Method, device, computer device, storage medium and program product for constructing scene library

Abstract

This application relates to a method, apparatus, computer device, storage medium, and program product for constructing a scene library. The method includes: acquiring map information of a target area and tracking data of target vehicles collected by roadside equipment within the target area; performing scene filtering based on the map information and tracking data to determine the scene information corresponding to the target vehicles; and constructing a scene library based on the scene information. Since roadside equipment has a large collection range and collects a large amount of data, introducing tracking data collected by roadside equipment expands the scope of scene information, thereby expanding the scene scope of the scene library. Furthermore, combining map information and tracking data for scene filtering makes the location of scene information more accurate, improving the accuracy of scene information and thus improving the accuracy of the scene library.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, apparatus, computer device, storage medium, and program product for constructing a scene library. Background Technology

[0002] In the field of autonomous driving, the autonomous driving scenario library is an important tool for testing and evaluating the performance of autonomous vehicles. During the autonomous driving process, various traffic environments and driving situations can be simulated based on the scenario data in the scenario library, helping researchers and engineers to test and verify autonomous driving systems.

[0003] In traditional technologies, perception data is typically acquired through cameras and sensors on the vehicle, and then classified to build a scene library.

[0004] However, traditional database construction methods suffer from incomplete coverage of scenario data. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, storage medium, and program product for constructing a scene library that can expand the coverage of scene data, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for constructing a scene library, the method comprising:

[0007] Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area;

[0008] Scene filtering is performed based on the map information and the tracking data to determine the scene information corresponding to the target vehicle;

[0009] A scene library is constructed based on the scene information.

[0010] In one embodiment, the step of determining the scene information corresponding to the target vehicle by performing scene filtering based on the map information and the tracking data includes:

[0011] Based on the map information and the tracking data, the lane area where the target vehicle is located is determined;

[0012] At least one scene filtering logic is determined based on the lane area;

[0013] The scene information is determined by filtering the scene based on the scene filtering logic and the tracking data.

[0014] In one embodiment, the step of determining the scene information by filtering the scene based on the scene filtering logic and the tracking data includes:

[0015] The driving trajectory of the target vehicle is extracted from the tracking data;

[0016] Determine whether the driving trajectory meets the scenario filtering logic;

[0017] If the driving trajectory satisfies the scene filtering logic, then the scene information is extracted from the tracking data.

[0018] In one embodiment, determining whether the driving trajectory satisfies the scene filtering logic includes:

[0019] Based on the driving trajectory, determine the coordinate positions of the target vehicle at multiple times;

[0020] Based on the scene filtering logic, determine the coordinate range corresponding to multiple time points;

[0021] If there exists a coordinate position at any given moment that falls within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scenario filtering logic.

[0022] In one embodiment, constructing the scene library based on the scene information includes:

[0023] The scene information is formatted to form a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information;

[0024] Add the scene structure to the scene library.

[0025] In one embodiment, the method further includes:

[0026] Obtain weather information for the target area;

[0027] The weather information is format-converted to form a weather structure, and the weather structure is added to the weather information database; the tracking data is format-converted to form a tracking data structure, and the tracking data structure is added to the tracking database.

[0028] A first mapping relationship is established based on the time information of the scene database and the time information of the weather database, and a second mapping relationship is established based on the time information of the scene database and the time information of the tracking database.

[0029] In one embodiment, the method further includes:

[0030] Receive a scene library retrieval request sent by a user equipment, and determine user scene data from the scene library according to the scene library retrieval request;

[0031] A user scenario library is generated based on the user scenario data, and the user scenario library is sent to the user device.

[0032] Secondly, this application also provides an apparatus for building a scene library, comprising:

[0033] The first acquisition module is used to acquire map information of the target area and tracking data of target vehicles collected by roadside equipment within the target area;

[0034] The filtering module is used to filter scenes based on the map information and the tracking data to determine the scene information corresponding to the target vehicle.

