Method for establishing discrete trajectory of moving target

Abstract

The application provides a kind of mobile target discrete trajectory establishment method, comprising the following steps: S1: obtain city static data and build city function area, the city static data includes city road network;S2: according to the city road network extraction road center line, obtain traffic point, obtain topological road network;S3: the city function area is projected to the topological road network, obtains connection;S4: according to the topological relationship of road connection relationship, the topological relationship of traffic point and connection is established, obtains city topological graph;S5: according to the latitude and longitude information of mobile target determined mobile target coordinate in the position of city topological graph;S6: based on the topological connection of mobile target position class interval is established based on the time-space sequence of the mobile target, obtains discrete trajectory.The application can make travel traffic map and public traffic map present the same form, improve index efficiency;And topological road network can be obtained to simplify traffic junction, reduce storage pressure, thereby reduce trajectory storage cost.

Description

Technical Field

[0001] This invention relates to the field of traffic big data, and in particular to a method for establishing discrete trajectories of moving targets. Background Technology

[0002] The definition and calculation of trajectories are crucial foundations for traffic state detection and computation, and are the cornerstone of traffic management. Reasonable, accurate, and refined trajectories are of great significance for urban development. Currently, trajectories mostly refer to data information with spatiotemporal characteristics, formed by sampling the movement process of one or more moving objects, including sampling point location information, time information, speed, etc. As a type of big data, it meets the characteristics of large volume, real-time, and diversity. However, due to factors such as equipment and storage, it also exhibits characteristics such as spatiotemporal sequentiality, heterogeneous sampling frequency, and low data quality.

[0003] Unlike dynamic detection of fixed roads, trajectory data is obtained by periodically sampling marked individuals. It generally includes human activity trajectories, vehicle activity trajectories, animal activity trajectories, and natural law activity trajectories. Among them, traffic trajectory data is divided into two main categories: pedestrian movement data and data transmitted by various mobility positioning devices, such as vehicle-mounted GPS locators.

[0004] Recent studies on pedestrian movement data have explored various methods, including social media location tracking, mobile phone services, communication base station signals, credit card data, and subway / bus swipe data. Compared to the high independence of GPS sampling, swipe data is deeply linked to subway and bus station data, and mobile phone base stations naturally define urban spaces by their own radiation ranges.

[0005] GPS data is more readily available in the era of big data, but due to issues such as different frequencies, randomness, and low quality, a lot of effort is often spent on maps and map matching before data mining. Furthermore, due to different needs and processing methods, the results of data mining vary greatly in form but are similar and interconnected in conclusion. In addition, there are problems such as storage difficulty and high storage cost, and low indexing efficiency.

[0006] It should be noted that the information disclosed in the background section above is only for understanding the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this invention is to solve the problem of reducing the difficulty of storing urban traffic trajectories and to provide a method for establishing discrete trajectories of moving targets.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] A method for establishing a discrete trajectory of a moving target includes the following steps:

[0010] S1: Acquire urban static data and construct urban functional zones, wherein the urban static data includes the urban road network;

[0011] S2: Extract road centerlines and traffic points from the urban road network to obtain the topological road network;

[0012] S3: Project the urban functional areas onto the topological road network and obtain connections;

[0013] S4: Establish the topological relationships between traffic points and connections based on road connectivity to obtain a city topology map;

[0014] S5: Determine the location of the moving target's coordinates on the city topology map based on the obtained latitude and longitude information of the moving target;

[0015] S6: Based on the spatiotemporal sequence of the moving target, establish the topological connection relationship between the position classes of the moving target to obtain the discrete trajectory.

[0016] In some embodiments, the traffic point mentioned in step S2 includes location information and road segment information, represented by the following formula:

[0017] Transportation point i ={Type: Traffic, Attribute: {Longitude}} i ,latitude i ,Spend}}

[0018] i represents the i-th intersection, and type represents the type of record topological point. Attributes include: longitude, latitude, and degree. Degree represents the number of connections in the graph representation.

[0019] In some embodiments, step S2 includes: establishing a grid-filled urban road network, converting road lines into road surfaces, and then extracting connectivity relationships to obtain road centerlines.

[0020] In some embodiments, step S2 includes: interrupting roads longer than one kilometer at the traffic points, except for road hubs, to ensure that the interval between two adjacent hubs does not exceed one kilometer, so as to reduce traffic observation blind spots.

[0021] In some embodiments, step S5 uses the nearest neighbor algorithm to determine the location of the current coordinates in the city topology map.

