532 results about "Distance based" patented technology

The invention belongs to the technical field of intelligent traffic, and discloses a road vehicle speed and distance detection method, system and device based on unmanned aerial vehicle vision. The method comprises the steps of tracking a vehicle in a to-be-processed video aerially photographed by an unmanned aerial vehicle in real time through an improved YOLOv11 network and a BotSort algorithm to obtain a vehicle trajectory, and converting a vehicle pixel coordinate detected by each frame into a world coordinate in combination with a conversion matrix H of the pixel coordinate and the world coordinate to form a trajectory sequence of the vehicle in the world coordinate system; and for a certain vehicle i, according to the pixel coordinates at the t-th moment and the (t + t)-th moment in several continuous video frames, corresponding world coordinates are obtained through the conversion matrix H, the displacement between two points is calculated according to an Euclidean distance formula, and the average speed of the vehicle in the time period is calculated. According to the invention, efficient, stable and reliable vehicle speed measurement and vehicle distance calculation can be realized.

The invention discloses an aircraft 4D trajectory prediction method and system based on double-attention space-time diagram convolution, and belongs to the technical field of intelligent time sequence prediction. According to the method, the self-attention mechanism is utilized to reconstruct the predefined adjacent matrix, and optimization is continuously carried out along with network training so as to improve generalization of the network. The problem that the distance-based predefined adjacency matrix cannot fully reflect the potential relationship between the aircrafts in the dynamic scene is effectively solved. On the basis of a learnable adjacency matrix based on a self-attention mechanism, the correlation between nodes is further aggregated by using the graph attention network, and additional feature extraction is performed on the space-time diagram based on the powerful global information aggregation capability of the graph attention network, so that the model can capture more potential relationships between the nodes, and the accuracy of feature extraction is improved. And the problem that the correlation between the nodes cannot be effectively aggregated by the traditional graph convolution operation is improved. And the prediction accuracy of the future trajectory of the aircraft is further improved.

The invention relates to a UWB-based man-machine real-time positioning method in a long-distance tunnel hole. The method comprises the following steps: S1, collecting original ranging information of integrated signal characteristics; s2, correcting an original distance based on signal quality; s3, carrying out NLOS signal identification based on SVM (Support Vector Machine); s4, NLOS ranging error elimination based on an error distribution fitting model; s5, preliminarily resolving a tag position stake number; s6, label position correction based on Kalman filtering; and S7, determining a man-machine position based on label matching. According to the invention, the UWB positioning system is used for positioning and tracking personnel machinery in a hole, so that real-time transmission and analysis of man-machine position pile number information in the hole are realized, and management personnel can timely and accurately master man-machine operation positions; according to the man-machine real-time positioning method, the influence of the complex construction environment in the tunnel hole is reduced, and the man-machine positioning precision and stability in the tunnel hole are effectively improved.

The invention discloses a crowd clustering analysis method, system and device based on spatio-temporal data. The method comprises the following steps: acquiring spatio-temporal data; performing feature processing on the spatio-temporal data to obtain a feature number, and constructing a spatio-temporal data matrix based on the feature number; performing dimension reduction on the spatio-temporal data matrix through a preset analysis algorithm to obtain a data matrix; according to a preset point in the data matrix, the volume of a preset radius with the preset point as the center and the point number in the radius are calculated, and the local density is calculated based on the point number in the radius and the volume; calculating the distance between each point in the data matrix and the nearest target point, and selecting a target neighborhood radius based on the distance and the local density; determining a data dimension based on the number of features, and setting a minimum point number through the data dimension; marking each point in the data matrix through a density clustering algorithm according to the radius of the target domain and the minimum point number to obtain a clustering result; and analyzing features of clustering results based on the plurality of clustering clusters.

