203 results about "Mean square" patented technology

The invention discloses a pilot optimization method for large-scale MIMO channel estimation based on structural compressed sensing. The method comprises the steps of establishing a channel estimation model for a large-scale MIMO-OFDM (Multiple-Input-Multiple-Output-Orthogonal Frequency Division Multiplexing) system when pilots are placed in an overlapping mode; simplifying the channel estimation model for the large-scale MIMO-OFDM system, thereby enabling the channel estimation model to correspond to a structural compressed sensing model; and obtaining an optimum pilot matrix through utilization of a pilot optimization algorithm. Through adoption of the optimum pilot matrix, according to the channel estimation of the large-scale MIMO system based on structural compressed sensing, the mean square errors MSEs of the channel estimation are clearly reduced, and the channel estimation performance is improved.

The invention relates to a beam forming design method of an active RIS-assisted ISAC system, and belongs to the field of communication perception integration. A multi-user large-scale multiple-input single-output system model assisted by communication and perception integration and a system model based on an ISAC system assisted by an active RIS are constructed, and a beam forming vector and a reflection coefficient of the active RIS are respectively optimized by adopting an alternating optimization algorithm. According to the method, the propagation blockage problem is solved, the system performance is further improved, the multiplicative fading effect problem of the passive RIS is solved by using the active RIS, the weighted minimum mean square error algorithm, the continuous convex approximation algorithm and the positive semidefinite relaxation algorithm are combined, the system effectiveness is improved to the maximum extent, and the system performance is improved to the maximum extent. The system utility is the sum of the weighted sum rate of the system and the target detection power, the target detection capability is remarkably enhanced while the weighted sum rate of the user is improved, and a new solution is provided for performance optimization of the ISAC system.

The invention discloses a missile erection filtering method, system and device and a readable storage medium, and relates to the technical field of inertial navigation and the field of initial alignment. Based on the reference inertial unit pitch angle before erection, the reference inertial unit pitch angle at the current moment, the inertial unit angular velocity on the missile and the trajectory launching inclination angle, whether the missile is in any one of the non-target states of the non-erection state, the just erection state, the to-be-erected in-place state and the erection completion state or not is judged; if yes, measurement updating is not carried out in the Kalman filtering calculation process of the current moment, and time updating is carried out based on the state transition matrix of the current moment, the state vector of the previous moment, the mean square error matrix of the previous moment and the process noise variance matrix; and attitude information output by the inertial navigation system at the current moment is used as a missile attitude result for calculation at the next moment. According to the method, shaking between the guided missile and the launching box in the erecting process before launching is considered, and the attitude precision of initial alignment of the guided missile is improved.

The invention discloses a multi-factor tunnel surrounding rock deformation prediction method based on deep learning, and the method effectively improves the accuracy of tunnel surrounding rock deformation prediction through integrating an information collaborative analysis index and a long-short-term memory network fused with an attention mechanism. According to the method, the LSTM model integrating the information theory and the attention mechanism is constructed, and the model can be dynamically focused on key time sequence data, so that the prediction accuracy is improved. In addition, the method also comprises a model verification step: comparing a prediction result with measured data, and evaluating the performance of the model by using a mean absolute error and a mean square error. The informatization and automation level of tunnel surrounding rock deformation prediction is improved, and powerful technical support is provided for tunnel construction safety.

The invention provides a three-dimensional channel atlas construction method based on a conditional generation diffusion model, which belongs to the field of channel atlas construction, and comprises the following steps: S1, forming original channel atlas data psi0, and gradually adding noise to the original channel atlas data psi0 according to a time step t, the method comprises the following steps: S1, acquiring noise epsilon t of each time step t, S2, storing noise # imgabs0 # added at each time step t, S3, defining an input condition c of a condition generation diffusion model as # imgabs1 #, S3, generating the diffusion model based on a back propagation training condition on the basis of the noise epsilon t of each time step t and the input condition c obtained in the step S2, a loss function adopted in the training process is defined as a condition generation diffusion model to predict a mean square error of noise # imgabs2 and noise epsilon t; and S4, generating a diffusion model based on the trained conditions, and generating a three-dimensional channel map corresponding to the input conditions through a back diffusion process. According to the invention, high-precision generation of the three-dimensional channel map is realized.

