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

45results about How to "Guaranteed recognition effect" patented technology

Multi-source information fusion sealed electronic equipment redundancy positioning and material identification method and pulse extraction and matching method

The invention discloses a multi-source information fusion sealed electronic equipment redundancy positioning and material identification method and a pulse extraction and matching method, and belongs to the technical field of sealed electronic equipment redundancy detection. The objective of the invention is to solve the problem that the recognition accuracy of redundant object positioning and material recognition of existing sealed electronic equipment in the prior art needs to be further improved. Performing pulse extraction and pulse matching on multi-channel redundancy signals to obtain a plurality of pulse groups according to the signals obtained by simultaneous measurement of the plurality of acoustic emission sensors; respectively generating spectrograms for the pulses, obtaining a position and a material identification tag by using a neural network, and obtaining a result by majority voting; gray level co-occurrence matrix features are extracted for the spectrogram, recognition feature vectors are obtained in combination with time domain and frequency domain features of the same set of pulses, a position / material recognition tag is obtained through a classifier, and a result is obtained through majority voting; performing majority voting based on all the prediction labels to obtain a result; and performing majority voting on the basis of results obtained by all votes to obtain a final result.
Owner:HARBIN INST OF TECH

Single-scale field calibration method

The invention discloses a single-scale field calibration method, and belongs to the technical field of camera calibration, and the method comprises the steps: obtaining a calibration image through a linear scale and a binocular camera; relative orientation is carried out on each camera, and internal and external parameter initial values of the cameras are obtained: through relative orientation, the relative position and attitude relation between the cameras in the binocular camera is determined, a local coordinate system with the reference camera as a reference is established, and the internal and external parameter initial values of the cameras are obtained by using the coplanar condition between the cameras; performing absolute orientation on each camera and calculating external parameters of a calibration image acquired by each camera: determining the position and attitude of the binocular camera in a world coordinate system through absolute orientation, acquiring world coordinates of all calibration points of the calibration image, and calculating external parameter values of each calibration image relative to the world coordinate system; and performing parameter optimization adjustment on the camera parameters. According to the invention, the problem of difficulty in field calibration of a large field of view including a part of super-large fields of view is solved.
Owner:XINTUO 3D TECH (XIAN) CO LTD

Chemical process fault diagnosis method based on multi-scale spatial-temporal feature fusion

The invention relates to the technical field of chemical process fault diagnosis, in particular to a chemical process fault diagnosis method based on multi-scale spatial-temporal feature fusion, which comprises the following steps: regularly acquiring fault data in a chemical production process, preprocessing the fault data and inputting the preprocessed fault data into an MTS-F model; the MTS-F network comprises a time sequence feature extraction module and a spatial feature extraction module which are parallel, and the time sequence feature extraction module comprises a long short-term memory network, a channel attention mechanism module, a one-dimensional convolution layer and a global maximum pooling layer which are connected in sequence; the spatial feature extraction module comprises a GS-CNN module, a maximum pooling layer, two groups of spatial separable convolution layers and maximum pooling layers, and a global maximum pooling layer which are connected in sequence; and after the outputs of the two parallel networks are spliced, a prediction result of fault classification is output through a discarding layer and a full connection layer. According to the method, the time sequence and space features are extracted simultaneously in a parallel mode, the fault diagnosis capability is improved, the model parameter quantity and the calculation quantity are reduced, and good generalization performance is achieved.
Owner:ZHEJIANG SCI-TECH UNIV

Porphyromonas gingivalis detection method based on portable glucometer

The invention relates to the field of pathogen detection, in particular to a porphyromonas gingivalis detection method based on a portable glucometer. The method provided by the invention comprises the following steps: S101, adding a sample into a first reaction system and incubating to obtain a first mixture; s102, a modified matrix electrode is in contact with the first mixture and then washed; s103, inserting the washed modified substrate electrode into a blood glucose meter; s104, obtaining a glucometer reading, and further obtaining the concentration of the porphyromonas gingivalis in the sample; wherein the modified matrix electrode is modified by an Au (at) V4C3MXene material and is combined with an antibody for specifically recognizing porphyromonas gingivalis and a sealing agent. The detection method provided by the invention is sensitive, rapid, stable, accurate and simple, and accurate detection of the single-digit porphyromonas gingivalis in an actual sample can be realized in a relatively short time (such as 20 minutes).
Owner:STOMATOLOGICAL HOSPITAL OF CHONGQING MEDICAL UNIV

