Method and device for extracting road information

Abstract

This disclosure provides a method and apparatus for extracting road information, relating to the field of artificial intelligence, particularly intelligent transportation. The specific implementation scheme comprises: obtaining a set of vehicle trajectories; preprocessing the set of trajectories to filter out trajectories that meet predetermined conditions, thereby obtaining a target trajectory set; calculating the similarity distances between each pair of trajectories in the target trajectory set to obtain a similarity distance matrix; calculating the correlation of the target trajectory set based on the similarity distance matrix; and, if the correlation exceeds a predetermined correlation threshold, extracting road information from the target trajectory set based on the similarity distance matrix. This embodiment enables rapid and accurate extraction of road information based on vehicle trajectories, reducing the cost of map construction.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, in particular to the field of intelligent transportation, and specifically to a method and device for extracting road information. Background Art

[0002] Map development has entered the era of electronic maps. As the most fundamental information for maps, the speed of its production and update has become a primary concern for users. Currently, the most common method of producing road data in the industry still relies on manual drawing of road shapes. Therefore, it is particularly important to use technology to reduce the manual drawing process, improve road operation efficiency, and enhance the map user experience.

[0003] Road information extraction based on vehicle trajectory data is a hot topic and also one of the difficulties in the field of geographic information. Traditional methods face problems such as high requirements for trajectory data sources, complex road extraction algorithms, and poor adaptability of different road extraction model parameters. Summary of the Invention

[0004] The present disclosure provides a method, apparatus, device, storage medium, and computer program product for extracting road information.

[0005] According to a first aspect of the present disclosure, a method for extracting road information is provided, comprising: obtaining a set of vehicle travel trajectories; preprocessing the set of target trajectories to filter out trajectories that meet predetermined conditions, thereby obtaining a set of target trajectories; calculating similarity distances between any two trajectories in the set of target trajectories to obtain a similarity distance matrix; calculating a correlation degree of the set of target trajectories based on the similarity distance matrix; and, if the correlation degree is greater than a predetermined correlation degree threshold, extracting road information from the set of target trajectories based on the similarity distance matrix.

[0006] According to a second aspect of the present disclosure, a device for extracting road information is provided, comprising: an acquisition unit configured to acquire a set of vehicle travel trajectories; a filtering unit configured to preprocess the trajectory set, filter out trajectories that meet predetermined conditions, and obtain a target trajectory set; a calculation unit configured to calculate similarity distances between any two trajectories in the target trajectory set to obtain a similarity distance matrix; an association unit configured to calculate a correlation degree of the target trajectory set based on the similarity distance matrix; and an extraction unit configured to extract road information from the target trajectory set based on the similarity distance matrix if the correlation degree is greater than a predetermined correlation degree threshold.

[0007] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the first aspect.

[0008] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method described in the first aspect when executed by a processor.

[0010] The methods and devices for extracting road information provided by the embodiments of the present disclosure can reduce computational complexity and improve accuracy by preprocessing a trajectory set and filtering out invalid trajectories. By determining the correlation between trajectories based on similarity distance, road extraction can be performed only when the correlation between trajectories is high, thus avoiding the extraction of invalid roads.

[0011] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0013] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

[0014] Figure 2 is a flowchart of an embodiment of a method for extracting road information according to the present disclosure;

[0015] Figure 3 is a schematic diagram of an application scenario of the method for extracting road information according to the present disclosure;

[0016] Figure 4 is a flowchart of another embodiment of a method for extracting road information according to the present disclosure;

[0017] Figure 5a-5b is a schematic diagram of another application scenario of the method for extracting road information according to the present disclosure;

[0018] Figure 6is a schematic structural diagram of an embodiment of a device for extracting road information according to the present disclosure;

[0019] Figure 7 It is a schematic diagram of the structure of a computer system of an electronic device suitable for implementing the embodiments of the present disclosure. DETAILED DESCRIPTION

[0020] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of the method or apparatus for extracting road information disclosed herein may be applied.

[0022] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0023] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as navigation applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0024] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with GPS (Global Positioning System) and supporting navigation functions, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0025] The server 105 may be a server that provides various services, such as a background map server that supports the navigation map displayed on the terminal devices 101, 102, and 103. The background map server may analyze and process the received GPS data, extract road information from it, and update the map, and then feed the updated map back to the terminal device.

