Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1822 results about "Feature recognition" patented technology

The term "feature" implies different meanings in different engineering disciplines. This has resulted in many ambiguous definitions for feature. A feature, in computer-aided design (CAD), usually refers to a region of a part with some interesting geometric or topological properties. These are more precisely called form features. Form features contain both shape information and parametric information of a region of interest. They are now ubiquitous in most current CAD software, where they are used as the primary means of creating 3D geometric models. Examples of form features are extruded boss, loft, etc. Form feature is not the only type of feature that is discussed in CAD literature. Sometimes a part's functional or manufacturing features of the subject of attention. Although it is quite possible to see form features and manufacturing features are called by the same name, they are not exactly the same concepts. For example, one may either use the name "pocket" to refer to a swept cut on the boundary of a part model, or to refer to a trace left on the part boundary by a specific machining operation. The former is exclusively concerned with a geometric shape whereas the latter is concerned with both the geometric shape and a manufacturing operation, needing more parameters in its definition. As such, a manufacturing feature can be minimally defined as a form feature (if it has a form that can uniquely represent it), but not necessarily vice versa (forms can be interpreted differently in different manufacturing domains). Machining features are an important subset of manufacturing features. A machining feature can be regarded as the volume swept by a "cutting" tool, which is always a negative (subtracted) volume. Finally, there is also the concept of assembly feature, which encodes the assembly method between connected components.

Large-scene monitoring video abnormal event early warning method based on multi-modal large model

The invention relates to the technical field of abnormal event early warning, and provides a large-scene monitoring video abnormal event early warning method based on a multi-mode large model. According to the invention, the problems of delay, low accuracy and limited coverage range of abnormal event early warning of large-scene monitoring videos in the prior art are solved. According to the main scheme, multiple paths of high-resolution monitoring videos are spliced and preprocessed to generate a panoramic video; synchronously acquiring and preprocessing audio and sensor data to construct a multi-modal data set; video key frames are extracted by adopting a traditional small model, and the video key frames and multi-modal data are jointly input into a multi-modal large model based on a Transform architecture for deep feature fusion; abnormal events such as tumble, congestion and fight are identified based on the fusion features; triggering an early warning mechanism to send event type and position information in real time; and storing the full-dimensional data of the abnormal event for tracing analysis. The real-time processing performance is optimized through edge calculation, the complex scene understanding ability is enhanced in combination with a multi-modal large model, and the detection precision and the response speed are remarkably improved.
Owner:PEKING UNIV (TIANJIN BINHAI) NEW GENERATION INFORMATION TECH RES INST +1

Low-altitude unmanned aerial vehicle trajectory tracking and monitoring method based on 5G-A communication and inductance integrated base station

The invention discloses a low-altitude unmanned aerial vehicle trajectory tracking and monitoring method based on a 5G-A communication sensing integrated base station, and relates to the technical field of low-altitude traffic management and communication sensing fusion, and the method comprises the steps: firstly collecting multi-source data such as a communication sensing fusion signal, environment interference and unmanned aerial vehicle attributes, and carrying out the alignment and packaging of a unified timestamp and a coordinate system into a synchronous data frame; then, deep fusion and anti-interference processing are carried out on the data frames, noise is filtered out, and pure fusion data is generated; and furthermore, real-time track calculation and motion trend prediction are carried out on pure data by utilizing multi-base-station cooperative calculation and prediction. Based on this, through a multi-target feature recognition and clustering separation mechanism, independent individual trajectories are accurately stripped from a complex mixed data stream, and compliance verification and anomaly judgment are performed on the trajectories in combination with an airspace rule base. In this way, the problems of signal interference and multi-target aliasing in a complex environment can be effectively solved, and therefore high-precision global tracking of the low-altitude unmanned aerial vehicle and real-time monitoring of abnormal behaviors are achieved.
Owner:JIANGSU XINWANG VIDEO SOFTWARE TECH CO LTD

Mechanical transmission system fault trend prediction system based on dynamic feature recognition

