88results about How to "Improve fitting efficiency" patented technology

The invention relates to a virtual clothes fitting system. The virtual clothes fitting system comprises a clothes model database, a clothes selection module, a personal model database, a matching module and a combined display module. The invention further provides a virtual clothes fitting method. According to the virtual clothes fitting system and the virtual clothes fitting method, the clothes model database is established, a lot of clothes models are established and stored in the clothes model database, two-dimensional code information of the clothes is in index association with the clothes model database, one clothes model can be directly called by reading the two-dimensional code information of the clothes, the clothes model is matched with a user personal model, so on-site clothes model establishment is not needed, and clothes fitting efficiency is improved.

The present invention discloses a virtual fitting system in a shopping mall. The virtual fitting system in the shopping mall comprises: a three-dimensional virtual fitting module, a two-dimensional virtual fitting module, and a wireless communication module. The three-dimensional virtual fitting module comprises a color RGB camera, an infrared depth camera, a somatosensory device controller, a scene creation module, a posture identification module, a rigging module, a depth matching module, a logic module, and a rendering module, wherein the posture identification module comprises an infrared identification module and a gray identification module. According to a virtual scene fitting room disclosed by the present invention, the body bone and depth image information can be collected through somatosensory orientation and image identification and by using the depth camera sensor, the clothing is perfectly combined with realistic images, and display effects of different clothing in different scenes can be produced, so that the complicated procedure of traditional fitting is reduced, and fitting efficiency is improved.

The invention relates to a lane line detection method considering the preceding vehicle interference. A vehicle detection module, a lane feature point detection module and a lane detection module withpreceding vehicle interference elimination are arranged. The vehicle detection module acquires a road image in front of a vehicle by a camera image and acquires the position and size of a preceding vehicle by using an image processing technique. The lane feature point detection module acquires straight line feature points by using an edge detection method and acquires curve line feature points byusing an improved river point finding method in a model approximation mode with a near-end straight line and a far-end curve. The lane detection module with preceding vehicle interference eliminationuses a dual-curve model for approximation for the curve; when the residual lane line feature points are insufficient, lane line feature points are refilled by using a lane equal-width condition; andthe lane lines are detected by using a random sampling consistency algorithm. With consideration of the preceding vehicle interference to the lane line, a problem that the lane line is shielded or isaffected by the near vehicle is solved; and the lane line detection stability is improved.

The invention relates to an imaging method for virtual fitting. The imaging method comprises the following steps of: 1, establishing a human body AI model by utilizing label information of a clothingmeasurement rule and training the model on the basis of a Mask-RCNN; 2, obtaining a clothing data picture according to the label information of the clothing measurement rule and string the clothing data picture into a database; 3, obtaining a customer human body data picture according to the label information of the clothing measurement rule; and 4, carrying out data analysis and human-clothing matching: substituting the customer human body data picture obtained in the step 3 into the human body AI model in the step 1 to train, taking a human body position and a key point output by the AI model as the label information, estimating a size of each area of the customer human body, retrieving clothing with proper sizes and carrying out fitting according to the estimated size information of each area of the customer human body, and displaying a fitting success result between the clothing and the human body through an image engine. The method is capable of improving the fitting efficiency, displaying the effect of bodily form and fit clothing, and really displaying whether the clothing is matched with the skin color, head style and temperament or not.

The invention relates to a method of grabbing a shape symmetrical workpiece with a high precision by using a low precision depth camera. The method comprises the following steps: 1) measuring a position of a conveying workpiece tray in a grabbing area of a production line in a grabbing coordinate system O-XYZ; 2) carrying out hand-eye calibration on a grabbing system of a mechanical arm to obtaina homogeneous coordinate transfer matrix T1 between a camera coordinate system and the grabbing coordinate system; 3) generating a 3D workpiece model point cloud and marking the grabbing position; 4)constructing a workpiece detection network model based on deep learning and training the model; 5) carrying out 2D image target detection according to the trained workpiece detection network model; 6)integrating an image target detection result and tray position information, and cutting the 3D workpiece model point cloud to obtain a workpiece observation point cloud; and 7) estimating a grabbinggesture according to the cut workpiece observation point cloud. Compared with the prior art, visual guidance can be carried out by using the low precision depth camera to achieve the grabbing precision with visual guidance by a high precision depth camera.