The invention discloses a multi-level hybrid obstacle avoidance control method adaptive to environment complexity, and relates to the technical field of robot control, and the method comprises the steps: obtaining the global map information of an inspection environment, dividing a map into grid units, marking static obstacles, and calculating a global path of an inspection robot from a starting position to a target position through an A * algorithm; position and speed information of a dynamic obstacle is obtained in real time through a laser radar, a gravitational field model and a repulsive force field model are established, a gravitational field is generated by a target point, and a repulsive force field is generated by the detected dynamic obstacle. According to the invention, by establishing an obstacle classification mechanism based on the distance threshold, quantitative evaluation of the threat degree is realized, and the problem of low control efficiency caused by adopting a unified processing strategy for all obstacles in a traditional method is avoided.

The invention relates to an abnormal data analysis method and device, computer equipment and a readable storage medium. The method comprises the steps of obtaining multi-dimensional time sequence data at different time points, converting the multi-dimensional time sequence data into a multi-dimensional time sequence vector, determining the distance between the multi-dimensional time sequence vector and a reference distribution vector at each time point, constructing a one-dimensional time sequence matrix based on the distance based on the distance corresponding to each time point, and obtaining a one-dimensional time sequence matrix based on the one-dimensional time sequence matrix. And determining a Z score value of each data point in the one-dimensional time sequence matrix, and identifying an abnormal value in the data points based on the Z score value of each data point. By adopting the method, the abnormal value in the multi-dimensional time sequence data can be efficiently and accurately identified.

A system for navigation store, in a time-based buffer, a first set of frames acquired by a sensor; stores, in a distance-based buffer, a second set of frames acquired by the sensor, performs moving object segmentation on the first set of frames and the second set of frames to identify at least one moving object in a scene of the frames; predicts a trajectory of the at least one moving object; and performs a navigation function based on the predicted trajectory.

The embodiment of the invention provides an underground pipeline extraction method, system and device based on point cloud and a storage medium, and belongs to the technical field of point cloud space geometry extraction. According to the scheme, underground pipeline point cloud data are obtained; segmenting the pipeline point cloud data to obtain a segmentation result; when the segmentation result is a single-pipe scene, principal component analysis and cylinder fitting are carried out based on all pipeline point cloud data to obtain a normal vector and a pipeline radius of each data point; performing plane cutting according to the normal vector to obtain a tangential plane, and obtaining a pipeline center line based on the tangential plane; determining a distance threshold parameter according to the radius of the pipeline; based on the distance threshold parameter, performing segmented straight line fitting on the pipeline center line through a random sampling consistency algorithm to obtain a center line point set; performing feature extraction on the center line point set to obtain feature points; determining a connection relationship of adjacent feature points according to the geometrical relationship; the pipeline reconstruction model obtained based on the connection relation can be suitable for complex scenes, and the calculation efficiency is improved.

This document relates to distance-based estimation of energy propagation variation in synthetic three-dimensional scenes. For example, the disclosed implementations can detect geometric features, such as outside corners or portals, based on a distance field that identifies distances from points in a scene to the nearest geometry in the scene. Then, energy propagation variation within the scene can be estimated based on the locations of the geometric features. Energy propagation variation can be employed for a range of applications, such as deploying sampling probes within a given scene and simulating energy propagation to / from the probes within the scene.

The invention discloses a complex roadway network center line calculation method based on skeleton contraction, belongs to the technical field of underground mine three-dimensional modeling and point cloud data processing, is used for complex roadway network center line calculation, and comprises the following steps: establishing a neighborhood set of KDTree acquisition points for underground mine roadway point cloud data; calculating geometric features and neighborhood distances of the points according to the neighborhood point set; iteratively shrinking the underground mine roadway point cloud data; skeleton refinement is carried out according to geometric features of each shrinkage skeleton point, and discrete noise points are removed by combining an octree filtering method; processing the intersection area point set by using a principal component method and a DBScan algorithm, judging the type of the intersection, and performing center point refined calculation on each intersection; and the disordered center points are fitted into an ordered center line. According to the method, the integral roadway center line of underground mine well and roadway engineering can be accurately calculated, complex structural characteristics of crossing and staggering are overcome, and refined calculation is achieved for different roadway intersection types.