The invention discloses a mechanical transmission system fault trend prediction system based on dynamic feature recognition, and relates to the technical field of mechanical state monitoring. Comprising the following steps: synchronously acquiring a load torque signal and a lubrication state parameter signal of a transmission system and vibration acceleration signals of a plurality of measuring points through a signal acquisition module; the working condition decoupling characteristic generation module carries out time-frequency analysis on the vibration signal, calls a pre-stored load disturbance spectrum template according to a load torque signal to carry out adaptive differential processing so as to eliminate load fluctuation interference, and calls a correction rule set according to a lubrication state parameter signal to carry out form recombination on the signal so as to compensate the lubrication state influence; and finally outputting a working condition decoupling feature representing the health state of the mechanical part. And the trend prediction module calculates and obtains fault development trend and residual life estimation data through a pre-trained fault prediction model. According to the method, the dynamic characteristics representing the essential degradation of the part are effectively extracted, and the accuracy and reliability of fault trend prediction of the mechanical transmission system are improved.
Owner:HARBIN UNIV OF SCI & TECH

Glioma boundary identification method and system based on image fusion

The invention relates to the technical field of boundary recognition, in particular to a glioma boundary recognition method and system based on image fusion, and the method comprises the following steps: obtaining a multi-modal brain image, constructing a fusion matrix, extracting the gray features of an edge region and an adjacent region, recognizing signal-noise abnormal points, and revising a judgment standard. And adjusting the path direction and reconstructing an edge communication structure, and generating a glioma boundary region map under fusion. According to the method, high-precision alignment among modals is realized through multi-modal image gray scale unification and registration processing, key details are expanded and focused by enhancing edges and regions, the recognition accuracy is improved, gray scale comparison between the edges and outer adjacent regions is introduced, the signal distinguishing capability is enhanced, misjudgment is avoided, judgment conditions are dynamically revised according to the signal-noise difference, and the accuracy of recognition is improved. The method enables the recognition standard to have local adaptability, combines the path change trend to reorder and connect edge points, guarantees the continuity of a boundary structure, integrally improves the accuracy and integrity of fuzzy boundary recognition, and enhances the glioma contour extraction effect.
Owner:THE FIRST AFFILIATED HOSPITAL OF ARMY MEDICAL UNIV

Video tag recognition method and apparatus, and model training method and apparatus, device, and medium

A video tag recognition method, executed by an electronic device and comprising: by means of a video tag recognition model, respectively encoding video frames in a video to be recognized, to construct a global feature set comprising global features of the video frames obtained by encoding, and a local feature set comprising local features of the video frames obtained by encoding; on the basis of a feature similarity between the global features in the global feature set, compressing the global feature set to obtain a sequence of global features of a preset storage quantity; and on the basis of a feature similarity between the local features in the local feature set, compressing the local feature set to obtain a sequence of local features of a preset storage quantity (S91); concatenating a global query feature and a local query feature obtained by pre-training, and then using a self-attention mechanism to extract a self-attention feature, wherein the global query feature and the local query feature are obtained by training learnable query features on the basis of a sample video, and the self-attention feature fuses key information in the global query feature and the local query feature (S92); using a cross-attention mechanism to respectively extract a first cross-attention feature between the self-attention feature and each global feature in the global feature sequence, and to respectively extract a second cross-attention feature between the self-attention feature and each local feature in the local feature sequence (S93); and on the basis of the obtained first cross-attention features and second cross-attention features, recognizing a video tag of the video to be recognized (S94).
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Optical fiber embankment underwater piping leakage event time-space correlation analysis method

The invention discloses an optical fiber embankment underwater piping leakage event time-space correlation analysis method, and relates to the technical field of leakage event intelligent identification and risk assessment in embankment safety monitoring, and the method comprises the following steps: S1, obtaining continuous time-space monitoring data of an embankment underwater region obtained through monitoring by a distributed optical fiber sensing system; and S2, processing the continuous space-time monitoring data by adopting a feature recognition model based on a neural network, and recognizing a suspected leakage event. According to the time-space correlation analysis method for the underwater piping leakage event of the optical fiber embankment, by fusing multi-level data processing and self-adaptive feature learning, false alarms caused by environmental interference are effectively restrained, and the recognition accuracy of a real leakage event in a complex underwater scene is improved. An analysis framework combining space-time association diagram construction and physical mechanism verification is adopted, the internal relation between events can be deeply mined, and the space-time evolution rule of a seepage path is accurately restored.
Owner:NAT INST OF NATURAL HAZARDS MINISTRY OF EMERGENCY MANAGEMENT OF CHINA