[0035] The construction module is used to build a scene library based on the scene information.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area;

[0038] Scene filtering is performed based on the map information and the tracking data to determine the scene information corresponding to the target vehicle;

[0039] A scene library is constructed based on the scene information.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0041] Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area;

[0042] Scene filtering is performed based on the map information and the tracking data to determine the scene information corresponding to the target vehicle;

[0043] A scene library is constructed based on the scene information.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0045] Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area;

[0046] Scene filtering is performed based on the map information and the tracking data to determine the scene information corresponding to the target vehicle;

[0047] A scene library is constructed based on the scene information.

[0048] The aforementioned method, apparatus, computer equipment, storage medium, and program product for constructing the scene library acquire map information of the target area and tracking data of target vehicles collected by roadside equipment within the target area; perform scene filtering based on map information and tracking data to determine the scene information corresponding to the target vehicles; and construct the scene library based on the scene information. Since the roadside equipment has a large collection range and collects a large amount of data, the introduction of tracking data collected by roadside equipment expands the scope of scene information, thereby expanding the scope of the scene library. Furthermore, combining map information and tracking data for scene filtering makes the location of scene information more accurate, improving the accuracy of scene information and thus improving the accuracy of the scene library. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is an application environment diagram of a scene library construction method in one embodiment;

[0051] Figure 2 This is a flowchart illustrating the method for constructing a scene library in one embodiment;

[0052] Figure 3 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0053] Figure 4 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0054] Figure 5 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0055] Figure 6 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0056] Figure 7 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0057] Figure 8 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0058] Figure 9 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0059] Figure 10 This is a flowchart illustrating the method for constructing a scene library in another embodiment;

[0060] Figure 11 This is a structural block diagram of a scene library construction device in one embodiment;

[0061] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] The method for constructing a scene library provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, roadside device 102 communicates with server 104 via a network. A data storage system stores the data that server 104 needs to process. This data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server. Server 104 acquires map information of the target area and tracking data of target vehicles collected by roadside device 102 within the target area, thereby constructing a scene library based on the map information and tracking data. Roadside device 102 can be various sensors such as cameras and radar. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0064] In one embodiment, such as Figure 2 As shown, a method for building a scene library is provided, which can be applied to... Figure 1 Taking the server in the example of this, the explanation includes:

[0065] S201, acquire map information of the target area and tracking data of target vehicles collected by roadside equipment within the target area.

[0066] The map information for the target area may include lane number, lane area, lane center line, lane speed limit, etc.; the roadside equipment may include data collection devices such as LiDAR and cameras.

[0067] In this embodiment, the server may pre-store map information of the target area, or the server may interact with a third-party device to obtain map information of the target area. Roadside equipment within the target area collects driving images of the target vehicle and performs image processing, feature extraction, and other operations on the collected driving images to obtain tracking data of the target vehicle within the target area.

[0068] Optionally, the roadside equipment can send driving images to a server, where the server performs image processing and feature extraction on the driving images to obtain tracking data of the target vehicle within the target area; or, the roadside equipment can perform image processing and feature extraction on the driving images to obtain tracking data of the target vehicle within the target area and then send the tracking data to the server.

[0069] Optionally, the tracking data may include the latitude and longitude, speed information, and size information of the target vehicle at various times. The coordinate information of the target vehicle can be determined based on the latitude and longitude and speed information, and the coordinate information can be added to the tracking data. For example, the coordinate system can be set with the radar and camera as the origin, and the latitude and longitude information of the target vehicle can be converted to obtain the coordinate information of the target vehicle in the road coordinate system.

[0070] S202, based on map information and tracking data, performs scene filtering to determine the scene information corresponding to the target vehicle.

[0071] In this embodiment of the application, multiple candidate scenes can be determined based on map information, and further, scene information corresponding to each candidate scene can be filtered out from the tracking data.

[0072] Optionally, the tracking data may include tracking data of the target vehicle in multiple sub-regions of the target area. Scene filtering is performed based on map information and the tracking data of multiple sub-regions to determine the scene information corresponding to the target vehicle in each sub-region. Alternatively, the tracking data may include tracking data of the target vehicle in multiple time periods. Scene filtering is performed based on map information and the tracking data of multiple time periods to determine the scene information corresponding to the target vehicle in each time period.