An inertia-based method and system for measuring the bending strain of a pipeline, and a device and a medium. The method comprises: acquiring posture information of a pipeline having a preset length, which posture information is collected by an IMU (S1); performing wavelet transform on the posture information to obtain first target posture information (S2); according to a preset order and a preset window width, performing sliding filtering on the first target posture information by means of a sliding window, wherein one data window is determined each time the sliding window slides on the first target posture information (S3); on the basis of the data windows, determining a fitting coefficient by means of the minimum mean square error (S4); using the value at the central point of each data window as a filtering value, determining a filtering sequence on the basis of the filtering values and the fitting coefficient, and using the filtering sequence as second target posture information (S5); on the basis of the second target posture information, determining a bending strain force applied to the pipeline (S6); and measuring the bending strain of the pipeline on the basis of the bending strain force applied to the pipeline (S7). In the method, noise cancellation is performed twice, thereby improving the accuracy of posture information calculated by an IMU, and solving the problem of the posture information calculated by the IMU being affected by noise.

The invention discloses a multivariable time sequence prediction method and system based on an implicit neural network. The method comprises the following steps: 1) collecting data and preprocessing the data; 2) performing window division on the standardized or normalized multivariable time sequence and determining the length of a to-be-predicted window; 3) performing variable correlation coding on the input window to obtain a variable-level feature vector; 4) the implicit neural network based on time attention predicts target parameters by using the variable features in the step 3), and implicit neural representation of the target sequence is modeled through the parameters; 5) taking the output of the implicit nerve representation and the original input window as the input of the multi-head attention predictor, and obtaining a prediction result through cross-sequence cross attention calculation performed in the implicit space and multi-layer perceptron conversion output dimension; and 6) training and optimizing model parameters, calculating a mean square error of a prediction result and a real result, taking the mean square error as a loss function, carrying out back propagation to optimize trainable parameters of the variable correlation coding module, the implicit neural network module multi-head attention predictor and the multi-layer perceptron, and then repeating the steps 3) to 6) to obtain the multi-head attention predictor. Until the preset number of iterations is reached or the error of the model on the verification set meets the requirement of early stop; and 7) performing prediction by using a model of training convergence, and performing reverse normalization on a prediction result to obtain a final prediction result. The method has good generalization, and meanwhile, the interpretability of the attention mechanism is remarkably improved by generating the hidden space characteristics of the trend component and the season component.

The invention relates to the technical field of air computing, in particular to an air computing system optimization method under a non-ideal channel and total power constraint, which comprises the following steps: considering the optimal design problem of an air computing system under the total power constraint and imperfect statistical CSI (Channel State Information), and designing a scaling factor of an air computing receiving and transmitting end through joint optimization; and the MSE of system calculation distortion is minimized. Specifically, under the constraint of total power, a mean square error estimated by minimizing the sum of preprocessed signals of K sensors is taken as a target, a design problem of an optimal transmitter-receiver scaling factor is established, an original non-convex problem is converted into a convex problem by using an alternative optimization idea, and a closed-form solution of the optimization problem is obtained through a KKT condition. According to the method, the solving difficulty of the algorithm is reduced, and the calculation distortion is smaller in the full-power transmission range.

The invention discloses an asphalt pavement anti-slide performance index analysis method based on a multivariate quadratic polynomial. The method comprises the following steps: S1, extracting a pavement macroscopic texture average structure depth of a three-dimensional texture morphology rough characteristic; s2, extracting a contour single-peak average interval and a contour root-mean-square wavelength of the three-dimensional texture morphology rough characteristic; s3, extracting shape indexes of three-dimensional texture morphology roughness characteristics, wherein the shape indexes include contour skewness, hump degree, apparent anisotropy and three-dimensional morphology fractal dimension; s4, establishing a multivariate quadratic polynomial to solve a BPN regression model; and S5, establishing a multivariate quadratic polynomial to solve an SFC regression model. According to the method, the relationship between the texture roughness characteristic index and the pavement skid resistance is discussed from two perspectives of theoretical analysis and empirical regression by adopting a tribology theory and a multiple regression analysis method. A system for evaluating the skid resistance of the pavement based on the texture roughness characteristic is further established, and a new method and thought are provided for evaluating the skid resistance of the asphalt pavement.

The invention discloses a high-precision quantization method for non-uniformly distributed data, and aims to solve the problems that reconstruction errors are remarkably increased and codebook resources are wasted when a traditional uniform quantization algorithm processes complex data distribution. According to the scheme, firstly, a dynamic programming algorithm is used for carrying out local homogenization processing on data, and optimal segmentation is achieved by minimizing the sum of squares of a weighting range; and then introducing a particle swarm optimization algorithm to carry out iterative tuning on the end points of the quantization interval, and constructing an efficient codebook by taking the minimization of a mean square error (MSE) as a target. Experimental results show that the quantization errors of the method on a 128-dimensional data set and a 420-dimensional data set are respectively reduced by 93.52% and 98.05% compared with those of a traditional method, meanwhile, hardware compatibility is kept, and the method is suitable for scenes such as edge computing nodes, AI chips and the like which have strict requirements on compression efficiency and real-time performance.

The invention relates to an automatic grinding track generation method, a medium and equipment. The automatic grinding track generation method comprises the following steps: acquiring a workpiece point cloud, uniformly segmenting the workpiece point cloud to obtain a plurality of point cloud modules, obtaining a mean square error of each point cloud module, combining the point cloud modules into a plane according to the mean square error to obtain a workpiece plane image, and carrying out binary segmentation on the workpiece plane image to obtain a grinding track. Carrying out gradient calculation on the workpiece binary image to obtain a plurality of feature points, sequentially connecting all the feature points according to a set sequence to obtain an initial grinding track, fitting a curve of the initial grinding track, and determining a final grinding track. The problems that in the prior art, workpiece recognition and positioning are difficult, track calculation precision is low, and tracks are not smooth enough are solved.

The invention relates to a KV cache compression method based on attention alignment, and belongs to the technical field of large language models. Comprising the following steps: a target model self-generates dialogue data reply, and constructs training data; adding a soft token into a word list of the target model, and carrying out soft token random initialization; finely adjusting specified parameters, splicing soft tokens at the tail of an original input sequence, and transmitting the soft tokens to the model; and respectively calculating the soft token and the attention distribution of the self-generated reply, calculating the mean square error of the soft token and the attention distribution of the self-generated reply as a loss function, and completing training. According to the method, a limited number of soft tokens playing an auxiliary role are introduced into original input, and importance discrimination of KV cache elements is realized and expelling is completed by aligning attention distribution of the soft tokens and real generated content; according to the method, better compromise is achieved between sequence length compression and performance loss, and the loss of model performance is better controlled while it is guaranteed that KV cache video memory space occupation is reduced.

The invention belongs to the field of water-wind-light multi-energy complementary optimal scheduling, and particularly discloses a water-wind-light optimal scheduling method and system based on a two-stage dual-population evolutionary algorithm, and the method comprises the steps: taking the water level of a reservoir as a decision variable, taking the maximum power generation amount and the minimum residual load mean square deviation as objective functions, and constructing a multi-objective scheduling model; the two populations are initialized, and the water-wind-light multi-target scheduling model is solved; the two populations are initially in a fixed division stage, and operators A and B are respectively adopted for iterative updating; when a switching condition is met, switching to a self-adaptive cooperation stage for iterative updating, determining the selection probability of the operators A and B according to population performance at the moment, and selecting the operators based on the selection probability for iterative updating; the switching condition is that after the population is iteratively updated each time, if the population diversity is smaller than a threshold value or the evaluation frequency reaches the threshold value, stage switching is carried out. According to the method, the contradiction between convergence and diversity in water-wind-light multi-objective optimization can be solved, and accurate optimization is realized.

The invention discloses a method and a system for predicting the service life of a rolling bearing in multiple failure modes based on Weibull distribution, and relates to the technical field of rolling bearing service life prediction. In order to solve the problem that the service life discreteness of a rolling bearing is large due to multiple failure modes such as early failure, random failure and fatigue failure under different working conditions, the method comprises the following steps: firstly, determining first prediction time by using a random convolution kernel binary regression model, and dividing failure time data based on the first prediction time; a plurality of failure modes are identified by using Weibull distribution; secondly, through a particle filter (PF) dynamic updating mechanism and a soft resampling technology, improving a cell gate and a hidden state of a long and short term memory network (LSTM), constructing a particle filter and long and short term memory network (PF-LSTM) fusion prediction model, and enhancing adaptive capacity to complex working conditions; and finally, constructing a multi-criterion loss function by using the probability density function of the Weibull distribution and the mean square error again, and further improving the prediction precision of the PF-LSTM by integrating the traditional mean square error and the priori knowledge of the Weibull distribution. Experiments prove that the method provided by the invention can predict the service life of the rolling bearing in multiple failure modes, compared with a traditional LSTM method, the average absolute error is reduced by 13.69%, and in addition, compared with a CNN-LSTM model, the prediction average score is improved by 0.169.

The invention discloses a motor multi-objective optimization design method and system based on a Kriging agent model. Comprising the following steps: constructing an initial data set through an experimental design method and finite element simulation calculation, so as to train an initial Kriging agent model which takes a motor design variable combination as an input variable and takes motor performance as an output response; the proxy model serves as a target function, a multi-target optimization problem is solved, the proxy model is updated, and an updating strategy is as follows: after each round of optimization is finished, a high-error solution in a current Pareto solution set is screened based on a Kriging model prediction mean square error, a finite element response of the high-error solution is obtained and supplemented to a data set, and the proxy model is updated and trained; and repeating the process until the optimization result converges. According to the method, high-uncertainty region samples are selectively supplemented, the calculation cost is remarkably reduced while the local prediction precision of the proxy model at the Pareto leading edge is improved, and the method has good practicability and economical efficiency.

The invention belongs to the technical field of geomagnetic navigation, and particularly relates to a geomagnetic reference map construction method based on a super-resolution network, and the method comprises the following steps: S1, collecting geomagnetic data points in a rectangular region by using geomagnetic collection equipment, forming sparse collection data, and constructing a sparse matrix as a geomagnetic test set; s2, obtaining geomagnetic library data from a geological exploration bureau website to obtain a dense matrix, performing down-sampling on the dense matrix to obtain a sparse matrix, and combining the dense matrix and the sparse matrix to construct a geomagnetic training set; s3, inputting the geomagnetic training set into a super-resolution network composed of a generator and a discriminator for training; and S4, inputting the geomagnetic test set into the generator to obtain an output result, and further constructing a high-precision geomagnetic reference map. The geomagnetic reference map construction system based on the super-resolution network can more flexibly adapt to data of different scales and complexities, improves the accuracy of geomagnetic reference map construction, and has smaller mean square error and higher precision compared with a traditional Kriging interpolation method.

The invention discloses a 1-bit DAC precoding optimization design method suitable for a large-scale MU-MIMO system, and the method comprises the steps: setting base station data configuration, and modulating an input symbol vector; quantizing the modulated input signal by using a 1-bit DAC (Digital-to-Analog Converter); generating a complex cyclic symmetric Gaussian random channel matrix H by adopting Rayleigh distribution; designing a signal of a receiver end; establishing a 1-bit DAC precoding optimization problem based on a minimum mean square error according to the average transmitting power of the base station and a 1-bit DAC character set constraint; a mean square error between a recovery signal and an input signal is minimized by utilizing a designed ADMM-HB method under the constraint of the average transmitting power of a base station and a 1-bit DAC character set. According to the method, the ADMM-HB method is used in the optimization process, the signal mean square error of the receiving end and the transmitting end can be minimized with low calculation complexity, the system efficiency is improved, the system hardware cost and power consumption are reduced, and the method better conforms to engineering practical application.

The invention relates to a multi-channel multi-mode space-time 3D convolution and Transform fused satellite-borne GNSS-R wave height inversion model, and aims to solve the problems that a traditional empirical model is poor in adaptability to complex oceans and existing deep learning cannot fully excavate space-time correlation. According to the method, three modules are innovatively fused for cooperative processing: firstly, a 3D CNN-ConvLSTM is utilized to extract local spatial-temporal characteristics of multichannel GNSS-R data and capture a dynamic time sequence; secondly, performing deep coding on the sea surface environment parameters through a multi-head attention mechanism of Transform, and establishing global dependence between features; and finally, realizing cross-modal fusion by adopting a weighted summation and feature splicing strategy. And through training of an Adam optimizer and control of an early stop strategy, optimization is carried out by taking a mean square error as a loss function. Experiments show that compared with a traditional model and a machine learning model, the method has the advantages that the significant wave height estimation error is reduced by 40-53%, the correlation coefficient reaches 0.84-0.91, the precision and generalization ability under the complex sea condition are remarkably improved, and reliable support is provided for ocean remote sensing monitoring and disaster early warning.

The invention discloses a traversal measurement tracing number-setting interpolation algorithm based on source-load aggregation application, which comprises the following steps of: S1, selecting three points before and after missing data as original data, and learning an interpolation model to fit the original data through a cubic polynomial; and obtaining a cubic polynomial function coefficient through a least square method, and finally substituting the missing data into a cubic function to complete interpolation of the missing data. According to the traversal metering tracing number-setting interpolation algorithm based on the source load aggregation application, adjacent three-point data is selected to carry out cubic function interpolation of the least square method, and context information around missing points is fully considered, so that the trend and characteristics of original data are better restored, the average mean square error reaches the magnitude order of 10-3 power, and the calculation accuracy is improved. The missing load data is well interpolated, the deviation between the interpolation result and the real data is relatively small, and the validity of the interpolation algorithm in the aspect of interpolation accuracy is embodied.

The present invention discloses a method for denoising GNSS monitoring data of open-pit mine slopes by integrating multiple source indicators. The method comprises the following steps: S1, collecting GNSS monitoring data of the slopes and detecting and interpolating large gross errors using the 3σ method, then performing wavelet decomposition to obtain low-frequency coefficients and high-frequency coefficients; reconstructing the trend term Q using the low-frequency coefficients, solving the mean square error m using the first and second layer high-frequency coefficients, and then detecting gross errors again; S2, performing empirical mode decomposition on the GNSS monitoring data of the slopes to obtain a number of slope IMFs; screening to obtain high-noise modes, low-noise modes, and residuals, reconstructing the low-noise modes and residuals to obtain a preliminary denoised slope GNSS signal result EMD_A; and S3, processing the high-noise modes of the slopes using the interval soft threshold method and synthesizing them with the slope EMD denoising result EMD_A to obtain the final slope GNSS denoising result. The present invention achieves accurate denoising of GNSS monitoring data of open-pit mine slopes, providing more reliable data support for slope stability monitoring in mining areas.

The invention discloses a current transformer calibration method and device based on minimum mean square M estimation and a medium, and belongs to the technical field of current transformer calibration. The method comprises the steps that response signals are extracted from a to-be-calibrated transformer and a standard transformer, and response signal vectors are established; parameters of an N-order RVSSLMSM adaptive filter are initialized, the initial parameters and a to-be-calibrated mutual inductor response signal vector are substituted into the adaptive filter to obtain filter output, an error vector of an adaptive filter output signal vector and a standard mutual inductor response signal vector is calculated, and therefore a variance value is updated; and according to the variance variation, updating the parameters of the adaptive filter, substituting the response signal vector of the to-be-calibrated mutual inductor into the updated adaptive filter, and repeating the steps until the residual sum is converged or reaches a certain number of iterations, thereby obtaining the optimal coefficient of the filter and completing the calibration. And the calibration precision and the system robustness are effectively improved.

The invention provides a PMU harmonic data missing filling method and device based on multi-measuring-point data correlation, and aims to provide a higher-precision solution for a power grid harmonic monitoring system. When the harmonic data of the target station are missing, PMU measurement data of the target station and the adjacent monitoring stations in the same time period are extracted, and the PMU measurement data are divided into a known data set and a missing data set according to the integrity of the harmonic data; and performing strong correlation screening on the known data set: calculating type-by-type Pearson's correlation coefficients of harmonic data of the target station and PMU data of the target station and PMU data of other stations, removing data types lower than a threshold value, and retaining strong correlation data. Strong correlation data is used as an input feature, a target harmonic real value is used as an output label, a CNN-LSTM model (CNN extracts spatial features and LSTM captures time dependence) is adopted for training, and parameters are optimized through mean square errors until the error of a verification set reaches the standard. And finally, predicting a harmonic value of the missing data set by using the model, and finishing data restoration by taking a prediction result as a filling value.

The various implementations described herein include methods and systems for coding video. In one aspect, a video bitstream includes a current coding block of an image frame and signals a syntax element for a cross-component prediction (CCP) mode. When the CCP mode is enabled, a computing system identifies a reference area of the current coding block and downsamples the reference area to identify samples of a subset of reference area. A plurality of model parameters used in the CCP mode are determined for a first chroma sample of the current coding block based on the samples of the subset of reference area. The computing system combines a set of one or more luma samples (e.g., of a reference coding block) using the plurality of model parameters to generate the first chroma sample. The image frame is reconstructed based on the current coding block including the first chroma sample.

A method for predicting a fault in an industrial system (100), the method comprising the steps of: a) providing an input time series (1) comprising a plurality of data points (t1,..., n, y1,..., n), each data point comprising a timestamp (ti) and a value (y) of a variable W measured at the respective timestamp (ti); b) calculating a fitting parameter (2) of a log periodic power law model function W (t) (3), which minimizes a mean square error mse (4) of the input time series (1) or of at least a subset (1a) of data points of said input time series (1), in order to obtain a fitting function (5); c) identifying a local maximum (Nmax) and a local minimum (Nmin) of the fitting function (5); d) determining a trend (Tmax) from at least some of the identified local maxima (Nmax) and a trend (Tmin) from at least some of the identified local minimum (Nmin), the respective trend (Tmax, Tmin) being determined from a slope of a linear fit of the selected local maxima (Nmax) and the local minimum (Nmin); e) identifying whether a given data point (tn, yn) of the input time series (1) is a critical point (tc), if two trends (Tmax; if all the data points (tn, yn) are positive or negative, the given data point (tn, yn) is a critical point (tc); and, if the critical point (tc) has been identified in step e), performing step f) to output a signal (7) indicating a predicted fault of at least one component (8) in the industrial system (100).

The application discloses an iterative classification matching data association method suitable for complex environment, and comprises the following steps: performing primary association; the characteristic group of primary association success constitutes a data set Z t + and F t + ; the characteristic group of primary association failure constitutes a data set Z t ‑ and F t ‑ ; solving a least square matching vector Θ according to the data set Z t + and F t + ; updating the data set F t ‑ by the least square matching vector Θ to obtain an updated data set, combining the data set Z t ‑ and F into new input, and performing iteration until a mean square error detection is satisfied. The application optimizes the data association method, improves the consistency of algorithm estimation, and reduces the algorithm calculation complexity, and makes up for the deficiency of ICNN and JCBB algorithms in large-scale underwater environment.

