Track segmentation labeling method and related equipment

Abstract

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.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of trajectory data processing, in particular to a trajectory segmentation labeling method and related equipment. BACKGROUND

[0002] With the rapid development and wide application of positioning technologies such as Global Positioning System (GPS), Automatic Identification System (AIS), Beidou navigation system, a large amount of spatio-temporal trajectory data of mobile targets (such as ships, vehicles, pedestrians, drones, etc.) is generated. These trajectory data record the position, speed, heading and other information of the mobile target in the form of time series, and contain rich behavior patterns and motion laws. In order to extract valuable behavior patterns from original trajectory data, it is necessary to label the trajectory data, that is, to associate the trajectory segment with its corresponding behavior. High-quality trajectory labeling data is the basis for training and verifying trajectory pattern recognition models, anomaly detection algorithms and behavior prediction systems.

[0003] However, the current trajectory data labeling mainly faces the following technical challenges and problems: 1. Traditional trajectory labeling methods mainly include two types of complete manual labeling and complete automatic labeling: complete manual labeling relies on manual viewing of trajectory data one by one and judgment according to expert experience, although it can ensure high accuracy, but since a trajectory containing thousands of trajectory points may need tens of minutes or even longer time for labeling, for a data set containing thousands of trajectories, complete manual labeling may need weeks or even months of time, resulting in low labeling efficiency, and long-time repetitive labeling work is easy to cause labeling personnel fatigue, affecting labeling quality and consistency; complete automatic labeling method can improve labeling efficiency, but has obvious shortcomings in accuracy and adaptability. Rule-based automatic labeling methods (such as speed threshold method, stay point detection method, etc.) rely on pre-set rules and fixed parameter thresholds, and are difficult to adapt to the diversified behavior characteristics of different scenarios and different types of mobile targets. For example, the fishing behavior characteristics of different types of ships in different sea areas differ greatly, and a unified speed threshold cannot accurately distinguish between fishing operations and slow sailing. Although the automatic labeling method based on machine learning can learn complex patterns, it often needs a large amount of high-quality labeling data for training, and the generalization ability and robustness of the model are poor. Most labeling methods use point-level classification strategy, independently classifying and predicting each trajectory point, ignoring the continuity of the trajectory and the continuity of the behavior, resulting in frequent label jumps in the prediction results, and the same behavior pattern that should be continuous is mistakenly divided into multiple fragmented segments.

[0004] 2. Lack of effective trajectory segmentation method: trajectory segmentation is an important preprocessing step of trajectory analysis, which aims to divide the original trajectory into several relatively consistent segments according to the change of behavior characteristics. Reasonable trajectory segmentation can improve the accuracy and accuracy of labeling, and reduce the complexity of labeling. However, the existing trajectory segmentation method is mainly based on fixed parameter threshold segmentation, which is simple and intuitive, but lacks comprehensive analysis and adaptive adjustment ability of trajectory spatio-temporal characteristics; But it is difficult to adapt to the diversified needs of different types of moving targets and different application scenarios.

[0005] In summary, the existing trajectory labeling method has deficiencies in the balance of efficiency and accuracy, trajectory segmentation, human-computer cooperation and other aspects, and it is difficult to meet the needs of practical applications. Therefore, there is an urgent need for a trajectory semi-automatic labeling method that combines spatio-temporal adaptive segmentation, a small amount of manual labeling and intelligent automatic inference, which can significantly improve the labeling efficiency while ensuring the accuracy of labeling. SUMMARY

[0006] The present application provides a trajectory segmentation labeling method and related equipment, which aims to significantly improve the labeling efficiency while ensuring the accuracy of labeling.