The invention relates to a multi-modal perception fusion target following method and system. The method comprises the following steps: adopting an improved KCF algorithm to realize a closed-loop process of target tracking, multi-scale space construction, feature fusion, response calculation, optimal scale decision and model updating; designing a four-level shielding processing mechanism fusing motion prediction and depth verification, and realizing tracking recovery in a shielding scene through shielding judgment, motion prediction, fine search and template protection; constructing a target distance mapping function fusing geometric distortion correction and attitude compensation, and realizing high-precision distance estimation based on monocular vision; laser radar point cloud information is integrated, an obstacle threat degree model is constructed, and cooperative path planning of following and obstacle avoidance is realized in combination with an improved TEB algorithm; and designing a linear velocity control law and an angular velocity control law based on the distance deviation and the azimuth angle deviation, and driving the robot to complete target following motion. According to the invention, high-precision and robust following of the robot to the target can be realized.

Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and / or the like for a predictive data analysis system that is configured to rank one or more candidate entities. A machine learning model is trained to rank the one or more candidate entities for initiating the performance of one or more prediction-based actions based on one or more sets of a plurality of clusters generated based on population data merged with ancillary data, and an association of location data with external domain data. The plurality of clusters is generated by generating embeddings for one or more features associated with a plurality of entities selected for clustering and determining a similarity score for entity pairs selected from the plurality of entities based on a distance function and the embeddings.

The invention relates to the technical field of probe cards, and particularly discloses a probe card stroke compensation system and method, and the method comprises the steps: analyzing the distance value of each probe in a probe card, obtaining a distance characterization value WB, judging whether the abnormal degree of the probe card generates an adjustment signal or not based on the distance characterization value WB, and adjusting the stroke of the probe card based on the adjustment signal. The method comprises the following steps: applying test pressure to a single probe at a fixed rate, analyzing the change trend of a distance value along with the increase of the test pressure, judging whether the change of the distance value of the probe along with the increase of the test pressure is linear or not, and selecting an appropriate model as a prediction model based on the judgment result of whether the change of the distance value of the probe along with the increase of the test pressure is linear or not. According to the invention, the distance standard value can be adjusted in time according to the actual monitoring condition, and the pressure during the probe stroke compensation can be correspondingly adjusted, so that the problem caused by the overlarge difference between the actual distance value and the predicted distance value can be effectively solved, and the normal work of the probe card and the accuracy of the test effect can be ensured.

The invention belongs to the technical field of point cloud registration, and particularly relates to a point cloud registration method based on geometric information. Obtaining source point cloud data and target point cloud data; step 2; extracting geometric features of the source point cloud and the target point cloud, wherein the geometric features comprise normal vectors, curvatures and shape contexts of points; a third step; performing feature matching based on the extracted geometric features to obtain a matching point pair set; step 4; calculating a transformation matrix between the point clouds by using the matching point pair set; (5) carrying out drying; and optimizing the transformation matrix to realize accurate registration of the point cloud. According to the method, geometric information is used for registration, and compared with a traditional distance-based registration method, the dependence on the initial position is low, and noise and partially overlapped point clouds can be better processed.

The present application provides a federated learning system, a feature selection method and device in the federated learning system, the system includes at least a first participant and a second participant, the first participant holds a first feature of a sample and a sample label, and the second participant holds a second feature of the sample; the first participant is configured to: calculate the first distance between each sample in the joint sample set and the central sample based on the first feature, and obtain the second distance between each sample in the joint sample set and the central sample calculated by the second participant based on the second feature; update the first distance based on the second distance to obtain the comprehensive distance between each sample in the joint sample set and the central sample; screen out the first similar sample and the first heterogeneous sample based on the sample label and the comprehensive distance; update the weight of the first feature, and screen the first feature. The present application improves the accuracy of the first participant in feature selection of the first feature it holds.

