Patents
Literature
57results about How to "Good initial value" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Clustering and deep belief network-based leakage initial locating method
ActiveCN108647470ASolve problems that are easy to converge to a local optimumGood initial valueGeneral water supply conservationPipeline systemsDeep belief networkOperability
The invention discloses a clustering and deep belief network-based leakage initial locating method. The method comprises the steps of firstly performing calculation to obtain a pipe network monitoringpoint sensitivity coefficient matrix; secondly dividing a pipe network into multiple leakage regions based on K-means clustering, and generating a leakage sample by utilizing hydraulic simulation software; thirdly building and training a deep belief network-based leakage region identification model; and finally identifying the leakage regions according to actually measured pressure data. The method solves the problem of leakage sample scarcity during modeling, realizes quick locating of the leakage regions in an initial leakage stage, and has relatively high identification precision and relatively strong operability.
Owner:HANGZHOU DIANZI UNIV
Method and system for predicting load of power distribution network
InactiveCN107730039AOvercoming slow trainingImprove modeling capabilitiesForecastingCharacter and pattern recognitionMachine learningSmart grid
The present invention relates to a method and a system for predicting the load of a power distribution network. The method comprises the steps of obtaining a unsupervised training sample set, a supervised training sample set and a test sample set according to the time information and on the basis of the historical load influence factor of the power distribution network and the historical load value of a to-be-predicted area; according to the unsupervised training sample set, subjecting a DBN model layer in a pre-established load prediction model to unsupervised training layer by layer, wherein the load prediction model includes a DBN model layer and a linear neural network layer; adopting network parameters obtained through during the unsupervised training step as the network parameter initial values of the load prediction model; according to the supervised training sample set, subjecting the load prediction model to supervised training, and obtaining an optimal load prediction model; testing the test sample set by using the optimal load prediction model so as to obtain a load prediction value of the to-be-predicted area. The present invention can realize the high-precision loadprediction of the intelligent power grid environment under the influence of various factors.
Owner:POWER GRID TECH RES CENT CHINA SOUTHERN POWER GRID +2
A moving object detection method based on coarse-to-fine image segmentation
InactiveCN109087330AReduce dimensionalityThe detection process is fastImage analysisCharacter and pattern recognitionMotion cuesSimilarity measure
A moving object detection method based on coarse-to-fine image segmentation comprises the following steps: n frame detection images are acquired; feature points are extracted from the first frame image, and the feature points are extracted from the next n-1 frame image to generate motion cues, and a classification of the feature points in the n-th frame image is determined by performing motion segmentation on the motion cues; superpixel segmentation is performed on the n-th frame image to reduce the dimension of the n-th frame image; according to the classification of the mark points in the n-th frame image, the superpixels are marked, and the superpixels are clustered by the similarity measure method, and the rough segmentation of the image is completed on the basis of clustering. The coarse segmentation image is constructed into a quaternary image, and then the quaternary image is fine segmented, so as to realize the accurate detection of the moving object. Through the segmentation from the coarse to the fine, the invention not only has high accuracy rate to the detection of the moving object in the image, but also has faster detection speed, and is more suitable for the detection of the fast moving object.
Owner:NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI
Double-filter fusion positioning system for park automatic driving
ActiveCN112083726AImprove reliabilityImprove accuracyPosition/course control in two dimensionsSimulationOdometer
The invention discloses a double-filter fusion positioning method and system for park automatic driving, and aims to design the double-filter fusion positioning method and system for park automatic driving, so that by fusing a vehicle kinematics model and IMU integration through an extended Kalman filtering technology, a predicted pose of a vehicle is obtained. A particle filtering technology is used to fuse a vehicle prediction pose and a laser odometer so as to improve positioning precision and robustness of an automatic driving vehicle in a park environment.
