116 results about "Local matching" patented technology

The invention discloses a ship target tracking method based on radar imaging in a shielding environment, belongs to the technical field of target tracking, is used for ship target tracking, and comprises the following steps: obtaining multiple frames of echo images of a time sequence, obtaining a potential target on each frame by using a ship image feature detection method, and obtaining a time accumulation space diagram; initial tracks are extracted from the time accumulation space diagram, and a tracking ID is distributed to each initial track; a frame of echo image is read, the position of a potential target is detected, and the position of the potential target is associated and matched with the tracking ID; and updating the position of a potential target which is not normally associated and matched by using a ship target tracking method combining unscented Kalman filtering and LSTM. According to the method, more potential targets are extracted, and a local matching result is optimized; more and more accurate target information is provided for the VTS system, so that the VTS system can have more prior information of early warning, and safe passage of a main channel is ensured.

The invention discloses a business process multi-dimensional logic verification method and system based on a dynamic knowledge graph, and relates to the technical field of artificial intelligence and financial risk control. The method aims at solving the technical problems that a traditional rule engine cannot process unstructured data, and a large generative model has logic illusion and privacy risks. The method comprises the following steps: constructing a rule knowledge graph containing parameterized logic constraints (such as time sequence, mutual exclusion and numerical accumulation); converting the unstructured business operation record into a feature vector by using a locally deployed semantic model; performing global sequence alignment optimization by constructing a global semantic consistency objective function, mapping operation records to a theoretical decision path derived from a graph, and eliminating local matching ambiguity; and finally, on the basis of a mapping result, calling deterministic parameters in map edge attributes to execute strict mathematical logic verification (including complex workday calculation, mutual exclusiveness check and the like). According to the method, a'nerve-symbol 'dual architecture is adopted, accurate understanding of fuzzy semantics is achieved, logic verification certainty and data privacy security are guaranteed, and the method has a hidden process discovery capability.

The invention discloses a global and local feature fusion-based semi-supervised video target segmentation method and a global and local feature fusion-based semi-supervised video target segmentation system. According to the implementation scheme, the method comprises the following steps: firstly, acquiring required data sets including image and video data sets and corresponding segmentation labels, expanding the image data set, and sampling the video data set to obtain a training data set for training a segmentation model; and secondly, designing a segmentation model, constructing a loss function to train the segmentation model, and finally performing video target segmentation by using the trained segmentation model. According to the invention, a local-global branch fusion module is designed to carry out global context modeling and local detail enhancement on features used for non-local matching, so that the distinguishing capability of the model for distinguishing similar features is improved; therefore, the network can effectively solve the problem of wrong feature matching caused by similar interferents in a semi-supervised video target segmentation task. On this basis, a target scale self-adaptive down-sampling layer is further combined, and information of the same target under different scales is captured through the layer, so that the self-attention calculation complexity is reduced while the feature distinguishability is improved, and the balance between the model segmentation performance and the reasoning prediction efficiency is realized.

The invention discloses a video key frame extraction method fused with self-supervised deep learning, and the method comprises the following steps: carrying out the standardized sampling of an input video according to a fixed interval, extracting a SuperPoint local key point and a Video MAE global semantic feature, and generating a dense descriptor and a semantic vector; constructing multi-dimensional change indexes such as local matching degree and global similarity; constructing a soft distribution matrix and a matching point set based on the fusion features; dynamically judging the key frame through a self-adaptive multi-threshold rule; and outputting the key frame set. The method fuses local and global spatio-temporal information, has robust feature extraction and key frame discrimination capabilities under a weak supervision condition, and can effectively improve the efficiency and precision of video compression, abstract and event detection.

The invention relates to the technical field of intelligent recognition, in particular to a distributed edge calculation face recognition method and system for non-inductive passage, and the method comprises the steps: capturing a video stream through edge image collection equipment disposed at a passage entrance, and extracting a face image; and carrying out localized preprocessing, feature extraction and quick comparison with a local cache feature library by the edge computing node. If local matching succeeds, passing is controlled immediately; if the matching fails, the features are uploaded to a central cloud server, enhanced processing and global library comparison are performed by using the stronger computing capability of the central cloud server, and a result is issued and executed, so that the low delay of edge computing and the strong capability of cloud computing are effectively fused, and both the recognition efficiency and the system reliability are considered; and meanwhile, links such as encrypted transmission, dynamic updating, abnormal offline processing and detailed log recording are covered, the security, adaptability and maintainability of the system are remarkably improved while efficient non-inductive traffic is realized, and the method is suitable for intelligent traffic management in a large-scale and high-concurrency scene.