The invention discloses an efficient frequency domain enhanced traffic sign detection method suitable for a snowy city scene, and belongs to the technical field of computer vision and intelligent traffic. According to the efficient frequency domain enhanced traffic sign detection method suitable for the snowy city scene, by designing a frequency domain compensation enhancement module, capture and fusion of multi-scale frequency domain information are achieved, and therefore the feature representation capacity and the model generalization performance are improved. According to the method, the YOLOv5 is used as a basic model for construction, the OfficientViT is used as a backbone network for feature extraction, the problem that the feature representation ability and generalization of a traditional model in snowy days are reduced is solved through a different-frequency feature complementation method, and meanwhile a loss function is optimized based on the Wasserstein distance and the thought of Gaussian reweighting. According to the method, different frequency features can be effectively complemented and enhanced, the feature representation capability in a snowy day scene is improved, and the provided FENet has good effectiveness and robustness in snowy day traffic sign detection.

The invention discloses a mine car obstacle recognition and distance measurement method and device and a storage medium. The method comprises the steps of constructing a segmentation template, marking image feature points, extracting an obstacle contour line, performing coarse and fine segmentation on a target obstacle based on the intersection point proportion of a background segmentation surface and the obstacle contour line, and determining a contour segmentation area of the target obstacle; the method comprises the following steps: marking point cloud feature points, constructing an obstacle template, carrying out matching mapping on a target obstacle and the obstacle template by adopting a non-rigid iterative nearest point algorithm, correcting feature point offset in a matching process in combination with a KD-Tree method, and calculating to obtain point cloud parameters of the target obstacle. And identifying the type of the target obstacle and measuring the distance according to the contour segmentation region and the point cloud parameters. According to the method, the target obstacle image and the point cloud information are combined, the target obstacle is segmented according to the intersection point proportion, the fuzzy area is smoothly segmented, the point cloud parameters are measured while the target obstacle is segmented, and the purpose of identifying the type and the distance of the target obstacle is achieved.

A plasma processing apparatus includes a mounting table, an acquisition unit, a calculation unit, and an elevation control unit. The mounting table mounts thereon a target object as a plasma processing target. The elevation mechanism vertically moves a focus ring surrounding the target object. The acquisition unit acquires state information indicating a measured state of the target object. The calculation unit calculates a height of the focus ring at which positional relation between an upper surface of the target object and an upper surface of the focus ring satisfies a predetermined distance based on the state of the target object that is indicated by the state information acquired by the acquisition unit. The elevation control unit controls the elevation mechanism to vertically move the focus ring to the height calculated by the calculation unit.

The invention discloses a multi-modal large model reasoning acceleration method based on token variation discarding, and relates to the field of computer vision and artificial intelligence. The method comprises the following steps of: firstly, identifying an inert token with relatively small change amplitude by analyzing representation change of a visual token among layers of a large language model; secondly, designing a token variation measurement module based on an L2 distance, and quantifying the importance degree of each visual token; besides, a progressive discarding strategy is adopted, the visual tokens with low variation are gradually removed from a plurality of preset levels, and the problem of position deviation is avoided; and finally, by reserving a key visual token with high variation, the calculation complexity is remarkably reduced while the model performance is maintained, and the reasoning speed is increased. The method is completely compatible with a high-efficiency attention mechanism, does not need extra attention weight calculation, is mainly applied to the fields of intelligent question answering, video understanding, multi-modal content generation and the like, and has a wide application prospect.

Methods, systems, and apparatus for encoding a magic state in a surface code patch of physical qubits with a target distance. In one aspect, a method includes performing a first surface code cycle on a surface code patch of physical qubits with an initial distance to encode the magic state into the surface code patch. Performing the first surface code cycle introduces a hook error associated with a four-body stabilizer on a qubit included in the surface code patch, where the hook error rotates a logical observable of the surface code patch. Further, performing the first surface code cycle includes initializing the qubit in the magic state. One or more rounds of error detection are performed on the surface code patch that encodes the magic state. The surface code patch is expanded to the target distance based on results of the one or more rounds of error detection.

The invention relates to a lane group division method and device, equipment, a storage medium and a vehicle, and relates to the technical field of data processing. The lane group division method comprises the following steps: acquiring position information of a plurality of track points in a preset area; determining the distance between each track point in the plurality of track points and a preset road center line to obtain a distance sequence, and determining k reference segmentation positions based on the position information of the plurality of track points; the reference segmentation position is used for segmenting a plurality of track points, and k is a positive integer; and determining k target segmentation positions based on the distance sequence and the k reference segmentation positions, and dividing a preset area based on the k target segmentation positions to obtain a plurality of lane groups. And dividing the lane group by using the public source track, so that the divided lane group is close to a real lane group.