[0026] It should be noted that a server can be either hardware or software. When a server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When a server is software, it can be implemented as multiple software programs or software modules (for example, multiple software programs or software modules used to provide distributed services), or as a single software program or software module. This is not specifically limited here. The server can also be a server in a distributed system, or a server integrated with blockchain. The server can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0027] It should be noted that the method for extracting road information provided in the embodiments of the present disclosure is generally executed by the server 105 , and accordingly, the device for extracting road information is generally provided in the server 105 .

[0028] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0029] Continue to refer Figure 2, shows a process 200 of an embodiment of a method for extracting road information according to the present disclosure. The method for extracting road information includes the following steps:

[0030] Step 201: Obtain a set of vehicle travel trajectories.

[0031] In this embodiment, the execution subject of the method for extracting road information (eg Figure 1 The server (shown in the figure) can receive vehicle travel trajectories reported by the GPS device of a user-authorized terminal device. The GPS device periodically reports the vehicle's location, i.e., track points. Track points reported by the same terminal device form a single track. To extract roads in a target area, the server can obtain a set of tracks within the target area.

[0032] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of the user's vehicle location information are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0033] Step 202 : pre-process the trajectory set, filter out trajectories that meet predetermined conditions, and obtain a target trajectory set.

[0034] In this embodiment, the effectiveness of the trajectory routing strategy is affected by many factors, such as walking trajectories, GPS interference trajectories, and complex road conditions. To address these specific problem scenarios, a multi-level classification filter strategy is established to further improve accuracy and ensure user experience. The original trajectory set is filtered to obtain the target trajectory set, and subsequent steps involve processing the target trajectory set.

[0035] Step 203 : Calculate the similarity distance between each two trajectories in the target trajectory set to obtain a similarity distance matrix.

[0036] In this embodiment, similarity distances are calculated between arbitrary trajectories. High-quality trajectories are often more similar to the majority of trajectories in the set, thus enabling target trajectory selection. Similarity distances can be calculated using common existing methods, such as the Euclidean distance algorithm and the dynamic time warping (DTW) algorithm. The similarity distances between any two trajectories can be represented using a similarity distance matrix.

[0037] The following table shows the similarity distance statistics (similarity distance matrix) in a set of trajectory sets ABCD.

[0038]

[0039] Table 1

[0040] Among them, the repeated items are listed only once, as shown in the lower half of Table 1, and the remaining elements can be set to invalid values.

[0041] The sum of the similarity distances between each trajectory and the other trajectories is statistically calculated as follows: A = 28.1, B = 38.2, C = 68.5, and D = 58.4. Trajectory C has the highest similarity distance of 68.5, which is considered the best trajectory in this set and can be used as a reference for road shape extraction.

[0042] Step 204 : Calculate the correlation degree of the target trajectory set according to the similarity distance matrix.

[0043] In this embodiment, a correlation calculation formula can be pre-designed. For example, the correlation can be the sum of all valid values ​​in the similarity distance matrix normalized according to the trajectory length, or the correlation can be the maximum valid value in the similarity distance matrix.

[0044] Step 205 : If the correlation degree is greater than a predetermined correlation degree threshold, extracting road information from the target trajectory set according to the similarity distance matrix.

[0045] In this embodiment, if the correlation is greater than a predetermined correlation threshold, the target trajectory set is valid and can be used to extract road information. Otherwise, these trajectories cannot be used to extract road information, and more valid trajectories must be obtained. The method for extracting road information may include first clustering the trajectories (e.g., using k-means clustering), and then performing curve fitting based on each cluster center to obtain road information.

[0046] The method provided by the above-mentioned embodiments of the present disclosure improves the accuracy of road extraction, reduces interference, and speeds up extraction by filtering out invalid trajectories. Furthermore, trajectories with low correlation are not used for road extraction, thus avoiding the generation of invalid maps.

[0047] In some optional implementations of this embodiment, calculating the similarity distances between any two trajectories in the target trajectory set to obtain a similarity distance matrix includes calculating the length of the longest common subsequence between any two trajectories in the target trajectory set as the similarity distance to obtain the similarity distance matrix. By calculating the similarity distances between any trajectories using the LCSS (Longest-Common-Subsequence) model, high-quality trajectories are often more similar to the majority of trajectories in the set, thereby enabling the selection of target trajectories.

