm, the infrared sensor is particularly sensitive to detection of heat radiation, and the ultraviolet sensor can detect ultraviolet light generated by flames. According to the invention, the method can adapt to the condition of missing of actual data and partial sensor data, and the designed multi-modal data fusion module carries out effective feature extraction on the sensor data and image data, so that the generalization ability of the model is improved; according to the method, the correlation between different sensor data and the depth feature information of the specific time sequence mode of the fire can be captured from long-distance context information, and the historical data and the current data are adaptively fused.

Assisted checkout devices, including point-of-sale stations, can use computer vision and machine learning to speed the checkout process while maintaining human verification, assistance, and customer interaction provided by human clerks. A plurality of optical sensors, including cameras, can be arranged with different views of a checkout plane upon which items being purchased by a buyer are placed. Moreover, one or more support towers can be utilized to elevate the optical sensors to vertical heights at which the checkout plane, and items placed thereon, is within the field of view of the optical sensors. The information captured by the plurality of optical sensors can be analyzed using machine learning models to detect and identify the items placed on the checkout plane.

The invention relates to the technical field of intelligent logistics and supply chain management, and discloses a cross-border e-commerce logistics intelligent storage scheduling and transportation cooperation method based on AI path planning, and the method comprises the steps: building a monitoring module, a dynamic information capturing module, a data classification module, a data analysis module, a storage scheduling and transportation cooperation module and a management module; the monitoring module monitors storage and transportation information in real time through a sensor and monitoring equipment, the dynamic information capture module collects external environment data and internal abnormal events, the data classification module classifies the monitored data and the captured information, and the data analysis module constructs a path planning model according to the stored data of the data classification module. The system comprises a storage scheduling and transportation collaboration module, a storage scheduling and transportation collaboration module and a management module, the storage scheduling and transportation collaboration module generates an optimal path and calculates a storage efficiency index # imgabs0 #, a transportation path lifting coefficient # imgabs1 # and a storage-transportation collaboration index # imgabs2 #, the storage scheduling and transportation collaboration module optimizes the path according to a calculation result and sets an early warning mechanism, and the management module assists management personnel in monitoring and decision making through a visual interface.

In a traffic scene, a traditional target detection algorithm always faces the problems of strong background interference, difficulty in small target detection and the like, and detection precision and robustness are affected. Therefore, the invention provides an improved YOLOv12n vehicle detection method in which an EMA (Empirical Multi-scale Attention) attention mechanism and an SFA (Space Feature Aggregation) attention mechanism are fused. The invention further provides a method for detecting the YOLOv12n vehicle based on the improved YOLOv12n vehicle based on the attention mechanism of the EMA (Empirical Multi-scale Attention) and the attention mechanism of the SFA (Space Feature Aggregation). The SFA module is deployed in a shallow network, key target area expression is enhanced by aggregating spatial features, and background noise interference is suppressed; the EMA module is embedded into a neck network, and the global information capture and multi-scale sensing capabilities are improved by adopting multi-scale convolution, cross-space modeling and feature grouping mechanisms. According to the method, the real-time performance is kept, meanwhile, the detection precision in a complex scene is remarkably improved, and particularly, higher robustness is shown in the aspects of small target recognition and shielding processing.

The invention discloses a flexible job shop scheduling method based on a graph neural network and deep reinforcement learning, and relates to the technical field of flexible job shop scheduling. The method at least comprises the following steps: S1, firstly, carrying out Markov Decision Process (MDP) on a flexible job shop scheduling problem, namely, FJSP, and initializing a scheduling state; and S2, representing a complex relationship between a job and a machine by using a heterogeneity graph, and effectively mapping different entities (the job, the machine, the operation and the like) of the problem and the relationship between the different entities into a graph structure, wherein the different entities (the job, the machine, the operation and the like) of the problem and the relationship between the different entities (the job, the machine, the operation and the like) of the problem are represented by the heterogeneity graph. According to the method, the graph neural network based on the meta-relationships is provided, different graph convolution modes are innovatively adopted for different meta-relationships to extract features, original semantic information is reserved, the global information capturing capability is enhanced, and a reinforcement learning agent is more accurate when making a scheduling decision.

