172 results about "Trajectory analysis" patented technology

A system and method for real-time team intent modeling using persistent cognitive machines with federated human profiles which processes individual team member behavioral signals through geometric intent analyzers that generate high-dimensional vector representations of individual objectives and preferences. A team intent orchestrator aggregates individual vectors into collective representations within a dynamic geometric manifold that evolves based on team coordination patterns. Federated human profiles enable privacy-preserving knowledge sharing across teams through geometric abstraction techniques that preserve coordination utility while protecting individual privacy. The system implements proactive conflict detection through trajectory analysis that identifies potential coordination issues before performance impact, and provides real-time synchronization mechanisms that maintain team coordination coherence despite individual behavioral changes. Cross-team learning capabilities enable organizational intelligence development through pattern abstraction and context-aware adaptation of successful coordination strategies. The persistent cognitive architecture maintains coordination patterns across sessions and team composition changes, enabling continuous improvement through accumulated team experience.

The invention discloses a regional termite detection method and system based on multispectral fusion, and the method comprises the steps: carrying a multi-mode spectrum collection device through a movable detection platform, and synchronously collecting a visible light image, a near-infrared hyperspectral image and Raman spectrum data of a to-be-detected region; preprocessing and feature extraction are carried out on the modal data, and the modal data are converted to a frequency domain to obtain frequency features; based on the physical and biochemical characteristics of the termites and the nests thereof, calculating the matching degree and the credibility of each modal feature, and performing adaptive weighted feature fusion according to the matching degree and the credibility to generate comprehensive spectral features; inputting the fusion features into a pre-trained termite identification and risk assessment model to realize precise identification, positioning and threat level assessment of termite individuals, termite paths and nests; and carrying out trajectory analysis on termite activities by combining a multi-target tracking algorithm, and giving out early warning based on identification and tracking results. According to the invention, early-stage, lossless and accurate detection and active early warning of termites are realized, and the detection efficiency and reliability are significantly improved.

The invention discloses a personnel information security screening method and system based on big data, and relates to the technical field of image processing, and the method comprises the steps: obtaining to-be-processed face data in a region, screening out unregistered personnel, carrying out the matching and correlation of the images of the same unregistered personnel at different image collection points through calculating the feature similarity, and carrying out the recognition of the unregistered personnel. And connecting time points and spatial positions corresponding to the images of the same unregistered person at different image acquisition points into a spatial-temporal trajectory through a trajectory reconstruction algorithm, and pushing multi-modal feature information of the person to an adjacent preset area for the identified abnormal behavior. According to the invention, through a density clustering algorithm based on time and space constraints, feature association is carried out on personnel images collected by different cameras, a cross-region behavior track of the unregistered personnel is constructed, high-risk behaviors such as wandering are detected by using track analysis and an abnormal behavior identification technology, and early warning information is generated and sent to other regions. And the initiative and the coverage range of safety management are improved.

The invention relates to the technical field of data analysis, in particular to a cloud-based teaching platform student learning behavior trajectory analysis method, which comprises the following steps: acquiring a student interaction log, extracting task completion and control operation discontinuity points, identifying continuous learning behaviors and switching types, constructing a candidate period sequence, analyzing time and label changes, and generating a trajectory analysis result. According to the method, the non-interaction time period of the student in task switching can be identified by collecting the time interval between task completion and first control operation, so that the potential attention distraction or task interruption behavior of the student is captured, and the interaction characteristic and the duration of the continuous behavior segment are combined; and active and inactive learning period switching characteristics are further marked, and a task label difference degree and a time interval are introduced in the process of constructing a learning period sequence as a screening basis, so that the analyzed learning paragraph is ensured to have content continuity and behavior pattern difference, and the recognition capability of rule switching behaviors in trajectory analysis is enhanced.

The invention belongs to the field of safety monitoring of wind power equipment, and provides a multi-source data fusion and safety early warning system and method in the hoisting process of a wind turbine generator, and the system comprises a data collection and preprocessing module which collects and preprocesses multi-source sensor data such as a tower inclination angle and a suspension arm inclination angle; the state manifold construction module is used for mapping the preprocessed data to a multi-dimensional space to construct a state manifold and generating an ideal geodesic line; the trajectory analysis and risk assessment module is used for calculating the deviation degree between the real-time state trajectory and the ideal geodesic line and generating a risk score; the dynamic threshold generation module constructs a risk tensor field based on environmental parameters, and extracts a risk threshold curved surface after wind speed adjustment; the early warning decision module is used for comparing the risk score with a threshold curved surface to determine an early warning level and sending information; and the visual display module is used for displaying the state manifold, the track, the tensor field and the early warning information. By introducing a differential geometry theory, state manifold representation and geodesic deviation measurement are constructed, and accurate assessment of the hoisting process risk is realized.

The invention relates to a pressing plate operation behavior analysis and error prevention method and system based on image recognition and machine learning. The method comprises the following steps: acquiring a pressing plate operation area video stream through image acquisition equipment, and segmenting a video into independent operation event segments based on motion detection and trajectory analysis; extracting key point time sequence data of hands of an operator by using a human body posture estimation model, and constructing a dynamic feature sequence fusing a spatial relationship, kinematics and posture semantics; performing multi-level similarity comparison on the dynamic feature sequence and a standard operation template, and judging operation compliance by a machine learning model in combination with a dynamic threshold value; triggering graded early warning and intervention according to a judgment result; and an incremental learning mechanism is adopted, and the template and the threshold value are adaptively optimized based on historical data. According to the invention, accurate and intelligent analysis and active error prevention of the whole operation process of the pressing plate are realized, and the safety level of electric power operation is effectively improved.

The invention discloses a metamorphic rock P-T-t trajectory reconstruction method and system based on multi-source data fusion, and relates to the field of metamorphic rock P-T-t trajectory reconstruction.The method comprises the steps that electronic probe microcell map data and internal standard sample data of a metamorphic rock sample are obtained, and multi-stage data correction is conducted; carrying out mineral phase identification and chemical component quantitative interpretation to generate a mineral classification map, an element concentration distribution map and a total rock main component data set; thermodynamic phase equilibrium simulation is carried out, a P-T view profile map is generated, and a P-T track is extracted; performing microcell in-situ chronological analysis on selected minerals in the mineral classification map to obtain chronological data; and carrying out space-time coupling on the P-T trajectory and chronology data, constructing a P-T-t three-dimensional trajectory model of the metamorphic rock, and outputting a visual reconstruction report. According to the method, automation and standardization of the whole process of metamorphic rock P-T-t trajectory from data acquisition and processing to model reconstruction are realized, and the precision, efficiency and reliability of trajectory analysis are improved.

The invention relates to the technical field of intelligent traffic, in particular to a traffic abnormal event dynamic detection method and system based on trajectory analysis, and the method comprises the steps: receiving original space-time trajectory data; preprocessing the original spatio-temporal trajectory data, and mapping the original spatio-temporal trajectory data to a road section sequence of a road network through a map matching algorithm; constructing a behavior model based on the track sequence after map matching, learning the track sequence of the normal behavior mode on the road section, and establishing an observation emission model and a state transition matrix; in the online stage, the log-likelihood value of an observation sequence and / or the similarity between the observation sequence and a normal behavior pattern cluster are / is calculated for a real-time track in a set sliding window, and when the log-likelihood value and / or the similarity exceed a set threshold value, the track is marked as abnormal; performing time-space aggregation on abnormal trajectories of the same road section or intersection in unit time according to single vehicle abnormality judgment, and triggering group abnormal event alarm when aggregation data exceed a preset value.