Cable tunnel fire risk feature identification system and identification method

The invention discloses a cable tunnel fire risk feature identification system and identification method, and belongs to the technical field of cable tunnel safety monitoring. The whole stage of a fire is covered through multi-class cooperative detection, the target identification precision and scene adaptability are greatly improved, and the safety of the cable tunnel is improved. According to the whole system, a flame and smoke detection unit and a flame / smoke special detection unit are innovatively added to a detection engine module, an original heat source detection unit and an original human body detection unit are combined, a heat source-flame-smoke-human body four-category collaborative detection framework is formed, high-precision recognition is achieved on the basis of a YOLO model framework, and the detection efficiency is improved. Compared with the problems that a traditional system is high in single target detection omission ratio and cannot cover the whole stage of smoldering-initial open fire-violent combustion of a fire, the system has the advantages that the recognition rate of early flame and weak smoke is increased, the false alarm rate is greatly reduced, meanwhile, a heat source of operation and maintenance personnel is prevented from being misjudged as a fire hazard through human body detection, and the safety of the fire hazard is improved. And cable monitoring and personnel safety protection are both considered.
Owner:TIANJIN FIRE SCI & TECH RES INST OF MEM

Quartz sand flotation froth characteristic and dosage linkage control method

The invention is suitable for the technical field of quartz sand flotation, and particularly relates to a quartz sand flotation froth characteristic and dosage linkage control method which comprises the following steps: acquiring real-time process parameters and real-time image data; benchmark foam feature recognition is carried out based on the first image data, and the stable state and particle load characteristics of the foam under the current working condition can be accurately established; motion feature recognition is conducted on the second image data based on the reference foam features, and the dynamic evolution rule of the foam in the flotation tank can be captured in real time; real-time process parameters, moving foam characteristics and reference foam characteristics are combined to determine process adjustment parameters, and the residual state of chemicals in the system and the deviation condition of the flotation working condition can be quantitatively reflected; and the dosing control quantity is determined according to the process adjustment parameters, so that concentrate quality fluctuation and long-term potential quality hazards caused by excess or insufficiency are avoided, and the risk of secondary pollution is reduced.
Owner:GUANGXI GUOXING SILICON TECHNOLOGY CO LTD

Automobile chassis lightweight structure design method based on topological optimization

The invention discloses an automobile chassis lightweight structure design method based on topological optimization, and relates to the technical field of lightweight design. Constructing a macro-micro coupling model, and simulating and quantifying material parameter fluctuation by using Monte Carlo; establishing a rigid-flexible coupling multi-body dynamic model, simulating working conditions such as braking and turning, and generating a load spectrum by using a rain flow counting method; constructing a multi-objective function containing light weight, rigidity and modality, and solving manufacturing constraints such as pattern draft and the like by using an NSGA-II (Non-dominated Sorting Genetic Algorithm-II) algorithm; dividing steel, aluminum and carbon fiber material domains; and fusing bench test data to correct the model. According to the method, multi-scale collaborative optimization is realized, dynamic loads are accurately mapped, and light weight and performance are balanced; the connection reliability is improved through the multi-material gradient design; manufacturability is ensured through feature recognition and process verification; the batch consistency is guaranteed by digital twinning and robustness optimization; the chassis design efficiency and quality are integrally improved, and the service life is prolonged.
Owner:ANHUI TECHN COLLEGE OF MECHANICAL & ELECTRICAL ENG

Sludge treatment automatic monitoring method based on computer vision

The invention discloses a sludge treatment automatic monitoring method based on computer vision, and relates to the technical field of sludge treatment automatic monitoring, and the method comprises the following steps: collecting sludge image information through computer vision, extracting an edge integrity index and a brightness distribution index, and constructing a fusion judgment function based on the time sequence change of the two indexes, determining whether a thin water film exists on the sludge surface or not according to an output result of the fusion judgment function; under the condition of determining that a thin water film exists on the sludge surface, acquiring a pixel highlight gradient polymerization rate, a texture missing fluctuation frequency and an image saturation nonlinear deviation value of a corresponding image region, and establishing a specular reflection image feature recognition matrix; by constructing a multi-dimensional image feature recognition and dynamic regulation and control mechanism, the problem of image misjudgment caused by thin water film mirror reflection in the sludge dewatering process is solved, and accurate recognition and automatic closed-loop control of the real water-containing state of the sludge are achieved.
Owner:SHAOGUAN COLLEGE