[0073] S203, Build a scene library based on scene information.

[0074] In this embodiment of the application, the scene information is encapsulated to obtain a scene library, or the scene information is stored in an existing scene library to obtain an updated scene library.

[0075] Optionally, the storage location of the scene information in the scene library can be determined based on the scene corresponding to the scene information, and the scene information can be stored in the corresponding location to obtain the scene library.

[0076] The aforementioned method for constructing the scene library involves acquiring map information of the target area and tracking data of target vehicles collected by roadside equipment within that area; filtering scenes based on the map information and tracking data to determine the scene information corresponding to the target vehicles; and constructing the scene library based on this scene information. Since roadside equipment has a large collection range and collects a large amount of data, introducing tracking data from roadside equipment expands the scope of scene information, thereby expanding the scene library's scope. Furthermore, combining map information and tracking data for scene filtering makes the location of scene information more accurate, improving the accuracy of scene information and ultimately enhancing the accuracy of the scene library.

[0077] In one embodiment, one implementation of S202 above is provided, such as... Figure 3 As shown, the above-mentioned "screening scenes based on map information and tracking data to determine the scene information corresponding to the target vehicle" includes:

[0078] S301 determines the lane area where the target vehicle is located based on map information and tracking data.

[0079] In this embodiment, the map information includes lane numbers for each lane area, as well as information such as the lane area, lane center line, and lane speed limit corresponding to each lane number. Based on the latitude and longitude of the target vehicle in the tracking data, the lane area where the target vehicle is located is determined in the map information. Optionally, the map information includes the latitude and longitude range of each lane area. The latitude and longitude range corresponding to the target vehicle is determined, and the lane area corresponding to this latitude and longitude range is determined as the lane area where the target vehicle is located.

[0080] S302, determine at least one scene filtering logic based on the lane area.

[0081] The scene filtering logic can include speeding scene filtering logic, red light running scene filtering logic, lane changing scene filtering logic, collision scene filtering logic, etc.

[0082] In this embodiment of the application, a filtering logic library is pre-established, as well as the correspondence between each filtering logic in the filtering logic library and the lane area. Based on the correspondence and the lane area where the target vehicle is located, at least one scene filtering logic corresponding to the tracking data of the target vehicle is determined.

[0083] S303: Based on the scene filtering logic and tracking data, scene information is determined by filtering scenes.

[0084] In this embodiment of the application, for each scene filtering logic, it is determined whether the tracking data meets the scene filtering logic. If it does, the scene information corresponding to the scene filtering logic is determined from the tracking data, and it is determined whether the tracking data meets the next scene filtering logic. If it does not meet, it is determined whether the tracking data meets the next scene filtering logic.

[0085] For example, the scene selection logic may include a logic rule function that iterates through the tracking data of each frame, executes the logic rule function for each type of scene determination in turn, performs threshold determination on each parameter in the tracking data and performs logical determination on parameter changes between consecutive frames, records the target information that meets the logic rule or threshold and the corresponding timestamp, and continuously performs determination and updates. If the determination logic and threshold are not triggered within a specified time threshold after the timestamp of the scene is recorded, it means that the scene ends, the scene number value is incremented by 1, and the scene information is recorded. The scene number can be in the format of "year_month_day_number", and the number is updated to 0 from 0:00 every day based on the timestamp determination.

[0086] In the above application embodiments, the lane area where the target vehicle is located is first determined based on map information and tracking data. Then, the scene filtering logic is determined based on the lane area, which improves the accuracy of the scene filtering logic and thus improves the accuracy of the scene information.

[0087] In one embodiment, one implementation of S303 above is provided, such as... Figure 4 As shown, the above-mentioned "screening scenes based on scene filtering logic and tracking data to determine scene information" includes:

[0088] S401 extracts the target vehicle's trajectory from the tracking data.