The invention relates to the technical field of vehicle trajectory analysis, in particular to a vehicle trajectory anomaly detection method and system based on deep learning, and the method comprises the following steps: obtaining trajectory coordinates and boundary distance to generate symbol offset, constructing a road offset continuous field through interpolation and spatial embedding, calculating the ratio of instantaneous speed to reference speed, and obtaining a vehicle trajectory anomaly detection result. And generating an unbalance degree parameter, executing vector dimension stretching, extracting a trajectory embedding vector and an abnormal score by using a long short-term memory network, executing square summation and difference operation, and generating a trajectory energy gradient value. According to the method, migration characteristics are mapped to a continuous field to achieve track and road geometric constraint association, unbalance degree parameters are used for remarking directional quantity scales to enhance speed dynamic perception, energy gradient modulation scoring is cooperated, a confidence probability curved surface is constructed by using trilinear interpolation, and a curved surface peak value is positioned to output a detection result. Positioning noise is suppressed; and abnormal precision under sparse sampling is improved.

The invention provides an eye movement trajectory analysis method and system based on hybrid clustering and time constraint, and belongs to the technical field of computer vision. Calculating a time difference and a moving speed between continuous original eye movement data points; comparing the moving speed with a speed threshold value, and classifying the moving speed into candidate fixation points and glancing points; extracting spatial features and time features of the candidate fixation points, performing standardization processing, and performing weighted fusion to obtain spatial-temporal feature vectors; clustering the spatio-temporal feature vectors to obtain preliminary clustering labels of the candidate fixation points; performing time constraint processing on each cluster; calculating the duration of the clustering cluster after the time constraint processing, and generating a final clustering label of the candidate fixation point; and outputting a final classification label of each original eye movement data point in combination with the classification result of the glancing points.

The invention provides a flight path analysis model, a training method, a flight path analysis method and device, and a medium, and belongs to the technical field of artificial intelligence, and the model comprises a flight path coding network which is used for receiving an aircraft flight path sequence and extracting a first flight path hidden feature; the physical consistency constraint network is used for predicting physical state features and performing constraint based on a motion feasible region so as to fuse and generate second track hidden features; the multi-modal adaptation network is used for performing cross-modal fusion on the second track hidden feature and the analysis instruction feature to obtain a multi-modal input feature; and the large language model network is used for receiving the input characteristics, performing semantic reasoning and generating a track analysis result text. According to the method, the physical constraint network ensures that the features conform to the physical motion law, and the cross-modal network is utilized to realize the deep alignment of the track and the language, so that the bottleneck of single-modal analysis is broken through, and the high-order analysis capability of track situation understanding and reasoning in a complex low-altitude scene is remarkably improved.

The invention discloses a user dynamic access control method and system based on multi-dimensional data, and belongs to the technical field of software. The invention aims to solve the problems of user access control policy jitter, security vulnerability and difficulty in explaining compliance caused by static threshold, module independent decision and non-explicit modeling user experience cost and compliance risk cost in the prior art. Therefore, the invention provides a dynamic access control method, which comprises the following steps of: constructing a session-level multi-dimensional access context; dividing risk signal detection according to a visual angle; carrying out risk evidence combination and mode recognition; performing risk trajectory and strategy hysteresis control based on a state machine; unifying action arrangement and conflict resolution of the strategy center; strategy execution and session consistency control are carried out; and effect evaluation and strategy evolution based on multi-dimensional indexes are carried out. Compared with the prior art, multi-view evidence combination, session-level trajectory analysis, state machine and constraint solution and other means are introduced, multi-layer integration from a data layer, a logic layer, a time layer to a control layer is achieved, strategy jitter is effectively relieved, user experience is improved, service continuity is guaranteed, and compliance interpretability is enhanced.