The invention discloses a multi-grid interpolation method and device for an unstructured grid in an aircraft simulation process, equipment and a storage medium, and relates to the technical field of fluid calculation research, and the method comprises the steps: determining a coarse grid interpolation unit having a common point with a to-be-interpolated fine grid unit based on the topological relation of the unstructured grid of an aircraft simulation model; determining a first central point and a first central point coordinate of the fine grid unit to be interpolated, and a second central point, a second central point coordinate and a corresponding first physical quantity value of the coarse grid interpolation unit, and determining a central point distance based on the first central point coordinate and the second central point coordinate; determining a first interpolation coefficient by using a target pseudo Laplace operator and based on the distance between the first physical quantity value and the central point; and normalizing the first interpolation coefficient to obtain a second interpolation coefficient, and interpolating the fine grid unit to be interpolated by using a second physical quantity value determined based on the second interpolation coefficient and the first physical quantity value. In this way, the robustness of the interpolation of the unstructured grid can be improved.

The invention discloses a business question answering method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining source domain and target domain data sets corresponding to new and old businesses of an electric power business hall, and extracting subsets to form a differential training set; determining a semantic association distance based on the difference between the vocabulary feature vector and the word vector, and obtaining a clustering cluster semantic association difference analysis value in combination with the similarity between the inter-cluster vocabulary semantic association distance and the text topic vector after the word is clustered; the vocabulary topic distribution conditions of different data set clustering clusters and the analysis values are fused, and the overall semantic feature values of the vth topic of the source domain and the kth topic of the target domain are calculated; determining attention weight and establishing a matrix, and generating a migrated intelligent language model by combining the two types of data sets; and answering can be obtained by inputting the questioning service text. The method can improve the accuracy of the output reply of the intelligent language model.

The invention provides a vibration acceleration monitoring point clustering optimization method and system for a satellite mechanical test, and the method comprises the steps: obtaining initial data of a frequency response function of each vibration acceleration monitoring point of a satellite through a dynamic test, carrying out the standardization and merging, and obtaining the final data of the frequency response function; dividing the vibration acceleration monitoring points with similar dynamic characteristics into a cluster by taking data correlation as a clustering distance based on a k-means clustering algorithm; classifying the clusters according to the number of the measuring points in the clusters, and determining reserved measuring points of each cluster and cutting measuring points of each cluster according to the correlation of each vibration acceleration monitoring point in each cluster; the number of the reserved measuring points is determined by calculating the redundant correlation coefficient between the cutting measuring points of each cluster and the reserved measuring points in the same cluster and the independent correlation coefficient between the reserved measuring points of each cluster, so that the information independence of the reserved measuring points and the information redundancy of the cutting measuring points are ensured, the cutting method is quantified, the measuring point cutting result is more reliable, and the measurement accuracy is improved. And the efficiency of a ground environment test link is improved.

The invention provides a cable-type temperature-sensing fire detection method and system with an intelligent positioning function, and relates to the technical field of artificial intelligence, and the method comprises the steps: laying an optical fiber temperature-sensing cable along a preset path, obtaining the real-time three-dimensional coordinates of a temperature measurement point through employing a reflective mark point and a multi-view three-dimensional reconstruction technology, enabling the temperature data to be correlated with the coordinates to form a temperature field data set, and obtaining a temperature field data set; and generating three-dimensional temperature field grid data by adopting a weight optimization method based on distance attenuation, and giving temperature early warning and positioning information according to the three-dimensional temperature field grid data. According to the invention, accurate positioning and real-time early warning of temperature abnormity at the early stage of the fire disaster are realized, and the accuracy and response speed of fire disaster monitoring are improved.