[0089] The target vehicle's trajectory may include the target vehicle's coordinates at various times; or, the target vehicle's trajectory may be a trajectory map.

[0090] In this embodiment of the application, the tracking data may include the driving trajectory of the target vehicle, and the driving trajectory of the target vehicle may be read from the tracking data; or, the tracking data may include the location information and time information of the target vehicle, so as to determine the driving trajectory of the target vehicle based on the location information and time information of the target vehicle. For example, the location information of the target vehicle may be the latitude and longitude of the target vehicle.

[0091] S402, determine whether the driving trajectory meets the scenario filtering logic.

[0092] As an optional implementation, if the driving trajectory includes the coordinates of the target vehicle at each time, it can be determined whether the driving trajectory meets the scene filtering logic based on the scene filtering logic and the coordinates of the target vehicle at each time.

[0093] As another optional implementation, if the driving trajectory includes a driving trajectory map and the scene filtering logic includes a preset trajectory map, then the overlap between the driving trajectory map and the preset trajectory map can be determined. When the overlap is greater than the preset overlap threshold, the driving trajectory is determined to meet the scene filtering logic.

[0094] S403 If the driving trajectory meets the scene filtering logic, then scene information is extracted from the tracking data.

[0095] In this embodiment of the application, if the driving trajectory meets the scene filtering logic, the tracking data can be determined as the scene information corresponding to the scene filtering logic. Alternatively, the scene information can be determined from the tracking data according to the preset scene information format. Optionally, the preset scene information format may include the data type in the scene information.

[0096] In the above application embodiments, based on whether the driving trajectory of the target vehicle meets the scene filtering logic, it is determined whether the scene information corresponding to the scene filtering logic can be extracted from the tracking data, thereby improving the accuracy and reliability of the scene information.

[0097] In one embodiment, one implementation of the above-described S402 is provided, such as... Figure 5 As shown, the above "determining whether the driving trajectory meets the scenario filtering logic" includes:

[0098] S501 determines the coordinates of the target vehicle at multiple times based on its driving trajectory.

[0099] In this embodiment of the application, the driving trajectory includes the latitude and longitude of the target vehicle at each time. The latitude and longitude of the target vehicle at each time are converted to obtain the coordinate position of the target vehicle in the road coordinate system at each time.

[0100] S502 determines the coordinate range corresponding to multiple time points based on the scene filtering logic.

[0101] In this embodiment of the application, the scene filtering logic includes multiple coordinate ranges and the correspondence between each coordinate range and time, so as to determine the coordinate ranges corresponding to multiple times from the scene filtering logic based on the correspondence and multiple times.

[0102] S503 If there exists a coordinate position at any given moment that is within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scenario filtering logic.

[0103] In this embodiment of the application, it is determined whether the coordinate position corresponding to each time point is within the coordinate range corresponding to each time point. If there is a coordinate position corresponding to any time point that is within the corresponding coordinate range, then it is determined that the driving trajectory satisfies the scene filtering logic.

[0104] For example, in a red light violation scenario, the coordinate range corresponding to each moment can be the same. If the coordinate position corresponding to any moment is within that coordinate range, it indicates that the target vehicle has violated the red light violation behavior, and the driving trajectory satisfies the red light violation scenario filtering logic.

[0105] In the above application embodiments, the coordinate positions of the target vehicle at multiple times are now determined based on the driving trajectory. Thus, based on the coordinate positions at each time, it is determined that the driving trajectory meets the scene filtering logic, thereby improving the accuracy of the determination results.

[0106] In one embodiment, one implementation of S203 above is provided, such as... Figure 6 As shown, the above "building a scene library based on scene information" includes:

[0107] S601 converts the scene information into a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information.

[0108] The scene time information includes the scene start timestamp and the scene end timestamp, and the scene main target identifier can be the target vehicle identifier.

[0109] In this embodiment, the scene information is format-converted according to a first preset format, thereby arranging the data in the scene information according to the first preset format to form a scene structure. Optionally, the process of constructing the scene library in this embodiment can be as follows: Figure 7 As shown, the data format of the scene structure can be [scene number, scene type, scene main target identifier, scene start timestamp, scene end timestamp].