Campus bullying behavior intelligent identification method based on multi-view panoramic camera

The invention relates to the technical field of campus bullying behavior identification methods, in particular to a campus bullying behavior intelligent identification method based on a multi-view panoramic camera, which comprises the following steps: collecting panoramic image information of a campus specified area through a multi-view panoramic camera device; acquiring spatial position parameters of the multi-view panoramic camera device; performing gridding and coordinate processing on the panoramic image information based on the panoramic image information and the spatial position parameters; performing scene positioning and abnormal behavior detection based on the panoramic image information after gridding and coordinate processing; based on the abnormal behavior detection result, obtaining the abnormal behavior detection result and a probability distribution diagram of abnormal types detected in each frame by using a space-time convolutional network; based on the panoramic image information, interactive postures of the students are analyzed to obtain intimacy among the students, and a student social relation graph is constructed; obtaining a training model based on the training data set and the federated learning framework; and inputting the panoramic image information into the training model to obtain an abnormal behavior prediction result.
Owner:DRAGONFLY INTELLIGENT VISION TECH (SHENZHEN) CO LTD

Sow body condition comprehensive scoring method based on data layer fusion

The invention discloses a sow body condition comprehensive scoring method based on data layer fusion, and belongs to a detection method. The method comprises the following steps: S1, image acquisition and data acquisition; s2, fusing the RGB image and the depth image into a point cloud; s3, fusing the original point cloud and the fused point cloud; s4, fusing the fused point cloud and the one-dimensional data; s5, establishing and training a sow body condition scoring model; s6, scoring the body conditions of the sows. According to the method, data layer fusion of one-dimensional data, two-dimensional images and three-dimensional images is completed through a data fusion method, a CIW method is provided, the method aims at improving the attention degree of a model on minority classes (long tail parts) and maintaining the recognition capacity on majority classes, and RGB images comprise the color, contour and texture features of pig bodies; pig body characteristics of a single laser point visual angle are collected by the depth camera; the laser radar collects pig body characteristics of the visual angles of a plurality of distributed laser points; the three types of different image features complement each other, and meanwhile, different varieties, tire numbers and production stages are considered, so that the scoring method has wide applicability.
Owner:NORTHEAST AGRICULTURAL UNIVERSITY

Electrocardiogram image enhancement processing method and system based on deep learning

InactiveCN119066349Akeep useful informationmaintain integrityBiological modelsData setWavelet denoising
The invention relates to the technical field of image processing, in particular to an electrocardiogram image enhancement processing method and system based on deep learning. The method comprises the following steps: acquiring an electrocardiogram training set; performing wavelet denoising and intrinsic mode decomposition denoising on the electrocardiogram training set to obtain a waveform denoising data set; adversarial enhancement of different abnormal types is carried out on the waveform denoising data set, so that an enhanced and expanded data set is obtained; performing multi-lead mode data simulation on the enhanced and expanded data set to obtain a multi-lead simulation data set; performing multi-dimensional data integration on the multi-lead data set to obtain a multi-dimensional electrocardiogram data set; and performing convolution model fusion on the multi-dimensional electrocardiogram data set to obtain an electrocardiogram enhanced convolution model. According to the invention, enhancement effects of various electrocardiogram images can be realized based on deep learning.
Owner:JINING KESHUN BIOTECHNOLOGY CO LTD

Single-phase contact tree grounding fault detection method and device

The invention provides a single-phase contact tree grounding fault detection method. The method comprises the following steps: acquiring initial zero-sequence voltage data in a power distribution network; the waveform amplitude of the initial zero-sequence voltage data is screened, and target zero-sequence voltage with the waveform amplitude abrupt change is obtained; judging whether the target zero-sequence voltage has a beat frequency characteristic or not, if so, determining that the target zero-sequence voltage has a first fault, and otherwise, entering the next step; and separating the target zero-sequence voltage by using a fixed point algorithm, judging whether the separated zero-sequence voltage has a beat frequency characteristic or not, and if so, determining that the target zero-sequence voltage has a second fault. The invention also provides a single-phase contact tree grounding fault detection device. According to the invention, single-phase contact tree grounding fault detection is carried out based on the fixed point algorithm FastICA, the identification speed is improved while the identification capability is ensured, and the detection efficiency can be effectively improved.
Owner:INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI

Code security vulnerability detection method based on deep learning

The invention discloses a code security vulnerability detection method based on deep learning, and the method comprises the following steps: 1, collecting a large amount of code data, including normal codes and codes containing security vulnerabilities; 2, preprocessing the collected code data, wherein the preprocessing comprises code analysis, feature extraction and label marking; 3, constructing a deep learning model for learning feature representation from the code data; 4, training the deep learning model by using the preprocessed code data until the model reaches a preset performance index; according to the method, complex vulnerability features can be automatically learned from a large amount of code data, the features possibly far exceed rules which can be made manually, the accuracy of security vulnerability detection can be remarkably improved, the situations of false report and missing report can be reduced, and therefore the security of software is improved.
Owner:SHENZHEN YUCHEN TECHNOLOGY CO LTD

Multi-person human body behavior identification method based on MIMO through-the-wall radar feature fusion

The invention belongs to the field of MIMO through-the-wall radar and computer vision, and discloses a multi-person human body behavior recognition method based on MIMO through-the-wall radar feature fusion, which comprises the following steps: carrying out preliminary feature extraction on behavior action information, including original features and Doppler features, preprocessing collected radio frequency signals, constructing a three-dimensional space power matrix, and carrying out feature fusion on the three-dimensional space power matrix; constructing a Doppler behavior matrix, combining a multi-frame data feature matrix, constructing a behavior feature model, and inputting the behavior feature model into an FS-Convnext network model to complete training.
Owner:NANJING UNIV OF POSTS & TELECOMM

Mctp-based event reporting method, setting device, target device and system

The application discloses an event reporting method, a setting device, a target device and a system based on MCTP, and the method comprises the following steps: the setting device sends a setting event message with the MCTP message type code being 0x77 to the target device, the message at least containing an event label, a data length and an event condition described by a formatted string key-value pair; the target device receives and stores the event condition; when the event condition is met, the target device actively sends a reporting event message with the code being 0x77 to the setting device. By using the event notification mechanism, the setting device does not need to poll frequently, the monitoring condition is configured on the target device by one time setting, the target device actively reports when the condition is met, repeated information transmission is avoided, the MCTP bus communication flow is greatly reduced, and the system load is reduced; meanwhile, the key information and the change information can be sent in real time, the information updating delay problem caused by reducing the polling frequency is solved, and the balance between the system load and the real-time response is realized.
Owner:SHENZHEN TONGTAIYI INFORMATION TECH CO LTD

Sorting machine control method and system and sorting machine

The invention discloses a sorting machine control method and system and a sorting machine, and the control method comprises the following steps: S1, after the sorting machine is started, a sorting trolley loop line is controlled to run according to a preset loop line speed; s2, when a loop line emergency braking signal is received, controlling a primary and a secondary of a linear motor of the sorting machine to cooperate to generate reverse thrust according to a stepped reverse thrust control strategy so as to enable the sorting trolley loop line to be reduced to a lower limit speed and then stop supplying power to the primary so as to enable the sorting trolley loop line to stop running; and S3, when a loop line normal stop signal is received, power supply to the primary stage is stopped, so that the sorting trolley loop line stops running. When emergency braking is needed, reverse thrust is generated through the primary part and the secondary part, so that stopping of the sorting trolley loop line can be effectively accelerated, meanwhile, through stepped control over the reverse thrust, the smoothness of braking can be achieved as much as possible, the situation that the sorting trolley loop line reversely runs due to the fact that the reverse thrust is too large can be effectively avoided, and the service life of the sorting trolley loop line is prolonged. And the braking reliability is ensured.
Owner:SUZHOU GP LOGISTICS SYST

