39 results about "Trajectory segmentation" patented technology

The invention discloses a truck trip chain identification method based on trajectory data, which comprises the following steps: S1, acquiring GPS trajectory data of a truck, and preprocessing the GPS trajectory data, including data cleaning, noise removal and trajectory segmentation; s2, by setting a speed threshold value and a time threshold value, the stop point of the truck is recognized; s3, spatial matching is carried out on the stay point and road network data, and the accurate position of the stay point is determined; s4, segmenting the track of the truck based on the time sequence and the space distribution of the stop points to form a plurality of travel segments; s5, analyzing the driving characteristics and the stop characteristics of each travel section, and removing stop points related to non-freight; and S6, identifying key staying points related to loading and unloading activities, and connecting the key staying points according to a time sequence to form a truck travel chain. According to the method, the actual running path and the logistics movable chain of the truck can be clearly restored, and high-precision technical support is provided for freight path analysis and industrial chain space structure recognition.

The invention relates to a ship arrival time high-precision prediction method and device based on a long-short-term neural network, and a storage medium, and the method comprises the steps: firstly carrying out the aggregation of an AIS and a navigation log according to hours, carrying out the space matching in a sliding window, and generating a fusion navigational speed; and then inverse distance weighted interpolation is carried out on meteorological data, wind wave parameters are complemented, and ship static information codes are unified. And then the three types of data are synchronized to a unified time sequence axis, after trajectory segmentation and Kalman filtering smoothing, an optimal feature subset is screened through recursive feature elimination and cross validation, the optimal feature subset is used as input to train a bidirectional long-short-term memory network model, and finally accurate prediction of the ship arrival time is achieved. Compared with the prior art, the method has the advantages that the long short-term memory network (LSTM) and the attention mechanism (Attention) are comprehensively utilized, high-precision and real-time prediction of the ETA of the ship is achieved, and the method can be widely applied to scenes such as port scheduling, shipping management and intelligent logistics.

The invention provides a track segmentation method, system and device based on space-time perception and adaptive learning, and belongs to the technical field of artificial intelligence and track data processing. The track segmentation method comprises the following steps: preprocessing original track data, and dividing an unlabeled data set and a labeled data set; the method comprises the following steps: constructing an encoder-decoder model based on Transform, and carrying out self-supervision pre-training through mask reconstruction and a contrast learning task; introducing a segmentation decision head, and performing supervised fine tuning on the pre-training model by using a small amount of labeled data; after model deployment, continuous adaptive learning is realized by constructing a dynamic database and regularly performing online mixing loss fine adjustment. The method effectively reduces the dependence of the model on labeled data, improves the generalization ability, long-term stability and decision interpretability in a complex scene, and is suitable for air traffic control, target intention recognition, trajectory prediction and other scenes.

The invention discloses a flight trajectory prediction method and system based on airspace information perception, and the method comprises the steps: obtaining historical aircraft trajectory information, and carrying out the multi-scale flight trajectory segmentation based on downsampling; carrying out aircraft flight mode correlation graph calculation on the aircraft trajectory information of different scales; performing high-order tensor graph neural network construction based on the flight mode correlation graph, and fusing trajectory information of different airplanes in the same airspace; acquiring historical wind speed and wind direction information, and fusing the wind speed and wind direction information with the aircraft trajectory information; and fusing the fusion results according to different scales, and outputting a predicted future aircraft trajectory. According to the method, sufficient information interaction of different airplanes in the same airspace can be ensured, and meanwhile, extra peripheral wind speed and direction information is fused as auxiliary features, so that the flight path is accurately predicted.

Systems and methods, implemented as computer programs on one or more computers for training a consistency model for use in generating a frame of data, such as a frame of image data, and methods of using a trained consistency model to generate a frame of data. A consistency model is used to generate a frame of data by predicting a succession of de-noised frames starting with an initial, noisy frame at an initial time and ending with a final frame, without noise, at a final time. The consistency model is trained to generate self-consistent predictions over a trajectory of predicted frames corresponding to these times. Implementations of the described techniques divide the trajectory into segments and only require the model to generate self-consistent predictions over each segment. This can facilitate the rapid generation of high quality frames of data.

The embodiment of the invention relates to a processing method and device for track extraction and labeling based on roadside data. The method comprises the following steps: receiving a roadside sensing data set; abnormal track cleaning, static track smoothing, abnormal inflection track repairing and course angle correction are carried out on the roadside sensing data set; performing lane feature addition, track behavior type segmentation identification and behavior fragment track segmentation on all tracks of the roadside perception data set, and constructing a labeling record set based on all fragment tracks; identifying a motion game relationship between every two target tracks in the labeling record set to obtain a game relationship matrix; and generating a multi-target game scene according to the game relation matrix and the annotation record set. According to the invention, a large number of complex game scenes can be constructed based on the road side real perception data.