[0110] S602, add the scene structure to the scene library.

[0111] In this embodiment, the scene structure is added to the scene library. Each scene data is saved separately as a comma-separated values ​​(csv) file, named "scene_scene number_scene type value". The files are stored in a folder named "scene_year_month_day_hour" and the files in the folder are named "scene_year_month_day_hour_number".

[0112] In the above application embodiments, scene information is added to the scene library according to a scene structure in a unified format, which facilitates the management of the scene library and the retrieval of scene information, thereby improving the efficiency of calling scene information.

[0113] In one embodiment, such as Figure 8 As shown, the method for constructing the above-mentioned scene library also includes:

[0114] S204, Obtain weather information for the target area.

[0115] In this embodiment of the application, image recognition processing can be performed on the images collected by the roadside equipment to obtain the weather information corresponding to the images in each time period; or, a weather information acquisition request can be sent to a third-party device to receive the weather information of the target area returned by the third-party device. Optionally, the weather acquisition device can be a server of a meteorological center.

[0116] S205 converts the format of weather information to form a weather structure and adds the weather structure to the weather information database; and converts the format of tracking data to form a tracking data structure and adds the tracking data structure to the tracking database.

[0117] In this embodiment, the weather information is format-converted according to a second preset format, thereby arranging the data in the weather information according to the second preset format to form a weather structure. Further, each weather structure is formed into a CSV file, named "env_year_month_day_hour_minute", and the CSV files formed by the weather structures are added to the weather information database. Similarly, the tracking information is format-converted according to a third preset format, thereby arranging the data in the tracking information according to the third preset format to form a tracking data structure. Further, each tracking data structure is formed into a CSV file, named "track_year_month_day_hour_minute", and the CSV files formed by the weather structures are added to the weather information database.

[0118] Optionally, the weather structure may include [start timestamp - scene requirement time value, end timestamp + scene requirement time value] and weather type; the data structure of the tracking data structure may be [target vehicle number, whether it is the main target of the scene, timestamp, center point x coordinate, center point y coordinate, center point z coordinate, length, width, height, speed, confidence, heading angle, frame number].

[0119] S206, establish a first mapping relationship based on the time information of the scene database and the time information of the weather database, and establish a second mapping relationship based on the time information of the scene database and the time information of the tracking database.

[0120] In this embodiment, the time information of the scene library can be the scene start timestamp and scene end timestamp information in the file name of each file in the scene library, so as to determine the time period corresponding to each file according to the time information of each file in the scene library. Further, the time period corresponding to each file is determined according to the time information of each file, and the time information of the weather information database, to establish a first mapping relationship between the scene library and the weather information database; the time period corresponding to each file is determined according to the time information of each file, and the time information of the tracking database, to establish a second mapping relationship between the scene library and the tracking database.

[0121] In the above-mentioned embodiments, both weather information and tracking data are stored in a preset data format, which makes data storage more standardized and improves the efficiency of data management. Furthermore, a first mapping relationship is established between the scene library and the weather information library, as well as a second mapping relationship between the scene library and the tracking database, which facilitates the retrieval of corresponding weather information and tracking data based on the scene information in the scene library.

[0122] In one embodiment, such as Figure 9 As shown, the method for constructing the above-mentioned scene library also includes:

[0123] S207, receive the scene library retrieval request sent by the user equipment, and determine the user scene data from the scene library according to the scene library retrieval request.

[0124] In this embodiment of the application, the server accepts a scene library retrieval request sent by the user equipment. The scene library retrieval request may include a scene type. Further, the server determines the user scene data that matches the scene type from the scene library according to the scene type in each file name.

[0125] S208 generates a user scenario library based on user scenario data and sends the user scenario library to the user device.

[0126] In this embodiment of the application, user scenario data is categorized into storage folders corresponding to the scenarios, thereby generating a user scenario library based on the storage folders, and then sending the user scenario library to the user device.

[0127] In the above application embodiments, the user scenario library required by the user device is generated according to the user's needs, without having to send the entire scenario library to the user device, which improves file transfer efficiency and improves the user device's reading efficiency of the user scenario library.

[0128] In one embodiment, a method for building a complete scene library is provided, such as... Figure 10 As shown, the above method includes:

[0129] S1, acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area.

[0130] S2 determines the lane area where the target vehicle is located based on map information and tracking data.

[0131] S3, determine at least one scene filtering logic based on the lane area.

[0132] S4 extracts the target vehicle's trajectory from the tracking data.

[0133] S5 determines the coordinates of the target vehicle at multiple times based on the driving trajectory.

[0134] S6 determines the coordinate range corresponding to multiple time points based on the scene filtering logic.

[0135] S7. If there exists a coordinate position at any given moment that is within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scenario filtering logic.

[0136] S8. If the driving trajectory meets the scene filtering logic, then the scene information is extracted from the tracking data.

[0137] S9 converts the scene information into a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information.

[0138] S10, add the scene structure to the scene library.

[0139] S11, obtain weather information for the target area.

[0140] S12 converts the weather information into a weather structure and adds it to the weather information database; and converts the tracking data into a tracking data structure and adds it to the tracking database.

[0141] S13. Establish a first mapping relationship based on the time information of the scene database and the time information of the weather database, and establish a second mapping relationship based on the time information of the scene database and the time information of the tracking database.

[0142] S14, receive the scene library retrieval request sent by the user equipment, and determine the user scene data from the scene library according to the scene library retrieval request.

[0143] S15 generates a user scenario library based on user scenario data and sends the user scenario library to the user device.

[0144] The aforementioned method for constructing the scene library involves acquiring map information of the target area and tracking data of target vehicles collected by roadside equipment within that area; filtering scenes based on the map information and tracking data to determine the scene information corresponding to the target vehicles; and constructing the scene library based on this scene information. Since roadside equipment has a large collection range and collects a large amount of data, introducing tracking data from roadside equipment expands the scope of scene information, thereby expanding the scene library's scope. Furthermore, combining map information and tracking data for scene filtering makes the location of scene information more accurate, improving the accuracy of scene information and ultimately enhancing the accuracy of the scene library.

[0145] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0146] Based on the same inventive concept, this application also provides a scene library construction apparatus for implementing the scene library construction method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations of one or more scene library construction apparatus embodiments provided below can be found in the limitations of the scene library construction method described above, and will not be repeated here.

[0147] In one embodiment, such as Figure 11 As shown, a scene library construction apparatus is provided, including: a first acquisition module 10, a filtering module 11, and a construction module 12, wherein:

[0148] The first acquisition module 10 is used to acquire map information of the target area and tracking data of target vehicles collected by roadside equipment within the target area.

[0149] The filtering module 11 is used to filter scenes based on map information and tracking data to determine the scene information corresponding to the target vehicle.

[0150] Module 12 is used to build a scene library based on scene information.

[0151] In one embodiment, the filtering module 11 includes: a first determining unit, a second determining unit, and a filtering unit, wherein:

[0152] The first determining unit is used to determine the lane area where the target vehicle is located based on map information and tracking data.

[0153] The second determining unit is used to determine at least one scene filtering logic based on the lane area.

[0154] The filtering unit is used to filter scenarios based on scenario filtering logic and tracking data to determine scenario information.

[0155] In one embodiment, the filtering unit is specifically used to extract the driving trajectory of the target vehicle from the tracking data; determine whether the driving trajectory meets the scene filtering logic; and if the driving trajectory meets the scene filtering logic, extract scene information from the tracking data.

[0156] In one embodiment, the filtering unit is specifically used to determine the coordinate positions of the target vehicle at multiple times based on the driving trajectory; determine the coordinate range corresponding to the multiple times based on the scene filtering logic; and if the coordinate position at any time is within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scene filtering logic.

[0157] In one embodiment, the above-mentioned construction module 12 includes: a conversion unit and an addition unit, wherein:

[0158] The conversion unit is used to convert the scene information into a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information.