A laminated arc heater high-enthalpy airflow parameter diagnosis system is used for obtaining the airflow parameters (particle number density and static temperature) of a high temperature flow field in the ground heat protection test of an arc heater, and online diagnosing high temperature disassociated air test airflow in the arc heater by using an atom O (777.19 nm) spectral line to obtain the plasma airflow temperature and the atom oxygen particle number density in the arc heater. The system can be used as a routine way for the arc heater high-enthalpy airflow parameter diagnosis.

The invention discloses a hearing aid self-fitting method based on a deep learning network. Through building a comprehensive patient information bank and through deeply analyzing the patient and the fitting process, an effective strategy in the fitting process is found out, a new intelligent hearing aid self-fitting model is thus built, and the fitting efficiency is improved. The deep learning network is introduced, through a large amount of data training, the network is made to have artificial intelligence, voice information consistent with the hearing loss characteristics of the patient canbe quickly generated according to the basic information of the patient, the input gains can be adjusted automatically according to the evaluation feedback of the patient, the fitting time is greatly shortened, and the satisfaction of the user is improved.

The invention provides a genetic algorithm-based auxiliary automatic oil-reservoir history matching method, belonging to the field of numerical simulation of oil reservoirs. The method comprises the steps of: by taking a mean value of matched evaluation of estimates of oil, gas and water as the degree of adaptability, performing operations by using a single-objective genetic algorithm; and setting a file to record Pareto solutions of the matched evaluation estimates of oil, gas and water generated during the whole process based on the genetic algorithm. By adopting the single-objective genetic algorithm, results superior to those of a multi-objective genetic algorithm can be obtained, and meanwhile, a group of solutions rather than a solution can be provided for users, so that the automatic oil-reservoir history matching efficiency is improved. In addition, the invention provides a novel oil-reservoir history matching evaluation function, which can effectively improve the automatic oil-reservoir history matching efficiency.

The invention discloses a remez algorithm based Sigmoid function hardware high-efficiency implementation method. The remez algorithm based Sigmoid function hardware high-efficiency implementation method is characterized in that: the Remez optimal consistency algorithm is firstly used to implement polynomial piecewise approximation on the Sigmoid function for four times to improve the fitting precision; and then the pipeline architecture optimization hardness is used to implement a module. The method effectively balances the contradiction between the resource consumption and the fitting precision, meets the real-time requirement, and meets different design indexes through the relatively strong flexibility.

The invention belongs to the computer-aided machining related technology field, and discloses a five-axis B-spline cutter path arc length parameterization method based on the cutter axis stability. The method comprises the following steps that 1, cubic Bezier curves are established between every two adjacent cutter location points; 2, the cubic Bezier curves between every two adjacent cutter location points are subjected to isoparametric sampling to obtain cutter location point spline sampling points; 3, arc length parameters of the cutter location point spline sampling points are calculated to serve as arc length parameters of target sampling points of a six-dimensional space, and cutter axis vectors and arc length parameters of the cutter location points are calculated; 4, cutter axis point spline sampling points corresponding to the cutter location point spline sampling points are calculated, and then the target sampling points of the six-dimensional space are obtained; and 5, a target function is established according to the target sampling points of the six-dimensional space and the arc length parameters, and a five-axis B-spline cutter path subjected to nearly arc length parameterization is solved accordingly. According to the method, the speed fluctuation during machining is reduced, and the machining quality and efficiency are improved.