[0048] Principle: Assume that there are two time series data A and B with lengths n and m respectively, then the length of the longest common subsequence is:

[0049]

[0050] Where y is a member similarity threshold, t = 1, 2, ..., n; i = 1, 2, ..., m; the distance measurement formula is:

[0051]

[0052] lon1 and lon2 are point a on time series data A. t The vertical coordinate and point b on time series data B i The vertical coordinate of .

[0053] lat1 and lat2 are point a on time series data A. t The horizontal axis and point b on the time series data B i The horizontal axis of .

[0054] LCSS is insensitive to differences in individual points in a trajectory. If two time series have similar morphologies for most of the time period but differ only briefly (even small differences can affect the similarity measurement), Euclidean distance and DTW cannot accurately measure the similarity between the two time series. LCSS, however, can address this issue, thereby improving robustness.

[0055] In some optional implementations of this embodiment, the correlation degree of the target trajectory set is calculated based on the similarity distance matrix, including: calculating the sum of the elements in the similarity distance matrix as the numerator; calculating the sum of the shortest trajectory lengths between any two trajectories as the denominator; and determining the ratio of the numerator to the denominator as the correlation degree.

[0056] By analyzing the aggregation degree of the trajectory set C, we can determine whether it is a road trajectory. That is, we can analyze the correlation degree through the trajectory similarity distance matrix and define the correlation evaluation formula:

[0057] fl=∑ i∈N ∑ j∈N lcss(c i , c j )

[0058] fa=∑ i∈N ∑ j∈N min(c i ,c j )

[0059] sti<j

[0060] TH = fl / fa

[0061] TH is the correlation degree, c i ,c j into two different trajectories.

[0062] This correlation calculation method can comprehensively measure the correlation between different trajectories in a trajectory set, thereby improving the effectiveness of road extraction.

[0063] In some optional implementations of this embodiment, before calculating the similarity distance between any two tracks in the target track set, the method further includes: if the number of tracks in the target track set is less than a predetermined threshold, continuing to acquire tracks from vehicles that do not meet the predetermined condition and adding them to the target track set, so that the number of tracks in the target track set is greater than or equal to the predetermined threshold. The predetermined threshold can be set to 3. If the number of tracks in the track set is too small, it is not representative, and the server needs to continue collecting tracks and continue road extraction when the number condition is met. This can avoid extracting invalid road information.

[0064] In some optional implementations of this embodiment, the predetermined condition includes at least one of the following: a trajectory point speed less than a predetermined speed threshold, a trajectory point time interval greater than a predetermined time threshold, a trajectory point distance interval greater than a predetermined distance threshold, a trajectory curvature greater than a predetermined curvature threshold, or a number of self-intersection points in the trajectory greater than a predetermined intersection threshold. A trajectory point speed less than the predetermined speed threshold, for example, a speed less than 3 km / h, indicates that the trajectory is not a vehicle driving trajectory but likely a pedestrian one, and therefore needs to be filtered out. A trajectory point time interval greater than a predetermined time threshold, for example, the interval for trajectory point reporting is generally set to every 1 or 3 seconds. If the trajectory point interval is greater than 25 seconds, it indicates inaccurate GPS reporting and GPS interference with the trajectory. A trajectory point distance interval greater than a predetermined distance threshold, for example, a trajectory point distance interval greater than 120 meters, indicates GPS interference with the trajectory. A trajectory curvature greater than a predetermined curvature threshold indicates that the trajectory is excessively curved and unnatural. A trajectory point self-intersection number greater than a predetermined intersection threshold, for example, two or more self-intersection points, is also considered abnormal data. Many factors affect the effectiveness of trajectory routing strategies, such as walking trajectories, GPS interference trajectories, and complex road conditions. Aiming at these specific problem scenarios, a multi-level classification filter is established to further improve the accuracy of the strategy and ensure user experience.

[0065] Continue to see Figure 3 , Figure 3 This is a schematic diagram of an application scenario of the method for extracting road information according to this embodiment. Figure 3 In this application scenario, vehicle navigation devices periodically report trajectory information to the server. Upon receiving a request to extract road information from a specified area, the server filters the trajectory set within the specified area based on the stored trajectory information. Basic denoising is performed on the trajectory set, using the following noise determination criteria: 1. Speed ​​less than 3 km / h; 2. Track interval greater than 25 seconds; 3. Track interval greater than 120 meters. Trajectories identified as noise are filtered out. Trajectories with excessive curvature or self-intersections are also filtered out. Figure 3This filtering order is merely an example; in practice, the order of basic denoising, curvature filtering, and self-intersection filtering is not limited. After filtering, a determination is made as to whether the number of remaining tracks is sufficient. If not, the road extraction process is terminated. If the number of tracks is sufficient, similarity distances are calculated between each track, and then correlation is calculated based on these similarity distances. If the correlation exceeds a predetermined correlation threshold, the road extraction process is executed. The specific road extraction process can be shown in process 400.