[0022] In some embodiments, the latitude and longitude information of the moving target is acquired by a GPS device, and the nearest neighbor algorithm uses k-nearest neighbors based on Manhattan distance to calculate the affiliation of the i-th GPS latitude and longitude location point, as expressed by the following formula:

[0023]

[0024] Where i represents the i-th set of latitude and longitude data collected by the GPS device, and j represents the j-th topological point in the topological point set.

[0025] In some embodiments, the connection described in step S3 includes location information and semantic information, as expressed by the following formula:

[0026] connect j ={Type:Connection, Attribute:{Longitude}} j ,latitude j semantic vector j Regional center point j}}

[0027] j represents the j-th connection, the type indicates that the topological point is a connection, and the attributes include the point's longitude, latitude, the corresponding region's center point, and the semantic vector of the region it represents.

[0028] In some embodiments, in step S4, the city topology map uses urban demand units as basic topology points and urban road networks as the topology relationships of urban demand units in the macro-city layer reflecting city functions; and uses road intersections and connections as basic topology points and multi-directional road networks as the traffic topology relationships in the road meso-level layer reflecting traffic conditions; the topology points of the macro-city layer are connected to the topology points of the meso-level road layer.

[0029] In some embodiments, the discrete trajectory in step S6 is represented by an order of finite topological points, as expressed by the following formula:

[0030] trajectory 时刻1,时刻k ={Topological point 1→Topological point 2→…→Topological point k}

[0031] trajectory 时刻1,时刻k Let i represent the trajectory of the moving target between time 1 and time k. The topological point i represents the functional point where the individual is located at time i, and is the smallest observation unit of the individual trajectory topology, where i = 1, 2, ..., k.

[0032] The present invention also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0033] The present invention has the following beneficial effects:

[0034] This invention establishes a static and universal traffic pattern in cities based on traffic points and connections. It matches disordered and low-quality latitude and longitude information of mobile targets to a limited number of static topological points, resulting in a series of stable static semantic point settings. This enables travel maps and public transportation maps to present the same format, solving the problem of breaking down data fusion barriers between private and public travel, thereby improving indexing efficiency. By extracting road centerlines and obtaining traffic points from the urban road network, the topological road network settings can simplify traffic inflection points in the road network, reduce storage pressure and storage difficulty, and thus reduce trajectory storage costs.

[0035] Other beneficial effects of the embodiments of the present invention will be further described below. Attached Figure Description

[0036] Figure 1 This is a flowchart of the method for establishing the discrete trajectory of a moving target in an embodiment of the present invention. Detailed Implementation

[0037] The embodiments of the present invention will be described in detail below. It should be emphasized that the following description is merely exemplary and not intended to limit the scope and application of the present invention.

[0038] GPS data is often stored in JSON format. Each piece of information contains a large amount of irrelevant information in addition to its spatiotemporal coordinates, significantly increasing storage difficulty and cost. Furthermore, trajectory data mining only requires extracting the spatiotemporal coordinate information from the GPS data and performing various traffic observations based on the spatiotemporal topology map; the large amount of irrelevant information results in very low indexing efficiency. Therefore, this invention provides a method for establishing discrete trajectories of moving targets to solve this problem. (Refer to...) Figure 1 The embodiments of the present invention include the following steps:

[0039] S1: Acquire urban static data and construct urban functional zones, wherein the urban static data includes the urban road network;

[0040] S2: Extract the road centerline and obtain traffic points from the urban road network to obtain the topological road network. The traffic points are the coordinates of intersections in the urban road network.

[0041] S3: Project the urban functional areas onto the topological road network, and define the projection points of the urban functional areas as connections, and obtain the connections;

[0042] S4: Establish the topological relationships between traffic points and connections based on road connectivity to obtain a city topology map;

[0043] S5: Determine the location of the moving target's coordinates on the city topology map based on the obtained latitude and longitude information of the moving target. The latitude and longitude information of the moving target includes the latitude and longitude information of vehicles or pedestrians obtained through pedestrian mobile phones.

[0044] S6: Based on the spatiotemporal sequence of the moving target, establish topological connections between the moving target location classes. Topological connections refer to the relationships between points in the graph topology network to obtain discrete trajectories.

[0045] Specifically, the following steps are included:

[0046] S1. Obtain urban area outlines, latitude and longitude of area entrances and exits, urban road networks, and other static urban data to construct urban functional zones. Area outline data and static urban road network data can be obtained by accessing open-source street view maps, and area entrance and exit data can be obtained by accessing the Gaode Open Platform. In this embodiment, urban building land area data is downloaded from a geographic mapping website to obtain building outline information. A request is sent to the Gaode Open Platform to search for points of interest (POIs) and the latitude and longitude of parking lot entrances within the building land area, i.e., the latitude and longitude and names of area entrances and exits. The road grid encapsulates the building outlines into communities, and the parking lot entrances and exits are the interaction points between the communities and the outside world. The semantic information of the communities is quantitatively characterized by the use of points of interest.

[0047]

[0048] Continuing the point-of-interest (POI) classification method of the Gaode Open Platform, a total of eighteen categories of built environments are included in POIs: vehicle services, catering services, shopping services, lifestyle services, sports and leisure services, healthcare services, accommodation services, commercial and residential properties, government agencies and social organizations, science, education and culture services, transportation facilities services, financial and insurance services, and companies and enterprises. The proportion of each POI category in the total semantics is represented as the semantic vector of the region.

[0049] S2. Extract road centerline vectors to simplify the urban road network. Urban road networks, including expressways, arterial roads, secondary arterial roads, local roads, and internal roads, can be obtained through open-source street view maps (OpenStreetMap, OSM) or other means. In this embodiment, a raster-filled urban road network is established. After converting road lines into road surfaces, connectivity is extracted to obtain road centerlines. The specific steps are as follows: a 50-meter buffer zone is established for all roads; foreground points are blacked out and background points are whitened before re-importing; the urban road network is converted from line vectors to surface vectors; and the single line located at the center of the enclosure is directly derived using geographic mapping software based on the given width parameters, i.e., the road centerline is extracted, traffic points are obtained, and the topological road network is obtained. Traffic points contain location information and road segment information, represented by the following formula:

[0050] Transportation point i ={Type: Traffic, Attribute: {Longitude}} i ,latitude i ,Spend}}

[0051] i represents the i-th intersection, and type represents the type of topological point recorded. Attributes include: longitude, latitude, and degree. Degree represents the number of connections in the graph representation.

[0052] In this embodiment, in addition to road hubs, traffic points are manually interrupted for longer roads exceeding one kilometer to ensure that the interval between two adjacent hubs does not exceed one kilometer, thereby reducing blind spots in traffic observation. The road centerlines extracted in this embodiment only retain main roads, secondary roads, urban arterial roads, branch roads, and urban lanes.

[0053] S3. Project the area's entrances and exits onto the nearest neighbor city road network and define the projection points as connections. Project the urban functional areas derived in S1 onto the topological road network derived in S2. If the area's entrances and exits are accessible on Gaode Maps, then the entrances and exits are directly used to replace the urban functional area projection. For residential areas lacking urban functional area entrances and exits, the perpendicular from the center point of the residential area to this road is used as the alternative. Residential areas are subsets of urban functional areas. These projection points are called connections. The nearest neighbor projection involves drawing perpendicular lines from the coordinates of the area's entrance and exit to the surrounding roads, taking the shortest line as the road connected to the entrance / exit, and then defining the projection points located on these roads as connections. Connections contain both location and semantic information, represented by the following formula:

[0054] connect j ={Type:Connection, Attribute:{Longitude}} j ,latitude j semantic vector j Regional center point j}}

[0055] j represents the j-th connection, the type indicates that the topological point is a connection, and the attributes include the point's longitude, latitude, the corresponding region's center point, and the region's semantic vector;

[0056] S4. The simplified road network in S2 only contains road vectors and road intersection location information. This step adds the connections obtained in S3 to the road network, establishes the topological relationships between traffic points and connections based on road connectivity, obtains the redefined roads and road network, and acquires the city topology map:

[0057]

[0058] Topological graph = (topological vertex set, edge set)

[0059] In the above formula, the superscript O of the topological points in the edge indicates the starting intersection, D indicates the ending intersection, and k indicates the k-th connection in the road; the subscript indicates the attributes of the topological point, including intersection and connection. Finally, the urban road network is represented as a combination of the road set and the topological point set.

[0060] In this embodiment, the city topology map uses urban demand units as basic topology points and the urban road network as the topological relationship of urban demand units at the macro-level city layer, which reflects urban functions; and road intersections and connections as basic topology points at the meso-level road layer, which reflects traffic conditions, and multi-directional road networks as the traffic topology relationship. The topology points at the macro-level city layer are connected to the topology points at the meso-level road layer. The city topology map has formal consistency at both the macro and meso levels.

[0061] S5. Determine the location of the moving target's coordinates on the city topology map based on its latitude and longitude information. In this embodiment, the moving target is a vehicle, and its latitude and longitude information is collected by a GPS device. The nearest neighbor algorithm is used to determine the current coordinates' location on the city topology map. The nearest neighbor algorithm uses k-nearest neighbors based on Manhattan distance to calculate the membership of the i-th GPS latitude and longitude location point.

[0062]

[0063] In the formula, |·| represents the absolute value of a number or the number of elements in a set, where i represents the i-th set of latitude and longitude data collected by the GPS device, and j represents the j-th topological point in the topological point set. After determining the nearest neighbor topological point of a single GPS sampling location, a threshold of 20m is set to filter the nearest neighbor distance to determine whether the vehicle belongs to a node or a road, thus achieving trajectory discretization.

[0064] In this embodiment, the nearest neighbor algorithm is used to determine the current coordinates in the city topology map. Other algorithms may also be used in some embodiments.

[0065] S6. Based on the spatiotemporal sequence of the moving target, establish topological connections between the position classes of the moving target to obtain discrete trajectories: rearrange the spatiotemporal sequence obtained in S5 to obtain the discrete trajectory of a certain unit between time 1 and time k as follows:

[0066] trajectory 时刻1,时刻k ={Topological point 1→Topological point 2→…→Topological point k}

[0067] The above formula defines the trajectory as a time-ordered sequence of discrete and finite topological points, where the vehicle transitions between these points. 时刻1,时刻k The trajectory of the moving target is represented between time 1 and time k. The topological point i (i = 1, 2, ..., k) represents the functional point where the individual is located at time i, and is the smallest observation unit of the individual trajectory topology.

[0068] This embodiment proposes a method for establishing discrete trajectories of moving targets (vehicles) based on a limited set of semantically rich urban topological points. The method includes: collecting the latitude and longitude coordinates and building outlines of urban parking lots, charging stations, and gas stations as urban functional zones, which are the basic demand units of the city; calculating the semantic vectors of POIs (Points of Interest) within each functional zone as its basic attributes; collecting the main urban road network, calculating the latitude and longitude coordinates of all road intersections, defining the projections of each functional zone entrance / exit onto the road network as connections and calculating coordinates; connecting the points determined in the above steps to form roads; connecting the roads determined in the above steps to form the urban topological road network; collecting spatiotemporal sequence data of vehicle GPS data, and directly performing nearest neighbor analysis on the location sequences based on the topological points determined in the above steps; and establishing topological connections between location classes determined in the above steps based on the time series of GPS data. To bridge the differences in trajectory data mining across different forms, reduce trajectory storage costs, improve indexing efficiency, and extend vehicle travel paths from roads to communities, this embodiment draws on the topological relationship between stations and vehicles in rail transit, establishing static and universal traffic patterns in the city based on traffic points and connections, thereby matching disordered and low-quality GPS sampling data to a limited set of static topological points. The embodiments of this invention aim to extract discrete, static urban traffic patterns from continuous, dynamic GPS positioning signals, break down the data fusion barriers between private and public travel, achieve higher data mining efficiency with lower storage costs, and thus make it possible to establish an urban information system that integrates autonomous driving, traffic observation, and urban planning at all levels.

[0069] Experimental example:

[0070] Taking Hangzhou as an example, the city has six core areas with a population density exceeding 3,000 people per square kilometer: Shangcheng District, Xiacheng District, Jianggan District, Gongshu District, Xihu District, and Binjiang District, resulting in heavy traffic pressure. Downloading from open-source street view maps, the core areas of Hangzhou contain 26,659 roads and 26,299 buildings, encompassing 174,947 traffic vertices (the vertices typically used in vector road network storage). After road network reconstruction in this invention's experimental example, all Hangzhou semantics are compressed to 2,758 connections and 4,210 hubs, with 6,968 topological points combined into 9,055 topological edges.

[0071] Taking the journey of vehicle VIM code LB378Y4W8JA183234 on September 6, 2021 as an example, a point was sampled at a long interval of 50 seconds, resulting in 1396 GPS records for that day. The vehicle remained near 120.107432°E, 30.245266°N from 00:00 to 09:03 and after 17:24, and near 120.201032°E, 30.296128°N from 14:26 to 14:56. Using the method of this embodiment, the vehicle's stopping information was mined. The Lingyin Branch Road 2 and Lingyin Branch Road parking lot, located at 120.107352412°E, 30.2461876371°N, were considered the vehicle's main stopping points. The remaining journey was projected into a subgraph composed of 421 sequentially connected topological points.