A communication risk detection method, system, device and storage medium

The application discloses a communication risk detection method, system, device and storage medium, relates to the technical field of network security, and solves the problem of difficult data tracing by standardizing communication data and associating the standardized communication data with an abnormal list library to construct a dynamic network; through multi-time scale feature extraction combined with a parallel analysis architecture, fast response is realized by using a real-time rule matching layer, dynamic evolution rules are captured by using a hidden Markov model of a behavior pattern analysis layer, and group risks are identified by using a space-time weighted model of a correlation network analysis layer, so that the defects of poor adaptability and single dimension of traditional methods are overcome; finally, through multi-engine decision and hierarchical disposal mechanism, the recognition accuracy is guaranteed while the disposal efficiency is optimized, so that high-precision and low-delay identification and control of cross-border abnormal communication behaviors are realized.
Owner:BEIJING YOUKUN TECH CO LTD

Self-moving device and light supplementing assembly

The invention provides a self-moving device and a light supplementing assembly, and the self-moving device comprises a main body which walks forward on the ground of a working area; the visual component is arranged on the main body and is configured to collect an image of a predetermined area in the moving direction of the self-moving equipment and identify target information in the image so as to execute a corresponding action based on the target information; the light supplementing assembly is arranged on the main body and is configured to be started under a preset condition to project a light beam to the preset area so as to form an effective light supplementing area in the preset area; wherein the target information comprises non-grass information, and the effective light supplementing area at least covers a corresponding area of the target information in the predetermined area. The light supplementing assembly is used for supplementing light for the preset area including the target information, the recognition effect of the visual assembly in the dark light environment is guaranteed, and the stability and reliability of the self-moving equipment are improved.
Owner:POSITEC POWER TOOLS (SUZHOU) CO LTD

Method and device for identifying microstructure of 2.5-dimensional braided composite materials based on machine vision

ActiveCN118655086BImprove classification resultsClassification results are reliableMaterial classificationMachine vision
The present application provides a method and device for identifying the microstructure of a 2.5-dimensional woven composite material based on machine vision. The method provided by the present application includes: identifying the target woven composite material based on the top view and the structural tensor information identification method of the target woven composite material to obtain a first material classification result; determining the pixel range of the warp and weft yarns of the target woven composite material from the main view based on the first material classification result of the top view, and determining the number of pixels in each independent area based on the pixel range, thereby optimizing the first material classification result and obtaining a second material classification result; obtaining a third material classification result based on the main view recognition result and the side view recognition of the overlapping warp yarns, and combining the second material classification result and the third material classification result to obtain the recognition result of the microstructure of the target woven composite material. The method and device provided by the present application are used to accurately and efficiently identify the microstructure of woven composite materials.
Owner:JINCHENG NANJING ELECTROMECHANICAL HYDRAULIC PRESSURE ENG RES CENT AVIATION IND OF CHINA

A dual latent variable decoupling data analysis method based on plasma netrin-1 and scale features

PendingCN122291062AImprove legibilityFine characterizationAlgorithmStatistical analysis
This invention relates to the fields of medical data analysis and artificial intelligence, proposing a dual-latent variable decoupled data analysis method based on plasma Netrin-1 and clinical scale features. First, plasma Netrin-1 test data and clinical characteristics such as UPDRS scale scores and disease duration are acquired from the subjects. Batch effect correction is applied to the raw test values, and an input feature vector is constructed. Then, a variational autoencoder model is established. By setting orthogonal constraints, Netrin-1 regression constraints, and disease duration regression constraints, the latent space is structurally constrained, enabling the model to learn latent variables D representing disease progression and C representing adaptive changes during training. Based on this, an efficiency index η composed of latent variables C and D is calculated, and relevant trend indicator parameters are obtained by combining longitudinal follow-up data. This method can achieve decoupled representation of disease-related features and adaptive change features in multi-source clinical data, providing a new data analysis tool for statistical analysis and research of neurodegenerative disease-related data.
Owner:WUXI NO 2 PEOPLES HOSPITAL

System and method for assisting map making through middle table function

The invention belongs to the field of map making, and particularly relates to a system and method for assisting map making through a middle table function, and the system comprises a management middle table, a resource service node and a map making terminal. The management middle platform automatically collects metadata of map resources in a database mode and allows a manager to modify and edit the metadata, and the metadata of the map resources comprises time, technical collection information, user data and storage positions; the resource service nodes provide map services and are built into a plurality of nodes by adopting a distributed deployment method, and resource management modes of the resource service nodes are different according to map service requirements and are file management or database management; in the process of assisting map making, the whole system effectively improves the efficiency and quality of map making through cooperation and function improvement of all the modules, so that map making and management become more convenient and reliable.
Owner:NORTHEAST INST OF GEOGRAPHY & AGRIECOLOGY C A S +1

