33 results about "Sample distance" patented technology

The invention discloses a multi-scene universal pedestrian re-identification method and system based on scene semantic guidance feature decoupling, and the method comprises the steps: carrying out the standardization processing and feature coding of an input pedestrian image, and generating a global feature containing pedestrian and scene information; through a pedestrian feature encoder and a scene feature encoder which are mutually independent, the global features are decoupled into pedestrian identity features and scene features; splicing the pedestrian identity features and the scene features and then inputting the spliced features into a gating network to generate an adaptive weight value; performing normalization processing on the adaptive weight value to obtain a scene feature weight and a pedestrian feature weight; performing weighted fusion on the decoupling features according to the scene feature weight and the pedestrian feature weight to generate classification features; on the basis of the classification features, a sample distance is calculated by adopting a self-adaptive marginal triple loss algorithm, and classification information is output; and based on the classification information, deploying a training model to a camera through knowledge distillation to realize pedestrian re-identification. According to the invention, the recognition precision in a complex scene is improved.

The invention provides a photovoltaic inspection method and device, electronic equipment and a storage medium, and relates to the technical field of unmanned aerial vehicle photovoltaic inspection, and the method comprises the steps: obtaining the geographic information, photovoltaic array parameters and inspection task parameters of a photovoltaic station; wherein the inspection task parameters comprise inspection time and an expected sampling distance; determining a mirror reflection area of the photovoltaic array according to the geographic information, the photovoltaic array parameters and the inspection time; and by using a heuristic algorithm, based on at least one of the specular reflection area, the photovoltaic array parameters and the expected sampling distance, a determined constraint condition and a cost function, calculating a target shooting point and a target holder attitude of the unmanned aerial vehicle. The accuracy of a photovoltaic inspection result can be improved, and meanwhile, the overall efficiency of photovoltaic inspection is improved.

The invention discloses an X-ray pulsar frequency dynamic estimation method based on chaos learning, and belongs to the technical field of pulsar navigation, and the method comprises the steps: carrying out the SNE adaptive dimension reduction of a pulsar contour waterfall plot through the reconstruction of a high-dimensional space sample distance model, so as to meet the operation requirements of a satellite-borne industrial computer. A difference balance item is introduced into a cross entropy loss function, and the classification regression performance of the model is effectively improved by enhancing the distinction degree of net activity values of positive and negative sample output layers. According to a chaos phenomenon existing in a real neuron, a loss item based on chaos enhancement is designed and newly added. And the most suitable X-ray pulsar frequency is obtained after model screening. The method has the advantages of being suitable for navigating a pulsar source, high in estimation precision, high in estimation stability and the like, and the X-ray pulsar navigation performance can be improved.

The application discloses a boundary sample data enhancement method and device for knowledge distillation and a computer storage medium. The method comprises the following steps: before knowledge distillation is performed, the output of a teacher model is used to modify samples in each original data set along the decision boundary of the teacher model step by step, and a plurality of boundary samples suitable for knowledge distillation are expanded. In each iteration, the original sample or each sample modified in the last iteration is used as a basic sample, the approximate tangent plane of the decision boundary near the sample is calculated by using the output of the teacher model, and the sample is modified along multiple directions on the tangent plane; then, the modified sample is modified to be located near the boundary; finally, a plurality of samples farthest from other basic samples are selected as the result of the modification in the round and the basic samples for the next iteration. The application can meet the demand for data enhancement in current image classifier knowledge distillation.

The application discloses a semantic segmentation model training method, a semantic segmentation method, a device and equipment, relates to the technical field of artificial intelligence, and particularly relates to the technical field of deep learning, semantic segmentation, automatic driving and the like. The method comprises the following steps: determining sample point cloud data corresponding to a sample object from original point cloud data based on a preset down-sampling screening mode; the sample object comprises a compulsory object and a to-be-screened object; performing dimension reduction mapping on sample points in the sample point cloud data based on a preset projection rule to obtain sample distance images corresponding to the sample points; and training a semantic segmentation model according to sample label data corresponding to the sample distance images and the sample point cloud data. Through the above technical scheme, the accuracy of semantic segmentation can be improved.