The invention discloses a small sample learning and out-of-distribution detection method and system based on global and local image-text alignment, and the method comprises the steps: collecting image data and corresponding class labels, obtaining a data set, processing the data set, and dividing the data set into a training set, an in-distribution test set, and an out-of-distribution test set; an out-of-distribution detection model is constructed and trained, the training comprises two stages, in the pre-training stage, text description is carried out on various image data of a training set, text description is obtained, in the training stage, global and local image-text features are extracted, and related and unrelated local image features are screened out; performing local supervised contrast learning on the fine-tuned text and related local image features, calculating global and local matching scores by using the image features and the fine-tuned text features, and completing model training; and performing classification prediction probability detection on the trained model. According to the invention, the performance of small sample image classification and small sample target detection is improved at the same time.

The invention provides an SLAM (Simultaneous Localization and Mapping) optimization method and equipment based on point cloud registration and adaptive resolution, and a medium, and relates to the technical field of AGV (Automatic Guided Vehicle) positioning and mapping, and the method comprises the following steps: (1) inputting and preprocessing sensor data; (2) front-end scanning and matching: based on the preprocessed data, carrying out point cloud registration through a GICP algorithm, updating the pose of the current frame and constructing a local subgraph; (3) global SLAM: receiving sensor data, poses and subgraph data from the front-end scanning and matching step, and carrying out loopback detection and global optimization; wherein a self-adaptive resolution switching strategy based on environment complexity is adopted in the loopback detection process; according to the GICP algorithm, the surface of the point cloud is modeled as Gaussian distribution, local features are described through a covariance matrix, and a target error function constructed based on the mahalanobis distance is optimized to estimate pose transformation. According to the method, the local matching precision and robustness are improved by replacing ICP with GICP, and the global calculation efficiency is adjusted and optimized in combination with the dynamic resolution.

The invention discloses a dual-stage CBCT and oral scanning tooth registration method and system, and relates to the field of tooth three-dimensional digital model registration, and the method comprises the following steps: extracting a tooth voxel structure in a CBCT image and a dental crown grid structure in an oral scanning image through a segmentation network; a coarse-to-fine depth registration network is introduced, geometric feature coding and feature matching are carried out on super-points obtained through multi-resolution down-sampling, local matching is carried out on a dense point set in a super-point neighborhood, a rigid transformation matrix is calculated in parallel, and an optimal registration result is screened out from the rigid transformation matrix; and dividing a registration object into a plurality of three-tooth groups containing three adjacent teeth, and performing local iteration alignment based on an initial registration result. The method still has higher robustness and accuracy under the complex conditions of large cross-modal difference, high input point cloud density and the like, is shorter in time consumption, and provides reliable data basis and automatic support for clinical scenes such as orthodontics and implantation.

The invention discloses an image staged matching and positioning method, and relates to the technical field of image analysis. Comprising the following specific steps: constructing a model architecture, and inputting an unmanned aerial vehicle image u; candidate images {u, Si} are screened through global semantic feature matching; the method comprises the following steps: extracting image key points and description words, establishing an initial matching point pair set, introducing a mismatching screening mechanism, executing homography transformation on geotagging information in a satellite image, and determining ground target positioning under the view angle of an unmanned aerial vehicle. According to the method, through a mode of combining global feature optimization and local mismatching screening, accurate positioning of a ground target under the view angle of the unmanned aerial vehicle is realized, and an optimal matching candidate is rapidly screened out; in the local matching stage, mismatching point pairs are eliminated, and the geotagging information in the satellite image is accurately mapped to the unmanned aerial vehicle image coordinate system through homography transformation, so that the image matching problem under the large view angle change is effectively solved, and the accuracy and efficiency of image matching and positioning are improved.