Low-altitude traffic flow airspace-oriented real-time planning

The invention relates to the technical field of aerospace, in particular to low-altitude traffic flow airspace-oriented real-time planning, and provides a centimeter-level precision detection network covering a low-altitude airspace by integrating multi-dimensional data sources such as radar electromagnetic feature recognition, ADS-B (Automatic Dependent Surveillance-Broadcast) automatic monitoring, Beidou or GPS (Global Positioning System) space-time reference positioning and the like. The three-dimensional trajectory and motion situation of the aircraft are solved in real time, intelligent reconstruction of an airspace sector and adaptive optimization of a flight corridor are realized by adopting a dynamic programming algorithm driven by reinforcement learning based on the real-time pose data of the aircraft, and a flight conflict prediction model constructed by combining a space-time convolutional neural network is used for predicting the flight conflict. According to the method, potential risks can be pre-judged, an optimal avoidance path can be generated, full-process digital management and control from identity verification to airspace authorization can be realized by constructing an aircraft digital identity authentication system and a dynamic access control mechanism, and modules such as a three-dimensional navigation information service module, a low-altitude digital communication private network module and an intelligent early warning and warning system module are integrated. And the guarantee of full-life-cycle service is provided for the low-altitude aircraft.
Owner:CIVIL AVIATION FLIGHT UNIV OF CHINA

Turn-milling combined machining deformation control method and system for special-shaped parts

The embodiment of the invention provides a turning and milling combined machining deformation control method and system for a special-shaped part, and is used for the technical field of numerical control machining. The turning and milling combined machining deformation control method for the special-shaped part comprises the steps that structural feature analysis and process association marking are conducted on design data of the special-shaped part to generate a feature association data set, and clamping and process planning are conducted according to a machining constraint database and the feature association data set to generate initial turning and milling combined machining process data; cutting parameter multi-objective optimization solution is carried out on the initial turning-milling combined machining process data to obtain a turning-milling cutting parameter set, and multi-axis linkage analysis and instruction collaborative planning are carried out on the turning-milling cutting parameter set according to the equipment operation feature set to generate a combined machining control instruction set. According to the method, through part key feature recognition and risk marking, combined machining control instructions are generated after layered digital twinning verification in combination with process multi-objective optimization, and the one-time qualified rate of special-shaped part machining and turn-milling combined machining process stability are improved.
Owner:DONGGUAN LONGWIN PRECISION TECH CO LTD

Gas sensor environment anti-interference drift compensation method, system and equipment

The invention relates to a gas sensor environment anti-interference drift compensation method, system and equipment, and the method comprises the steps: collecting a mixed gas response signal in an environment, and obtaining an electromagnetic interference signal under the same timestamp; threshold truncation is carried out on spike pulses in the mixed gas response signals to obtain trend waveform signals caused by gas concentration changes, and denoising processing is carried out on the electromagnetic interference signals to obtain effective electromagnetic interference parameters; performing feature recognition on the effective electromagnetic interference parameters through a preset interference-response cooperative processing model to determine an interference mode and an interference intensity grade, synchronously analyzing the trend waveform signal to obtain a response feature curve of the target gas and the interference gas, and obtaining a drift compensation coefficient of the target gas; and carrying out collaborative optimization on the drift compensation coefficient through a preset interaction influence model to obtain a final compensation result so as to achieve the purpose of outputting a high-precision target gas concentration detection result.
Owner:SHENZHEN RUIDA TONGSHENG TECH DEV CO LTD