A device and method for detecting biochemical substances based on optical fiber composite liquid crystal

ActiveCN114047140BReliable and reliableGuaranteed recognition effectColor/spectral properties measurements
The invention discloses a device and method for detecting biochemical substances based on optical fiber composite liquid crystal, the device includes a reaction pool, a detection reagent input end, a waste liquid collection end, an optical signal transmitting end and an optical signal receiving and processing end; a glass chip is placed on the inner bottom surface of the reaction pool, and liquid crystal is placed on the surface of the glass chip; the top surface of the reaction pool has an optical signal input port and an optical signal output port; the detection reagent input end is connected to the reaction pool and is used to inject a reagent that reacts with the liquid crystal into the reaction pool; the waste liquid collection end is connected to the reaction pool and is used to discharge the reagent waste liquid after the reaction; the optical signal transmitting end is connected to the optical signal input port; the optical signal receiving and processing end is connected to the optical signal output port. The test reagent reacts with the liquid crystal, a light source is introduced through the optical fiber to irradiate the reaction liquid, and the optical signal reflected after the irradiation is received by a spectrometer, and then the signal output by the spectrometer is calculated by algorithm, thereby realizing the detection of the reagent.
Owner:INTELLIGENT BIOTECHNOLOGY (SHANDONG) CO LTD

Dialogue intention information determination method and device, equipment and storage medium

The invention discloses a dialogue intention information determination method and device, equipment and a storage medium. The method comprises the following steps: acquiring target speaking information of a target user in a communication dialogue; and performing complexity analysis processing according to the target speaking information, and determining a comprehensive complexity value corresponding to the target speaking information. And screening and determining a target reasoning module for intention analysis from a pre-constructed reasoning module set according to a pre-constructed complexity level threshold value and the comprehensive complexity value. And performing intention recognition processing on the target speaking information according to the target reasoning module, and determining dialogue intention information of the target user. According to the technical scheme, different resources are called according to the complexity of the user dialogue information, so that stable recognition of the intention category and intention intensity of the user is achieved, and the computing power and the cost are controlled while the recognition effect is guaranteed.
Owner:YI REN HENG YE TECH DEV (BEIJING) CO LTD

Sample screening method and device based on generalization optimization algorithm

PendingCN121935607Aeasy to identifyGuaranteed recognition effectBiological modelsData setAlgorithm
The invention discloses a sample screening method and device based on a generalization optimization algorithm, and the method comprises the steps: collecting to-be-screened target data, and constructing a to-be-screened data set; inputting the to-be-screened data set into a pre-trained intelligent recognition model to obtain sample categories output by the intelligent recognition model and the statistical number of the sample categories; wherein the intelligent identification model is obtained by training a machine learning network by using a training data set, the training data set is constructed after marking screened training data, and the training data is obtained by screening collected original data in batches through a high-value sample selection system. According to the method, the optimal recognition effect of the model can be achieved with the minimum labeling workload, the samples with the highest information value are scientifically selected for labeling, redundant samples in a data set are effectively removed, and the time needed by expert labeling is greatly shortened.
Owner:BEIJING XIAOYING TECH CO LTD

A method and system for identifying liver cancer blood supply arteries in DSA angiography images

The present invention relates to the field of medical image recognition technology, and in particular to a method and system for identifying liver cancer blood supply arteries in DSA angiography images, comprising the following steps: dividing the clarity of the vascular contours of the tumor tissue blood supply arteries according to the edge detection algorithm of each target image, and obtaining a clear target image and a fuzzy target image; using a cycle consistency generative adversarial network cycleGan to convert the fuzzy target image into a clear target image according to the clear target image; and marking the vascular contours of the tumor tissue blood supply arteries in the liver tissue model in all clear target images by the edge detection algorithm. The present invention enables all images obtained by a single angiography to present high definition, and thus can identify all blood supply arteries, achieve low radiation dose of angiography rays, and at the same time ensure the recognition effect of the blood supply arteries.
Owner:XIEHE HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI & TECH UNIV