The invention relates to the technical field of basketball judgment, and discloses an infrared time sequence verification basketball goal anti-misjudgment detection method. According to the method, infrared signal sequences of shooting actions are collected in real time through an infrared sensor array on the periphery of a basketball hoop, shooting track fragments are segmented, space-time coupling characteristics are extracted, then a multi-scale track analysis grid is generated, and the grid precision of an infrared signal violent change area is higher than that of a smooth area. Interference feature analysis is conducted on the grid time sequence to generate an infrared signal interference index, the abnormal deviation degree of the basketball track is calculated through a dynamic path verification algorithm in combination with the index, and finally a misjudgment verification conclusion of the shooting action is generated according to the comparison result of the abnormal deviation degree and a preset threshold value. According to the method, the basketball movement track can be comprehensively captured, interference is effectively eliminated, the accuracy and the real-time performance of goal penalty are improved, and the fairness of basketball match penalty is improved.

The present application relates to a kind of based on AIoT gateway's multi-prevention area intelligent linkage alarm method and related equipment, including the following steps, the present application proposes a kind of based on AIoT gateway's multi-prevention area intelligent linkage alarm method, by the Internet of Things sensor environmental data of multiple prevention areas and video image stream are fused, generate prevention area scene three-dimensional reconstruction data, and it is monitored and analyzed, extract environmental characteristic sequence and trajectory analysis sequence.When detecting that multiple prevention area threat level exceeds threshold value, in combination with gateway historical alarm data, cause and effect inference is generated, generates cross-prevention area correlation event chain.Subsequently, matching AIoT gateway's preset collaborative response strategy, and through 4G / 5G network linkage SP voice call module, realize multi-channel alarm push, solve the technical problems that lack depth fusion and collaborative analysis means between video image data and environmental sensor data, it is difficult to form the overall understanding and dynamic modeling of prevention area scene.

The invention relates to a ship trajectory analysis and anomaly detection method and system based on multi-source data fusion, and relates to the technical field of maritime affair intelligent supervision, and the method comprises the steps: extracting spatial-temporal features, environmental risk features and ship interaction features through real-time fusion of AIS data, environmental data and static archive data; self-adaptive weighted fusion is carried out by using a multi-head self-attention mechanism to form a unified feature vector; then inputting the data into a space-time diagram neural network model, taking a ship as a node, constructing an edge by a spatial distance, and aggregating space-time neighborhood information to output an abnormal probability score; and finally, a reference threshold value is set based on historical normal data, dynamic adjustment is performed according to the real-time environment risk index, and self-adaptive early warning is realized. According to the method, the defects of single sensing dimension, shallow space-time modeling and rigid early warning mechanism in the prior art are effectively overcome, and the accuracy, environmental adaptability and real-time performance of anomaly detection are remarkably improved.

The invention relates to the technical field of general control or regulation systems, and discloses a heat pipe self-adaptive heat regulation and control system based on two-phase flow state prediction, which comprises a feature acquisition unit, a flow state prediction unit, a trajectory analysis unit and a control decision unit, and is characterized in that the system acquires a temperature vibration coupling signal of a controlled heat circulation loop and converts the temperature vibration coupling signal into a multi-dimensional feature vector; the working medium flow state phase change trend is predicted according to a mapping operator, a trajectory analysis unit generates an evolution trajectory through phase-space reconstruction and calculates the curvature of the trajectory in a sliding window, a control decision unit adjusts and controls a topological structure according to the trajectory curvature, and when the curvature is lower than a threshold value, a linear adjustment instruction is output. According to the method, the instability forebodes are monitored and recognized through the track curvature, a regulation and control blind area caused by phase change lag is eliminated, nonlinear oscillation generated by thermal load fluctuation is restrained, stable operation of a thermal regulation and control loop is ensured, and the stability margin of the system is improved.

The invention relates to the technical field of code analysis, in particular to a code business logic vulnerability static analysis method based on a large language model, which comprises the following steps: performing semantic feature extraction based on a source code file set and a business requirement document to obtain a code business semantic feature map; constructing a business logic constraint knowledge network based on the code business semantic feature map, and generating a business scene simulation test case set based on the business logic constraint knowledge network; and executing the service scene simulation test case set, obtaining corresponding function runtime state data, and carrying out state transition trajectory analysis based on the function runtime state data to obtain an actual service state circulation sequence. By executing the test case and capturing the state data when the function runs, the state change of the program can be monitored in real time, an objective basis is provided for subsequent state transition trajectory analysis, and the reliability of an analysis result is ensured.