The present application relates to a multi-sensor-based relocalization method and apparatus, a device, and a storage medium. The method comprises: acquiring environment images acquired respectively by sensors; performing global matching for each environment image against images in a prior environment image library, so as to respectively obtain each pre-update robot pose corresponding to each sensor; performing local matching for each environment image against surrounding environment images corresponding to each pre-update robot pose in the prior environment image library, so as to obtain a score value of each post-update robot pose of a robot; and on the basis of the score value of each post-update robot pose, determining a relocalization result of a current pose of the robot.

The invention discloses a tumor diagnosis method and system for generating a molecular spatial distribution diagram based on MRI (Magnetic Resonance Imaging), and belongs to the technical field of image data processing. The method comprises the following steps: constructing an MRI-pathological local matching data set; the Transform and the GAN are combined to construct a local MRI (Magnetic Resonance Imaging) to generate a small pathological graph model; and constructing and verifying a molecular spatial distribution diagram. According to the method, the histopathology is taken as a bridge, a two-layer mapping relation is constructed between the MRI and the molecular features, the global molecular features are estimated through local matching data, existing clinical resources are effectively utilized, and three-dimensional space distribution evaluation of the molecular features is indirectly achieved at low cost. And the constructed model can be used for pathological diagnosis in any region on the brain MRI sequence, so that the potential invasion region of the tumor can be explored, and reference is provided for the surgical resection range definition and treatment strategy planning of the glioma.

The invention relates to a self-adaptive mask space-time alignment GPR positioning method, device and equipment, and aims to sequentially solve the problem of channel and time dimension dislocation in a GPR sequence by adopting a self-adaptive alignment and dynamic time warping strategy and then calibrate a query sequence. In addition, GPR low-frequency features can be enhanced through multi-stage discrete wavelet transform, meanwhile, signals can be optimized through channel dimension self-adaptive alignment, and the positioning precision when channel dimension features are distorted under the influence of rain and snow weather is remarkably improved. In addition, a local matching DTW algorithm is introduced to achieve robust temporal image sequence alignment. A wide range of experiments have been performed on a common LGPR data set GROUNDED and self-collected data covering five challenging scenes, and the result shows that compared with an existing method, the method provided by the invention has higher positioning precision and stronger robustness.

The invention relates to an environment sensing method based on target detection and stereo matching. According to the environment perception method based on target detection and stereo matching, targets in an environment image can be recognized through model training, and category information and position information of each target can be recognized, so that a target detection model can recognize the category information and the position information of the targets in the environment image in real time; through a local matching strategy of a target area delineated by focusing on the position information of the target, huge calculation overhead caused by full-image matching is avoided; pixel-level parallax information in the two-dimensional image is accurately converted into a physical depth distance in a three-dimensional space in combination with calibration parameters of a binocular camera in an environment sensing system; and finally outputting an environment perception image capable of displaying a detailed perception result of each detected target through information fusion. According to the environment sensing method, the efficiency and robustness of the whole sensing process are remarkably improved while the accuracy and integrity of environment sensing are ensured.

The invention relates to the technical field of three-dimensional modeling, in particular to an augmented reality-oriented three-dimensional scene reconstruction method and system, and is used for solving the technical problem that an iterative nearest point algorithm cannot meet high real-time performance and high-precision reconstruction requirements required by augmented reality at the same time. The method comprises the following steps: acquiring a pose transformation relationship between multiple frames of point cloud data and adjacent frames of point cloud data; extracting a plurality of feature points in each frame of point cloud data, and determining a feature descriptor of each feature point; according to the feature descriptors of the feature points, calculating a matching weight between feature point pairs in two adjacent frames of point cloud data, and calculating a local matching error based on the matching weight and a pose transformation relationship; performing global matching optimization based on the local matching error of the plurality of feature point pairs and the distribution density of each feature point in the respective point cloud frame, and determining an optimal matching point pair set which minimizes the global matching error; and according to the optimal matching point pair set, fusing the multi-frame point cloud data, and reconstructing a three-dimensional scene model.

The invention provides a multi-level retrieval generation method based on graph enhancement, which comprises a knowledge graph construction stage and a query engine operation stage, and realizes a multi-dimensional information retrieval scheme combining local query and global query in combination with a graph technology and a multi-level retrieval mode. According to the method, efficient storage and management of complex associated information are achieved through graph construction, meanwhile, high-quality knowledge association and question and answer support are provided for a user in a local matching and global screening mode in the query process, and the method is particularly suitable for processing a long unstructured text knowledge base of a complex structure.