Image feature recognition method based on computer vision

The invention relates to the field of computer vision, in particular to an image feature recognition method based on computer vision, which comprises the following steps of: preprocessing an input image, removing image noise and correcting image gray deviation to obtain a preprocessed image; performing multi-scale feature extraction on the preprocessed image, obtaining image local texture features and global contour features under different scales, performing dynamic weight fusion, calculating dynamic fusion weight based on a feature response value and a local complexity factor, and performing dimension reduction processing on fusion features through a principal component analysis algorithm to obtain a target feature set; and matching the reference features, calculating the Euclidean distance between the target feature set and the reference features, determining an adaptive matching threshold, judging a matching result, and completing image feature recognition. According to the method, through adaptive filtering and gray level equalization preprocessing, Gaussian pyramid multi-scale feature extraction and dynamic fusion and adaptive threshold matching, feature extraction accuracy, characterization capability and recognition robustness are improved.
Owner:CHANGCHUN GUANGHUA UNIV

Anti-migration PPG identification method based on rate perception and state space model

The invention relates to the technical field of biological feature recognition, and particularly provides an anti-migration PPG recognition method based on rate perception and a state space model. The method comprises the following steps: performing physiological feature front-end extraction on an original single-channel PPG signal to obtain a high-dimensional shallow feature sequence; performing double-flow cooperative processing on the high-dimensional shallow-layer feature sequence, and distributing the high-dimensional shallow-layer feature sequence to two parallel branches, namely a control flow branch and a data flow branch; in the control flow branch, an amplitude spectrum and an instantaneous physiological rate curve are obtained; in the data stream branch, acquiring a deep global feature sequence with rate invariance; obtaining multi-scale refinement features based on the high-dimensional shallow feature sequence and the deep global feature sequence; according to the multi-scale refinement features, a final biological feature recognition result is obtained, the method can actively sense the physiological rate change, and efficient nonlinear modeling can be achieved with the extremely low parameter quantity.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +1

Power transmission line intelligent analysis system based on feature recognition

The invention relates to the technical field of power transmission line analysis, and discloses an intelligent power transmission line analysis system based on feature recognition. The system comprises a line working condition feature library construction module, a spatial distribution analysis module, a dynamic risk assessment module, an abnormal mode recognition module and a risk decision output module. The line working condition feature library construction module obtains multiple types of data, associates equipment identifiers and calculates working condition feature score values to generate a feature library; the spatial distribution analysis module extracts related data, and marks consistent and conflict areas to form a partition mark set; the dynamic risk assessment module is used for generating a load fluctuation influence superposition assessment result in combination with multi-parameter analysis for consistent area equipment nodes; an abnormal mode identification module screens abnormal points and establishes an abnormal equipment node set; and the risk decision output module marks risk diffusion path nodes and outputs operation state detection and risk early warning results. The system realizes comprehensive intelligent analysis of the power transmission line.
Owner:GANSU ELECTRIC POWER TIANSHUI POWER SUPPLY

Elevator multi-mode crowd feature perception and intelligent advertisement putting method and system

The invention provides an elevator multi-mode crowd feature perception and intelligent advertisement putting method and system, and relates to the technical field of intelligent advertisement putting, and the method comprises the steps: collecting multi-mode perception data in an elevator through an edge computing terminal; performing feature decoupling on the data, performing cross-modal semantic alignment, establishing a directed association relationship between modals, and constructing a scene feature map; calculating the topology importance degree of map nodes, screening feature nodes, and extracting context information for semantic coding; mapping the scene semantic code and the advertisement audience semantic code to a two-dimensional coordinate system to construct a semantic matching graph, and extracting an optimal matching path to form a candidate set; predicting a scene evolution trend based on the scene characteristic spectrum evolution trajectory, and calculating an advertisement adaptive score to generate a playing sequence; putting and collecting user interaction data feedback according to the sequence to update the graph structure. According to the invention, accurate crowd feature recognition and advertisement dynamic matching are realized, and the advertisement putting efficiency and the user experience are improved.
Owner:LIXIN (JIANGSU) INTELLIGENT TECHNOLOGY CO LTD

Energy storage rapid compensation method and system based on track overhead line system voltage fluctuation feature recognition