The invention discloses a remote sensing cloud layer repairing method based on time-spectral domain fusion and time sequence self-attention enhancement, and relates to the technical field of remote sensing cloud layer image processing. The method comprises the steps of receiving a remote sensing missing image as a source image; the method comprises the following steps: constructing a generator, inputting a remote sensing missing image into the generator for preliminary processing, the generator comprising a feature extractor, a ConformerPlus module and a cloud detection module, and a new multi-head self-attention mechanism being embedded in the ConformerPlus module. According to the method, time-frequency spectrum domain information extraction and fusion can be carried out on data, so that the feature expression ability is enhanced, the edge information capturing ability of the model is improved, the model is guided to realize progressive cloud layer removal from outside to inside, the detail expression can be improved, noise interference can be suppressed, and the method is suitable for large-scale popularization and application. And the detail definition and the texture fidelity of the image are effectively improved.

The invention provides a video generation method based on diffusion model optical flow trajectory control. The video generation method comprises the following steps: S1, processing a training video and modeling an optical flow trajectory; s2, optical flow trajectory calculation and dynamic attention optimization; s3, carrying out diffusion modeling; and S4, model reasoning and implicit vector reconstruction. Through three core technologies of optical flow trajectory modeling, dynamic attention optimization and implicit vector reconstruction, the precision of motion information capture and the detail quality of video generation are improved, personalized style control is realized, and compared with a traditional method, the method has remarkable advantages in motion accuracy, video coherence and personalized customization ability, and the method is suitable for popularization and application. The problems that in the prior art, the precision in few-sample video generation is insufficient, and motion information in a training video cannot be effectively extracted are solved.

The invention discloses a synthetic aperture optical image restoration method based on local-global feature enhancement, and the method comprises the steps: obtaining a synthetic aperture optical image data set, carrying out the simulation degradation, obtaining a simulation degradation data set, and carrying out the division to obtain a training set, a verification set and a test set; constructing a synthetic aperture optical image restoration network; inputting the training and verification set into a synthetic aperture optical image restoration network for training, calculating a loss function and performing back propagation, updating network parameters, and obtaining a trained optimal parameter model; and inputting the test set into the trained optimal parameter model to obtain a synthetic aperture optical restoration image. According to the method, global information attention is performed on an extracted feature sequence by using an LGA-Transform layer, the sequence length is reduced, advanced semantic information is extracted, local information of features is focused by using a GRM-Conversion layer and an ASFE layer, and the defect of local information capture capability of Transform is made up.

The invention provides a real-time monitoring and analyzing system for tooth orthodontic correction, and relates to the technical field of oral treatment, the real-time monitoring and analyzing system comprises an information capturing system, an intelligent operation system and an appliance dynamic regulation and control system, the information capturing system comprises a three-dimensional oral cavity imager, a health condition evaluator, a multifunctional induction network and a portable monitoring device, the three-dimensional oral cavity imager generates a three-dimensional oral cavity image through triangulation positioning, extracts oral cavity mucous membrane features by combining an improved local binary pattern algorithm and adding an edge enhancement filter, and confirms the identity when the Euclidean distance is calculated to be smaller than a preset threshold value. According to the system, mucous membrane texture features are extracted through combination of the three-dimensional oral cavity imager and the improved LBP algorithm for identity verification, the health condition assessment instrument collects temperature, humidity and pH value every 6 minutes, the portable monitoring device collects pressure and biological signal data, and comprehensive collection of multi-dimensional data is achieved.

The present disclosure relates to a virtual reality-based control method and apparatus, and an electronic device, and relates to the technical field of virtual reality. The method comprises: first monitoring image information captured by a camera for a user; identifying movement information of a target object in the image information; then, according to the movement information of the target object, displaying at least one interactive component model in a virtual reality space, and executing an interaction function event that is pre-bound to an interactive component model selected by the user. By means of applying the technical solution in the present disclosure, the technical problem that user control is easily influenced due to the buttons of an entity device being easily damaged can be effectively solved. A stronger technological sense can be brought to users, thereby enhancing the VR usage experience of users.

