463 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.

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 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 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.

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 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 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 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.

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 provides a business path tracking and fault tracing method and device for a video monitoring system, and relates to the technical field of video monitoring fault diagnos.The video monitoring system is divided into a plurality of layers, and multiple types of data acquisition probes are deployed at key nodes of each layer; when a user initiates a video request, generating a Trace ID to be spread along with a video streaming signaling, and reconstructing an end-to-end service path in combination with node information captured by a probe; associating and fusing the multi-dimensional performance data by taking the TraceID as a key, and establishing an end-to-end total delay decomposition and dynamic health baseline; and positioning a root cause node based on the weighted directed graph, the node anomaly confidence score and the fault propagation consistency, displaying a path, data and a traceability result through a visual interface, and generating a precise alarm. According to the method, service link visualization is realized, traditional equipment alarm is upgraded to service fault root cause positioning, the troubleshooting efficiency is improved, and the method is suitable for an isomerized large-scale video monitoring system.

The invention discloses a language-guided structure-aware network architecture and method for camouflage target detection, and relates to the technical field of camouflage target detection. According to the method, the text is guided to focus on a potential target, text semantic and visual features are fused through the CLIP model, the target mask is generated, the problems that a traditional model lacks semantic guidance and is difficult to focus on a camouflage area are solved, and background interference is greatly reduced; edge details can be accurately extracted, a Fourier edge enhancement module (FEEM) is combined with spatial domain edge enhancement and frequency domain high-frequency information capture, the problem of a fuzzy pain point of a camouflage target boundary is effectively solved, and the edge positioning precision is improved; structural and local dual optimization is proposed, a structural awareness attention module (SAAM) is fused with semantic and edge information, and a coarse guidance local refinement module (CGLRM) is designed through double branches of global guidance and local refinement, so that the regional consistency and structural integrity of a segmentation result are guaranteed, and local details are prevented from being lost.

The invention discloses an agricultural hyperspectral image classification method based on a hypergraph and Mama, and the method comprises the steps: S1, constructing a spectrum-space hypergraph according to an agricultural hyperspectral image; s2, a Mama framework used for hyperspectral classification is constructed; and S3, inputting the spectrum-space hypergraph into a Mama framework for hyperspectral classification, and carrying out classification, the method effectively fuses space and spectrum information, improves the precision of hyperspectral image classification, and solves the problem of information capture in a traditional method.

The invention belongs to the field of computer science and technology, and particularly relates to a multi-mode weak supervision video anomaly detection method and device, equipment and a medium. The method comprises the following steps: firstly, carrying out dynamic modeling on inter-fragment information by utilizing an external attention mechanism to obtain cross-fragment global context information; the temporal context aggregation module and the multi-scale time network are used to capture global and local information of the visual information and the text information within the fragment, and a feature representation containing local context details and the global information is generated. In addition, a multi-modal adaptive fusion mode is adopted, key modal features are focused in combination with target weights, further processing is performed through a multi-scale convolution attention module, and feature representation with higher discrimination is extracted. According to the method, the dependence on accurate annotation data in traditional video anomaly detection is effectively reduced; through hierarchical context modeling and an adaptive attention mechanism, the feature expression ability and the key information capture efficiency are enhanced, and a reliable anomaly detection solution is provided for an intelligent monitoring system.

The invention discloses a scale and semantic feature fused power equipment instance segmentation method and device, electronic equipment and a storage medium, and belongs to the field of power equipment.The method comprises the steps that a power distribution image is acquired; inputting the power distribution image into a preset model, so that the model generates a plurality of hierarchical features corresponding to different scales according to the power distribution image through an image coding module; generating a plurality of context enhancement features according to the plurality of level features through a scale sensing module; generating a plurality of semantic alignment features according to the plurality of level features through a semantic perception module; through a feature fusion module, generating a plurality of fusion features according to the plurality of context enhancement features and the plurality of semantic alignment features; generating the category of the power equipment, the coordinate frame of the power equipment and the boundary of the power equipment according to the plurality of fusion features through an instance segmentation decoding module; by implementing the method and the device, the problem of insufficient target information capture caused by single-scale feature capture in the prior art can be solved.