Attendance checking and access control all-in-one machine intelligently recognized through AI software

The utility model discloses an attendance and access control all-in-one machine intelligently identified through AI software, which comprises a main control module, an access control lock and a power supply module, the main control module is connected with a data storage module, a sensor module, an expansion module and a conversion module, and the expansion module is connected with a data transmission module; the access control lock is in communication connection with the main control module through the data transmission module, and the main control module controls opening and closing of the access control lock; and the power supply module is used for supplying power to the main control module and the access control lock. According to the utility model, through an AI software intelligent identification technology, efficient and safe access control and attendance management are realized, through the face identification module, the accuracy and the stability are higher, the phenomenon of card punching by others can be effectively avoided, and the authenticity of attendance data is improved.
Owner:CND ELECTRONICS TECH SHENZHEN

Electric energy meter and electric energy meter box

The invention provides an electric energy meter and an electric energy meter box, and relates to the technical field of electric instruments, and the electric energy meter comprises an instrument body which is provided with a card insertion port and a dust discharge port; the conduction assembly is installed on the instrument body and connected with the card insertion opening so as to conduct the electricity purchase card inserted into the card insertion opening towards the inner side of the instrument body; a reading port is formed in one side of the isolation assembly, and the isolation assembly is installed in the instrument body so as to isolate the electricity purchase card when the electricity purchase card is input to the isolation assembly, perform self-cleaning when the electricity purchase card exits from the isolation assembly, and discharge cleaned dust from the dust discharge port; and the card reader assembly is installed in the instrument body and is movably arranged in the reading port so as to carry out mobile identification card reading on the electricity purchasing card inserted into the isolation assembly. According to the electric energy meter and the electric energy meter box provided by the invention, the electricity purchasing and recharging efficiency of the electricity purchasing card on the electric energy meter can be improved, the cleanliness in the charging port can be ensured, and the recharging operation is easy.
Owner:CSG SMART SCI&TECH CO LTD +1

Area-array camera five-face code reading device

InactiveCN222014765UGuaranteed recognition effectSensing by electromagnetic radiationElectric machineryWorkbench
The utility model discloses an area-array camera five-surface code reading device, which relates to the technical field of code scanning devices and comprises a workbench, a positioning camera mounted on the workbench, a fixing plate arranged on one side of the positioning camera, a code scanning assembly mounted on the fixing plate and used for five-surface code reading, a control assembly, a controller mounted on the workbench and a control motor. The express box code scanning device is reasonable in design structure, an express box entering the position below the code scanning assembly is photographed through the positioning camera, the angle of the express box relative to the conveying belt can be calculated, an output rotating shaft of the control motor is made to rotate through the controller, and under the action of the rotating rod, the express box is automatically scanned. The fixing plate drives the code scanning assembly to carry out relative adjustment according to the angle of the express box on the conveying belt, it is guaranteed that the five faces of the code scanning assembly are parallel to the five faces of the express box, the recognition effect of the code scanning assembly on the two-dimensional code on the express box is guaranteed, and the scanning missing phenomenon of the code scanning assembly is effectively reduced.
Owner:BEIJING GUOTAI LANDUN TECH CO LTD

Wind power plant unmanned aerial vehicle inspection data fault identification system based on artificial intelligence

The invention relates to the technical field of fault identification, and provides a wind power plant unmanned aerial vehicle inspection data fault identification system based on artificial intelligence, which comprises an unmanned aerial vehicle, a server, a data acquisition module, an interaction module, an analysis module, a decision module and an inspection control module, the data acquisition module acquires appearance image data of a wind driven generator in a wind power plant, the interaction module interactively transmits the appearance image data acquired by the data acquisition module and ground data receiving equipment, and the inspection control module acquires the position of the wind driven generator and real-time position data of an unmanned aerial vehicle. The data acquisition module acquires the position of the wind driven generator, evaluates the inspection route of the unmanned aerial vehicle according to the position of the wind driven generator and the real-time position data of the unmanned aerial vehicle, adjusts the acquisition posture of the data acquisition module according to the evaluation result, and analyzes the wind driven generator according to the appearance image data acquired by the data acquisition module to form an analysis result. And the decision module evaluates the state decision of the wind driven generator according to the analysis result.
Owner:CGN YUXI HUANING WIND POWER CO LTD