The invention discloses an energy storage rapid compensation method and system based on track overhead line system voltage fluctuation feature recognition, and relates to the technical field of track traffic traction power supply. The method comprises the following steps: synchronously acquiring voltage and current signals of the overhead line system, and extracting a composite feature vector containing disturbance root attributes and transient change rate; on the basis of the vector, a transient energy vacancy sequence covering the ultra-short-term future is output in real time through a prediction model fusing dynamic phasor analysis and a feedforward neural network; according to the sequence, a cooperative control strategy fusing overshoot and active damping is generated in combination with a proximity compensation principle and a voltage recovery state so as to drive an along-line energy storage unit; the strategy is executed in advance, compensation energy is injected, and finally double closed-loop correction is conducted based on the voltage residual error. According to the method, the problems of response lag, unclear disturbance identification, poor collaboration and lack of adaptive ability in the prior art are solved, and advanced, accurate, collaborative and self-optimized rapid suppression of the voltage fluctuation of the overhead line system is realized.
Owner:ZHEJIANG XINGKONG ELECTRIC CO LTD

Film and television play table book extraction method and device, storage medium and computer equipment

According to the movie and television play table book extraction method and device, the storage medium and the computer equipment provided by the invention, after an audio and video file of a movie and television play is split into a video file and an audio file, feature recognition is performed on the video file to obtain a subtitle text, speaker face information and a video understanding text; performing voice understanding on the audio file to obtain a voice transcription text and a voice understanding text; wherein the voice transcription text can be corrected into the standard transcription text with high accuracy through the subtitle text. Therefore, based on the face information of the speaker, the line segment of each speaker in the standard transcriptional text and the audio and video file is aligned, so that speaker information with accurate segmentation and semantic coherence can be obtained; and then, through combination with a character side-writing text generated by side-writing analysis on the speaker based on the video, the voice understanding text and the speaker information, table book information is constructed, and related feature description of the character can be covered on the basis of containing the line content, so that the content and depth of the table book are enriched.
Owner:GUANGZHOU QUWAN NETWORK TECH CO LTD +1

Blind sidewalk identification method based on image processing

The invention relates to the technical field of image recognition, in particular to a blind sidewalk recognition method based on image processing. The method comprises the following steps: collecting a ground scene image, and carrying out noise suppression and illumination normalization processing to obtain a ground scene image to be processed; inputting the to-be-processed ground scene image into a pre-constructed convolutional neural network model to identify feature textures of the blind sidewalk bricks; dividing a blind sidewalk area in the ground scene image to be processed by using the blind sidewalk brick feature texture, and determining a direction gradient feature of the blind sidewalk area; executing blind sidewalk direction consistency constraint based on the direction gradient features to collect blind sidewalk structured path segments; recognizing a blind sidewalk fracture area based on directional gradient features; and performing cross-frame target tracking according to the structured path segment of the blind sidewalk, and outputting a continuous blind sidewalk trajectory. The automatic recognition rate of the blind sidewalk area is improved based on the image recognition technology, and the continuous recognition capacity of the blind sidewalk path in the complex illumination and shielding environment is enhanced.
Owner:SHANDONG SAIFEITE SAFETY ENG TECH DEV CO LTD

Human-helmet matching method, system and equipment based on intelligent safety helmet

The invention discloses a human-hat matching method, system and equipment based on an intelligent safety helmet, and relates to the technical field of biological feature recognition, and the human-hat matching method based on the intelligent safety helmet comprises the steps: determining a matching strategy according to a working area where the intelligent safety helmet is located; receiving a human-hat matching instruction, and generating a voice prompt-data acquisition instruction according to the matching strategy and the human-hat matching instruction; the voice prompt-data acquisition instruction is sent to the intelligent safety helmet located in a working electronic fence coverage area, so that the intelligent safety helmet sends a preset voice prompt and feeds back acquired identity data, and the intelligent safety helmet is in a power-on state and a wearing in-place state; and carrying out human-hat matching according to the matching strategy and the identity data to obtain a human-hat matching result. According to the invention, people-hat matching can be accurately carried out in construction areas under various working conditions, and the construction safety management level is effectively improved.
Owner:POWERCHINA ZHONGNAN ENG

Welding seam recognition and trajectory optimization method and system based on 3D vision