The present invention discloses a method for dynamic estimation of X-ray pulsar frequency based on chaotic learning, which belongs to the field of pulsar navigation technology, including: performing adaptive dimensionality reduction of the pulsar outline waterfall chart by stochastic neighbor embedding (SNE) by reconstructing a high-dimensional space sample distance model, etc. to meet the requirements of on-board industrial computer operations. A difference balance term is introduced into the cross entropy loss function, and the classification and regression performance of the model is effectively improved by enhancing the discrimination of the net activity values ​​of the positive and negative sample output layers. According to the chaotic phenomenon existing in real neurons, a loss term based on chaos enhancement is designed and added. After model screening, the most suitable X-ray pulsar frequency is obtained. The present invention has the advantages of being suitable for navigating pulsar sources, having high estimation accuracy, and strong estimation stability, and can improve the navigation performance of X-ray pulsars.

The present disclosure provides a model training method, device and electronic device, which relate to the field of computer technology, and in particular to the field of deep learning. The specific implementation scheme is as follows: obtaining labeled samples and unlabeled samples, and labeling the unlabeled samples based on the labeled samples to obtain labeled unlabeled samples; combining the labeled samples and the labeled unlabeled samples to obtain initial labeled samples; calculating the loss value of the semi-supervised loss function based on the sample distance between multiple sample data in the initial labeled samples and the weight ratio between sample data of different label types; updating the weight ratio, and updating the initial labeled sample based on the updated weight ratio until the loss value is less than a preset value, obtaining a target labeled sample based on the updated initial labeled sample; training the preset model based on the target labeled sample to obtain a graph embedding model, which is used to determine the graph embedding features that characterize the risk level of the object to be analyzed.

This invention relates to a method for color matching of architectural coatings based on particle swarm optimization (PSO) algorithm. The method includes the following steps: using a standard color swatch and a colorimeter, under the same light intensity, light angle, and sampling distance, calibrating the basic color of a display one by one; saving the architectural coating color designed using the calibrated display as a standard color and displaying the standard color on this display; adjusting to obtain multiple different standard colorant ratios; iteratively searching for the optimal standard colorant ratio using the PSO algorithm; and outputting the optimal standard colorant ratio. This invention eliminates the industry's reliance on manual experience in color matching, achieving controllable results for the final product without human intervention; making the experimental process highly directional, quickly obtaining satisfactory results with a small number of iterations and very few samples per iteration; achieving color matching results with much higher accuracy than manual color matching; and enabling large-scale application.

A method of coding implemented by a decoding device, comprising obtaining a bitstream; obtaining a value of an indicator for a current block according to the bitstream; obtaining a value of a first parameter for the current block and a value of a second parameter for the current block, according to the value of the indicator and a predefined lookup table; obtaining a value of a sample distance for a sample which is located in the current block, according to the value of the first parameter and the value of the second parameter; obtaining a prediction value for the sample, according to the value of the sample distance for the sample.

A method of coding implemented by a decoding device, comprising obtaining a bitstream; obtaining a value of an indicator for a current block according to the bitstream; obtaining a value of a first parameter for the current block and a value of a second parameter for the current block, according to the value of the indicator and a predefined lookup table; obtaining a value of a sample distance for a sample which is located in the current block, according to the value of the first parameter and the value of the second parameter; obtaining a prediction value for the sample, according to the value of the sample distance for the sample.

This invention discloses an image feature point description method based on sample mixing and an improved ternary loss function, comprising the following steps: S1, keypoint detection is performed on a given image; S2, image patches of the same size are extracted, centered on each keypoint; S3, the extracted image patches are input into a pre-trained convolutional neural network for image feature description, and the feature descriptor vectors of all keypoints are output. This invention considers the diversity of sample distances and utilizes the classification of sample feature vectors to further increase the accuracy of sample feature description, thereby effectively improving the accuracy of image matching.

The invention describes a scanning probe imaging system with the probe held at a small distance from a sample (7) surface of the part during raster-scanning image acquisition. The interaction between the sample (7) and the probe's cantilever arm (17′) is achieved due to microwave near fields formed at the sharp probe tip (18). Due to the near fields, the electrical impedance of the probe depends on the distance between the probe and the sample (7) and on the sample electrical properties, both in the immediate vicinity of the probe tip (18). The microwave detection system senses the electrical impedance of the probe at a set microwave frequency. The probe-sample distance is set and controlled with the use of an optical chromatic confocal displacement sensor as well as with the signals of the microwave detection system.

A method of coding implemented by a decoding device or encoding device, the method comprising obtaining a value of an angle parameter for a current block; obtaining a value of a width of the current block and a value of a height of the current block; calculating a ratio value between the value of the width and the value of height; obtaining a first value according to the value of angle parameter and the ratio value; calculating a sample distance value for a sample in the current block according to the first value; obtaining a prediction value for the sample in the current block according to the sample distance value.

The SVD algorithm separates a clutter subspace, a target subspace and a noise subspace in radar echoes through singular value decomposition, and the purpose of clutter suppression is achieved. However, due to aliasing of the target and the sea clutter, the clutter suppression effect can be affected by clutter subspace division. In order to solve the problem that the clutter subspace is difficult to determine after the radar echo signal is subjected to SVD decomposition, the invention provides a method for adaptively selecting the clutter subspace by using an improved K-means clustering method. Aiming at the problems that K-means is sensitive to the initial centroid and different characteristic parameters are different in the aspects of statistical stability and anti-noise performance, the initial centroid is fixed, and the sample distance is calculated in a weighted mode. According to the method, after four characteristics of singular value distribution, echo component correlation, Doppler bandwidth and relative Doppler variable coefficient are used as K-means input, clutter subspaces are selected in a self-adaptive mode, and the purpose of clutter suppression is achieved by mapping signals into orthogonal spaces of the clutter subspaces.

The invention discloses an efficient estimation method for picture classification confidence. The method comprises the following steps: 1) determining a plurality of reference sampling directions of a to-be-detected picture; 2) generating a reference point according to each reference sampling direction; 3) sampling around each reference point to generate a Gaussian spherical surface; 4) taking the classification accuracy of the sampling points on the Gaussian spherical surface as a discrimination index, and determining the sampling distance of the corresponding reference point; and 5) synthesizing the sampling distances of the reference points to obtain an approximate distance, and mapping the approximate distance into a confidence score of the to-be-detected picture. Compared with an existing adversarial sample method and a Gaussian sampling method, the method has the advantages that fewer sampling times are realized, so that the measurement efficiency is improved, measurement resources are saved, meanwhile, the accuracy of confidence calculation in a high-dimensional space is also kept, and the expenditure of time and hardware resources can be greatly reduced.

An embodiment of the present application discloses a data classification method, apparatus, device, and storage medium. The method includes: obtaining a sample distance set, where the sample distance set includes distances between every two sample data in a sample data set; obtaining a classification distance threshold according to the sample distance set; clustering the data to be classified in a data set to be classified according to the classification distance threshold to obtain a plurality of category sets, where the data set to be classified includes the sample data set. By adopting the above classification method of the present application, when clustering the data set to be classified according to the classification distance threshold, the number of category sets can be dynamically determined according to the distribution of the data to be classified in the data set to be classified, so as to obtain a plurality of category sets, thereby effectively improving the accuracy of data classification.

To provide an apparatus and method for coding and decoding.SOLUTION: A method of coding implemented by a decoding device or an encoding device includes the steps of: obtaining the value of an angle parameter for a current block; obtaining the value of the width of the current block and the value of the height of the current block; calculating a comparison value between the value of the width and the value of the height; obtaining a first value according to the value of the angle parameter and the comparison value; calculating a sample distance value for a sample in the current block according to the first value; and obtaining a prediction value for the sample in the current block according to the sample distance value.SELECTED DRAWING: Figure 20

A method of coding implemented by a decoding device or encoding device, the method comprising obtaining a value of an angle parameter for a current block; obtaining a value of a width of the current block and a value of a height of the current block; calculating a ratio value between the value of the width and the value of height; obtaining a first value according to the value of angle parameter and the ratio value; calculating a sample distance value for a sample in the current block according to the first value; obtaining a prediction value for the sample in the current block according to the sample distance value.

The invention discloses a seal verification and evidence collection system and a seal verification and evidence collection method based on machine learning, and aims to solve the problem of seal authenticity identification. According to the method, real and forged seal images are obtained and marked, samples are expanded through SI FT algorithm operation, and sample data are constructed; a deep twin network is utilized, the deep twin network is composed of two deep neural networks sharing parameters and comprises a feature extraction network of a specific structure and a similarity calculation layer, a contrast loss function is adopted, network parameters are trained through a stochastic gradient descent method, the distance between similar samples is decreased progressively, and the distance between different samples is increased progressively; the system function module covers image acquisition, sample searching, seal verification, rechecking and seal management, and the operation is simple, convenient and efficient. The method has obvious advantages, can improve the print identification accuracy, is suitable for small sample learning, is stable and reliable in system and good in expansibility and safety, and has great application value in the field of print inspection.

The application discloses a kind of X-ray pulsar frequency estimation methods based on swarm optimization, belong to pulsar navigation technical field.The method includes: through waterfall chart folding to observation task, from the consistency of profile signal intensity and segmented phase two aspects to candidate frequency is jointly analyzed;According to the actual sample distribution characteristics reconstruction high-dimensional space sample distance model, nonlinear random neighborhood embedding dimension reduction is carried out to waterfall chart;Three-dimensional image information is converted into two-dimensional plane point group data, and the mean distance origin standard deviation of plane point group is used as the evaluation index of frequency estimation;Combined with the principle of local focusing, the search behavior of scout bees in the bee colony optimization algorithm is improved, and the optimal frequency is efficiently searched;Through simulation comparison with existing methods, the superiority of the method proposed in the application in the performance of pulsar frequency estimation is proved from the aspects of estimation accuracy and operation time.

The application discloses a gradient-prior-based robust bilateral dense feature up-sampling method and application, and belongs to the technical field of image processing. The method comprises the following steps: extracting image features needing up-sampling from a dense prediction network to obtain input feature maps; performing mean value processing on the input feature maps to obtain mean value feature maps; performing gradient mapping on the mean value feature maps to obtain gradient prior features, and arranging the gradient prior of each corresponding point into an up-sampling gradient kernel; performing distance mapping on the relative distance between original pixels and pixels after up-sampling in the up-sampling process to generate distance prior features, and arranging the distance prior features of each corresponding point into an up-sampling distance kernel; combining the distance kernel and the gradient kernel to generate an up-sampling kernel; and finally performing convolution operation between the input feature up-sampling kernels to obtain feature maps after up-sampling of the corresponding input feature maps. The application can overcome the limitation that previous operators need high-resolution feature guidance, and can have multi-task robustness.

A method carried out by a computer for generating a 3D model of an object, the method (100) comprising: obtaining a plurality of first 2D images (2A, 2B) which reproduce respective parts of the object (200), obtaining one or more groups of second 2D images (3A, 3B), wherein for each group of second images: the second images of the same group reproduce respective zones of a portion of the object, each second image being at least partially coincident with another second image of the same group, the second images have a respective second ground sample distance which is less than the ground sample distances of the first images, and at least one of the first images and at least one of the second images of the same group reproduce the same element (ei) of the object. For each group of second images, the method comprises: determining a scaling factor between the first images and the second images of the same group on the basis of the element which is reproduced in at least one of the first images and at least one of the second images of this group, resizing the second images of the group of second images by applying the scaling factor and generating a third image (3) which reproduces the portion of the object by merging the second resized images by means of a stitching algorithm which comprises a transformation function which correlates the points of the second resized images with the points of the third image. The method further comprises storing in a data-storage unit (4) the third image of each group of second images in addition to the plurality of first images, and generating a 3D model (5) of the object in a virtual space by means of a photogrammetry technique on the basis of the plurality of first images and the third image of each group of second images.

The invention relates to a high-throughput testing device and method for electrical properties of a component gradient film material, belongs to the field of material property testing, and solves the problem that a measurement result is wrong due to the fact that a scanning probe easily damages a sample. Comprising a probe device which is located above a to-be-detected sample, comprises a probe and a fixing device thereof and is used for detecting the response of the sample to an external field; the electrical property testing device is used for applying an external field to the sample, collecting response signals detected by the probe and transmitting the collected data to the computer; the displacement device is used for loading a sample and adjusting the position of the sample; the probe-sample distance monitoring device is used for monitoring the distance between the probe and the sample in real time and feeding back the distance to the computer; and the computer is used for controlling the displacement device to stop moving at the moment when the probe is in contact with the sample, and calculating the electrical performance of the sample based on the collected data. The device for testing the electrical properties of the component gradient film can effectively prevent the sample from being damaged, and is high in speed, high in efficiency and accurate in result.

The invention discloses an X-ray pulsar frequency estimation method based on bee colony optimization, and belongs to the technical field of pulsar navigation. The method comprises the following steps: carrying out waterfall plot folding on an observation task, and carrying out conjoint analysis on candidate frequencies from two aspects of contour signal intensity and segmented phase consistency; reconstructing a high-dimensional space sample distance model according to actual sample distribution characteristics, and performing nonlinear random neighborhood embedding dimensionality reduction on the waterfall plot; the three-dimensional image information is converted into two-dimensional plane point group data, and the average distance original point standard deviation of a plane point group is adopted as an evaluation index of frequency estimation; the reconnaissance bee exploration behavior in the bee colony optimization algorithm is improved in combination with the local focusing principle, and the optimal frequency is efficiently searched; compared with an existing method, the method provided by the invention is proved to have superiority in the aspect of pulsar frequency estimation performance from the aspects of estimation precision, operation duration and the like.