Robot automatic fiber placement defect online detection method and system based on 3D vision

PendingCN122084646Aquality improvementImprove image signal-to-noise ratioImage analysisBiological modelsPoint cloudRobotic arm
This invention provides a method and system for online automatic wire layup defect detection using a robot based on 3D vision. The method includes: constructing and calibrating a 3D vision imaging system based on a Sham lens and a line laser; synchronously moving with a wire layup robotic arm to acquire two-dimensional images of the layup and reconstruct three-dimensional point cloud data; fusing and analyzing the two-dimensional images and three-dimensional point cloud data; using a lightweight deep learning network to perform real-time defect detection on the two-dimensional images; simultaneously locating and segmenting defect regions based on point cloud normal vectors and curvature information; fusing two-dimensional texture features and three-dimensional geometric features through a collaborative representation model to achieve accurate defect identification and location; transforming the defect information in a unified coordinate system; and controlling multiple laser projection devices to project onto the layup surface in real-time using a segmented relay method. This invention achieves high-quality imaging under low reflectivity, large depth of field, and short-range conditions by fusing Sham lens imaging and line laser scanning; achieves a recognition rate of over 95% in high-speed wire layup by combining dual-modal fusion and lightweight few-sample learning; and utilizes multi-device collaborative calibration and relay projection to achieve real-time defect feedback.
Owner:XINTUO 3D TECH (XIAN) CO LTD +1

Method and system for identifying sustainable Internet of Things equipment based on traffic time sequence characteristics

The invention relates to a sustainable Internet of Things equipment identification method and system based on traffic time sequence characteristics, and the method comprises the steps: capturing traffic data packets of Internet of Things equipment according to a set time interval, and carrying out the feature extraction of each traffic data packet, and obtaining a time sequence characteristic construction data set; constructing an Internet of Things equipment identification model, and training by using the data set to obtain an Internet of Things equipment identification deployment model; obtaining the time sequence characteristics of the newly-added Internet of Things equipment to obtain a newly-added data sample and a new data set; performing continuous comparative learning based on the new data set by using parameters of the deployment model to obtain an updated deployment model; inputting the to-be-identified Internet of Things equipment into the updated deployment model, and outputting to obtain an identification result; the efficient and accurate identification of the Internet of Things equipment is realized by using the time sequence characteristics of the traffic, the sustainable identification of the Internet of Things equipment is realized by using the continuous comparison learning framework, the types of the newly added equipment are accurately classified, and the identification accuracy of the known equipment is kept.
Owner:HUAZHONG UNIV OF SCI & TECH

A single scale field calibration method

The present application discloses a single-scale on-site calibration method, which belongs to the field of camera calibration technology, including: using a straight-line scale and using a binocular camera to obtain a calibration image; relative orientation of each camera and obtaining the initial values ​​of the camera's internal and external parameters: by relative orientation, determining the relative position and posture relationship between each camera in the binocular camera, establishing a local coordinate system with the reference camera as a reference, and using the coplanar condition between the cameras to obtain the initial values ​​of the camera's internal and external parameters; absolute orientation of each camera and solving the external parameters of the calibration image obtained by each camera: by absolute orientation, determining the position and posture of the binocular camera in the world coordinate system, obtaining the world coordinates of all calibration points of the calibration image, solving the external parameter values ​​of each calibration image relative to the world coordinate system; and optimizing and adjusting the camera parameters. The present invention solves the problem of difficulty in on-site calibration of large fields of view, including some ultra-large fields of view.
Owner:XINTUO 3D TECH (XIAN) CO LTD

Sensitive information identification method and device, electronic equipment and storage medium

The present disclosure provides a sensitive information identification method and device, electronic equipment and storage medium, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and information security. A specific implementation scheme is: obtaining entity information of a target webpage text; using a preset sensitive information identification model to identify and process the entity information to obtain an identification result of the entity information, the preset sensitive information identification model is obtained by performing knowledge distillation processing on a pre-training model, the pre-training model includes a pre-training network, a first text feature extraction network and a first classifier, and the preset sensitive information identification model includes a second text feature extraction network and a second classifier; and obtaining a sensitive information identification result of the target webpage text according to the identification result of the entity information.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD