12 results about "Trajectory pattern" patented technology

The invention discloses a multi-mode body intelligent agent track prediction method, which comprises the following steps of: receiving and processing input data, and standardizing dynamic and static contexts; an encoder-feature fusion device-decoder architecture model is constructed, the encoder maps high-dimensional features to a low-dimensional space and keeps key information, the feature fusion device fuses the features, the decoder extracts a trajectory mode probability, Gaussian noise is injected to enhance variation capture, and a multi-modal three-dimensional trajectory sequence is generated through GRU; and dynamically selecting an optimal path in combination with real-time environment feedback to complete prediction. Through standardization processing, multi-feature fusion and noise injection, prediction accuracy and environmental adaptability are improved, and efficient trajectory prediction is realized.

The invention discloses a control method, control equipment and a control system of an unmanned aerial vehicle. The control method of the unmanned aerial vehicle comprises the steps of determining a target trajectory pattern of the unmanned aerial vehicle; determining a flight route of the unmanned aerial vehicle based on the target trajectory pattern; and controlling the unmanned aerial vehicle to fly according to the flight route, and shooting the flight trajectory of the unmanned aerial vehicle during the flight period of the unmanned aerial vehicle according to the flight route to obtain a flight trajectory image matched with the target trajectory pattern.

The invention discloses a VLBI measurement multi-epoch data fitting and visualization method based on a regression voltage regulation stripping algorithm. The method is suitable for identification and matching of a radio astronomical jet flow component trajectory. The method comprises the following steps: firstly, reading multi-epoch observation data and carrying out self-adaptive preprocessing to extract effective data; the core is to strip an entanglement component through double-loop iterative fitting; a main loop identifies a local trajectory mode based on sampling point pseudo normal distribution; in the secondary cycle, a curve is fitted through orthogonal distance regression, extrusion-fine tuning is carried out by utilizing an adjustable cycle gain and a dynamic threshold value, and the corresponding relation of components among multiple epochs is automatically matched. According to the method, non-uniform sampling and linear and non-linear trajectories can be processed, and finally fitting parameters, physical quantities, a corresponding relation table and a multi-subgraph visualization result integrating fitting curves, residual errors and probability distribution are output. The whole process is highly automatic, false components are effectively eliminated through cross validation, the precision and efficiency of jet flow motion characteristic analysis are remarkably improved, and subjective errors are reduced.

The invention provides an integrated large-screen key target trajectory situation generation processing method and system, and relates to the technical field of data processing, and the method comprises the steps: 2, based on a unified trajectory sequence, extracting the deep spatial features of a trajectory through employing a convolutional neural network, and combining a bidirectional long-short-term memory network and a self-attention structure to generate a trajectory situation; time sequence dependence features are extracted; performing spatial structure analysis on the unified trajectory sequence, constructing a trajectory dynamic model, performing constraint analysis on the speed and acceleration of continuous trajectory points, calculating curvature change and tangential direction continuity between trajectory segments, and performing fitting and smoothing processing on the trajectory points to obtain a trajectory dynamic model; and generating morphological calibration parameters for describing and calibrating the trajectory morphological evolution law, and realizing trajectory pattern recognition and classification of the key target. According to the method, key target trajectory mode identification and real-time threat grading are realized, and the real-time performance and accuracy of monitoring decision making are improved.

The invention relates to the technical field of charging piles, in particular to a direct current charging pile safety management method and system, and the method comprises the following steps: determining the operation parameter information of a to-be-monitored direct current charging pile, and constructing a multi-dimensional data layout based on the operation parameter information; acquiring operation parameter information of the to-be-monitored direct current charging pile in different operation states, and drawing on the corresponding data layout based on the operation parameter information to obtain a plurality of track graph streams; setting a calling rule for the plurality of track graph streams; current operation parameter information of the charging pile is collected, a real-time graph flow formed by the current operation parameter information in the data layout is obtained, and the real-time graph flow and the multiple track graph flows are compared and analyzed based on the calling rule; identifying an information point position deviating from the standard track graph in the current real-time graph stream to obtain a deviation symptom point; the accuracy of abnormality diagnosis of the charging pile can be improved, and the effect of safety management of the charging pile is improved.

The application relates to the technical field of flight trajectory pattern recognition, and discloses a terminal area airspace traffic flow space pattern mining method considering abnormal trajectories, which comprises the following steps: acquiring historical flight trajectories of an airport terminal area airspace, constructing an airspace description matrix T of the airport terminal area after pretreatment of the terminal area flight trajectories; establishing a deep self-encoding model; optimizing the deep self-encoding model, and extracting a normal trajectory set Y from the airspace description matrix T; and extracting the space pattern of the normal trajectory set Y to support the decision of airspace management. The method can avoid the influence of abnormal trajectories on the clustering results of terminal airspace data, avoid the influence of high-dimensional information on the discrimination ability of a clustering model, and guarantee the clustering effect of the clustering model.

This application provides a map partitioning and construction method, object recognition and cleaning method, device, and storage medium. In this application embodiment, because the autonomous mobile device uses multiple trajectory patterns with different main travel directions to traverse the working environment, it can cover the entire working environment as much as possible, thereby capturing as many partition reference objects in the working environment as possible, and increasing the probability of capturing frontal angle images of partition reference objects. This is beneficial for more accurately identifying partition reference objects and their locations in the working environment, and improving the accuracy of map partitioning based on partition reference objects.

The present application relates to the technical field of intelligent transportation and vehicle behavior prediction, in particular to a real-time trajectory prediction method for over-limit and over-load vehicles based on collaborative filtering, especially to a trajectory prediction method for over-limit and over-load vehicles, combining multi-dimensional behavior clustering and BiLSTM-Transformer hybrid model, introducing a DBSCAN clustering step based on multi-dimensional comprehensive similarity, which can automatically and accurately classify over-limit and over-load vehicles with similar behavior patterns into the same group. The most similar group is matched for the target vehicle for model training, effectively solving the problem of fuzzy model learning target caused by data heterogeneity. At the same time, the hybrid model architecture layer is good at capturing local time series dynamics and short-term driving rules, while the self-attention mechanism of the encoder can effectively model global long-distance dependence and complex trajectory patterns, and the two complement each other, thus achieving a leap in prediction accuracy as a whole. The algorithm can automatically identify noise points, further enhancing the robustness of the method to data noise.

The invention discloses a crop canopy three-dimensional reconstruction method based on track generation type space information acquisition, relates to the technical field of plant three-dimensional reconstruction, can adapt to different user requirements and plant characteristics by setting a plurality of multi-view shooting track modes, breaks through the limitation of traditional horizontal surround shooting, and improves the reconstruction efficiency. Complete images of overlook, look-up and side middle and lower parts can be obtained, information loss of the top and the bottom of a three-dimensional model is made up, and the reconstruction effect of crops with complex structures, such as vine plants, is greatly improved. Meanwhile, coordinate discretization and inverse kinematics solution are carried out on a continuous track, the track is converted into an executable instruction of a mechanical arm, and an acquisition device is driven to move and shoot, so that plant shaking caused by rotation of a rotary table is avoided, non-rigid deformation in an image sequence is reduced, and the defects of ghosting, trailing, local data missing and the like in three-dimensional point cloud are effectively eliminated. And a more reliable three-dimensional data support is provided for crop phenotype analysis, pest and disease detection and the like.

This invention belongs to the field of engineering progress diagnosis technology, specifically disclosing a method and system for diagnosing engineering construction progress deviations based on cluster analysis. The method includes: slicing the original progress data of the target project into time-series states to obtain a continuous progress state sequence; measuring the similarity of the evolution trajectory of the continuous progress state sequence and performing topological mapping on the measurement results to obtain a trajectory similarity matrix; based on the trajectory similarity matrix, performing trajectory pattern clustering on the continuous progress state sequence to obtain progress state trajectory clusters; locating key turning points in the evolution trajectory to obtain state transition points; performing critical condition backtracking on the state transition points to obtain preconditions, and performing correlation mining on the preconditions to obtain common conditions; and based on the common conditions, performing predictive risk analysis on the target project to obtain deviation diagnosis results. This invention can improve diagnostic efficiency and decision support capabilities.

The invention relates to the technical field of intelligent traffic and vehicle behavior prediction, in particular to a real-time track prediction method for an over-limit and overload vehicle based on collaborative filtering, and particularly relates to a track prediction method which is oriented to the over-limit and overload vehicle and combines multi-dimensional behavior clustering and a BiLSTM-Transformer hybrid model. A DBSCAN clustering step based on multi-dimensional comprehensive similarity is introduced, and overrun and overload vehicles with similar behavior patterns can be automatically and accurately classified into the same group. And the most similar group is matched for the target vehicle for model training, so that the problem of model learning target fuzziness caused by data heterogeneity is effectively solved. Meanwhile, the hybrid model architecture is combined, the layers are good at capturing local time sequence dynamic and short-term driving rules, the self-attention mechanism of the encoder can effectively model global long-distance dependence and complex track modes, and the advantages of the two modes are complementary, so that the leap of prediction precision is realized on the whole. The algorithm can automatically identify noise points, and the robustness of the method to data noise is further enhanced.

The present invention relates to a method for monitoring a plurality of rotary machines. In the present invention, the method for monitoring a plurality of rotary machines respectively installed at multiple locations comprises: a step for installing a first rotary machine at a first location and acquiring reference data having a trajectory pattern from the first rotary machine in a normal state; a step for installing a second rotary machine at a second location different from the first location; a step for processing a signal output from the first rotary machine to acquire first output data having a trajectory pattern; a step for processing a signal output from the second rotary machine to acquire second output data having a trajectory pattern; and a step for comparing the reference data and the first output data and comparing the reference data and the second output data to monitor the first rotary machine and the second rotary machine.