The invention discloses a vehicle driving track monitoring system based on artificial intelligence, and belongs to the technical field of artificial intelligence, and the system comprises an environment sensing module which collects the dynamic data flow of the surrounding environment of a vehicle in real time, and generates environment sensing information; the trajectory analysis module is used for judging whether the vehicle needs to be subjected to running trajectory adjustment according to the environment perception information and generating alternative adjustment sub-routes; the judgment module is used for receiving the alternative adjustment sub-routes and judging the consistency of each alternative adjustment sub-route and a preset original main route of the vehicle; if yes, a consistency confirmation signal and the optimal alternative adjustment sub-route are output; and the control execution module is used for driving the own vehicle to run along the optimal alternative adjustment sub-route. According to the method, the comprehensive risk assessment parameter is generated by extracting the target object and fusing the dynamic risk calculation factor, and continuous quantification and comprehensive assessment of the complex time-varying risk in the dynamic traffic scene are realized.

The invention provides a high-speed aircraft online trajectory planning method based on improved polynomial guidance, which solves the problems of calculation delay and poor trajectory smoothness in the existing autonomous path planning, and comprises the following steps: establishing a plane-coordinate system and a motion equation set of a high-speed aircraft, and determining constraint conditions in the flight process of the high-speed aircraft; constructing an optimization model containing an adaptive penalty function based on an improved sequential quadratic programming algorithm, and generating an obstacle avoidance path point set; performing trajectory optimization by adopting an improved polynomial, generating a trajectory meeting aircraft dynamics constraints among the path points generated in the step 2, and selecting a key path point set; based on the obstacle avoidance path point set and the key path point set, adopting a centripetal parameterized Catmull-Rom spline curve to process the generated path to obtain a smooth trajectory; a guidance instruction is obtained based on smooth trajectory analysis and calculation, and the high-speed aircraft is guided to sail according to the planned trajectory. And the real-time calculation efficiency is improved on the basis of realizing the smooth trajectory.

The invention discloses an eye movement track analysis and classification method and system based on three-dimensional fixation estimation, and relates to the field of computer vision, and the method comprises the specific steps: obtaining a face video, estimating a head posture based on the face video, and extracting a plurality of face images; inputting the facial image into a multi-task learning model, extracting facial features and eye features in parallel, processing the fused features, and outputting an eye prediction state and a three-dimensional fixation vector estimation value; converting the three-dimensional fixation vector estimation value into a fixation point sequence under a screen coordinate system based on a relative pose relationship between the camera and the screen; clustering the fixation point sequence to obtain multi-dimensional eye movement features; and inputting the head posture and the multi-dimensional eye movement features into a fusion de-noising variational auto-encoder to obtain a classification result. According to the method, the text reading task is combined with the space-time distance function, and the extracted multi-dimensional eye movement features such as fixation, eye jump and review can accurately reflect the reading process of the subject, so that the classification accuracy is improved.

The invention relates to the technical field of shooting training, in particular to an image target shooting data processing method for drop point prediction, which comprises the following steps: acquiring the coordinates of a drop point through trajectory calculation and decomposing transverse and longitudinal components, calculating the deviation distance between the drop point and the center of a target and sorting; dividing a data track set by utilizing trend analysis and calculating direction consistency and amplitude stability, screening a deviation group to give a calibration weight, giving a continuation weight in combination with a stable group, performing integration to generate dynamic weight data, and generating a target display optimization control instruction set in combination with a distribution concentration ratio and a cross-regional trend parameter. The method comprises the steps of obtaining coordinates of drop points through trajectory calculation and sorting, providing trajectory analysis basic data, dividing groups through trend analysis and calculating direction consistency and amplitude stability, improving trajectory recognition and prediction precision, enhancing personalized feedback by combining calibration and continuation weight, and performing target fine adjustment through drop point sequence screening. The feedback reliability and the training effect are improved.