The invention provides a track segmentation labeling method and related equipment, and relates to the technical field of track data processing. Original track data of a moving target is acquired; clustering the original trajectory data by adopting a space-time clustering method to obtain a plurality of clusters, and segmenting trajectories in all the clusters in combination with an adaptive sliding window to obtain a segmentation result; carrying out manual annotation on the segmentation result to obtain a manual annotation result, taking the manual annotation result as priori knowledge, and carrying out feature extraction on the segmentation result to obtain multi-dimensional spatial-temporal features; performing automatic label inference on unlabeled segments in the segmentation result based on the multi-dimensional spatio-temporal features to obtain an inference result, and calculating the confidence of the inference result; the inference result is optimized according to the confidence coefficient, and a trajectory labeling result of the moving target is obtained; and the labeling efficiency is remarkably improved while the labeling accuracy is ensured.

The application discloses a kind of filtering and remaining area spray trajectory replanning method and system across station has been sprayed area, belong to industrial robot vision and automatic spraying technical field.This system is composed of mobile chassis, six-axis robot arm, terminal RGB-D camera, spray gun, station visual label and supporting function module;Robot generates standard spraying trajectory by visual segmentation, point cloud processing in first station and records sprayed area data, after moving across station, relies on visual label to complete multi-frame fusion relocation, calculates inter-station coordinate transformation matrix, maps historical sprayed area to current coordinate system and eliminates from real-time point cloud, re-plans serpentine spraying trajectory for remaining to be sprayed area, and accurately controls spray gun on-off in combination with trajectory segmentation logic.The application solves the problem that traditional mobile spraying robot is prone to repeated spraying, uneven paint film and repeated teaching when working across station, realizes multi-station continuous automatic spraying, and the trajectory runs smoothly with high spraying consistency.

A kind of agricultural machinery motion mode recognition method combining road network map and agricultural machinery trajectory clustering algorithm belongs to the technical field of map matching, the steps of the method include: obtaining agricultural machinery positioning trajectory original data;Original agricultural machinery positioning trajectory data is cleaned;Road network map in corresponding target area is obtained using agricultural machinery positioning trajectory data;The mapping deviation between agricultural machinery positioning trajectory and road of road network map is corrected using HFTMM algorithm;Determine agricultural machinery road driving motion mode according to the high-precision mapping relationship between agricultural machinery positioning trajectory and road of road network;Determine agricultural machinery field operation and field transfer motion mode using DBSCAN density clustering algorithm.The road scene of road network map and density clustering algorithm are fused in the present application to improve the accuracy and efficiency of agricultural machinery positioning trajectory segmentation, and more accurate agricultural machinery motion mode recognition results are obtained.

The invention discloses a mechanical arm track segmentation method based on Z-axis state transition and speed troughs. According to the method, a Z-axis height sequence and a speed vector sequence are extracted from a motion trail position sequence of an end effector of the mechanical arm. Firstly, features of a Z-axis height sequence are counted, a relative threshold value is set, Z-axis height is subjected to state division, and state conversion points are searched; and the moment of conversion from the high-order state or the intermediate state to the low-order state is paired with the nearest moment of conversion from the low-order state to the high-order state or the intermediate state to form a candidate interval. Then selecting an interval with the longest time span from all candidate intervals as a rough candidate interval; and then speed trough detection is conducted on the speed size sequence in the rough candidate interval, speed minimum value points closest to the starting point and the ending point of the interval are found to serve as boundary candidate points of starting and ending, a boundary point pair based on speed troughs is constructed, a mechanical arm track is segmented, and an action track of task execution is obtained.

The application discloses a trajectory compression method. In view of the deficiency of the prior art, the solution idea of the application is that, based on the global optimization idea, the feature trajectory sub-chain obtained by simplifying and compressing a line segment is globally optimized, and multiple influence factors such as an offset angle, a perpendicular Euclidean distance, a trajectory segmentation number and the like are comprehensively considered, an evaluation index capable of comprehensively reflecting space and time characteristics of a compression result is established, and therefore the contradiction between compression efficiency and effective information reservation and between the original trajectory and the possibility of being as similar as possible is well balanced. The application also discloses a trajectory compression device. Compared with the prior art, the application can realize offline compression of all trajectories containing more effective information and having higher accuracy, and the overall operation accuracy and efficiency of trajectory compression is improved.

The invention relates to the technical field of intelligent manufacturing, in particular to a trajectory planning method and device for a machine tool, equipment and a medium. The method comprises the following steps: analyzing a G code track file of the numerical control machine tool to generate a middle track instruction; in a Cartesian space trajectory represented by the intermediate trajectory instruction, calculating a direction included angle and a theoretical speed variation according to the pose parameter and the motion parameter; according to the direction included angle and the theoretical speed variation, dividing the trajectory points into segmentation points or merging points so as to perform trajectory segmentation and merging processing on the Cartesian space trajectory; based on the Cartesian space trajectory subjected to trajectory segmentation and merging processing, a joint space trajectory is constructed through discrete and inverse solution processing; and performing smooth transition processing and speed planning processing on the joint space trajectory to generate a machine tool control instruction. Compared with the prior art, the problems that a track planning method is low in machining efficiency, poor in precision and large in vibration in machine tool application are solved.

The invention discloses a super real-time simulation and cooperative control integration method based on track segmentation calculation. The method comprises the following steps: for a plurality of missiles which the same target arrives at at the same time, acquiring real-time positions of the missiles in a flying process; performing super-real-time simulation according to the real-time position, and determining the remaining flight time of each missile; determining expected time according to the remaining flight time; and the time constraint guidance rate of each missile is determined according to the expected time, and then the path of the corresponding missile is adjusted. According to the invention, accurate prediction of the residual flight time is realized, closed-loop control of flight time error and lateral overload is established, and thus high-precision cooperation of multi-missile attack time is realized.

The application discloses a space-based space target trajectory segmentation fitting method based on infrared radiation characteristics, and comprises the following steps: (1) acquiring initial positioning information of a space target in a ground-fixed coordinate system through double-star joint observation; (2) monitoring the infrared radiation intensity of the space target in real time through an infrared sensor, identifying the classification points of the space target in different flight stages according to the infrared radiation intensity and signal-to-noise ratio change, and completing target trajectory segmentation; (3) for different flight stages, the least square method is introduced through an adaptive factor, the trajectory optimization fitting of the space target in the space-based scene is completed, high-precision positioning and tracking are realized, and the motion characteristics of the target are acquired. By using the application, the overfitting or underfitting problems in the traditional method can be reduced, so that the precision and reliability of space-based space target detection and tracking are improved, and the application is suitable for a complex space target observation environment.

The application provides a trajectory segmentation labeling method and related equipment, and relates to the technical field of trajectory data processing. The original trajectory data of a moving target is obtained. A space-time clustering method is used to cluster the original trajectory data, a plurality of clustering clusters are obtained, and the trajectories in all the clustering clusters are segmented by combining an adaptive sliding window to obtain a segmentation result. The segmentation result is manually labeled to obtain a manual labeling result. The manual labeling result is used as prior knowledge to extract features from the segmentation result to obtain multi-dimensional space-time features. Unlabeled segments in the segmentation result are automatically labeled based on the multi-dimensional space-time features to obtain an inference result, and the confidence of the inference result is calculated. The inference result is optimized according to the confidence to obtain the trajectory labeling result of the moving target. The labeling accuracy is ensured while the labeling efficiency is significantly improved.

This invention relates to the field of image enhancement technology, specifically to a method for segmenting rotary tillage operation trajectory images based on the gray-level co-occurrence matrix. The method includes: adaptively remapping and quantizing the original farmland image to obtain a quantized enhanced grayscale image; combining spectral components and performing mask convolution to obtain a spectral feature enhancement image; extracting the second-order probability distribution statistics of the multi-directional gray-level co-occurrence matrix to construct a multi-dimensional feature space vector map; quantizing the inverse smoothness using the inverse differential moment operator to obtain a texture feature gradient map; and determining physical faults through tensor fusion and morphological evolution to obtain a binarized trajectory segmentation image. This invention utilizes texture statistical characteristics to characterize differences in surface fragmentation, eliminating interference from uneven lighting and stubble occlusion, and achieving accurate extraction of operation trajectory boundaries in complex farmland environments.

The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving automobile layered trajectory planning method and system for a dynamic city scene, and the method employs a layered architecture: an upper global planner generates an initial trajectory under a Frenet coordinate system, and actively screens a non-homotopy trajectory as an optimization starting point, so as to optimize the optimal trajectory; an optimal control problem is solved by combining a lane center line tracking cost function, and a global trajectory conforming to traffic rules is obtained; when a lower-layer local re-planner detects sudden change of an obstacle, safe starting and ending points are determined based on track segmentation diagnosis, a middle obstacle avoidance point is introduced to guide a detouring direction, and a local track is rapidly solved by using a double-disc simplified collision model; and finally, fusing the global track and the local track through space-time splicing to form a safe, smooth, dynamic and feasible final execution track. The system correspondingly comprises a global planning module, a local re-planning module and a trajectory fusion module. According to the method, the planning success rate and the driving safety and comfort in a complex dynamic scene are remarkably improved.

The application discloses a kind of cognitive impairment detection method and device based on energy capture system, by deploying RFID and solar panel, real-time signal strength and energy collection intensity are collected, the movement original data of the target to be detected in room is generated, trajectory segmentation is carried out to original data, single mode feature extraction is carried out to trajectory section, speed feature image is generated, conditional variational autoencoder based on Transformer architecture is constructed, pseudo image is generated using its decoder to realize data expansion, and the deep latent space features of image are extracted using its encoder.Finally, the extracted high-dimensional feature vector is input into the classifier, and the classification result is output, so as to realize the judgment of cognitive state.The application solves the problems of data scarcity and insufficient long-time behavior capture through generative data augmentation, achieving high-precision non-invasive monitoring.

The invention relates to the technical field of satellite navigation and inertial navigation integrated positioning, and discloses an adaptive control point-based GNSSINS continuous time trajectory optimization method, which comprises the following steps of: S1, performing trajectory segmentation and uncertainty analysis to obtain discrete moment state estimation and a covariance matrix of a GNSS / INS integrated navigation filter; recognizing a GNSS updating moment and dividing track segments; s2, control points of geometric driving are distributed, the discrete curvature of each piece of axial smooth position data is calculated, a local curvature maximum value point is identified and refined, and a global dominant control point is selected; according to the method, the local support characteristic of a B-spline curve is utilized, GNSS recovery information is made to backtrack to influence trajectory estimation during interruption through an observation constraint mechanism, a pre-convergence effect is generated, the position RMSE is reduced by 52% in a 30-second interruption scene, and the peak error is reduced by 58%; the position RMSE is reduced by 66% in a 90-second interruption scene, and the peak error is reduced by 70%.

The invention provides an electronic commerce image background generation method and device, equipment and a storage medium, and the method comprises the steps: receiving target input information which comprises a product foreground image, a corresponding product mask and a text prompt; the image is input into the optimized diffusion model to execute a multi-step denoising process, a matched electronic commerce image background is generated, the multi-step denoising process comprises denoising operation of at least one time step, and the denoising operation of any time step sequentially comprises short track sampling, image state prediction, quality evaluation and input determination of the next time step. The optimized diffusion model is obtained by performing iterative training on a pre-trained initial diffusion model by using an image preference data set and direct expected preference optimization DEPO loss. According to the method, DEPO loss combined with track segmentation is introduced, and more frequent and more information amount reward feedback can be realized, so that better alignment with user preference is realized, and meanwhile, high image fidelity is kept.

The embodiment of the invention provides a vehicle energy management method, device and system and a vehicle, and the method comprises the steps: obtaining the original driving data of a target region; performing track cleaning and track segmentation processing on the original driving data, and determining at least one track segment; generating a standard path according to the at least one track segment; performing path information analysis on the standard path, and extracting slope mileage information; acquiring a slope change threshold value; determining a gradient change parameter according to the gradient mileage information, and when the gradient change parameter is greater than or equal to a gradient change threshold value, determining at least one energy management position on the standard path; acquiring the real-time position of the vehicle; and when the real-time position is matched with the energy management position, controlling the vehicle terminal to execute a corresponding energy management control instruction so as to adjust power parameters of the vehicle. According to the scheme, the overall energy utilization efficiency of the mine vehicle is improved.

The invention relates to the technical field of multi-point touch, in particular to a capacitive touch screen multi-point touch response optimization method based on an AI (artificial intelligence) algorithm, which comprises the following steps: acquiring touch point instantaneous capacitance signals, converting the touch point instantaneous capacitance signals into a two-dimensional coordinate sequence, calculating track displacement deviation and local curvature, generating basic track characteristic data, and calculating the basic track characteristic data; the method comprises the following steps: calculating a curvature change rate, identifying abnormal points, extracting an average curvature and a direction parameter, generating track segment characteristic data, inputting the data into a support vector machine to judge an action mode, carrying out clustering analysis to judge stability, generating an action classification stable identifier, and calculating a response weight to generate a multi-point touch response optimization signal. By dynamically analyzing the curvature and the change rate of a touch track, describing touch characteristics in real time and recognizing an action mode, stability is evaluated by utilizing curvature and direction clustering, touch weight is adaptively adjusted, multi-point consistent response is kept, high-precision feedback is provided in rapid sliding and complex interaction, the operation accuracy is improved, and the user experience is improved. The problems of response delay and trajectory drift are solved.