Owner:HUNAN UNIV
Online identification method for pneumatic parameters of vertical take-off and landing vehicle
ActiveCN110276144AGood initial valueImprove real-time performanceGeometric CADAerodynamic testingEngineeringVertical take off and landing
The invention discloses an online identification method for pneumatic parameters of a vertical take-off and landing vehicle. According to the method, on the basis of wind tunnel data, the pneumatic parameters under different flight conditions are identified by using a maximum likelihood method, and then the relationship between the flight conditions of the vehicle and the pneumatic parameters is established by training a neural network so as to adapt to the condition that the pneumatic parameters of the vehicle change along with the flight conditions. Pneumatic parameter identification is performed based on the wind tunnel data and the maximum likelihood method, and the pneumatic parameters obtained by the wind tunnel data pneumatic interpolation table can provide good initial values for parameter identification by the maximum likelihood method; the trained neural network can be used for pneumatic parameter on-line identification, is good in real-time performance, and has good engineering practicability. The method solves the problems that a group of pneumatic parameters correspond to various flight conditions in offline identification of the pneumatic parameters of the vertical take-off and landing vehicle and are not consistent with reality, and the online identification real-time performance of the pneumatic parameters of the vehicle is poor, and can be used for online pneumatic parameter identification.
Owner:哈尔滨逐宇航天科技有限责任公司
Grid map positioning method fusing NDT and ICP
PendingCN112612029AHigh precisionReduced execution timeNavigation instrumentsGeographical information databasesMobile robotEngineering
The invention discloses a grid map positioning method fusing NDT and ICP, and the method comprises the following steps: S1, obtaining the initial pose of a laser radar through employing an NDT algorithm for a last frame of laser point cloud and a current laser frame of point cloud; and S2, matching the point cloud of the current laser frame with the laser point cloud of the previous frame based on the initial pose, and obtaining the current pose of the laser radar. The repositioning problem of the mobile robot after abnormal conditions such as'binding 'or restarting and the like occurs is solved, and accurate positioning is realized only through a laser sensor.
Owner:哈尔滨工业大学芜湖机器人产业技术研究院
Breast nodule detection method and system based on ultrasonic medicine
ActiveCN112086197ASame sizeData augmentationMedical simulationImage enhancementMalignant Breast TumorRadiology
The invention discloses a breast nodule detection method and system based on ultrasonic medicine. The method comprises the steps of obtaining breast ultrasonic video data, carrying out the preprocessing, carrying out training on the preprocessed data through a transfer learning method, building a breast nodule detection model, inputting to-be-tested video data into the breast nodule detection model, and obtaining a result. The breast nodule detection method and system based on ultrasonic medicine aim to establish a precise method for judging benign and malignant breast tumors and carrying outpathological typing by taking ultrasonic breast video image examination as a main means, and solve the difficult clinical problem that dynamic identification and identification of breast tumors are difficult. The establishment of the highly accurate breast tumor qualitative system is of great clinical significance to the diagnosis and treatment of breast tumor patients.
Owner:厦门大学附属翔安医院
Low-overlapping-rate three-dimensional point cloud registration method
ActiveCN112150523ANarrow searchGood initial valueImage enhancementImage analysisMachine visionPoint cloud
The invention discloses a low-overlapping-rate three-dimensional point cloud registration method, and belongs to the technical field of machine vision. The method aims at solving the problems of highregistration difficulty, low precision and the like of two point clouds with low overlapping rate. The method comprises the following steps: firstly, establishing a multi-scale descriptor by utilizingcurvature characteristics of point cloud to ensure that point cloud data is complete and redundant data is minimum; secondly, performing corresponding relation clustering partitioning by utilizing the angle difference of the multi-scale descriptors to obtain an overlapping region of the source point cloud and the target point cloud; and finally, substituting the point clouds of the overlapping region and the corresponding relationship of the point clouds into a convex optimization problem, removing outliers and optimizing the corresponding relationship, realizing coarse registration, and refining by utilizing an ICP algorithm. According to the invention, the useful search range of point cloud registration can be reduced, the registration calculation amount is reduced, and more advantageous registration precision and time efficiency are provided for point cloud data with a low initial overlapping degree. The method can be widely applied to the fields of three-dimensional model reconstruction, cultural heritage management, robot navigation and positioning and the like.