[0066] Further references Figure 4 , which shows a process 400 of another embodiment of a method for extracting road information. The process 400 of the method for extracting road information includes the following steps:

[0067] Step 401: Calculate the sum of similarity distances between each trajectory and other trajectories according to the similarity distance matrix.

[0068] In this embodiment, the method for extracting road information is executed on the electronic device (eg Figure 1 The server shown in FIG200 calculates the sum of similarity distances between each trajectory and other trajectories based on the similarity distance matrix obtained in step 203. For example, as shown in Table 1, the similarity distance between A and B is 15.5, the similarity distance between A and C is 0, and the similarity distance between A and D is 12.6. The sum of similarity distances between A and other trajectories is: 15.5 + 12.6 = 28.1. Similarly, the sum of similarity distances between B and other trajectories is 38.2, the sum of similarity distances between C and other trajectories is 68.5, and the sum of similarity distances between D and other trajectories is 58.4.

[0069] Step 402: The trajectory with the largest sum of similarity distances in the target trajectory set is used as a reference trajectory.

[0070] In this embodiment, if the sum of similarity distances of trajectory C in Table 1 is the largest, trajectory C is considered to be the best trajectory in the set and is used as the reference trajectory for road extraction.

[0071] Step 403: extract at least one trajectory in the same cluster as the reference trajectory from the target trajectory set.

[0072] In this embodiment, at least one clustered trajectory of the reference trajectory can be extracted from the trajectory set based on a probability density estimation algorithm. A clustered trajectory is a trajectory within a predetermined distance range around the reference trajectory. For example, the vertical coordinate of a clustered trajectory point is within a range of ±10 meters of the reference trajectory point.

[0073] Step 404 : Calculate the center line of the reference trajectory and at least one trajectory in the same cluster as the extracted candidate road.

[0074] In this embodiment, the coordinates of the reference trajectory and at least one trajectory in the same cluster are averaged to obtain a coordinate set that constitutes the center line, which is used as the extracted candidate road. This is because a road may have multiple lanes, and the center line can be used to represent the center of multiple lanes. Figure 5a As shown, the road L1 is extracted first.

[0075] Step 405 : Filter out the reference trajectory and at least one trajectory in the same cluster from the target trajectory set.

[0076] In this embodiment, the present application performs road extraction by cluster, filtering out the tracks for which road information has been extracted, without affecting the extraction of other roads.

[0077] Step 406 : If there are still other trajectories in the target trajectory set, the sums of the similarity distances of the trajectories in the updated target trajectory set are reordered, and steps 402 - 406 are repeated.

[0078] In this embodiment, if there are still other tracks in the target track set, it means that roads can be further extracted. Then, after filtering the tracks that have been confirmed as roads, the track with the largest sum of similarity distances in the target track set is taken as the reference track, and steps 402-406 are repeated. Figure 5a As shown in Figure 2, after N rounds of iterations, each calculation will output an independent path shape.

[0079] Step 407: If there are no other trajectories in the target trajectory set, the extracted candidate roads are connected and supplemented according to geometric relationships, and the road information is output.

[0080] In this embodiment, if there are no other trajectories in the target trajectory set, it means that the roads have been extracted and the topological relationship of the roads L1-LN obtained in step 406 in the set can be reconstructed. Figure 5b As shown in the left figure, L1-LN in the original trajectory is not connected. The road can be extended in the reverse direction and intersected with other roads to connect and supplement, and we can get Figure 5b The road network effect diagram on the right side of the middle. Road curves can also be fitted and then extended to intersect with other roads.

[0081] The process 400 of the method for extracting road information in this embodiment reflects the steps of extracting roads based on the similarity distance matrix, calculating the iteration conditions based on the trajectory optimization model, and realizing road network extraction by fitting the trajectory centerline. At the same time, data pre-processing, correlation analysis and other methods are combined to avoid noise areas and improve the overall road network quality.