The invention discloses a hearing aid self-fitting method. The method includes the steps that firstly, a knowledge base is established, a historical patient most similar to a current present is found out, and the optimal hearing aid algorithm parameters of the historical patient are obtained; the current patient conducts satisfaction evaluation on the sound quality, the hearing aid algorithm parameters are updated in an iteration mode according to evaluation indexes, and interaction with the knowledge base is conducted; test sounds are generated for the current patient according to the updated hearing aid algorithm parameters until the current patient feels satisfied. The knowledge base is introduced into the hearing aid self-fitting method, the matching range of the hearing aid algorithm parameters is greatly narrowed, and the fitting efficiency of a hearing aid is obviously improved. The expected value of the hearing aid of the current patient is met to the maximum degree due to the fact that the hearing aid algorithm parameters are updated in the iteration mode according to the evaluation indexes, and the accuracy of the hearing aid algorithm parameters is improved.

A first fitting part is in geared connection with a second fitting part, and a rotatably mounted eccentric drives a rolling movement of the first and second fitting parts on each other. The eccentric includes at least one driver and wedge segments. The components of the eccentric bear at least indirectly by way of their inner side and / or their outer side in each case against one of the fitting parts, at least one component of the eccentric is mounted with its inner side on the first fitting part and / or with its outer side on the second fitting part and interacts directly with the relevant fitting part, wherein the component of the eccentric or the associated fitting part, in the interacting region, is coated with a thin layer, and the thin layer has a lower coefficient of friction than the material of the component.

The invention provides a production data analysis method for a shale gas well with varying production systems, and belongs to the field of oilfield development. The method comprises: (1) establishinga shale gas well test analysis model; (2) obtaining production data and required basic data; (3) calculating output regularized pressure and an output regularized pressure differential coefficient, drawing a double logarithmic chart, the double logarithmic chart including two curves of a double logarithmic curve for the output regularized pressure and material balance time, and a double logarithmic curve for the output regularized pressure differential coefficient and material balance time; or calculating output regularized pressure integral and an output regularized pressure integral differential coefficient, drawing a double logarithmic chart, the double logarithmic chart including two curves of a double logarithmic curve for the output regularized pressure integral and material balancetime, and a double logarithmic curve for the output regularized pressure integral differential coefficient and the material balance time.

The invention provides an automatic oil deposit history fitting system and method based on a genetic algorithm, belonging to the field of oil deposit numerical simulation. In the invention, automatic history fitting is realized by taking a database as a data storage and computation center based on a generic algorithm flow. The system comprises an algorithm management module, a simulator pre-processing module, a simulator calling module, a simulator post-processing module a user interface module. Due to the adoption of the system and the method, automatic oil deposit history fitting is realized by organically combining the generic algorithm with a data technology, the indexing and storing process technology of a database is fully utilized, efficient storage of data is realized, a fitting evaluation value is calculated easily and rapidly, and the efficiency of automatic oil deposit history fitting is effectively increased.

The invention discloses a method for monitoring ground surface settlement and deformation of separate underground spaces on line. The method comprises the following steps: (1) calculating a settlementtank curve by means of an array; (2) selecting a transverse measurement point array on each cross section; (3) setting a longitudinal measurement point array on each longitudinal section; (4) diggingrectangular drill holes with certain lengths, widths and heights at the positions of the transverse measurement point arrays and the longitudinal measurement point arrays, putting protective wells into the holes, injecting fast setting concrete into the protective wells, putting micro-electromechanical system (MEMS) inclination angle sensing devices into the fast setting concrete; (5) enabling all the MEMS inclination angle sensing devices to automatically measure inclination angles, and sending results to a terminal by means of a network; (6) automatically receiving measured data in a wireless way by means of the terminal, interpreting the data, and then sending the data to a tunnel cloud monitoring server; (7) completing the functions of receiving, storing, processing, analyzing, alarming and visualizing showing the monitored data in an on-line way by means of the server. The monitoring method can realize intelligent measurement in the whole process, and has the advantages of high measurement accuracy and simple installation.