The invention provides an inspection equipment remote sensing data recording method, system, equipment and medium, and the recording method comprises the steps: obtaining inspection task data of inspection equipment, and generating a sampling frequency based on the inspection task data; based on route planning information in the inspection task data, controlling the inspection equipment to fly so as to acquire remote sensing data, and acquiring coordinate data of the inspection equipment in real time according to the sampling frequency; calculating a sampling distance between the inspection equipment at the current sampling moment and the current inspection target according to the coordinate data; and based on the sampling distances of all the sampling moments, calculating a deflection value of the current sampling moment, calculating a difference value between the deflection value of the current sampling moment and the deflection value of the previous sampling moment, and when the difference value is smaller than or equal to a preset deflection threshold value, recording remote sensing data of the current inspection target collected by the inspection equipment. According to the invention, a specific inspection target can be identified from an inspection flight task, and collected remote sensing data records can be independently stored.

The present application relates to a kind of semi-supervised image classification method based on uncertainty selection and contrast learning, belong to image processing technical field.Firstly, the present application selects those high confidence unlabeled data for model training by measuring the uncertainty of model, reduces the problem that model precision is not high due to the pseudo-label noise caused by lack of labeled information;Secondly, by contrast learning, to close positive sample distance, push far negative sample, to obtain better representation information;Finally, maintain a feature prototype for each category, by calculating the distance between unlabeled data representation and feature prototype to assign more correct pseudo-label, while good representation obtained by contrast learning is used to update feature prototype after uncertainty selection, to form virtuous cycle.The experimental results on two public datasets show that the present application algorithm has good classification performance.

The invention mainly provides a bistable detection and regulation method for an atomic force microscope. The method comprises the following steps: establishing a nonlinear dynamic model of an atomic force microscope probe; setting parameters according to AFM experiment conditions; performing numerical solution on the kinetic equation by adopting a four-order Runge-Kutta method to obtain a steady-state amplitude and phase response curve of the probe under different probe-sample distances; the kick behavior in the amplitude and phase response curve is analyzed, the occurrence interval of the bistable region is recognized, and kick represents irreversible transition or sudden change of the amplitude and the phase; and outputting a regulation and control suggestion, and adjusting at least one parameter to enable the system to work in a non-bistable interval. According to the technical scheme, through nonlinear dynamic modeling, multi-parameter collaborative optimization and intelligent feedback regulation and control, remarkable beneficial effects are shown in the aspects of bistable suppression and imaging quality improvement of the atomic force microscope in different scenes.

The invention discloses an extreme weather prediction method and system, and relates to the technical field of artificial intelligence. The method comprises the following steps: collecting multi-modal meteorological observation data; performing space-time alignment and quality correction to obtain an assimilation data set; adjusting a feature extraction weight based on a quality identifier, and projecting the assimilation data set to a low-dimensional hidden space to obtain a hidden space feature vector; based on the sample distance measurement of the hidden space, adopting a meta-learning framework to carry out multi-task prediction on the feature vector of the hidden space; performing multi-target collaborative optimization and antagonism training on the neural network by using the prediction result to obtain a prediction model; and verifying the prediction result by using a digital twin simulation environment to obtain a verification result, and updating model parameters of the prediction model. According to the method, the problem of insufficient prediction precision caused by a complex coupling relationship of meteorological factors and data isomerism is effectively solved, and the accuracy and reliability of extreme weather evolution trend prediction are improved.

A method of coding implemented by a decoding device, comprising obtaining a bitstream; obtaining a value of an indicator for a current block according to the bitstream; obtaining a value of a first parameter for the current block and a value of a second parameter for the current block, according to the value of the indicator and a predefined lookup table; obtaining a value of a sample distance for a sample which is located in the current block, according to the value of the first parameter and the value of the second parameter; obtaining a prediction value for the sample, according to the value of the sample distance for the sample.

The invention provides a resting human body recognition method based on a civil millimeter wave radar and a related device. The civil millimeter wave radar transmits a plurality of frames, and each frame comprises a plurality of chirp signals. The resting human body recognition method comprises the following steps: determining the maximum Doppler velocity of an effective target of each sampling distance in the frame through echo data of a plurality of chirp signals in the same frame, and calculating the sum of the maximum Doppler velocities of each frame at the same sampling distance; performing distance fast Fourier transform on the echo data of the chirp signals of the plurality of frames and accumulating the echo data to obtain inter-frame sampling data; and based on the inter-frame sampling data, identifying a resting human body from each sampling distance in which the sum of the maximum Doppler velocities of each frame is not greater than a threshold value. According to the invention, the method can achieve the recognition of the resting human body through a small amount of data and simple calculation.