[0159] Add a unit to add the scene structure to the scene library.

[0160] In one embodiment, the above-mentioned scene library construction apparatus further includes: a second acquisition module, a conversion module, and a mapping module, wherein:

[0161] The second acquisition module is used to acquire weather information for the target area.

[0162] The conversion module is used to convert the format of weather information to form a weather structure and add the weather structure to the weather information database; and to convert the format of tracking data to form a tracking data structure and add the tracking data structure to the tracking database.

[0163] The mapping module is used to establish a first mapping relationship based on the time information of the scene library and the time information of the weather information library, and to establish a second mapping relationship based on the time information of the scene library and the time information of the tracking database.

[0164] In one embodiment, the above-mentioned scene library construction apparatus further includes: a receiving module and a sending module, wherein:

[0165] The receiving module is used to receive scene library retrieval requests sent by user equipment and determine user scene data from the scene library based on the scene library retrieval requests.

[0166] The sending module is used to generate a user scenario library based on user scenario data and send the user scenario library to the user device.

[0167] Each module in the aforementioned scene library construction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0168] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 12 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data for building a scene library. The I / O interfaces allow the processor to exchange information with external devices. The communication interface allows communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for building a scene library.

[0169] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0170] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0171] Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area;

[0172] Scenes are filtered based on map information and tracking data to determine the scene information corresponding to the target vehicle;

[0173] Build a scene library based on scene information.

[0174] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0175] Based on map information and tracking data, determine the lane area where the target vehicle is located;

[0176] At least one scene filtering logic is determined based on the lane area;

[0177] Scene information is determined by filtering scenes based on scene selection logic and tracking data.

[0178] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0179] Extract the target vehicle's trajectory from the tracking data;

[0180] Determine whether the driving trajectory meets the scenario filtering logic;

[0181] If the driving trajectory meets the scene filtering logic, then scene information is extracted from the tracking data.

[0182] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0183] Based on the driving trajectory, determine the coordinate positions of the target vehicle at multiple times;

[0184] Based on the scene filtering logic, determine the coordinate range corresponding to multiple time points;

[0185] If there exists a coordinate position at any given moment that falls within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scenario filtering logic.

[0186] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0187] The scene information is converted into a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information.

[0188] Add the scene struct to the scene library.

[0189] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0190] Obtain weather information for the target area;

[0191] The weather information is formatted to form a weather structure, which is then added to the weather information database; the tracking data is formatted to form a tracking data structure, which is then added to the tracking database.

[0192] A first mapping relationship is established based on the time information from the scene database and the weather database, and a second mapping relationship is established based on the time information from the scene database and the tracking database.

[0193] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0194] Receive the scene library retrieval request sent by the user equipment, and determine the user scene data from the scene library according to the scene library retrieval request;

[0195] A user scenario library is generated based on user scenario data, and the user scenario library is sent to the user's device.

[0196] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0197] Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area;

[0198] Scenes are filtered based on map information and tracking data to determine the scene information corresponding to the target vehicle;

[0199] Build a scene library based on scene information.

[0200] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0201] Based on map information and tracking data, determine the lane area where the target vehicle is located;

[0202] At least one scene filtering logic is determined based on the lane area;

[0203] Scene information is determined by filtering scenes based on scene selection logic and tracking data.

[0204] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0205] Extract the target vehicle's trajectory from the tracking data;

[0206] Determine whether the driving trajectory meets the scenario filtering logic;

[0207] If the driving trajectory meets the scene filtering logic, then scene information is extracted from the tracking data.

[0208] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0209] Based on the driving trajectory, determine the coordinate positions of the target vehicle at multiple times;

[0210] Based on the scene filtering logic, determine the coordinate range corresponding to multiple time points;

[0211] If there exists a coordinate position at any given moment that falls within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scenario filtering logic.

[0212] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0213] The scene information is converted into a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information.

[0214] Add the scene struct to the scene library.