The invention provides a trajectory fitting method and device, electronic equipment and a storage medium, and relates to the field of path data processing of traffic management. The trajectory fittingmethod comprises the steps of preprocessing trajectory data of a target vehicle to obtain a to-be-processed trajectory point set; acquiring first road grabbing information of the first track point set according to the road network mapping data of the monitoring area; obtaining a target path combination through which the target vehicle passes according to the first road grabbing information, wherein the target path combination comprises at least one road; and fitting the to-be-processed track point set in the target path combination to obtain a fitting track of the target vehicle in the monitoring area. By using the trajectory fitting method provided by the embodiment of the invention, the dense trajectory points of the vehicle can be removed, and the road network mapping data of the monitoring area can be called, so that the fitting of the vehicle trajectory is realized, and the trajectory fitting efficiency is improved.

An ultrasonic wire bonding wedge with multiple bonding wire slots is provided. The wire bonding wedge includes a pillar fixing part for providing fixed connection to the bonding device. One end of the fixing part includes a wire bonding wedge nozzle, with feature that the tip of the nozzle including at least two bonding wire slots. The tip of nozzle of the wire bonding wedge includes at least two bonding wire slots, and is able to realize bonding operations between two or more bonding wires and the chips to improve bonding operation efficiency. When bonding operation is performed on a smaller bonding area, or two or more parallel bonding wires, the wire bonding wedge is able to perform a single bonding operation in a smaller bonding operation so as to reduce defective rate of the chips and ensure sufficient bonding strength of the bonding operation.

The invention relates to a virtual three-dimensional fitting method and system. The fitting method comprises the steps of performing simulation on part samples of garments in three-dimensional human body models with different body shapes according to corresponding sewing methods; obtaining deformation corresponding relationships between the garments and the three-dimensional human body models withthe different body shapes, and corresponding garment three-dimensional models; and according to the body shapes of the three-dimensional human body models of users and garment parameters selected bythe users, obtaining the corresponding garment three-dimensional models to be fused with the three-dimensional human body models of the users, and performing display. By inputting the part samples andthe sewing methods of the garments, the simulation is performed on the three-dimensional human body models with the different body shapes, and the corresponding deformation corresponding relationships and garment three-dimensional models are obtained, so that when the three-dimensional human body models of the users are obtained, the corresponding garment three-dimensional models can be quickly obtained; and a scene that the users perform garment fitting is simulated, so that the fitting efficiency is improved.

The invention discloses a bezier curve surface fitting method and system based on the de Casteljau algorithm. The method includes the steps of obtaining n data points of a Bezier curve, obtaining 2*(n-2) control points through the n data points of the Bezier curve according to the de Casteljau algorithm, setting control coefficients at the control points, and obtaining the Bezier curve by adjusting the curvature, at the data points, of the Bezier curve by changing the control coefficients, and by determining the control coefficients when the curvature is the target curvature. According to the method, fitting is conducted on the Bezier curve surface by changing the control coefficients, the Bezier curve which is high in profile modeling degree can be obtained through fitting when a small number of data points are selected according to actual application, it is ensured that the curve can pass through all the data points, continuity of the curve is ensured at the data points, and on the aspect of curve fitting, complexity is lowered, and fitting efficiency is improved.

The invention discloses a method and device for realizing virtual try-on. The method includes the following steps that: a pre-generated picture or video about a user himself or herself who serves as atry-on model is displayed for the user; when a user garment try-on instruction is received, the matching parts of the body of the try-on model are identified according to the types of garments; and the images of garments selected by the user in a garment database and the images of the identified matching parts of the body of the try-on model are synthesized, and synthesized images are displayed.With the method provided by the embodiments of the invention adopted, the simulation of the try-on effect of the customer can be realized, time and labor can be saved, shopping efficiency is high, andthe shopping experience of the user can be enhanced.

The invention discloses a segmenting method for a surface electromyogram signal activity section based on sample entropy and a Gaussian model. The segmenting method comprises the steps that 1 electricpotential values of surface electromyogram signals are collected from the related muscles of the human body, widths u and step lengths f of sliding windows are set, and sliding segmentation is conducted on data; 2 sample entropy parameters m and r are set, and the sample entropy of each sliding window is calculated; 3 a DBSCAN cluster method is adopted for determining a Gaussian polynomial basicmodel, and then model parameters are initialized; 4 a nonlinear least square method is adopted for fitting of the Gaussian model; 5 according to the Gaussian model, an energy threshold is determined,and the activity section is segmented. According to the method, the characteristic can be utilized that the sample entropy has an inhibition effect on noise, the influence of the noise on signal segmentation is overcome, and therefore the foundation is provided for precision and reliability of further analysis for the surface electromyogram signals.