The invention discloses a text matching method and device based on probability distribution, equipment and a storage medium, and relates to the technical field of natural language processing, and the method comprises the steps: obtaining semantic feature distribution of each professional knowledge text from a professional knowledge base, obtaining a knowledge probability distribution set, abstracting the intrinsic features of the text through probability distribution, and obtaining a knowledge probability distribution set; and standardized representation of the knowledge base is realized. The text input by the user is obtained, the corresponding user text probability distribution is calculated, and the fault tolerance of text matching is remarkably improved. The similarity distance between the user text probability distribution and each distribution in the knowledge probability distribution set is calculated, and the overall semantic similarity instead of local matching is measured through the distribution distance, so that the comparison process can tolerate the distribution offset. Finally, a text matching result is determined according to the minimum value of the similarity distance, the effect of stably retrieving semantic related professional knowledge under high noise is achieved, and fault tolerance and matching precision are remarkably improved.

The invention relates to the technical field of strain measurement, in particular to a three-dimensional full-field strain measurement method and system based on multi-view collaboration, and the method comprises the steps: constructing a sparse topology skeleton model of a measured target under a global coordinate system, and building a bidirectional projection mapping relation between the global situation and each local situation; the method comprises the following steps: synchronously acquiring a time sequence texture feature image of a measured target, calculating a luminosity geometric coupling confidence tensor of each pixel point and extracting an initial texture feature field under each view angle; utilizing a skeleton model to guide the initial texture feature field to perform limited local matching, and resolving to obtain a local independent displacement field and residual energy distribution of each view angle; performing multi-view weighted fusion based on a bidirectional projection mapping relation, and reconstructing a global three-dimensional displacement field; and performing differential calculation on the global three-dimensional displacement field to obtain a deformation gradient tensor and generate three-dimensional full-field strain distribution. According to the method, gradient mutation caused by view field splicing errors can be effectively inhibited, and physically real and full-field continuous three-dimensional strain distribution is obtained.

The invention discloses a sewer pipe network defect detection method based on multi-label zero sample learning. The method comprises the following steps: generating defect description corresponding to each pipeline defect category through a large language model; performing feature extraction and domain adaptation on the pipeline inner wall image and the defect description by using a representation guide module to obtain global and local image features and defect detailed description text features; synthesizing global and local image features of the image, respectively calculating global and local matching scores of the global and local image features and detailed description text features, and fusing to obtain a defect initial prediction score; constructing a semantic relationship adjacency matrix for displaying the relationship between different defect categories; and correcting the initial prediction score by using the semantic relationship adjacency matrix between the categories to obtain a final prediction score of each defect category. According to the method provided by the invention, knowledge migration from known defects to unknown defects is realized by constructing a guidance-fusion-correction network, and the difficulty in identifying types of unseen defects is effectively solved.

This invention proposes a cross-coordinate system road network data fusion method based on hierarchical matching and non-rigid registration, belonging to the field of road network technology, and solves the problems of computational complexity and poor versatility of existing methods. The method includes: acquiring and preprocessing benchmark and target road network data; estimating global transformation relationships by calibrating feature points, and initially aligning the benchmark road network to the target coordinate system to obtain a global region; constructing a fixed image of the target road network and a moving image of the benchmark road network within the global region; using algorithms such as B-spline free deformation that can model local nonlinear deformations to perform non-rigid registration on the fixed and moving images, optimizing the cost function to obtain pixel-level deformation fields; geometrically correcting the benchmark road network based on the deformation field, transferring the target road network attribute information, and summarizing and outputting a fused dataset. This method improves local matching accuracy and versatility through a hierarchical strategy and pixel-level registration, overcoming the influence of differences in road segmentation.