The invention discloses an efficient semantic perception pre-training track representation learning method and device, and relates to the technical field of artificial intelligence, and the method comprises the steps: generating track embedding of a vehicle track through a first encoder; training a first encoder according to the road view and the interest point view of the vehicle trajectory; initializing a second encoder according to the weight of the first encoder; generating a compressed embedding of the vehicle trajectory by a second encoder; and aligning the track embedding with the compression embedding. Through travel purpose perception pre-training, a large language model does not need to be introduced in a downstream task coding stage, the travel purpose is effectively captured, additional calculation overhead is avoided, the problem that calculation burden is heavy when text information is integrated through a traditional method is solved, semantic information in a vehicle track can be efficiently and fully learned, and the method is suitable for being used for a vehicle. And possibility is provided for real-time trajectory analysis.

The present application relates to a method for detecting loosening of ceramic dewatering elements for papermaking based on vibration spectrum analysis, aiming to solve the problems of difficult early identification of loosening and weak anti-working condition interference ability of ceramic dewatering elements in the running of the paper machine wire section. The scheme synchronously collects vibration signals and multi-dimensional working condition parameters, generates a structured frequency spectrum through time-frequency analysis and power spectrum density processing, and then fuses the knowledge base to match the reference structure template, realizing the topological edit distance quantization of the measured and reference frequency spectrum. Combined with the fuzzy rule engine, the different loosening degrees are dynamically weighted and inferred, and the positioning accuracy is improved through graph structure evolution trajectory analysis and high-resolution order tracking. The technology has high robustness and early loosening identification ability, which is beneficial to improve the intelligentization and intelligent decision level of the health monitoring of the clean production line ceramic elements.

The invention provides a verification method and a verification system, and belongs to the technical field of network security. According to the method, by generating the verification code image containing the non-character pattern contour, dependence of traditional OCR on characters can be avoided essentially, and safety is improved from the attack root. And meanwhile, a plurality of text feature options and at least one interference option are generated in combination with a visual feature extraction model, so that dual verification (including option semantic verification and behavior track verification) on user operation can be realized, multi-level cross inspection can be performed on the user operation, and attack of an automatic script can be effectively identified and blocked. In addition, by introducing depicting track verification based on a non-character pattern contour, the interaction mode that a traditional click verification code is single is broken, and an active behavior dimension which is difficult to be simulated by a machine is added for the verification process. Thus, through a dual verification mechanism of semantic hiding and behavior trajectory analysis, the success rate of machine attacks can be significantly reduced, and dual improvement of security protection and user experience is realized.

The invention discloses an edge computing device deployment method for realizing table tennis recognition based on RT-DETR, belongs to the technical field of crossing of computer vision and sports, and aims at deploying a complex deep learning model on a resource-limited edge computing device to meet the requirement of efficient and real-time object recognition. According to the method, the RT-DETR model is deployed by using an NVIDIA Jetson Orin Nano edge computing platform so as to carry out table tennis ball detection. According to the method, the unique Transform architecture advantages and the end-to-end detection capability of RT-DETR are utilized, delay fluctuation caused by non-maximum suppression (NMS) in a traditional anchor frame-based method (such as a YOLO series) is effectively avoided, and the GPU acceleration and TensorRT optimization capability of Jetson Orin Nano is fully utilized while extremely high accuracy is ensured, so that the reasoning speed is remarkably increased. The system is suitable for precise tracking and trajectory analysis of tiny objects in a rapid dynamic environment, and high-frame-rate detection and intelligent training assistance of table tennis balls are completed through a monocular camera.