The invention provides a welding seam identification and trajectory optimization method and system based on three-dimensional vision, and the method specifically comprises the following steps: firstly, collecting the three-dimensional point cloud data of a welding seam, extracting the local geometric features of the welding seam, and carrying out the feature enhancement of the local geometric features, so as to screen out representative effective edge points; and then, collecting multi-source point cloud data of the welding seam area, constructing a multi-scale welding seam feature recognition network, inputting effective edge points obtained by screening into the network, realizing accurate recognition of the welding seam area, and further extracting a linear welding seam area. According to the recognition result, a fitting algorithm is adopted for conducting curve fitting on the weld joint area, and a preliminary welding track is generated; and for the condition that multiple sections of welding seams are intersected, an optimal fitting point searching mechanism is further introduced, the preliminary track is optimized, and the continuity and integrity of a welding path are ensured. And finally, based on the center line of the welding seam, the posture of the welding gun is precisely planned in combination with the dihedral structure model, and therefore high-precision track control and posture adjustment are achieved.
Owner:XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY

Concrete structure crack full life cycle monitoring method and system

The invention relates to the technical field of crack monitoring, in particular to a concrete structure crack full-life-cycle monitoring method and system, and the method comprises the following steps: arranging sound wave points to obtain a stress change to generate an initial signal, extracting an image feature recognition extension path, analyzing a size acceleration to generate an extension identifier, and screening an active cycle at intersection time to generate an evolution fragment. And classifying crack behaviors according to displacement and width trends to generate an annotation set. According to the method, stress evolution is reflected based on interval transit time, a crack expansion trend is extracted in combination with an image feature point track, an active state is identified by superimposing crack size speed increase synchronism, a high-frequency change fragment is positioned through multi-index time intersection, and crack behavior types are divided according to a displacement direction and a width increase trend. Continuous tracking and classified marking of the whole process from crack starting to evolution are achieved, the response capacity to abnormal crack behaviors is enhanced, and the precision and timeliness of structural safety state recognition are improved.
Owner:济南天下第一泉风景区服务中心

Cross-modal biological feature generation type enhancement method and system

The embodiment of the invention discloses a cross-modal biological feature generation type enhancement method and system. The method comprises the following steps of: constructing a cross-modal biological feature recognition model, respectively acquiring long-distance modal data and short-distance modal data of a user, extracting feature vectors, pre-recognizing the user based on the long-distance feature vectors, finely recognizing the user based on the short-distance feature vectors, and carrying out mutual complementation and fusion on various modal features, so as to improve the recognition accuracy of the user. According to the method, the limitation that a single mode is low in recognition accuracy and prone to being interfered under different distance scenes is overcome, the identity recognition safety is improved, and through a secondary recognition mechanism combining pre-recognition and fine recognition, the efficiency and precision of identity recognition are improved while the system load is reduced.
Owner:HANGZHOU MINGGUANG MICROELECTRONICS TECH CO LTD

Multi-source data fusion geological disaster early warning system

The invention relates to the technical field of geological disaster monitoring and early warning, and discloses a geological disaster early warning system based on multi-source data fusion. The system comprises a data acquisition and preprocessing module, a dynamic coupling modeling module, a space mapping and feature recognition module and a risk analysis and early warning generation module. Firstly, transient disturbance and long-term steady-state components in monitoring data are separated; a dynamic coupling model containing bidirectional geomechanical feedback is constructed, the component fusion proportion is automatically adjusted according to the feedback intensity, and physically consistent fusion data is generated; spatial mapping is carried out by using an adaptive grid, and an effective abnormal feature cluster is identified through parallel scanning and prior geological knowledge constraint; and constructing a causal graph based on the abnormal clusters to carry out risk assessment and early warning. According to the system, physical driving of data fusion and knowledge guidance of anomaly recognition are realized, and the accuracy and reliability of early warning are improved.
Owner:ZHEJIANG CHENGAN BIG DATA CO LTD +2

Automatic identification and reasoning system for spatial geometric features and process knowledge of parts

The invention relates to the technical field of automatic feature recognition, in particular to a part space geometric feature and process knowledge automatic recognition reasoning system, which comprises a model acquisition module for acquiring a B-Rep model of a part to obtain triangular patches in each plane in the B-Rep model; the curved surface segmentation module is used for calculating a region attribution degree and dividing a surface into a plurality of sub-regions; the curved surface evaluation module is used for calculating a discrimination coefficient and distinguishing all surfaces into process surfaces and auxiliary surfaces; calculating a coherence evaluation value and structural complexity of each process surface; and the feature recognition and process reasoning module is used for determining the sampling precision of each surface, discretizing the surfaces and the edges, constructing an attribute adjacency graph of coding B-Rep model information, and machining the part based on a machining feature recognition result of the attribute adjacency graph. According to the invention, the processing technology feature identification precision of the part is improved.
Owner:HUNAN SANYUE SUWEI TECH CO LTD