The invention discloses a fire-fighting monitoring room personnel on-duty monitoring method and system, a medium and a product, and relates to the field of image recognition. The method comprises the following steps: in response to detection that a to-be-monitored object completely enters a preset entrance area, extracting a visual feature vector in an unshielded image frame as an initial reference feature; when the to-be-monitored object moves to the on-duty monitoring area, deducting a shielding part based on an overlapping relationship between the real-time detection frame and the environment shielding mask, and extracting an exposed area; and calculating the local matching degree of the exposed area and the initial reference feature to determine the on-duty state of the personnel, and generating an updated reference feature when the conditions of the spatial overlapping degree and the texture similarity are met. According to the method, the complete features obtained at the entrance are used as the reference, and local comparison is carried out in combination with the exposed area, so that the problem of misjudgment alarm caused by the fact that an existing general target detection model cannot recognize an incomplete human body target in a static facility shielding environment is effectively solved, and the accuracy of on-duty monitoring is improved.

This invention discloses a heterogeneous robot collaborative scheduling method for multiple modules of a space station. It employs a hierarchical distributed collaborative architecture based on a semi-Markov decision process. Physical constraints are transformed into filtering conditions through a pre-defined physical constraint sub-mask that includes area access, resource capacity, deadline reachability, and skill matching. A task residual update mechanism mitigates the waiting and overhead issues caused by explicit synchronization negotiation under communication constraints. A task commitment mechanism is introduced, dynamically updating the task residual based on the confidence level of the preceding robot's commitment to the target task. Subsequent robots then fill in, replace, or re-match based on the updated task residual. When local matching enters an oscillating state or local matching convergence stalls, a skill gap tension vector reflecting the gap status of each skill dimension is generated and fed back to the upper layer. The upper layer determines the cause based on the gap type and degree of different skill dimensions and takes appropriate measures for collaborative scheduling.

The application discloses a kind of based on ecological environmental protection supervision big language model address resolution and geographic coding acquisition method and system.For the fuzzy, non-standard and positioning difficult problems of environmental supervision letter and visit complaint address description, the method first uses big language model to parse the original text into structured address, and cooperates multi-level fault tolerance mechanism to ensure the reliability of parsing result.In the matching stage, the system adopts local priority strategy, and preferentially searches the environmental special position database containing key polluting units and other information;If the initial matching is not hit, the self-defined part-of-speech tag segmentation technology is used to accurately extract the core environmental entities such as pollution outlet and water source protection area for secondary matching.To ensure accurate positioning, the system verifies by semantic similarity and geographical distance, to prevent errors caused by the same name in different places.When local matching fails, the system automatically accesses the network query, and uses big language model to simplify the redundant description and retry, forming a closed-loop error correction mechanism.The application significantly improves the accuracy and efficiency of pollution source positioning, protects data privacy, and provides strong technical support for environmental law enforcement personnel to achieve accurate positioning, rapid verification and scientific division of responsibility area.

The application relates to a multi-sensor-based repositioning method, device, equipment and storage medium. The method comprises the following steps: acquiring environment images collected by respective sensors; performing global matching on the respective environment images and images in a prior environment image library to obtain respective robot poses before updating corresponding to the respective sensors; performing local matching on the respective environment images and respective surrounding environment images corresponding to the respective robot poses before updating in the prior environment image library to obtain score values of respective robot poses after updating; and determining a repositioning result of a current robot pose according to the score values of the respective robot poses after updating. By performing global matching and local matching on the environment images collected by different types of sensors and the images in the prior environment image library, the repositioning result of the current robot pose can be ensured to have accuracy and reliability.

The embodiment of the invention relates to the technical field of federated learning and information security, in particular to a federated multi-target scheduling method and system for industrial control crowdsourcing testing, which is characterized in that sensitive data such as ability, experience and the like of a tester are only reserved at a local terminal by constructing a framework combining local feature coding and federated model training, so that the test efficiency is improved, and the test efficiency is improved. Outward transmission is not carried out; only the model update quantity after the privacy enhancement processing such as gradient cutting and differential privacy noise injection is uploaded to the federated matching learning server, and only the model update quantity after the privacy enhancement processing is uploaded to the federated learning server, so that the leakage risk of concentrated data storage is avoided from the source, the requirements of privacy regulations such as GDPR and the like are completely met, and the reliability of the system is improved. Compared with traditional privacy technologies such as homomorphic encryption, the method has the advantages that the calculation and communication overhead is greatly reduced, the design of local matching degree calculation is matched, the task matching response speed is greatly increased, and the real-time requirement of industrial control system testing is met.