Methods, systems, and computer programs are presented to detect potential collisions of vehicles with a Vulnerable Road User (VRU). The provided solution includes a system designed to detect and warn against potential collisions with vulnerable road users (VRUs) using a combination of hardware and software components. The system employs one or more cameras installed on a vehicle to monitor the surrounding environment. These cameras capture image frames, which are processed by an onboard model to estimate potential collisions through trajectory analysis. In one aspect, the trajectory estimation includes using a bird's eye view transformation, which provides a top-down perspective of the scene to aid in trajectory estimation. Camera parameters are personalized per installation by determining a transformation matrix used to derive the bird's eye view.

The invention provides a space dimension reduction method for dynamic trajectory analysis, and belongs to the field of data analysis and machine learning. The method takes dynamic trajectory data as Riemannian function type data to carry out nonlinear full dimension reduction, and comprises the following steps of: 1, converting the Riemannian function type dynamic trajectory data into Euclidean space function type dynamic trajectory data; 2, constructing a Gram matrix of time data and a distance matrix of measurement space data for the Euclidean space function type dynamic trajectory data; and step 3, constructing a dimension reduction function to carry out nonlinear dimension reduction on the Euclidean space function type dynamic trajectory data. According to the method, dynamic trajectory data with a complex geometric structure can be effectively processed.

This application provides a reasoning and decision-making method, apparatus, device, and storage medium based on a large language model. The method includes: acquiring a decision instruction input for a target scene and a video frame sequence corresponding to the target scene; when the decision instruction corresponds to a logical reasoning task, identifying at least one object to be analyzed, and using a first large language model to perform dynamic trajectory analysis and scene association analysis on the object to be analyzed based on the video frame sequence to obtain corresponding scene description information; combining the decision instruction and scene description information, performing semantic retrieval in a preset domain rule base to obtain at least one target rule information; combining the decision instruction, video frame sequence, scene description information, and at least one target rule information to generate corresponding text prompt information; and using a second large language model to perform logical reasoning based on the text prompt information to obtain the corresponding decision result. This improves the accuracy of decision results for dynamic environments.

The invention provides an operation type identification method and device for finger trajectory analysis, equipment and a medium, and is suitable for the technical field of projection touch control. The method comprises the following steps: performing finger key point extraction on an original image sequence to obtain a target finger coordinate sequence, performing Kalman filtering processing on the target finger coordinate sequence to generate target finger trajectory data, performing motion feature extraction on the target finger trajectory data to obtain motion feature data, and performing motion state division on the motion feature data to obtain segmented trajectory unit data; and converting the segmented track unit data into track feature description data, and performing classification decision on the track feature description data according to an operation type to obtain operation type identification data. According to the method, through frame-by-frame key point extraction and distortion correction, anomaly detection, Kalman filtering, multi-scale feature extraction, segmented coding and gradient lifting classification, high-precision recognition of finger operation is realized, and the robustness of finger track recognition is improved.

The invention discloses a monocular laser point cloud-based goods yard vehicle monitoring method and system, and aims to solve the problems of low vehicle monitoring precision and insufficient data integrity in a complex goods yard environment. The method comprises the following three steps: S1, building a multi-condition constraint portable experimental field, planning a sensor layout through a multi-target optimization model, carrying out view angle consistency calibration, carrying out weighted fusion on point clouds, dynamically adjusting weights, and generating a real-time updated panoramic distance image; s2, Gaussian filtering denoising and point cloud quality improvement are carried out, a neighborhood is determined in combination with spatial features, dynamic kernel width filtering denoising is carried out, abnormal points are eliminated through a dynamic threshold value, and weights are updated according to a denoised signal-to-noise ratio in a multi-sensor scene; and S3, complementing the invisible area of the point cloud through 3D Gaussian splash processing, generating a preliminary panoramic video frame through multi-scale fusion and projection, and optimizing to obtain a panoramic video of which the time sequence is consistent with the visual angle. The system adapts to the dynamic environment of the goods yard and provides high-precision data support for vehicle detection and trajectory analysis.