Owner:ZHONGBEI UNIV
Three-phase asynchronous motor parameter off-line acquisition method and system
ActiveCN106842018ALeakage inductance intelligent identificationSecure bootElectronic commutation motor controlVector control systemsElectric machineControl engineering
The invention provides a three-phase asynchronous motor parameter off-line acquisition method and system. The method includes the steps: driving an inverter by a controller to apply excitation voltage to any two phases of a three-phase asynchronous motor at different time periods, and acquiring response current generated by the three-phase asynchronous motor according to the excitation voltage at different time periods; acquiring the leakage inductance of the three-phase asynchronous motor according to the excitation voltage, the response current and a first equivalent circuit, and acquiring a first time constant of the three-phase asynchronous motor according to the response current and a second equivalent circuit. According to the technical scheme, parameters of the motor can be statically recognized under the condition of finishing installation of the motor, good initial values are provided for an online identification algorithm, safe and reliable starting of the three-phase asynchronous motor is further ensured, and convergence of the online identification algorithm is accelerated.
Owner:CRRC DALIAN R & D CO LTD
Image processing method and device, and AR equipment
ActiveCN108510520AIncrease success rateGood initial valueImage enhancementImage analysisImaging processingError function
The embodiment of the invention provides an image processing method and device, and AR equipment; the method comprises the following steps: determining continuous a first frame image and a second frame image in a continuous video frame image sequence, wherein the second frame image is the present frame image, and the first frame image is the image in front of the second frame image; using a targetarea of the first frame image as a template to determine the position information of the target area in the second frame image; using the position information as an iteration initial value so as to carry out iteration processing for the first and second frame images in whole graph alignment, wherein the iteration processing for the first and second frame images in whole graph alignment uses a robustness error function for iteration. The image processing method and device, and the AR equipment can improve the tracking success rate of the whole system.
Owner:SHICHEN INFORMATION TECH SHANGHAI CO LTD
Active power reduction calculation method for suppressing photovoltaic access point voltage limit exceeding
ActiveCN106972552AThe calculation formula is simpleSmall amount of calculationSingle network parallel feeding arrangementsPhotovoltaic energy generationCommunications systemLow voltage
The invention discloses an active power reduction calculation method for suppressing photovoltaic access point voltage limit exceeding. Firstly, the voltage of a photovoltaic power station access point and the voltage of a main transformer low-voltage bus are monitored in real time, and when the voltage of the access point exceeds an upper limit and a photovoltaic active power reduction condition is met, the active power reduction is calculated, and photovoltaic output is adjusted according to a calculation result. The invention provides a distributed photovoltaic active power reduction calculation method for eliminating access point voltage upper limit exceeding caused by distributed photovoltaics, the calculation formula is simple, the calculation amount is small, massive data transmission of the communication system is not needed, the real-time applicability is high, a strong theoretical basis and a control method are provided for suppressing voltage upper limit exceeding of the access point caused by the distributed photovoltaic access, and the method is applicable to a voltage control condition for the voltage upper limit exceeding caused after distributed photovoltaic access.
Owner:SHANDONG UNIV OF TECH
Binocular semantic SLAM method for automatic driving scene
PendingCN112101160AHigh precisionImprove robustnessCharacter and pattern recognitionNeural architecturesPattern recognitionComputer graphics (images)
The invention discloses a binocular semantic SLAM method for an automatic driving scene, and the method can detect and track other vehicles, pedestrians and other objects in a scene while enabling a vehicle to accurately track the pose of the vehicle in the environment in an automatic driving scene. According to the method, the quadric surface is used as the expression of a three-dimensional object, and compared with the prior art that the quadric surface can only be used for mapping or for a road sign for a static object, the quadric surface can be used for expressing the states of objects atdifferent moments no matter for the static object in a scene or a moving object. For the situation that semantic object observation is insufficient, the neural network and priori information are fully utilized for constraint, an error term for object observation is constructed, and nonlinear optimization solving of object state parameters is achieved.