[0072] The above steps successfully converted the continuous GPS sequence into a discrete topological trajectory, abstracting a series of stable static semantic points from the disordered vehicle signals, which is of great significance for traffic condition observation and trajectory storage.

[0073] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0075] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0076] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0077] The above description provides a further detailed explanation of the present invention in conjunction with specific / preferred embodiments, and it should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various substitutions or modifications can be made to these described embodiments without departing from the concept of the present invention, and all such substitutions or modifications should be considered within the scope of protection of the present invention. In the description of this specification, the reference to terms such as "an embodiment," "some embodiments," "preferred embodiment," "example," "specific example," or "some examples," etc., indicates that the specific features, structures, materials, or characteristics described in connection with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples. Although the embodiments of the present invention and their advantages have been described in detail, it should be understood that various changes, substitutions, and modifications can be made herein without departing from the scope of protection of the patent application.

Claims

1. A method for establishing a discrete trajectory of a moving target, characterized in that, Includes the following steps: S1: Acquire urban static data and construct urban functional zones, wherein the urban static data includes the urban road network and the urban functional zones include the basic demand units of the city; S2: Extract road centerlines and traffic points from the urban road network to obtain the topological road network; S3: Project the urban functional areas onto the topological road network and define the projection points as connections, then obtain the connections; S4: Establish the topological relationships of traffic points and connections based on road connectivity to obtain the redefined roads and topological road network, and obtain the city topology map; S5: Determine the location of the moving target's coordinates on the city topology map based on the obtained latitude and longitude information of the moving target; S6: Based on the spatiotemporal sequence of the moving target, establish the topological connection relationship between the position classes of the moving target, and represent the discrete trajectory of the moving target with the sorting of a finite number of topological points.

2. The method as described in claim 1, characterized in that, The traffic point mentioned in step S2 includes location information and road segment information, which is represented by the following formula: ； Indicates the first Each intersection is a record of a topological point. The type indicates the type of the record, and the attributes include longitude, latitude, and degree. The degree represents the number of connections in the graph representation.

3. The method as described in claim 1, characterized in that, Step S2 includes: establishing a grid-filled urban road network, converting road lines into road surfaces, and then extracting connectivity relationships to obtain road centerlines.

4. The method as described in claim 1, characterized in that, Step S2 includes: interrupting roads longer than one kilometer at the traffic points, except for road hubs, to ensure that the interval between two adjacent hubs does not exceed one kilometer, so as to reduce traffic observation blind spots.

5. The method as described in claim 1, characterized in that, In step S5, the nearest neighbor algorithm is used to determine the current coordinates in the city topology map.

6. The method as described in claim 5, characterized in that, The latitude and longitude information of the moving target is collected by a GPS device, and the nearest neighbor algorithm uses the k-nearest neighbor algorithm based on Manhattan distance to calculate the k-th nearest neighbor. A GPS latitude and longitude location point is subordinate, as expressed by the following formula: ； Where i represents the i-th set of latitude and longitude data collected by the GPS device, and j represents the j-th topological point in the topological point set.

7. The method as described in claim 1, characterized in that, The connection described in step S3 includes location information and semantic information, as expressed by the following formula: ； Indicates the first Each connection is a topological point that is connected. Its attributes include the point's longitude, latitude, the center point of the corresponding region, and the semantic vector of the region it represents.

8. The method as described in claim 1, characterized in that, In step S4, the city topology map uses urban demand units as basic topology points and urban road networks as the topology relationships of urban demand units in the macro-city layer that reflects urban functions; and uses road intersections and connections as basic topology points and multi-directional road networks as the traffic topology relationships in the road meso-level layer that reflects traffic conditions; the topology points of the macro-city layer are connected to the topology points of the meso-level road layer.

9. The method as described in claim 1, characterized in that, In step S6, the discrete trajectory is represented by a finite order of topological points, as shown by the following formula: ； Let i represent the trajectory of the moving target between time 1 and time k. The topological point i represents the functional point where the individual is located at time i, and is the smallest observation unit of the individual trajectory topology, where i = 1, 2, ..., k.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method as described in any one of claims 1-9.

Images