The invention discloses a health level evaluation method of a thermal power generating unit based on data analysis, belongs to the field of thermal power generation, The aim of invention is to providea health level evaluation method of a thermal power generating unit based on data analysis to evaluate the operation status. The main points of the technical scheme are as follows: S1, acquiring historical operation data for a period of time from the real-time information monitoring and management system of thermal power generating units, screening the historical operation data, and selecting thehealthy operation data; S2, determining the parameters to be measured, selecting the independent variables related to the parameters, and carrying out curve fitting on the parameters and the independent variables related to the parameters to establish a mathematical model of each parameter; S3: establishing the scoring rules based on the mathematical models of each parameter. The method can be used to realize the real-time prediction of parameters and to judge whether the predicted value is normal or not.

The invention provides an establishment method for a pipe network leakage prediction model based on EPR evolution polynomial regression, and belongs to the field of an urban water supply network. The method comprises: processing original data of modeling, determining pipe diameters, pipe lengths, and pipe age as influence factors; then respectively modeling five kinds of pipes, grouping each kind of pipes according to pipe diameters, pipe lengths, average weighted pipe age, and leakage frequency per year, establishing a leakage prediction model with pipe diameter, pipe length, and pipe age as independent variables, and leakage frequency per year as a dependent variable, using fitting degree of a CoD determination model; using actual leakage data to verify the leakage prediction model, using predictive ability of a RMSE judging model; finally, summing the leakage frequency per year which is predicted according to the leakage prediction models respectively established for the five kinds of pipes, to obtain final leakage frequency total amount of the pipe network in a region. Through the establishment of the model and determination of the leakage number of the region, the pipes which have leakage risks can be found out as early as possible in daily management, so as to reduce probability of accidents and reduce economical loss.

The invention relates to in-plane curve fitting methods, in particular to a geometric optimization approximation based minimum region fitting method for profiles of parabolas. The method comprises the steps: firstly, approximate coordinates of an initial focus and a vertex of a measured parabola are roughly estimated according to coordinates of measuring points, and a series of auxiliary points are arranged around the initial focus and the vertex according to certain rules; next, supposed that the auxiliary points around the initial focus and the vertex are focuses and vertexes of the parabolas to be fit, the supposed focuses and vertexes can be used for constructing a series of parabolas; then, range values from the measuring points to the parabolas are calculated, and finally, the minimum region fitting of the measured parabola is realized through comparing, judging and transforming reference points and establishing a new supposed auxiliary parabola. The method has the advantages that the fitting process is simple, the accuracy of fitting is high, and the minimum region fitting and evaluation of profile tolerance errors of the parabolas can be effectively realized.

The invention provides a bandwidth characteristic curve fitting system, method and device, and belongs to the technical field of bandwidth data, and the method comprises the steps: generating a digital quantity sequence according to initial reference point information, wherein the reference point information comprises a frequency and an amplitude corresponding to the frequency; controlling broadband signal generation equipment to convert the digital quantity sequence into a digital calibration signal, and converting the digital calibration signal into an initial waveform; controlling a spectrum analyzer to perform fast Fourier transform on the initial waveform to obtain a target amplitude-frequency response curve; acquiring a target reference point amplitude in the amplitude-frequency response curve, and fitting a bandwidth characteristic curve according to the amplitude of the initial reference point in the digital calibration signal and the target reference point amplitude, wherein the target reference point amplitude and the amplitude of the initial reference point correspond to reference points with the same frequency. According to the invention, the calibration frequency is reduced, and the fitting efficiency is improved.