Owner:ZHEJIANG UNIV
Multi-path channel estimation method based on all-pole model
InactiveCN101471905AGood initial valueAvoid the defect of inaccurate signal receptionBaseband system detailsAnti jammingMultipath channels
The invention relates to a multipath channel estimation method based on an all-pole model, which comprises the following steps: converting an impulse response of a multipath channel from time domain to frequency domain to obtain a frequency domain response of the multipath channel; expressing the frequency domain response with an all-pole model to obtain an all-pole expression of the multipath channel model; recurring the all-pole model with the corresponding sending end data and receiving end data to obtain model parameters, and constructing an all-pole model with the model parameters; searching poles in the constructed all-pole model to obtain an initial estimated value of a multipath channel time-lag from the searched poles; and determining the impulse response of the multipath channel model according to the path number of the multipath channel and the initial estimated value of the multipath channel time-lag, and obtaining a multipath channel model. The method roughly estimates the multipath channel time-lag, which can prevent the multipath channel parameters trapping in local optimum in the subsequent refining, so as to reduce the complexity of the available multipath channel model estimation and improve the robustness, the anti-jamming property and accuracy.
Owner:TSINGHUA UNIV
Complex pipe network leakage positioning method based on deep belief network
PendingCN112862063AImprove diagnostic efficiencyImprove forecast accuracyNeural architecturesNeural learning methodsDeep belief networkMonitoring site
The invention relates to the technical field of complex pipe network leakage positioning, in particular to a complex pipe network leakage positioning method based on a deep belief network, and the method is implemented according to the following steps: 1, obtaining a training sample and a test sample comprising a monitoring point pressure value and a leakage position coordinate; 2, constructing a complex pipe network leakage positioning model based on a deep belief network; 3, pre-training the complex pipe network leakage positioning model by adopting a layer-by-layer unsupervised learning algorithm according to the test sample; 4, performing parameter optimization on the pre-trained complex pipe network leakage positioning model by adopting a BP algorithm; step 5, performing leakage positioning on the test sample in the step 1 by using the complex pipe network leakage positioning model obtained in the step 4, and outputting a positioning result; and calculating the diagnosis accuracy of the model. According to the method, monitoring of the whole pipe network can be completed only by establishing the complex pipe network leakage database training network, and the diagnosis efficiency of pipe network leakage is greatly improved.
Owner:珠海横琴能源发展有限公司
Robot repositioning method, device and equipment and storage medium
The invention discloses a robot repositioning method, device and equipment, and a storage medium. The method comprises the steps of obtaining an image key frame captured by a photographing device of a robot, wherein the image key frame comprises a 2D image; performing image matching on the 2D image and a map key frame pre-stored by a robot to obtain an estimated pose; performing point cloud transformation on the image key frame to obtain a first 3D point cloud, and obtaining a second 3D point cloud of the map key frame, wherein one 3D feature point of the first 3D point cloud and the corresponding 3D feature point of the second 3D point cloud serve as a matching point pair, and each pair of matching points corresponds to the same point in a real scene; calculating a distance error between each pair of matching points, and determining a total distance error according to the distance errors; obtaining a repositioning pose according to the total distance error and the estimated pose; carrying out relocation by combining the 2D image and the depth image, effectively correcting the wrong 2D relocation pose, and improving the relocation precision.
Owner:KEYIZHAN INTELLIGENT EQUIP CO LTD +1
A method and system for determining probabilistic power flow based on power system
ActiveCN109376494AHigh precisionAccurate outputDesign optimisation/simulationResourcesNormal densityPower flow
The invention discloses a probabilistic power flow determination method and a system based on a power system. The method comprises the following steps of: acquiring power data of a plurality of wind turbines; A Gaussian mixture model of input variables of power system is constructed according to the power data of all wind turbines. Genetic algorithm is used to solve the parameters of Gaussian mixture model. The parameters include the weight coefficient of each Gaussian sub-component, the mean value of each Gaussian sub-component and the variance of each Gaussian sub-component. Gaussian MixtureModel with Input Variables Determined by Parameters; Obtaining the linear equation model of tidal current equation; According to the Gaussian mixture model of input variables and the linear equationmodel of power flow equation, the joint probability density function of output variables of power system is obtained to determine the probabilistic power flow of power system. The invention can greatly reduce the fitting error, has good fitting effect on the output of the fan, thereby improving the analysis precision of the probability tidal current, more accurate analysis on the stability of theline, and the whole process is simple and the calculation speed is fast.
