429 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 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.

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.

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.

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 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.

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.

Systems and methods are disclosed for identifying relationships between complex datasets and / or high-dimensional datasets for predictive modeling. The method includes clustering data associated with one or more entities in a first dataset based on distance data; clustering the data associated with the one or more entities in a second dataset based on longitudinal data; consolidating the first dataset and the second dataset into a third dataset based on weights assigned to one or more edges between one or more nodes in the first dataset and the second dataset; generating a diagnosis space indicating a condition of the one or more entities based on the third dataset; and determining, via input of the diagnosis space into a machine learning model, an optimization of a weighting scheme for assigning weights to one or more features within the longitudinal data.

The invention discloses an online vectorization high-precision map generation method based on point features, which is characterized in that real-time high-quality generation of an online vectorization high-precision map is realized by utilizing a Point MapNet network, and the Point MapNet network is obtained by improving a BEV feature coding module and a map element decoding module of an original MapTR network; the BEV feature coding module is improved in the following steps: replacing BEV features sampled at fixed positions with position learnable point features, naming the improved BEV coding module as a point feature coding module, enabling the point features to learn a spatial position containing a detection object in a sensing area through bipartite graph matching and distance loss calculation, and updating the position of the point features; the map element decoding module is improved as follows: attention masks based on distance are used, so that map element features are only interacted with point features of a near space. Through the improvement, the reasoning speed is increased and the training cost is reduced while higher map generation quality is achieved.

The invention discloses a multi-aircraft cooperative autonomous navigation method in a satellite denial environment, which comprises the following steps of: constructing a measurement edge network adjustment model, reducing a distance estimation error by utilizing an inherent distance constraint in a cluster topology network, and generating a high-precision distance measurement network in real time; cooperative relative positioning is carried out based on a distance measurement adjustment theory, cluster global optimal positioning is realized by fully utilizing a distance network under a measurement edge network adjustment model, and the realization range of cooperative positioning in local connection topology is expanded while the positioning precision and robustness of a cluster system are improved; based on a multi-dimensional scaling technology and a coordinate registration technology, a two-stage cooperative positioning framework based on TOSA is constructed, and high-precision positioning of a multi-aircraft cluster absolute space coordinate system is realized. According to the method, the cluster positioning precision is improved by effectively utilizing distance network information formed by paired relative distance measurement.

The invention provides a method, system and device for restoring a defective mural in a historical and cultural scenic area by using AI, and relates to the technical field of data restoration, and the method for restoring the defective mural in the historical and cultural scenic area by using AI comprises the steps: collecting a to-be-restored defective mural image, a complete mural image and a historical image set of the defective mural image; performing normalization processing on the historical image set and dividing the historical image set into a training set and a test set; and constructing a network model based on the self-attention encoder and the self-attention decoder. The self-attention encoder is used for obtaining a global dependency relationship and calculating a weighted feature map based on distance dependency. And training the network model by adopting the training set to obtain an optimal recovery model. And inputting the defective fresco image into the optimal restoration model, and outputting a restored fresco. By constructing the network model based on the self-attention encoder and the self-attention decoding, the bottleneck problems of structural distortion, fuzzy details, incoherent vision and the like during restoration of the defective fresco are solved.

The invention provides a cable force detection method, device and system for a cable bearing bridge, and relates to the technical field of bridge monitoring. The method comprises the following steps: acquiring an echo signal of an inhaul cable in a to-be-detected bridge; constructing a corresponding radar cube matrix according to the echo signal; peak value searching is carried out on the signal amplitude of the signal data under the distance dimension in the radar cube matrix, the distance index of each peak value point on the distance dimension is determined, and the distance index is used as the distance index corresponding to each inhaul cable; based on the distance index and the radar cube matrix, incident angle information corresponding to each inhaul cable is determined; and based on the distance index and the incident angle information corresponding to each inhaul cable, determining an enhanced signal corresponding to each inhaul cable by using a beam forming technology. According to the invention, the signal data of each inhaul cable can be effectively separated, the signal data precision of each inhaul cable is improved, and the cable force detection precision is further improved.

The invention belongs to but is not limited to the technical field of big data, and particularly relates to a high-dimensional function solving method and system based on a distance decision wolf pack algorithm. The improved algorithm realizes significant optimization in the aspects of migration behavior, call behavior, purse behavior, population update and the like. Experimental results show that the improved wolf pack algorithm is obviously improved in solving precision in a low-dimensional single-peak function compared with an original algorithm, and meanwhile, the solving precision of a high-dimensional multi-peak function is further improved. In addition, the algorithm also has the characteristics of good global convergence, high operation speed and the like, and is excellent in performance on a plurality of standard test functions. In the theoretical level, the convergence of the algorithm is deeply analyzed by using the non-aftereffect characteristic of the Markov chain, and the population sequence of the improved wolf pack algorithm is proved to be traversal through mathematical derivation, so that the algorithm can be converged to the global optimal solution of the problem to be solved with the probability 1.

The invention discloses an incremental sample screening method for power grid transient stability discrimination model training. The method comprises the steps of obtaining a basic sample set based on a plurality of initial operation modes of a power grid; obtaining a to-be-selected sample based on the generated power grid operation mode; calculating the distance between the to-be-selected sample and each basic sample in the basic sample set; constructing a neighbor sample subset of the to-be-selected sample based on the distance; calculating a neighbor distance between the to-be-selected sample and the neighbor sample subset; judging whether the to-be-selected sample is an incremental sample based on the neighbor distance; and training the power grid transient stability discrimination model by adopting the incremental sample. The screening of the incremental samples only depends on time domain simulation and distance calculation, the identification difficulty of the incremental samples can be greatly reduced, and the data requirement of the artificial intelligence model training for the transient stability discrimination of the power grid can be effectively reduced by identifying the key samples with important value for stability discrimination.

The invention discloses a structured data anomaly detection method and device. The method comprises the steps that multiple pieces of structured data in a to-be-detected data set are acquired; for each piece of structured data, detecting the structured data by using multiple groups of first-layer base models to obtain a first anomaly detection score output by each group of first-layer base models, each group of first-layer base models including a base model based on distance, density and a neural network; the first anomaly detection score output by each group of first-layer basis models is analyzed by using a second-layer basis model to obtain a corresponding second anomaly detection score, and the second-layer basis model comprises a basis model based on a support vector machine and a basis model based on a local outlier factor algorithm; and determining abnormal structured data in the to-be-detected data set according to the second abnormal detection score. According to the method and the device, the technical problems of relatively high manpower and time cost and relatively low accuracy when the abnormal structured data is detected in a manual mode are solved.

The invention relates to the technical field of typhoon analysis, and discloses a typhoon path prediction method and system based on a comprehensive standard and computer equipment, and the prediction method comprises the steps: dividing the whole year into at least two seasonal sections according to the weather characteristics of a predicted target, and carrying out the first-stage screening of historical typhoon data according to the seasonal sections; defining a geographic area by taking the prediction target as a center, giving a weight, and carrying out second-level screening; key factors are comprehensively considered based on distance, wind direction and wind speed similarity; then flexibly adjusting the weight of each factor according to typhoon characteristics by applying a dynamic weight distribution formula, and generating a comprehensive similarity score; and finally, selecting a historical typhoon path with the highest score, predicting a current typhoon moving track and an influence range, and accurately and efficiently providing a reliable basis for disaster prevention and reduction so as to prevent typhoon hazards.

A smart mirror system is provided, comprising a mirror, a camera, and a processor in communication with the camera and the mirror. In use, an image of a face is received for performing facial recognition. Based on the facial recognition, at least one of a plurality of users of the mirror is identified, for tailoring operation of the mirror for the at least one user.

The present invention belongs to the field of power distribution technology and relates to a method for identifying electricity theft users in low-voltage power distribution areas based on an improved whale optimization algorithm, which includes the following steps: calculating the calculated value of the total power consumption of the power distribution area within a time period; establishing an objective function by using the calculated value of the total power consumption of the power distribution area and the measured value of the total power consumption of the power distribution area; solving the objective function through the improved whale optimization algorithm; and analyzing the power loss rates of each user obtained by the solution by using a distance-based outlier detection algorithm, and outputting the users suspected of electricity theft. The present invention improves the traditional whale algorithm by introducing a dynamically changing convergence factor, a random position update coefficient and a directional search behavior, then uses the improved whale optimization algorithm to estimate the power loss rates of each user in the power distribution area, and finally identifies the users with abnormal power loss rates through a distance-based outlier detection algorithm.

The invention provides a virtual model generation method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the steps of determining description information for generating a virtual model in response to a received generation instruction of the virtual model, and generating a grid model based on the description information; determining a distance field set corresponding to the grid model, and performing structure sensing alignment processing on the grid model based on the distance field set to obtain a first model, the first model comprising a plurality of first geometric primitives; determining a first distance field subset corresponding to each first geometric primitive from the distance field set, and trimming the first model based on each first distance field subset to obtain a second model; and determining a plurality of target components based on the second model, constructing a target model based on the plurality of target components, and outputting the target model. According to the method and the device, efficient generation and accurate optimization of the virtual model can be realized, so that the quality and the efficiency of model generation are improved.