The invention provides an intelligent purchase recommendation system and method based on an AI technology, and relates to the field of intelligent recommendation, and the method comprises the steps: employing an AI-based data information analysis and processing mode to extract text information from a bidding project file uploaded by a demand side and a bidding file provided by a first supplier, and carrying out the semantic coding of the text information; and meanwhile, semantic coding and kernel dynamic aggregation are performed on evaluation information captured on the Internet, so that whether the first supplier is recommended or not is intelligently judged according to the adaptation degree measurement between a joint feature between a bidding semantic feature and an evaluation aggregation feature and a bidding semantic feature. Thus, automatic file auditing can be achieved, deep meanings which cannot be touched by keyword matching can be captured, suppliers can be selected more accurately, and therefore more intelligent purchase recommendation is achieved.

The invention belongs to the technical field of natural language processing, and aims to identify and extract a relationship between entities from a long text so as to solve the problems of insufficient feature expression and inaccurate context information capture of an existing relationship extraction method. According to the method, a document-level relation extraction model based on multi-granularity feature fusion, an axis attention mechanism and evidence enhancement is provided, so that the extraction performance is improved. The model adopts multi-granularity feature fusion, and provides richer context information by combining local fragment features and global semantic features; attention weights in different axial directions are dynamically adjusted through an axial attention mechanism, and the accuracy of relation recognition is improved. Through evidence enhancement, the relationship between entities can be comprehensively understood and judged. The method is suitable for application such as knowledge graph construction, intelligent question and answer and information retrieval, and the performance of relation extraction in the long document can be effectively improved.

The invention relates to deep learning, and discloses an edge-enhanced pavement crack segmentation network processing method and system, so as to reduce information loss and improve segmentation accuracy. The method comprises the steps of image preprocessing, up-sampling, down-sampling, feature fusion and image restoration processing, and recursive aggregation processing is carried out after the image preprocessing, between two adjacent sampling layers and before the image restoration processing. According to the recursive aggregation processing, global context information is aggregated by scaling an input feature map, local details can be enhanced, information loss can be reduced, global modeling is realized based on an attention mechanism, and meanwhile, high-order space information and edge information are respectively extracted from the input feature map by applying recursive gated convolution and an edge operator; the global information capturing performance is greatly improved; therefore, the accuracy of the segmentation result is ensured.

The invention relates to a deformable object manipulation method and device based on a vision and language model, and the method comprises the steps: building an operation environment for a deformable object, and the operation environment comprises a camera used for collecting the visual data of the deformable object and a mechanical arm used for manipulating the deformable object; performing visual information capture on the deformable object in the operation environment to obtain image data, and recording a corresponding language instruction; extracting a key action and a target object through a language model according to the language instruction, and generating an operation instruction; extracting spatial features according to the image data through a visual processing model; the spatial features and the operation instructions are fused, and a final operation strategy is generated through a machine learning algorithm; the operation strategy is converted into an execution instruction of the mechanical arm so as to control the deformable object; compared with the prior art, the precision and efficiency of the robot for processing the flexible object are remarkably improved, and effective technical support is provided for application in the fields of intelligent manufacturing, home furnishing, service and the like.

Methods and systems are described for identity verification and deepfake prevention. A first video of a person is captured during an in-person interaction, the person's identity is verified, and the video is associated with the verified identity. In a subsequent electronic interaction, information about a second person is accessed, a second video of the second person is captured, and a trained neural network model is used to determine if the second person is attempting to identify as the first person. If the second person is not attempting to identify as the first person, the electronic interaction proceeds. If the second person is attempting to identify as the first person, the model determines if the first person is likely the same as the second person, transmitting a positive indicator if likely the same, and a negative indicator if not. Related networks, models, apparatuses, devices, techniques, and articles are also described.

An environmental capture system (ECS) captures image data and depth information in a 360-degree scene. The captured image data and depth information can be used to generate a 360-degree scene. The ECS comprises a frame, a drive train mounted to the frame, and an image capture device coupled to the drive train to capture, while pointed in a first direction, a plurality of images at different exposures in a first field of view (FOV) of the 360-degree scene. The ECS further comprises a depth information capture device coupled to the drive train. The depth information capture device and the image capture device are rotated by the drive train about a first, substantially vertical, axis from the first direction to a second direction. The depth information capture device, while being rotated from the first direction to the second direction, captures depth information for a first portion of the 360-degree scene. The image capture device captures, while pointed in the second direction, a plurality of images at different exposures in a second FOV that overlaps the first FOV of the 360-degree scene. The depth information capture device and the image capture device are rotated by the drive train about the first axis from the second direction to a third direction. The depth information capture device, while being rotated from the second direction to the third direction, captures depth information for a second portion of the 360-degree scene. The image capture device, while pointed in the third direction, captures a plurality of images at different exposures in a third FOV that overlaps the second FOV of the 360-degree scene.

The invention discloses a YOLOv5n-based industrial part surface defect detection method and device, and the method comprises the steps: embedding an attention mechanism into a convolution layer of a backbone network, introducing dynamic snakelike convolution to capture cross-channel information, capturing direction perception and position perception information, and carrying out the detection of the surface defect of an industrial part. Inputting the industrial part surface defect image data set into the backbone network for feature extraction to obtain three feature maps with different scales; a Gold-YOLO structure is introduced, multi-layer features are globally fused, global information is injected to a higher level, and a feature map highlighting the global information is generated; inputting the obtained feature maps into a feature pyramid network, and carrying out weighted fusion on the feature maps on different scales step by step through a down-sampling mode and an up-sampling mode; and outputting a defect detection result, and marking a detection frame, a defect type and confidence. The device comprises a processor and a memory. According to the invention, the detection precision of the surface defects of the industrial parts is higher, and the requirements of monitoring and maintaining the health conditions of the parts in industrial production are met.

The invention discloses a target detection method suitable for a shielded vehicle in an urban road scene, and aims to solve the problem of confusion of a target and a background caused by various shielding in the fields of unmanned driving, intelligent transportation and the like so as to improve the target detection precision. According to the method, on the basis of a YOLOv8 network, a mixed attention mechanism is introduced into a backbone network, so that the channel and space information capturing capability in feature extraction is enhanced; meanwhile, a multi-scale feature adaptive fusion module is added to the neck network, features of different scales are fused through cross-layer information, and the detection capability of the network is improved; and an up-sampling module of YOLOv8 is improved, a dynamic hierarchical up-sampling strategy is adopted, dynamic hierarchical sampling is performed on input features, and the spatial resolution and semantic expression ability of the features are optimized. According to the method, the target detection precision is effectively improved, the interference of shelters is reduced, the high precision is ensured, the rapid detection is realized, and the method is particularly suitable for carrying out the target detection task of an automatic driving system in an urban road environment.

The invention discloses a foggy day perception-based feature refinement ship instance segmentation method and equipment, and belongs to the field of instance segmentation of ship images in a foggy day scene. According to the method, YOLOv8s is used as a basic model, a joint learning framework is designed, and defogging and feature refinement enhanced perception strategies are combined. Through a state space model and a multi-scale channel aggregation gating strategy, modeling image features are refined, and foggy day long-distance dependence feature information captured by the model is enhanced. And through the adaptive defogging module, fog background interference features are reduced. Through multi-window branch feature extraction and a multi-angle similarity measurement strategy, the ability of the model to extract local detail information and global information is further enhanced, the focusing ability of a ship target area and the adaptability to a complex haze scene are improved, and the ship instance segmentation performance and generalization ability in a foggy day scene are effectively improved.

The invention discloses an infrared and visible light image fusion network system and an application method thereof, and relates to the technical field of image fusion. According to the method, a feature extraction block is constructed preferentially, and a multi-scale separable convolution module and deformable convolution are combined in the feature extraction block, so that extraction of environment information and highlighted information in a fused feature map is improved; then, by introducing a space channel cooperation attention module, channel information and space information of the feature map are refined, meanwhile, the channel information and the space information are made to interact to aggregate more information, and the information capturing capacity of the feature map is improved; experimental results show that the performance of the proposed method on an MSRS data set is superior to that of the most advanced method, and the future potential research direction is highlighted, so that the precision of the fused image is improved, and meanwhile, the development of advanced visual tasks is promoted.

Systems and methods for authenticating a user in an authentication system using a computing device configured to capture authentication biometric identity information. The authentication biometric identify information captured during an authentication session. The authentication biometric identify information may comprise or be derived from one or more images of the user being authenticated. The authentication biometric identify information is compared to root identify biometric information. The root identify biometric information is captured from a trusted source, such as trusted devices located at trusted locations, such as a government entity, financial institution, or business. Identity verification may occur by comparing the trusted root identify biometric information to the biometric identify information captured during an authentication session. Liveness determination may also occur to verify the user is a live person. Liveness determination may include comparing two images of the user such that the two images are captured at different distances from the user.