Owner:NORTH CHINA ELECTRIC POWER UNIV (BAODING)
Multi-viewpoint cloud global optimization registration method based on hierarchical closed loop constraint
ActiveCN112561975AReduced average distance errorVerify validityImage enhancementImage analysisPoint cloudGeometric consistency
The invention discloses a multi-view cloud global optimization registration method based on hierarchical closed loop constraint, and belongs to the crossing field of computer vision and laser scanningdata processing. The method comprises the steps: aiming at the spatial difference of neighborhood information of registration primitives generated by different scanning view angles of a hand, performing connectivity analysis on point clouds according to the feature consistency and geometric consistency of the registration primitives, constructing a connected graph for multi-view clouds, and unifying similarity transformation between paired point clouds to a reference coordinate system; and obtaining a global optimization fine registration result through error analysis and correction of leastsquare joint adjustment based on hierarchical closed loop constraints.
Owner:WUHAN UNIV
Method for improving expansibility of deep neural network power flow model
ActiveCN110829434AImprove training efficiencyVerify validityNeural architecturesNeural learning methodsFeature vectorAlgorithm
The invention discloses a method for improving the expansibility of a deep neural network power flow model, which mainly comprises the following steps: (1) acquiring basic data of a power system; (2)determining a feature vector; (3) establishing an original DNN power flow model; (4) training the original DNN power flow model to obtain a trained original DNN power flow model; (5) expanding the original DNN power flow model to obtain an expanded DNN power flow model; and (6) calculating the probabilistic power flow of the expanded system to obtain a probabilistic power flow result. The method can be widely applied to the calculation of the probabilistic power flow of the power system, and is particularly suitable for the situation in which the DNN of the original system is not suitable forbeing used due to the expansion of the system.
Owner:CHONGQING UNIV +2
A dual-filter fusion positioning system for park autonomous driving
ActiveCN112083726BImprove reliabilityImprove accuracyPosition/course control in two dimensionsLocalization systemPositioning system
The invention discloses a dual-filter fusion positioning method and system for automatic driving in parks, and its purpose is to design a dual-filter fusion positioning method and system for automatic driving in parks, and integrate vehicle motion by extending Kalman filter technology Learning model and IMU integration to obtain vehicle predicted pose. The particle filter technology is used to integrate the predicted pose of the vehicle and the laser odometer, in order to improve the positioning accuracy and robustness of the autonomous driving vehicle in the park environment.
Owner:HUNAN UNIV
Nonlinear equation system solving method and device based on chemical equilibrium model
ActiveCN111539117AImprove the efficiency of searching for multiple solutionsGood initial valueDesign optimisation/simulationComplex mathematical operationsComputational physicsStatistical physics
The invention relates to the technical field of chemical equilibrium, in particular to a nonlinear equation system solving method and device based on a chemical equilibrium model. The method comprisesthe following steps: generating a global search solution according to to-be-optimized parameters, and enabling ng global search solutions to form a global search set Q; if the fitness value reductionamount of the global search solution in recent k iterations is smaller than a threshold beta, calling an SQP algorithm to perform local fine adjustment, otherwise, generating nl local search solutions; when the fitness value of the local search solution is smaller than that of the corresponding global search solution, setting the local search solution as a new global search solution; generating aglobal search solution in the whole solution space; according to the fitness value, screening out ng global search solutions from the newly generated global search solutions and Q, updating Q, and storing the global search solutions with the fitness value not greater than a threshold mu to S; when the fitness evaluation frequency is greater than mf, outputting S; otherwise, returning to the localsearch step to continue iteration. According to the method, the efficiency of searching multiple solutions is improved, and the distribution characteristics of the solutions are described.