The application discloses a kind of trajectory prediction-based urban mobile charging pile migration method.The method obtains the position information of user terminal dispersion, constructs trajectory embedding sequence after vectorization processing, obtains the trip trajectory table based on trajectory embedding sequence.The historical trajectory T of user in trip trajectory table is segmented into n segment trajectories, trajectory grouping is carried out with segment trajectory similarity, the address preference probability of user in different group is determined, the complete trajectory of user is predicted according to the address preference probability and trajectory confidence of user charging, the site expectation value of any user route subinterval is determined according to complete trajectory, and the highest expected place in trip trajectory table is selected as the recommended urban mobile charging pile site location.The application also discloses a kind of migration system for realizing trajectory prediction-based urban mobile charging pile migration method.

The invention discloses a flight departure behavior analysis method based on trajectory data. The method comprises the following steps: defining a concept of a flight departure behavior; acquiring broadcast type automatic correlation monitoring track data and carrying out grid mapping on the broadcast type automatic correlation monitoring track data; constructing a flight path redundancy index based on flight behaviors; constructing a flight trajectory deviation index based on trajectory redundancy; designing a flight path deviation degree detection model; flight departure behavior detection; aiming at the problems of the flight behavior analysis method in the aspects of evaluation efficiency and safety, the method provides concepts of flight trajectory redundancy and deviation, establishes a unified flight behavior evaluation framework, constructs a flight behavior detection model, realizes automatic segmentation of the trajectory by adopting a self-adaptive sliding time window, and improves the evaluation efficiency and safety of the flight behavior analysis method. The method can focus on a certain section of deviation on a flight path, designs a flight path deviation degree test method, and can effectively recognize various flight deviation behaviors such as step descent, fly-around and waiting.

The application discloses a diesel engine fault prediction method based on big data analysis and relates to the technical field of big data analysis, which comprises the following steps: collecting diesel engine multi-source state data and preprocessing to generate a standardized data set; performing working condition segmentation, phase marking and transition arrangement to generate a working condition chain sample set; constructing a working condition parameter baseline, extracting a deviation to generate a multi-dimensional running residual set; decomposing the residual by using MSTL and correcting the misclassified fragments to generate a degradation residual feature package; constructing an improved MLP-Mixer network to generate a diesel engine degradation prediction package; performing degradation trajectory segmentation and risk mapping to generate a fault risk prediction package; marking the early warning level and matching the guarantee task window to generate a maintenance scheduling. By introducing the MSTL algorithm and the improved MLP-Mixer network, the application realizes accurate extraction of early degradation features of the diesel engine under complex task working conditions, joint prediction of fault risks and generation of predictive maintenance scheduling.

The invention relates to an infrared weak and small target detection and tracking method based on time-space domain trajectory fitting, and belongs to the technical field of infrared weak and small target detection and tracking. An infrared weak and small target track fitting data set Data-match is constructed; building an infrared weak and small target detection network model Model-Det; the Model-Det is trained and verified by using the Data-match repeatedly, and the Model-Det is verified; obtaining an infrared weak and small target detection candidate box Bbox; the method comprises the following steps of: inputting a target trajectory A of each sequence into a Kalman filtering unit, and generating a target trajectory Trajectory-A of each sequence; building an infrared weak and small target track segmentation network model Model-Seg; the Model-Seg is trained and verified by repeatedly using the Data-match, and the Model-Seg is verified; a target track Trajectory-B of each sequence is obtained; and taking an intersection of the Trajectory-A and the Trajectory-B to obtain a final infrared weak and small target detection tracking result and target trajectory output. According to the method, the data dependence is reduced, and the infrared weak and small target can be stably and accurately detected in different scenes.

The application discloses a point cloud sequence ground segmentation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a point cloud sequence and a pose sequence corresponding to the point cloud sequence in the driving process of an unmanned vehicle; extracting ground point clouds in the point cloud sequence to obtain ground scene point clouds; segmenting a motion trajectory according to the pose sequence and a preset trajectory segmentation length to obtain a segmented line segment set; wherein the motion trajectory is obtained by splicing the pose sequence; using the segmented line segment set to perform regional blocking on the point clouds in the ground scene point clouds to obtain a segmented region set; and performing ground fitting on the segmented region set to obtain a ground point cloud segmentation result. The technical scheme can realize the effects of ground segmentation and fitting of a scene in the driving process of an unmanned vehicle, filters out point cloud information of obstacles of the autonomous vehicle in the ground point cloud segmentation result, avoids ground point cloud noise interference, and restores the real ground conditions.