[0082] Further references Figure 6 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for extracting road information. Figure 2Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0083] like Figure 6 As shown, the apparatus 600 for extracting road information in this embodiment includes: an acquisition unit 601, a filtering unit 602, a calculation unit 603, an association unit 604, and an extraction unit 605. The acquisition unit 601 is configured to acquire a set of vehicle trajectories; the filtering unit 602 is configured to pre-process the trajectory set, filter out trajectories that meet predetermined conditions, and obtain a target trajectory set; the calculation unit 603 is configured to calculate the similarity distance between each two trajectories in the target trajectory set to obtain a similarity distance matrix; the association unit 604 is configured to calculate the correlation degree of the target trajectory set based on the similarity distance matrix; and the extraction unit 605 is configured to extract road information from the target trajectory set based on the similarity distance matrix if the correlation degree is greater than a predetermined correlation threshold.

[0084] In this embodiment, the specific processing of the acquisition unit 601, the filtering unit 602, the calculation unit 603, the association unit 604 and the extraction unit 605 of the device for extracting road information 600 can be referred to. Figure 2 These correspond to step 201, step 202, step 203, step 204 and step 205 in the embodiment.

[0085] In some optional implementations of this embodiment, the calculation unit 603 is further configured to: calculate the length of the longest common subsequence between any two trajectories in the target trajectory set as the similarity distance, and obtain a similarity distance matrix.

[0086] In some optional implementations of this embodiment, the association unit 604 is further configured to: calculate the sum of the elements in the similarity distance matrix as the numerator; calculate the sum of the shortest trajectory lengths between any two trajectories as the denominator; and determine the ratio of the numerator to the denominator as the degree of association.

[0087] In some optional implementations of this embodiment, the extraction unit 605 is further configured to: calculate the sum of similarity distances between each trajectory and other trajectories based on a similarity distance matrix; perform the following extraction steps: use the trajectory with the largest sum of similarity distances in the target trajectory set as a reference trajectory; extract at least one trajectory in the same cluster as the reference trajectory from the target trajectory set; calculate the centerline of the reference trajectory and the at least one trajectory in the same cluster as the extracted candidate road; filter out the reference trajectory and the at least one trajectory in the same cluster from the target trajectory set; if there are still other trajectories in the target trajectory set, repeat the above extraction steps; if there are no other trajectories in the target trajectory set, connect and supplement the extracted candidate roads based on geometric relationships, and output road information.

[0088] In some optional implementations of this embodiment, the acquisition unit 601 is further configured to: before calculating the similarity distance between any two trajectories in the target trajectory set, if the number of trajectories in the target trajectory set is less than a predetermined threshold, continue to acquire trajectories of vehicles that do not meet the predetermined condition and add them to the target trajectory set, so that the number of trajectories in the target trajectory set is greater than or equal to the predetermined threshold.

[0089] In some optional implementations of this embodiment, the predetermined condition includes at least one of the following: the trajectory point speed is less than a predetermined speed threshold, the trajectory point time interval is greater than a predetermined time threshold, the trajectory point distance interval is greater than a predetermined distance threshold, the trajectory curvature is greater than a predetermined curvature threshold, and the number of self-intersection points in the trajectory is greater than a predetermined intersection threshold.

[0090] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0091] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0092] An electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in process 200 or 400.

[0093] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method described in process 200 or 400.

[0094] A computer program product includes a computer program, wherein the computer program implements the method described in flow 200 or 400 when executed by a processor.

[0095] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0096] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0097] Various components in device 700 are connected to I / O interface 705, including an input unit 706, such as a keyboard, mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, optical disk, etc.; and a communication unit 709, such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0098] The computing unit 701 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as the method for extracting road information. For example, in some embodiments, the method for extracting road information can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method for extracting road information described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the method for extracting road information by any other suitable means (e.g., via firmware).

[0099] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0101] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0104] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0105] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0106] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for extracting road information, comprising: Get the vehicle's trajectory set; Preprocessing the trajectory set, filtering out trajectories that meet predetermined conditions, and obtaining a target trajectory set; Calculating similarity distances between any two trajectories in the target trajectory set to obtain a similarity distance matrix, including: calculating the length of the longest common subsequence between any two trajectories in the target trajectory set as the similarity distance to obtain the similarity distance matrix; Calculating the association degree of the target trajectory set according to the similarity distance matrix; If the correlation degree is greater than a predetermined correlation degree threshold, extracting road information from the target trajectory set according to the similarity distance matrix includes: calculating the sum of similarity distances between each trajectory and other trajectories according to the similarity distance matrix; performing the following extraction steps: taking the trajectory with the largest sum of similarity distances in the target trajectory set as a reference trajectory; extracting at least one trajectory in the same cluster of the reference trajectory from the target trajectory set; calculating the center line of the reference trajectory and the at least one trajectory in the same cluster as the extracted candidate road; filtering the reference trajectory and the at least one trajectory in the same cluster from the target trajectory set; if there are still other trajectories in the target trajectory set, repeating the above extraction steps; if there are no other trajectories in the target trajectory set, connecting and supplementing the extracted candidate roads according to geometric relationships, and outputting road information.

2. The method according to claim 1, wherein Calculating the association degree of the target trajectory set according to the similarity distance matrix includes: Calculate the sum of each element in the similarity distance matrix as a numerator; Calculate the sum of the shortest lengths of any two trajectories as the denominator; The ratio of the numerator to the denominator is determined as the degree of association.

3. The method according to claim 1, wherein Before calculating the similarity distances between any two trajectories in the target trajectory set, the method further includes: If the number of trajectories in the target trajectory set is less than a predetermined threshold, then continue to obtain trajectories of vehicles that do not meet the predetermined condition and add them to the target trajectory set, so that the number of trajectories in the target trajectory set is greater than or equal to the predetermined threshold.

4. The method according to any one of claims 1 to 3, wherein The predetermined condition includes at least one of the following: The speed of the trajectory point is less than the predetermined speed threshold, the time interval of the trajectory points is greater than the predetermined time threshold, the distance interval of the trajectory points is greater than the predetermined distance threshold, the trajectory curvature is greater than the predetermined curvature threshold, and the number of self-intersection points in the trajectory is greater than the predetermined intersection threshold.

5. A device for extracting road information, comprising: an acquisition unit, configured to acquire a set of vehicle travel trajectories; a filtering unit configured to pre-process the trajectory set, filter out trajectories that meet predetermined conditions, and obtain a target trajectory set; a calculation unit configured to calculate similarity distances between any two trajectories in the target trajectory set to obtain a similarity distance matrix, comprising: calculating the length of the longest common subsequence between any two trajectories in the target trajectory set as the similarity distance to obtain the similarity distance matrix; an association unit, configured to calculate the association degree of the target trajectory set according to the similarity distance matrix; The extraction unit is configured to extract road information from the target trajectory set according to the similarity distance matrix if the correlation degree is greater than a predetermined correlation degree threshold, including: calculating the sum of similarity distances between each trajectory and other trajectories according to the similarity distance matrix; performing the following extraction steps: taking the trajectory with the largest sum of similarity distances in the target trajectory set as a reference trajectory; extracting at least one trajectory in the same cluster of the reference trajectory from the target trajectory set; calculating the centerline of the reference trajectory and the at least one trajectory in the same cluster as the extracted candidate road; filtering the reference trajectory and the at least one trajectory in the same cluster from the target trajectory set; if there are still other trajectories in the target trajectory set, repeating the above extraction steps; if there are no other trajectories in the target trajectory set, connecting and supplementing the extracted candidate roads according to geometric relationships, and outputting road information.

6. The device according to claim 5, wherein The association unit is further configured to: Calculate the sum of each element in the similarity distance matrix as a numerator; Calculate the sum of the shortest lengths of any two trajectories as the denominator; The ratio of the numerator to the denominator is determined as the degree of association.

7. The device according to claim 5, wherein The acquisition unit is further configured to: Before calculating the similarity distance between each pair of trajectories in the target trajectory set, if the number of trajectories in the target trajectory set is less than a predetermined threshold, then further trajectories of vehicles that do not meet the predetermined condition are obtained and added to the target trajectory set, so that the number of trajectories in the target trajectory set is greater than or equal to the predetermined threshold.

8. The device according to any one of claims 5 to 7, wherein: The predetermined condition includes at least one of the following: The speed of the trajectory point is less than the predetermined speed threshold, the time interval of the trajectory points is greater than the predetermined time threshold, the distance interval of the trajectory points is greater than the predetermined distance threshold, the trajectory curvature is greater than the predetermined curvature threshold, and the number of self-intersection points in the trajectory is greater than the predetermined intersection threshold.

9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

11. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 4.

Images