Owner:NANYANG NORMAL UNIV
A 3D Point Cloud Registration Method with Low Overlap Rate
ActiveCN112150523BNarrow searchGood initial valueImage enhancementImage analysisComputational scienceMachine vision
The invention discloses a three-dimensional point cloud registration method with a low overlap rate, and belongs to the technical field of machine vision. Aiming at the problems of difficulty and low precision in the registration of two point clouds with low overlap rate. First, use the curvature feature of the point cloud to establish a multi-scale descriptor to ensure the integrity of the point cloud data and minimize redundant data; secondly, use the angle difference of the multi-scale descriptor to cluster and block the corresponding relationship to obtain the source point cloud The overlapping area with the target point cloud; finally, the point cloud in the overlapping area and their corresponding relationship are substituted into the convex optimization problem, and the outliers are removed and the corresponding relationship is optimized, and the coarse registration is realized and the ICP algorithm is used for refinement. The invention can narrow the useful search range of point cloud registration, reduce the amount of registration calculation, and provide more advantageous registration accuracy and time efficiency for point cloud data with a low initial overlapping degree. The method can be widely used in three-dimensional model reconstruction, cultural heritage management, robot navigation and positioning and other fields.
Owner:ZHONGBEI UNIV
An image processing method, device and AR equipment
ActiveCN108510520BIncrease success rateGood initial valueImage enhancementImage analysisImaging processingError function
Embodiments of the present invention provide an image processing method and device, and an AR apparatus. The method comprises: determining consecutive first and second images in a continuous video frame image sequence, wherein the second image is a current image, and the first image is a previous image of the second image; determining, by using a target region of the first image as a template, location information of the target region in the second image; and performing, by using the location information as an iterative initial value, iterative processing of an entire image alignment on the first image and the second image, wherein the iterative processing of the entire image alignment of the first image and the second image is iterated by using a robust error function. The image processing method and device and the AR apparatus disclosed in the embodiments of the present invention improve success rates in tracking of an entire system.
Owner:SHICHEN INFORMATION TECH SHANGHAI CO LTD
Seismic super-resolution inversion method based on model-driven deep learning
ActiveCN112083482BRealize seismic super-resolution inversionSeismic super-resolution inversion avoidsSeismic signal processingAlgorithmNetwork structure
The invention discloses a seismic super-resolution inversion method based on model-driven deep learning, comprising the following steps: 1) mapping each iteration in the model-driven alternating direction multiplier method ADMM to each layer in the deep network, And use the mathematics-driven method to learn the proximal mapping, complete the construction of the deep network ADMM-SRINet; 2) obtain the label data used to train the deep network ADMM-SRINet; 3) use the obtained label data to perform Training; 4) Inverting the data to be tested using the deep network ADMM-SRINet trained in step 3). This method combines the advantages of the model-driven optimization method and the data-driven deep learning method to make the network structure interpretable; at the same time, due to the increase of physical knowledge, the iterative deep learning method alleviates the requirements for the training set, making The inversion results are more credible.
Owner:XI AN JIAOTONG UNIV
Image restoration method and computer-readable storage medium
ActiveCN114418902BGood initial valueImprove accuracyImage enhancementImage analysisPattern recognitionImaging processing
An image repairing method and a computer-readable storage medium, wherein an image to be repaired is reduced and filtered according to adaptive reduction parameters and filtering parameters, a filtered image to be repaired is obtained, and pixel points to be filled in the filtered image to be repaired are obtained , and obtain a better initial value of the pixel to be filled, based on the constraints that minimize the sum of the divergences of the gradient values of all the pixels to be filled and the initial value of the pixel to be filled, the value of the pixel to be filled is calculated. In the first iterative process, the coarse processing value of the pixel to be filled is obtained, and the coarse processing value of the pixel to be filled is re-used as the initial value of the pixel to be filled. According to the energy equation and the initial value of the pixel to be filled, the pixel to be filled is The second iterative process is performed on the value of the pixel to be filled to obtain the fine-processing value of the pixel to be filled, the fine-processing value of the pixel to be filled is taken as the target value of the pixel to be filled, and the restored image is obtained by up-sampling, which improves the efficiency of image processing. .