The present application discloses a fast iterative line-circle optimal fitting method, which comprises: constructing candidate fitting results according to all data points; iteratively optimizing thecandidate fitting results; selecting an optimal curve. The candidate fitting results are obtained by full traversal in a basic search space to obtain a set of curves containing the optimal curve or the curves near the optimal curve and with the smallest error; the iterative optimization utilizes the prior knowledge that the outlier removed from the optimal fitting result must be the farthest datapoint to the curve, and iteratively modifies the outlier in the candidate fitting result, so that the candidate fitting result becomes stable and the RMS error is further reduced. Screening the optimal curve is to compare the RMS error of the iteratively optimized fitting curves and screen is the curves with the smallest error as the best fitting results. The line-circle optimal fitting method provided by the present application greatly shortens the fitting time, and the fitting process is non-random, so that the global optimal fitting result can be obtained quickly, stably and accurately.

A Doppler parameter quadratic fitting method based on time division multiplexing comprises the steps of (101) establishing a quadratic fitting unit which comprise a multiplying unit a2, a multiplying unit b2, a multiplying unit c2, a multiplying unit d2, a multiplying unit e2, a divider a2, a summator a2, a mean value module a2, a mean value module b2 and a mean value module c2; (102) calculating fitting parameters m, m21, m22, m23, m24 and m25 by means of the quadratic fitting unit with the abscissa xi of a scatter signal as the input end; (103) calculating the fitting coefficient summation by means of the quadratic fitting unit based on the fitting parameters m, m21, m22, m23, m24 and m25; (104) achieving quadratic curve fitting of the scatter signal based on the fitting coefficient summation. Compared with traditional quadratic fitting, the Doppler parameter quadratic fitting method based on time division multiplexing has the advantage that the number of hardware resources needed is reduced greatly by means of time division multiplexing of hardware resources in the quadratic fitting unit.

The invention aims at disclosing a nuclear power real-time data trend fitting algorithm, and compared with the prior art, the accuracy problem when historical data is used for trend analysis fitting in the nuclear power production process is effectively solved, the accuracy of a trend fitting curve is improved by 200% or above, the accuracy of operation and maintenance management fault diagnosis by using the trend fitting curve is improved by more than 200%, and the demand of trend fitting analysis of historical data of a nuclear power plant unit can be completely met. And when long-term trend fitting is used, the fitting efficiency is effectively improved, and the purpose of the invention is achieved.

The invention discloses a method for extracting physical parameters of a resistance model, which comprises the following steps: step 1, manufacturing a plurality of resistors, and testing the length,width and resistance value of each resistor; 2, selecting physical parameters of that resistance model, wherein the number of the physical parameters of the resistance model is three, namely, normalized square resistance, corrected line length and corrected line width; 3, setting an accumulated error function of the resistance, the equation is described in the description; 4, a genetic algorithm is used to extract the normalized square resistor, and the values of the line length and the line width are corrected. The resistance cumulative error function is used as the fitness function in the genetic algorithm flow. The invention can effectively reduce parameter fitting error and fitting time.

The invention discloses a threshold distribution fitting method, device and system for a flash memory, and the method comprises the steps: carrying out the fitting of the distribution of storage units in a plurality of voltage intervals in initial threshold voltage distribution, obtaining a first fitting normal distribution parameter, and then carrying out the fitting of one of two adjacent threshold voltage distribution states; if the fitted threshold voltage distribution state and the to-be-fitted threshold voltage distribution state are two adjacent threshold voltage distribution states, obtaining a second fitted normal distribution parameter of the fitted threshold voltage distribution state; and according to the second fitting normal distribution parameter, performing fitting to obtain a third fitting normal distribution parameter of the threshold voltage distribution state to be fitted. In the embodiment of the invention, the fitting of the threshold voltage distribution state can be carried out in sequence, and only the fitting normal distribution parameter of the threshold voltage distribution state adjacent to the threshold voltage distribution state obtained by previous fitting is referred to in the fitting process of the threshold voltage distribution state, so that the data calculation amount is reduced, and the fitting efficiency is improved.