The invention discloses an interpretable data-knowledge-free distillation method based on a class activation graph, and the method comprises the following steps: inputting random noise to a generator, and generating a composite image similar to the distribution of a target data set; respectively inputting the synthesized image into a teacher model and a student model which are subjected to structure adjustment; respectively generating corresponding class activation diagrams through the teacher model and the student model; inputting the teacher class activation graph and the student class activation graph into a pre-trained scale mapping network, and performing cross-scale scaling on the class activation graphs; performing regularization processing on the scaled class activation diagram to obtain a standardized teacher class activation diagram and a student class activation diagram; calculating mean square error loss based on the teacher type activation graph and the student type activation graph to realize knowledge transmission; and finally, optimizing the generator in combination with information entropy loss, one-time heat loss and activation loss. According to the method, effective knowledge distillation can be realized under the condition of no real data, and the interpretability and stability of the distillation process are improved.

The invention provides an uplink MIMO-NOMA (Multiple Input Multiple Output-Non-Orthogonal Multiple Access) system optimization method with a maximized sum rate, which comprises the following steps: firstly, in order to suppress interference between a transmission cluster and a reflection cluster, providing an inter-cluster SIC method: clustering users according to transmission characteristics, adopting space division multiple access in each cluster, and performing inter-cluster SIC of NOMA transmission so as to reduce the interference between the clusters; secondly, a non-convex optimization problem aiming at maximizing the total rate of the system is formulated and solved by using an alternating optimization framework, in the framework, a receiving equalizer is optimized according to a minimum mean square error standard, and transmitting power control of a user is processed through successive convex approximation, so that sub-problems are easy to process; and finally, the beam forming of the active STAR-RIS adopts a sequential rotation design. According to the invention, the dual-fading effect is effectively overcome by adjusting the phase shift and amplitude of electromagnetic waves, an alternating optimization framework is also provided to solve the described non-convex problem, user power is controlled through continuous convex approximation, and active STAR-RIS beam forming is realized through sequential rotation.

In examples, a filter used to denoise shadows for a pixel(s) may be adapted based at least on variance in temporally accumulated ray-traced samples. A range of filter values for a spatiotemporal filter may be defined based on the variance and used to exclude temporal ray-traced samples that are outside of the range. Data used to compute a first moment of a distribution used to compute variance may be used to compute a second moment of the distribution. For binary signals, such as visibility, the first moment (e.g., accumulated mean) may be equivalent to a second moment (e.g., the mean squared). In further respects, spatial filtering of a pixel(s) may be skipped based on comparing the mean of variance of the pixel(s) to one or more thresholds and based on the accumulated number of values for the pixel.

The invention relates to the technical field of computer vision, and discloses a datamation intelligent construction method and system. According to the method and system, cross control lines, horizontal lines and space information of a site are obtained through a laser scanner, point cloud data obtained through scanning are obtained, coordinates of intersection points of the cross control lines and the horizontal lines and the relative positions of all the control lines are calculated, a basic layer model is automatically generated according to the point cloud data, geometric information of all the decoration completed surfaces is recognized, and the decoration completed surfaces are obtained. Calculating the density of the point cloud and the three-dimensional coordinates of the basic model, combining the automatically generated basic model, inputting the distance between each decoration finished surface and the basic model, calculating the mean square error of the vertical distance between the finished surface and the basic model and the flatness based on the flatness of the ground, and calculating the angle of the light beam and the coordinates of the decoration finished surface lines; the light beam is automatically adjusted, more than two points on the decoration finished surface are formed on the ground, a finished surface line is formed, and a complete model of the wall surface and the ground is automatically generated through the finished surface line and a set horizontal line.

The application provides a method for generating symmetric lace images based on a generative adversarial network, and proposes an improved model SStyleGAN (Symmetry StyleGAN) based on StyleGAN2 for generating cross-symmetric lace images. In the aspect of the discriminator, in order to strengthen the attention of the proposed model to the symmetry of the image, the method increases the symmetric discriminator, that is, the SStyleGAN adopts a double-discriminator structure; in the aspect of the generator, in order to improve the similarity of the feature maps on the left and right sides of the lace image, the method increases the mean square error loss term based on the loss function of the StyleGAN2; in the aspect of the noise input, in order to control the symmetry of the lace image at lace, lace border and other details, the noise sampling function of the StyleGAN2 model is modified to a symmetric structure, so that the noise input itself has symmetry.