Owner:SHENZHEN HUAHAN WEIYE TECH
A method to improve the scalability of deep neural network power flow models
ActiveCN110829434BImprove training efficiencyVerify validityNeural architecturesNeural learning methodsFeature vectorPower flow
Owner:CHONGQING UNIV +2
Setting method for the semi-automatic production of a process-capable basic setting for an injection molding machine
Owner:KEBA AG
Robust sound source positioning system and method
ActiveCN111308423AImprove universalityGood initial valuePosition fixationAcoustic source localizationSelf adaptive
The invention discloses a robust sound source positioning system and method. The method comprises the following steps: step 1, establishing a time difference equation set; 2, estimating a time difference tauij; 3, implementing a sound velocity processing mode; 4, solving an equation by a regularization Newton method; 5, setting an initial solution; and 6, carrying out weight initialization and self-adaptive updating. In combination with other structures or methods, the defects that in the prior art, errors can be caused by a time difference positioning method under sound source positioning, and large positioning errors can be generated under the environment that a microphone has large noise are effectively overcome.
Owner:ARMY ENG UNIV OF PLA
Multi-view point cloud global optimal registration method based on hierarchical closed-loop constraints
ActiveCN112561975BReduced average distance errorVerify validityImage enhancementImage analysisPoint cloudGeometric consistency
The invention discloses a multi-view point cloud global optimization registration method based on hierarchical closed-loop constraints, which belongs to the intersection field of computer vision and laser scanning data processing. The present invention aims at the spatial difference of the registration primitive neighborhood information generated by different scanning angles of the hand, and analyzes the connectivity of the point cloud according to the feature consistency and geometric consistency of the registration primitive, constructs a connectivity graph for the multi-viewpoint cloud, and converts the The similarity transformation between point clouds is unified to the reference coordinate system. Based on the hierarchical closed-loop constraints, through the error analysis and correction of the least squares joint adjustment, the global optimal fine registration result is obtained.
Owner:WUHAN UNIV
Face relative posture estimation method combined with face key point detection
ActiveCN112580496AHigh precisionGood initial valueImage enhancementImage analysisPattern recognitionData set
The invention discloses a method for estimating the relative posture of a human face by combining key points of the human face with RGBD data. According to the method, face key points on an RGB imageare recognized, an initial posture angle difference is calculated, depth data is combined, RGBD point cloud is matched, and high-precision relative posture estimation of a face between different angles is obtained. Different from a previous recognition method, RGB-D data are used in the method, the requirement for the size of a data set is low, and high-precision relative attitude estimation can be achieved on data of small samples. Face key point information is also combined, so that the robustness of attitude estimation is enhanced.
Owner:ZHEJIANG UNIV
Model parameter extraction method and system for 3D scanning contour
PendingCN119540573AReduce screening workloadavoid blindnessThree-dimensional object recognitionPattern recognitionOriginal data
The invention discloses a 3D scanning contour model parameter extraction method and system, and belongs to the field of robot contour tracking. The method comprises the following steps: firstly, acquiring 3D contour scanning data, and carrying out data preprocessing, including downsampling, data filtering, smoothing, defect identification and compensation and the like, according to the characteristics of original data; then judging the number and the approximate positions of key points according to priori knowledge, and extracting key points of each frame of the contour; the local contour shape is identified according to an iteration nearest point; according to the key point of each frame of the contour and the local contour shape, extracting model parameters of the 3D contour; and finally reconstructing the 3D model according to the model parameters. The 3D scanning contour parameter extraction method overcomes the defects of the 3D contour, such as the negative effects of convex hulls, recesses, abrasion and the like on contour parameter extraction, and also overcomes the problems of target contour dislocation, data missing and the like caused by environment jitter or sensor reasons when the sensor scans data, so that the accuracy of 3D scanning contour parameter extraction is effectively improved.
Owner:SHANGHAI SECOND POLYTECHNIC UNIVERSITY