The invention relates to a credibility evaluation method, device and equipment for an equipment digital model. The method comprises the following steps: aiming at any one output index in a plurality of output indexes related to equipment digital model credibility evaluation, under the same working condition, carrying out simulation operation on the digital model for multiple times, and carrying out tests on real equipment for multiple times to respectively obtain a group of experimental data of the output index; calculating the coincidence degree of the two groups of experimental data, and designing a credibility distance based on the coincidence degree; constructing a vector of a distance value on each dimension according to the credibility distance corresponding to each working condition; calculating an average value of the distances according to the vectors of the distance values on each dimension, and calculating the initial credibility of the equipment digital model by using the average value; and calculating a comprehensive distance according to the initial credibility of the equipment digital model under the plurality of indexes, and calculating the credibility of the to-be-evaluated equipment digital model by using the comprehensive distance. By adopting the method, the credibility evaluation of the equipment digital model can be realized.

The invention discloses an incomplete multi-mode smooth contrast clustering method based on information interpolation, which comprises the following steps of: firstly, modeling a missing view into multivariate Gaussian distribution based on distance weighted nearest neighbor by utilizing a view interpolation mechanism based on statistical information, and carrying out interpolation on the missing view to obtain a complete multi-view data set; secondly, using an encoder to extract potential features, capturing global structure information of multiple views through an FFN-Attention-FFN structure, and extracting local structure information of the multiple views through a graph convolutional network; thirdly, reconstructing a view by using a graph decoder; and finally, generating a clustering distribution result by using the MLP. According to the method, a view interpolation mechanism based on statistical information is introduced, the influence of a weak correlation view on a completion result is reduced by introducing distance weighting, and the data recovery quality is improved; the FFN-Attention-FFN structure is combined with the graph convolutional network, so that the global and local structure information of the data can be effectively captured; and negative sample pairs are expanded by adding Gaussian noise, so that sample distribution is smoother.

The invention relates to the technical field of artificial intelligence, and provides a tensor processing method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: determining the shape of a first physical tensor based on the shape of a logic tensor; under the condition that the first dimension of the first physical tensor exceeds the dimension limit, splitting the first physical tensor into a plurality of second physical tensors with the same size, and determining a tensor distance based on the shapes of the second physical tensors; traversing all the second physical tensors, and executing the following operations in the traversing process: obtaining tensor data corresponding to the currently traversed second physical tensor based on the index and tensor distance of the currently traversed second physical tensor, and calling the operator library interface to process the tensor data to obtain a processing result. According to the method, the operator library interface is cyclically called, so that a plurality of physical tensors are processed, the operator library interface does not need to be modified on a large scale, and the modification workload is greatly reduced.

Aiming at a traditional data-driven regional power grid reinforcement learning optimization scheduling scene, a deep reinforcement learning optimization scheduling strategy based on data intelligent enhancement is provided, that is, training data is enhanced through a Wasserstein distance-based conditional generative adversarial network gradient penalty method; more effective training is provided for formulating a more accurate and more reliable power grid dispatching strategy, and convergence of a near-end strategy optimization algorithm is accelerated. The result shows that the scheduling decision of the method is closer to the scheduling result with known global information in the future, and the strategy scheduling decision is obviously superior to that of a traditional method. According to the method, the problems that historical data used for training models in existing research often cannot completely cover various actual scenes in the day, or although the historical data can cover the scenes, the data volume is huge and mixed, and the maximization of the training effect is limited are solved.

The invention provides a key point path planning method and device based on distance transformation, and the method comprises the steps: converting a grid map of a target region into a distance transformation map based on a distance definition method; a distance maximum value point is extracted from the distance transformation map to serve as a candidate key point, the candidate key point is screened to obtain a global key point, and at least two contact points exist between a circle generated with the global key point as the circle center and the distance value of the global key point as the radius and a grid representing a non-passing area; and constructing a connection relationship between the global key points, and searching and determining a navigation path based on the connection relationship between the global key points by using a # imgabs0 # algorithm. According to the method, the global key points are screened in the distance conversion map, and path search is performed based on the connection relation between the global key points, so that a more efficient robot path planning algorithm is realized.