[0007] In order to achieve the above purpose, the present application provides a trajectory segmentation labeling method, comprising: Step 1, obtaining the original trajectory data of the moving target; Step 2, using a spatio-temporal clustering method to cluster the original trajectory data, obtaining a plurality of clustering clusters, and combining an adaptive sliding window to segment the trajectories in all clustering clusters, obtaining a segmentation result; Step 3, manually labeling the segmentation result to obtain a manual labeling result, and using the manual labeling result as prior knowledge to extract features from the segmentation result to obtain multi-dimensional spatio-temporal features; Step 4, based on the multi-dimensional spatio-temporal features, automatically inferring the labels of the unmarked segments in the segmentation result to obtain an inference result, and calculating the confidence of the inference result; Step 5, optimizing the inference result according to the confidence to obtain the trajectory labeling result of the moving target.

[0008] Further, before using the spatio-temporal clustering method to cluster the original trajectory data, it further comprises: Pretreating the original trajectory data to obtain pretreated trajectory data.

[0009] Further, using the spatio-temporal clustering method to cluster the original trajectory data to obtain a plurality of clustering clusters, comprising: Calculating the spatio-temporal distance between any two trajectory points in the pretreated trajectory data based on the ST-DBSCAN spatio-temporal clustering algorithm; According to the space-time distance, the trajectory points in the preprocessed trajectory data are clustered to obtain a plurality of clustering clusters.

[0010] Further, the calculation expression of the space-time distance of any two trajectory points in the preprocessed trajectory data based on the ST-DBSCAN space-time clustering algorithm is: ; Wherein, denotes the space-time distance between two trajectory points 、 , denotes the geographical distance between two trajectory points 、 , denotes the spatial neighborhood radius, denotes the time neighborhood radius, 、 denote the time stamp of the trajectory point 、 .

[0011] Further, the segmented result is manually annotated to obtain a manual annotation result, including: The segmented result is displayed in the form of a line through a map component; Trigger a segmentation selection event by selecting a segmented line, and manually annotate the corresponding behavior label in the segmentation selection event according to the space-time characteristics and behavior semantics of the trajectory to obtain a manual annotation result.

[0012] Further, the multi-dimensional space-time characteristics include: The time dynamic characteristics composed of average speed, speed standard deviation, speed change frequency and average acceleration; The spatial pattern characteristics composed of trajectory curvature, convex hull area, local point density and heading change mode.

[0013] Further, the expression for calculating the confidence of the inference result is: ; Wherein, denotes the confidence, denotes the maximum similarity, denotes the standard deviation of the top-k similarity, denotes the average value of the top-k similarity.

[0014] The application also provides a trajectory segmentation and labeling device, comprising: An acquisition module for acquiring original trajectory data of a moving target; The segmentation module is configured to cluster original trajectory data by using a spatiotemporal clustering method to obtain a plurality of clustering clusters, and segment trajectories in all the clustering clusters by combining an adaptive sliding window to obtain a segmentation result. The extraction module is configured to manually annotate the segmentation result to obtain a manual annotation result, and extract features of the segmentation result by taking the manual annotation result as prior knowledge to obtain multi-dimensional spatiotemporal features. The inference module is configured to automatically infer labels of unannotated segments in the segmentation result based on the multi-dimensional spatiotemporal features to obtain an inference result, and calculate a confidence of the inference result. The optimization module is configured to optimize the inference result according to the confidence to obtain a trajectory annotation result of the moving target.

[0015] The present application also provides a terminal device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the trajectory segmentation annotation method when executing the computer program.

[0016] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the trajectory segmentation annotation method.

[0017] The above scheme of the present application has the following advantages: The present application obtains original trajectory data of a moving target, clusters the original trajectory data by using a spatiotemporal clustering method to obtain a plurality of clustering clusters, segments trajectories in all the clustering clusters by combining an adaptive sliding window to obtain a segmentation result, manually annotates the segmentation result to obtain a manual annotation result, extracts features of the segmentation result by taking the manual annotation result as prior knowledge to obtain multi-dimensional spatiotemporal features, automatically infers labels of unannotated segments in the segmentation result based on the multi-dimensional spatiotemporal features to obtain an inference result, calculates a confidence of the inference result, optimizes the inference result according to the confidence to obtain a trajectory annotation result of the moving target, and significantly improves annotation efficiency while ensuring annotation accuracy by improving annotation intensity from a point level to a segmentation level through a collaborative mechanism of “trajectory segmentation + manual annotation + label inference” compared with the prior art.

[0018] Other advantages of the present application will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 The figure is a flowchart of an embodiment of the present application; Figure 2 The figure is a structural diagram of a trajectory segmentation annotation device in an embodiment of the present application; Figure 3This is a schematic diagram of the structure of the terminal device in an embodiment of the present invention. Detailed Implementation

[0020] To make the technical problems, solutions, and advantages of this invention clearer, a detailed description will be provided below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0021] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0022] This invention addresses existing problems by providing a trajectory segmentation and annotation method and related equipment.

[0023] like Figure 1 As shown, an embodiment of the present invention provides a trajectory segmentation annotation method, including: Step 1: Obtain the raw trajectory data of the moving target; Step 2: The original trajectory data is clustered using a spatiotemporal clustering method to obtain multiple clusters. An adaptive sliding window is then used to segment the trajectories in all clusters to obtain the segmentation results. Step 3: Manually label the segmented results to obtain manually labeled results. Use the manually labeled results as prior knowledge to extract features from the segmented results and obtain multidimensional spatiotemporal features. Step 4: Based on multidimensional spatiotemporal features, perform automatic label inference on the unlabeled segments in the segmentation results to obtain the inference results, and calculate the confidence level of the inference results; Step 5: Optimize the inference results based on the confidence level to obtain the trajectory labeling results of the moving target.

[0024] The original trajectory data used in this embodiment of the invention is the AIS trajectory data of a ship in a certain sea area. The AIS trajectory data contains several ship trajectories, each trajectory consists of several trajectory points, and each trajectory point records the ship's maritime mobility service identifier, longitude, latitude, timestamp, speed, heading and other attribute information.

[0025] The preferred embodiment is that, before using the spatiotemporal clustering method to cluster the original trajectory data, the method further includes: preprocessing the original trajectory data to obtain preprocessed trajectory data.

[0026] In this embodiment of the invention, the preprocessing process includes: A linear interpolation method is used to perform time series alignment processing on the trajectory data, unifying trajectory points with different sampling intervals to the same time interval; The trajectory data after time series alignment processing is subjected to coordinate system normalization processing, and all trajectory point coordinates are uniformly converted to the WGS84 geographic coordinate system; The trajectory data after coordinate conversion is subjected to abnormal value detection and filtering processing based on rules such as speed mutation, position jump, and reverse timestamp, to identify and process abnormal trajectory points. For trajectory points lacking speed or heading attributes, the position and time difference of adjacent points are calculated to supplement.

[0027] Specifically, the original trajectory data is clustered by using a spatiotemporal clustering method to obtain multiple clustering clusters, including: The spatiotemporal distance between any two trajectory points in the preprocessed trajectory data is calculated based on the ST-DBSCAN spatiotemporal clustering algorithm. The trajectory points in the preprocessed trajectory data are clustered according to the spatiotemporal distance to obtain multiple clustering clusters.

[0028] Specifically, the calculation expression of the spatiotemporal distance between any two trajectory points in the preprocessed trajectory data based on the ST-DBSCAN spatiotemporal clustering algorithm is as follows: ; wherein, denotes the spatiotemporal distance between two trajectory points , denotes the geographic distance between two trajectory points , , denotes the spatial neighborhood radius, denotes the time neighborhood radius, , , denote the timestamps of the trajectory points , respectively.

[0029] The geographic distance between the two trajectory points , is calculated by the Haversine formula, and the calculation expression is as follows: ; wherein, denotes the radius of the earth, about 6371 kilometers, denotes the latitude, denotes the longitude.

[0030] In the embodiment of the present application, when and the number of trajectory points contained in the spatiotemporal neighborhood of the trajectory point is not less than the minimum number of trajectory points , the trajectory point As the core point, the spatiotemporal reachable core point and its neighborhood points are classified into the same spatiotemporal clustering cluster.

[0031] In the embodiment of the application, the dense point group is marked as a dense clustering cluster, and the sparse point is marked as a noise cluster.

[0032] Specifically, the trajectories in all clustering clusters are segmented by combining an adaptive sliding window to obtain a segmentation result, including: First, the trajectory points are arranged in chronological order to form an ordered sequence , and each trajectory point is labeled with its belonging clustering label; Then, the segmentation window is constructed by arranging cumulative clustering, and the window length threshold is set to The threshold is dynamically determined according to the total length of the trajectory, and the window construction process is as follows: (1) Starting from the first cluster, all trajectory points contained in the first cluster are added to the current window; (2) The subsequent clusters and the trajectory points contained in the subsequent clusters are sequentially accumulated until the total number of trajectory points in the current window reaches or exceeds ; (3) The current window is marked as a segment , and the trajectory point sequence contained in the segment and the belonging clustering identifier are recorded; (4) When constructing the next window, an overlapping strategy is adopted: backtracking to the middle position of the current window, and starting from the middle position to accumulate clusters to construct a new window; (5) Steps (2)-(4) are repeated until all trajectory points of the entire trajectory are covered.

[0033] The window construction method provided in the embodiment of the application can make the segmentation boundaries naturally aligned to the behavior transition points. The number of clusters contained in each window varies according to the density and size of the clusters. A dense large cluster may constitute a window alone, and multiple small clusters may be combined into a window. The overlapping between windows ensures the continuity of the segmentation boundaries and avoids abrupt changes at the junctions of the windows.

[0034] It should be noted that the segmentation result of the embodiment of the application meets the constraint condition: the segments of the same source trajectory do not overlap in time and are in chronological order, and each segment maintains the behavior coherence.

[0035] Specifically, the segmentation result is manually labeled to obtain a manual labeling result, including: The segmentation result is displayed in the form of a line through a map component; The segment selection event is triggered by selecting the segment line, and a corresponding behavior label is selected in the segment selection event according to the spatiotemporal characteristics and behavior semantics of the trajectory, so as to obtain a manual annotation result.

[0036] In the embodiment of the application, manual annotation is realized through a map visualization interface; and the behavior label is defined according to an application scenario, for example, a fishery activity recognition scenario includes fishing operation, sailing, anchoring, entering a port, and leaving a port; and a cargo ship monitoring scenario includes normal sailing, waiting for entering a port, berthing operation, and slow movement.

[0037] It should be noted that the map visualization interface supports multi-scale interactive operations such as zooming and panning when the embodiment of the application performs manual annotation, and a user can observe the spatial distribution mode and motion characteristics of the trajectory from a macroscopic to a microscopic view.

[0038] The embodiment of the application adopts a key segment annotation strategy when performing manual annotation, and the key segments include: segments near the seven points and the end point of the trajectory, which usually correspond to fixed behavior modes such as entering and leaving a port; segments near obvious behavior conversion points, which represent the switching between different behavior modes; and representative segments of typical behavior modes, such as a typical anchoring mode and a typical sailing mode. When a user clicks a “start annotation” button through the map visualization interface to enter an annotation mode, selects a sailing annotation category, and clicks a target segment on the map to perform annotation, the annotation source is manual. After the annotation is completed, the user continues to manually annotate other key segments, and follows the key segment annotation strategy to focus on annotating the representative segments of the trajectory start and end points, behavior conversion points, and typical behavior modes.

[0039] It should be noted that the manual annotation of the embodiment of the application is not for all segments, but only for key segments.

[0040] The embodiment of the application establishes a priority management mechanism. For the same segment, if manual annotation and automatic annotation exist at the same time, the system only retains and displays the manual annotation result, and in the subsequent automatic inference process, the segment with the existing manual annotation is not covered by the automatic inference result. For the segment with the existing manual annotation, if the user clicks the annotation again, the system prompts whether to modify the annotation, and updates the annotation information after the user confirms.

[0041] Specifically, the multi-dimensional spatiotemporal characteristics include: temporal dynamic characteristics composed of average speed, speed standard deviation, speed change frequency, and average acceleration, used to describe the motion state change characteristics of the segment; spatial mode characteristics composed of trajectory curvature, convex hull area, local point density, and heading change mode, used to describe the spatial form characteristics of the segment.

[0042] Specifically, the calculation process of the multi-dimensional spatiotemporal characteristics is as follows: Average speed, i.e. the average value of the speed of all trajectory points in the segment, is calculated as follows: ; wherein, denotes the average speed, denotes the speed of the i-th trajectory point, denotes the number of trajectory points; Speed standard deviation, which is used to reflect the fluctuation degree of the speed in the segment, is calculated as follows: ; wherein, denotes the speed standard deviation; Speed change frequency, i.e. the frequency of the speed change of adjacent points exceeding the threshold, is used to reflect the intensity of the speed change; Average acceleration, i.e. the average value of the acceleration in the segment, is calculated as follows: ; wherein, denotes the average acceleration; Trajectory curvature, which is used to reflect the bending degree of the trajectory, is defined as the ratio of the actual length of the trajectory to the straight-line distance between the start and end points, and is calculated as follows: ; wherein, denotes the trajectory curvature, denotes the actual length of the trajectory, denotes the straight-line distance between the start and end points, wherein if the trajectory curvature is greater than 1, it indicates that the trajectory is curved or back-and-forth, and if the trajectory curvature is close to 1, it indicates that the trajectory is close to a straight line; Convex hull area, i.e. the minimum convex hull area of the trajectory point set in the segment, is used to reflect the spatial coverage range of the trajectory; Local point density, which is used to reflect the distribution density of the trajectory points per unit area, is calculated as follows: ; wherein, denotes the number of trajectory points in the segment; Heading change pattern, i.e. the statistical characteristics of the heading angle change, such as the heading standard deviation and the maximum turning angle, is used to reflect the direction change law of the trajectory.

[0043] Specifically, automatic label inference for unannotated segments in the segmentation result based on multi-dimensional spatiotemporal features can be implemented through one or more of the following strategies: 1. In-segment label inheritance strategy: For unannotated segments in the same cluster, calculate the time distance thereof from the annotated segments, and inherit the label of the annotated segment with the smallest time distance, and the calculation formula is as follows:​ ; wherein, denotes the time distance, , denote the start time and end time of the unlabeled segment , , denote the start time and end time of the labeled segment ; This strategy is based on the assumption that the behavior patterns of adjacent time periods within the same trajectory are usually correlated.

[0044] 2. Label propagation strategy based on feature similarity: First, normalize the feature vector to obtain the normalized feature vector : ; wherein, and are the mean and standard deviation of the i-th feature in all segments; Then calculate the weighted Euclidean distance: ; wherein, is the weight of the i-th feature, satisfying , the weight can be determined by feature importance evaluation or information gain method, and higher weight is given to the feature with high discrimination; The feature similarity is defined as: ; The similarity value is in the interval , the larger the value, the more similar the behavior features of the two segments, and the label of the labeled segment with the highest similarity is taken as the candidate label; 3. Label propagation strategy based on clustering: K-means clustering or DBSCAN clustering is performed on the feature vectors of all segments, and the labeled segments are taken as seed points to propagate labels to unlabeled segments in the same cluster, which can effectively utilize the global similarity relationship between segments. Specifically, the expression for calculating the confidence of the inference result is:

[0045] ; wherein, denotes the confidence, denotes the maximum similarity, denotes the standard deviation of the top-k similarity, ​​The average value of the top-k similarity.

[0046] In the embodiment of the present application, the confidence formula comprehensively considers the highest similarity and the stability of the similarity distribution. When the highest similarity is high and the top-k similarity distribution is concentrated, the confidence is high. When the confidence is greater than or equal to the threshold, the record is recorded as an effective automatic annotation. This mechanism ensures the reliability of the automatic inference result and avoids false annotations with low confidence.

[0047] In the embodiment of the present application, the inference result includes information such as segment identification, label, annotation source, and confidence.

[0048] Specifically, step 5 includes: The annotation coverage is calculated as follows: ; Wherein, represents the annotation coverage, represents the number of annotated segments, represents the total number of segments; The manual annotation ratio is calculated as follows: ; Wherein, represents the manual annotation ratio, represents the number of manually annotated segments; The label distribution balance degree is calculated using entropy measurement as follows: ; Wherein, represents the entropy value, the greater the entropy value, the more balanced the label distribution, that is, the higher the label distribution balance degree, represents the number of label categories, represents the proportion of segments of the i-th label category. The segment result is annotated and supplemented by the annotation coverage, the manual label ratio, and the label distribution balance degree, and steps 3 and 4 are repeated to realize iterative optimization until and the label distribution is reasonable, the optimization is stopped, and the trajectory annotation result of the moving target is obtained. The trajectory annotation result includes segment identification, label type, annotation source, and confidence information.

[0049] ​This invention acquires the original trajectory data of a moving target; it uses a spatiotemporal clustering method to cluster the original trajectory data, obtaining multiple clusters, and combines an adaptive sliding window to segment the trajectory in all clusters, obtaining segmentation results; it manually labels the segmentation results, obtaining manually labeled results, and uses the manually labeled results as prior knowledge to extract features from the segmentation results, obtaining multidimensional spatiotemporal features; based on the multidimensional spatiotemporal features, it automatically infers labels for unlabeled segments in the segmentation results, obtaining inference results, and calculates the confidence level of the inference results; it optimizes the inference results based on the confidence level, obtaining the trajectory labeling results of the moving target; compared with the prior art, this invention improves the labeling level from point level to segment level through a collaborative mechanism of "trajectory segmentation + manual labeling + label inference", significantly improving labeling efficiency while ensuring labeling accuracy.

[0050] Corresponding to the trajectory segmentation and annotation method described in the above embodiments, such as Figure 2 As shown, this embodiment of the invention also provides a trajectory segmentation and annotation device 100, which includes: The acquisition module 101 is used to acquire the original trajectory data of the moving target; The segmentation module 102 is used to cluster the original trajectory data using a spatiotemporal clustering method to obtain multiple clusters, and to segment the trajectory in all clusters using an adaptive sliding window to obtain the segmentation result. Extraction module 103 is used to manually annotate the segmented results, obtain manually annotated results, and use the manually annotated results as prior knowledge to extract features from the segmented results to obtain multi-dimensional spatiotemporal features; The inference module 104 is used to automatically infer labels for unlabeled segments in the segmentation results based on multidimensional spatiotemporal features, obtain inference results, and calculate the confidence level of the inference results; The optimization module 105 is used to optimize the inference results based on the confidence level to obtain the trajectory labeling results of the moving target.

[0051] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0052] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0053] This invention also provides a terminal device, such as... Figure 3 As shown, the terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 3 The diagram shows only one processor, a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, it implements the trajectory segmentation annotation method described above.

[0054] The terminal device D10 can be a desktop computer, laptop, handheld computer, server, server cluster, or cloud server, etc. This terminal device may include, but is not limited to, a processor D100 and a memory D101. Those skilled in the art will understand that... Figure 3 This is merely an example of terminal device D10 and does not constitute a limitation on terminal device D10. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0055] The processor D100 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0056] The memory D101 can be an internal storage unit of the terminal device D10 in some embodiments, for example, a hard disk or a memory of the terminal device D10. The memory D101 can also be an external storage device of the terminal device D10 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory D101 can include both the internal storage unit and the external storage device of the terminal device D10. The memory D101 is used to store an operating system, application programs, a boot loader, data, and other programs, for example, program codes of the computer programs, etc. The memory D101 can also be used to temporarily store data that has been output or is to be output.

[0057] It should be noted that the information interaction and execution process between the above apparatuses / units are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the same can be referred to the method embodiments part, which will not be described herein.