The invention relates to a scene photographing recognition intelligent glasses system based on Bluetooth, and solves the problems of large response delay, low positioning precision and heavy equipment of traditional navigation equipment. The system comprises an intelligent glasses terminal, a local edge server and a cloud knowledge base. The glasses terminal is integrated with a miniature camera and a bone conduction loudspeaker, and a 128-bit visual feature vector is extracted by optimizing an ORB algorithm; a centimeter-level 3D scene map is pre-stored in the edge server, and a lightweight MobileNetV3 model is adopted to realize millisecond-level local matching; and the cloud generates personalized explanation based on the BERT model and the knowledge graph. The method has the technical effects that the indoor scene recognition accuracy is greater than 92%, the end-to-end response is less than 0.8 second, and the equipment cost is reduced to 1 / 5 of an AR scheme. The extended function supports barrier-free interaction and dialect protection, is suitable for scenes such as museums and scenic spots, and realizes integrated experience of cultural cognition and convenience service.

The application discloses a kind of power line fault visual detection method and system based on unmanned aerial vehicle inspection, it is related to electric power line intelligent inspection and computer vision field.The method comprises the following steps: collecting inspection image and environment information, calculating environment disturbance index and self-adaptive threshold updating, soft threshold and joint denoising pretreatment are carried out on the image;The pretreated image is input into a single-stage detection model to obtain a component candidate box, and a core component image is obtained by fine classification through a deep confidence network;The two-stage detection model is used to locate the fault area, the local feature is extracted, and the core fault feature is obtained by singular value decomposition;According to the component category and the environment index, select the template sub-library, determine the danger level by overall and local matching, and output the fault result, mark the abnormal time for review.The application improves the detection accuracy and environmental adaptability of components such as conductors and insulators through environment adaptive processing, component fine classification, low-rank feature extraction and hierarchical matching strategy.

A system and method for generating synthetic high-frequency seismic data for subsurface imaging comprises injecting a first seismic shot having a low frequency into a surface region and receiving reflected waves at a plurality of seismic receivers. Seismic traces are recorded and processed to generate a low-frequency seismic shot gather. A second seismic shot having a high frequency is injected, and a sparse number of high-frequency traces are recorded. A computing device resamples the low-frequency traces to match the sparse high-frequency dataset and applies a one-dimensional (1D) local matching filter to transform the low-frequency traces into simulated high-frequency traces. The transformed dataset is used to generate a high-resolution subsurface image of geological interfaces. The system enables computationally efficient high-frequency seismic data synthesis, optimizing seismic inversion accuracy while reducing acquisition costs and computational overhead.

The invention discloses a visual inertia SLAM system pose guiding method and system, and relates to the technical field of data processing. The method comprises a first data acquisition step, a first calculation step, a preliminary matching step, a second calculation step, a judgment step, a first feedback step, a first data processing step, a second data processing step, a third calculation step, a second data acquisition step, a pose optimization step and the like. According to the method, the precision and robustness of the visual inertia SLAM in a dynamic environment can be improved, the visual inertia SLAM is not easily influenced by speed change in a dynamic scene, the probability of local matching failure is reduced, and the precision of pose guidance is further improved.

The invention provides a binocular stereo matching method and device of an image, electronic equipment and a storage medium, and relates to the technical field of computer vision. According to the method, format conversion is carried out on the collected first initial image and the collected second initial image, the collected first initial image and the collected second initial image are converted into the first gray-scale image and the second gray-scale image with set digits, the method can be used for binocular matching of weak textures, pure color environments or dark environments, and the matching precision and speed are improved through local matching.

The present disclosure provides a kind of light node-oriented transaction verification method based on blockchain.The method does not depend on super node, through the process of transaction graph publishing-transaction propagation-transaction verification-transaction packaging chain, light node synchronizes DAG transaction graph, when light node carries out transaction verification judgment, first find the transaction that reaches verification condition, form the block to be verified with transaction digest, and publish to network;Light node received to the block to be verified carries out the judgment whether to pass according to the number of local matching consistency verification.The present application first filters the transaction that reaches verification condition by each light node local, then publishes the abstract to each light node for verification judgment, avoids the problem of large amount of calculation and network information interaction caused by each light node according to transaction content for verification judgment, both meets the demand of mobile device light weight storage, reduces the computing cost, and realizes data verification.