Multi-target license plate recognition method based on visual attention mechanism

The invention discloses a multi-target license plate recognition method based on a visual attention mechanism, and belongs to the technical field of image processing and mode recognition, and the method comprises the steps: obtaining an input image, carrying out the multi-scale feature extraction, and generating a multi-scale feature map; performing spatial saliency calculation and normalization processing on the multi-scale feature map to generate an attention map; carrying out region division on the input image, and adopting differentiated image preprocessing strategies for different regions to generate a preprocessed image; based on the preprocessed image and the attention map, multi-target detection is carried out through a target detection network, candidate area screening is carried out, and a candidate license plate area is generated; and performing binarization processing, character segmentation and feature recognition on the candidate license plate region, and performing verification in combination with context information to generate a license plate recognition result. The attention map is generated by adopting a visual attention mechanism, differentiated image preprocessing and multi-target detection are guided according to the attention map, and multi-target license plate recognition can be completed in a complex scene.
Owner:SHENZHEN BOTE TECH CO LTD

Integrated federated learning optimization method based on clustering weight sampling

The invention discloses an integrated federated learning optimization method based on clustering weight sampling, and the method specifically comprises the following steps: a federated learning system comprises a plurality of clients and a server, and the server calculates the similarity between the clients through model updating information uploaded by the clients, clustering the clients by adopting a dynamic clustering method according to the similarity; the server carries out secondary clustering according to a set sampling rule and judges whether a first-stage iteration threshold value is reached, all the clients obtain a latest global model and freeze a model feature recognition layer for fine tuning, the server collects parameters of all the clients after fine tuning, and then the parameters are clustered according to similarity and are subjected to secondary clustering according to the sampling rule; and combining into an enhanced global model through an ensemble learning strategy. The method can be widely applied to data privacy protection scenes in the fields of medical image analysis, financial risk control, intelligent transportation and the like, and a new technical solution is provided for efficient application of federal learning in a heterogeneous environment.
Owner:SHANGHAI UNIV

Fish school photoacoustic feature recognition method based on multi-modal deep network

The invention discloses a fish school photoacoustic feature recognition method based on a multi-modal deep network, and the method comprises the steps: 1, obtaining data: obtaining acoustic data and visual data; 2, acoustic data preprocessing and feature engineering; 3, visual data preprocessing and labeling alignment are carried out; 4, constructing a sample and organizing a data set; step 5, designing a multi-mode branch network; step 6, carrying out cross-modal fusion and joint representation; step 7, performing multi-task output and a loss function; and step 8, model training and evaluation. According to the invention, by fusing acoustic, optical and environmental sensor data, an acoustic-vision-environment three-branch feature extraction network is constructed, adaptive fusion of multi-modal features is realized, the problems of low fish school recognition precision, difficulty in alignment and fusion of multi-modal data and the like in a complex marine environment are effectively solved, and the accuracy of fish school recognition is improved. The method is suitable for real-time fish school monitoring and analysis tasks of unmanned ships, buoys and fishery administration monitoring platforms.
Owner:NINGBO YUYAO TECH CO LTD

High-frequency instrument power adjusting system based on image recognition and impedance recognition

The invention provides a high-frequency instrument power adjusting system based on image recognition and impedance recognition, and the system comprises an image recognition module which is used for responding to a collection instruction, collecting an image of a tissue, and carrying out the feature recognition of the image, and obtaining an image feature; the impedance identification module is used for responding to the acquisition instruction, acquiring an electric signal of the tissue and processing the electric signal to obtain impedance information; the main control module is used for responding to the control signal, generating an acquisition instruction, sending the acquisition instruction to the image identification module and the impedance identification module, and carrying out weighted fusion calculation on image features and impedance information to obtain a power issuing parameter; and the power control module is used for adjusting the power of the high-frequency instrument based on the power issuing parameters.
Owner:HANGZHOU HUAJAN MEDICAL ROBOTICS CO LTD