[0058] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software function unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the unit and module in the system can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0059] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the trajectory segmentation labeling method.

[0060] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the construction device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc.

[0061] The above is the preferred embodiment of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application.

Claims

1. A trajectory segmentation and annotation method, characterized in that, include: Step 1: Obtain the raw trajectory data of the moving target; Step 2: The original trajectory data is clustered using a spatiotemporal clustering method to obtain multiple clusters. An adaptive sliding window is then used to segment the trajectories in all clusters to obtain the segmentation results. Step 3: Manually annotate the segmented results to obtain manually annotated results, and use the manually annotated results as prior knowledge to extract features from the segmented results to obtain multidimensional spatiotemporal features; Step 4: Based on multidimensional spatiotemporal features, perform automatic label inference on the unlabeled segments in the segmentation results to obtain the inference results, and calculate the confidence level of the inference results; Step 5: Optimize the inference result based on the confidence level to obtain the trajectory labeling result of the moving target.

2. The trajectory segmentation and annotation method according to claim 1, characterized in that, Before clustering the original trajectory data using a spatiotemporal clustering method, the following steps are also included: The original trajectory data is preprocessed to obtain preprocessed trajectory data.

3. The trajectory segmentation and annotation method according to claim 2, characterized in that, The original trajectory data was clustered using a spatiotemporal clustering method, resulting in multiple clusters, including: The spatiotemporal distance between any two trajectory points in the preprocessed trajectory data is calculated based on the ST-DBSCAN spatiotemporal clustering algorithm. Based on the spatiotemporal distance, the trajectory points in the preprocessed trajectory data are clustered to obtain multiple clusters.

4. The trajectory segmentation and annotation method according to claim 3, characterized in that, The expression for calculating the spatiotemporal distance between any two trajectory points in the preprocessed trajectory data based on the ST-DBSCAN spatiotemporal clustering algorithm is as follows: ； in, Represents two trajectory points , The spacetime distance between them Represents two trajectory points , Geographical distance between them Represents the spatial neighborhood radius. Represents the time neighborhood radius. , Representing trajectory points respectively , Timestamp.

5. The trajectory segmentation and annotation method according to claim 3, characterized in that, The segmentation results are manually annotated to obtain the manually annotated results, including: The segmentation results are displayed in line form using a map component; By selecting segmented lines to trigger segment selection events, and selecting corresponding behavior labels in the segment selection events based on the spatiotemporal characteristics and behavioral semantics of the trajectory, manual annotation results are obtained.

6. The trajectory segmentation and annotation method according to claim 5, characterized in that, The multidimensional spatiotemporal features include: The time-dynamic characteristics consist of average velocity, velocity standard deviation, velocity change frequency, and average acceleration; Spatial pattern features consisting of trajectory curvature, convex hull area, local point density, and heading variation pattern.

7. The trajectory segmentation and annotation method according to claim 1, characterized in that, The expression for calculating the confidence level of the inference result is as follows: ； in, Indicates the confidence level. Indicates the maximum similarity. The standard deviation of the top-k similarity is represented by the following: This represents the average of the top-k similarities.

8. A trajectory segmentation and annotation device, characterized in that, include: The acquisition module is used to acquire the raw trajectory data of the moving target; The segmentation module is used to cluster the original trajectory data using a spatiotemporal clustering method to obtain multiple clusters, and then uses an adaptive sliding window to segment the trajectory in all clusters to obtain the segmentation result. The extraction module is used to manually annotate the segmented results to obtain manually annotated results, and use the manually annotated results as prior knowledge to extract features from the segmented results to obtain multidimensional spatiotemporal features; The inference module is used to automatically infer labels for unlabeled segments in the segmentation results based on multidimensional spatiotemporal features, obtain inference results, and calculate the confidence level of the inference results; An optimization module is used to optimize the inference result based on the confidence level to obtain the trajectory labeling result of the moving target.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the trajectory segmentation annotation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the trajectory segmentation annotation method as described in any one of claims 1 to 7.

Images