The invention discloses a foundation pit early warning method based on multi-source monitoring data and dynamic evaluation, which relates to the technical field of foundation pit safety early warning and comprises the steps of S1, multi-element monitoring, S2, data processing and normalization, S3, dynamic safety level establishment, S4, dynamic weight and credibility calculation, S5, evidence fusion and safety level judgment and S6, dynamic risk evaluation and calibration. According to the method, all-dimensional data acquisition and high-quality data processing are formed through the steps S1 and S2, all-dimensional information capture of foundation pit engineering characteristics, geological conditions, surrounding environments and body states is achieved, data quality is guaranteed through data cleaning, normalization and validity verification, and the problems of monitoring data fragmentation and uneven quality are avoided; through the steps S3 and S5, a security level judgment system of dynamic probability allocation and multi-source evidence fusion is constructed, limitation of a static threshold method is prevented, and scientificity and accuracy of security level judgment are improved.

An object-collection system is disclosed. The system including a vehicle connected to a bucket, a camera connected to the vehicle, and an object picking assembly configured to pick up objects off of ground. The system further includes a processor that obtains object information for identified objects, guides the object-collection system over a target geographical area toward the identified objects based on the object information, captures images of the ground relative to the object picker as the object-collection system is guided towards the identified objects, identifies a target object in the images, tracks movement of the target object across the images as the object-collection system is guided towards the identified objects, and employs the tracked movement of the target object to instruct the object picker to pick up the target object.

The invention discloses a multi-modal neural network-driven product style trend analysis method and system, and relates to the technical field of image processing, and the method comprises the steps: receiving product multi-modal data, including text, image and audio data, carrying out the tensor extraction of the product multi-modal data, enabling each modal data to correspond to a single-peak tensor, and carrying out the tensor extraction of the product multi-modal data; carrying out feature fusion on the single-peak tensor to obtain a multi-modal feature tensor, and then carrying out dimension reduction processing; calculating a cross-modal multi-head attention score by using the single-modal tensor based on a language tensor, wherein the cross-modal multi-head attention score is used for weighting single-modal features; fusing weighted features, dimensionality reduction tensors and manually labeled style labels, constructing a supervised training target, and generating single-mode pseudo labels for multi-task model training; cross-modal shared information capture is carried out on the unimodal tensor based on a covariance matrix, cross-modal shared information is constrained through modal alignment loss, and under a multi-task learning framework, a trained multi-task model takes output of a multi-modal main task as a final style label to realize product trend analysis.

A remote sensing image-text retrieval method based on information processing comprises the steps of preprocessing before modal input, building of an image-text retrieval model and characterization alignment, and the step of building of the image-text retrieval model comprises designing a target information enhancement module and a noise information compression module. The target information enhancement module aims at features of multiple scales to integrate detail information into visual features through the detail guide information attention module so as to enrich detail expressions of images, and the noise information compression module compresses graphic and text information so as to filter redundant information. According to the remote sensing image-text retrieval method, the problems that in an existing remote sensing image-text retrieval method, remote sensing image-text information capture is insufficient, and redundant information is excessively concerned are solved, and the remote sensing image-text retrieval precision is improved.

The invention discloses a deep learning aircraft skin damage detection method suitable for a dark light condition, and the method comprises the following steps: enabling an unmanned plane to fly around an aircraft to obtain the original image data of the aircraft skin damage, carrying out the preprocessing of the collected image data, completing the screening and label marking, and carrying out the detection of the aircraft skin damage. The invention relates to the technical field of aircraft skin detection, in particular to an aircraft skin damage detection method based on a PENet network, an aircraft skin damage data set needed by a training network is made, image data of the training data set is input into the PENet network, the dark light information capture rate is increased, and the training data set processed by the PENet is input into an improved yolov8 network and a CSPDarknet backbone network for feature extraction. The SCConv module is used for carrying out CNN compression by using space and channel redundancy between features, redundancy calculation is reduced, learning of representative features is promoted, the training calculation amount is reduced, the model is lightened, the model training time is shortened, an algorithm is deployed on the unmanned aerial vehicle, consumption of manpower and material resources can be greatly reduced, and the detection cost is reduced.