[0215] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0216] Obtain weather information for the target area;

[0217] The weather information is formatted to form a weather structure, which is then added to the weather information database; the tracking data is formatted to form a tracking data structure, which is then added to the tracking database.

[0218] A first mapping relationship is established based on the time information from the scene database and the weather database, and a second mapping relationship is established based on the time information from the scene database and the tracking database.

[0219] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0220] Receive the scene library retrieval request sent by the user equipment, and determine the user scene data from the scene library according to the scene library retrieval request;

[0221] A user scenario library is generated based on user scenario data, and the user scenario library is sent to the user's device.

[0222] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0223] Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area;

[0224] Scenes are filtered based on map information and tracking data to determine the scene information corresponding to the target vehicle;

[0225] Build a scene library based on scene information.

[0226] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0227] Based on map information and tracking data, determine the lane area where the target vehicle is located;

[0228] At least one scene filtering logic is determined based on the lane area;

[0229] Scene information is determined by filtering scenes based on scene selection logic and tracking data.

[0230] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0231] Extract the target vehicle's trajectory from the tracking data;

[0232] Determine whether the driving trajectory meets the scenario filtering logic;

[0233] If the driving trajectory meets the scene filtering logic, then scene information is extracted from the tracking data.

[0234] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0235] Based on the driving trajectory, determine the coordinate positions of the target vehicle at multiple times;

[0236] Based on the scene filtering logic, determine the coordinate range corresponding to multiple time points;

[0237] If there exists a coordinate position at any given moment that falls within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scenario filtering logic.

[0238] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0239] The scene information is converted into a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information.

[0240] Add the scene struct to the scene library.

[0241] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0242] Obtain weather information for the target area;

[0243] The weather information is formatted to form a weather structure, which is then added to the weather information database; the tracking data is formatted to form a tracking data structure, which is then added to the tracking database.

[0244] A first mapping relationship is established based on the time information from the scene database and the weather database, and a second mapping relationship is established based on the time information from the scene database and the tracking database.

[0245] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0246] Receive the scene library retrieval request sent by the user equipment, and determine the user scene data from the scene library according to the scene library retrieval request;

[0247] A user scenario library is generated based on user scenario data, and the user scenario library is sent to the user's device.

[0248] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0249] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0250] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of constructing a scene library, characterized by, The method includes: Acquire map information of the target area, as well as tracking data of target vehicles collected by roadside equipment within the target area; Scene filtering is performed based on the map information and the tracking data to determine the scene information corresponding to the target vehicle; A scene library is constructed based on the scene information.

2. The method of claim 1, wherein, The step of filtering scenes based on the map information and the tracking data to determine the scene information corresponding to the target vehicle includes: Based on the map information and the tracking data, the lane area where the target vehicle is located is determined; At least one scene filtering logic is determined based on the lane area; The scene information is determined by filtering the scene based on the scene filtering logic and the tracking data.

3. The method of claim 2, wherein, The step of filtering scenarios based on the scenario filtering logic and the tracking data to determine the scenario information includes: The driving trajectory of the target vehicle is extracted from the tracking data; Determine whether the driving trajectory meets the scenario filtering logic; If the driving trajectory satisfies the scene filtering logic, then the scene information is extracted from the tracking data.

4. The method of claim 3, wherein, Determining whether the driving trajectory meets the scenario filtering logic includes: Based on the driving trajectory, determine the coordinate positions of the target vehicle at multiple times; Based on the scene filtering logic, determine the coordinate range corresponding to multiple time points; If there exists a coordinate position at any given moment that falls within the corresponding coordinate range, then the driving trajectory is determined to satisfy the scenario filtering logic.

5. The method of claim 1, wherein, The step of constructing a scene library based on the scene information includes: The scene information is formatted to form a scene structure; the scene structure includes scene number, scene type, scene main target identifier, and scene time information; Add the scene structure to the scene library.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Obtain weather information for the target area; The weather information is format-converted to form a weather structure, and the weather structure is added to the weather information database; the tracking data is format-converted to form a tracking data structure, and the tracking data structure is added to the tracking database. A first mapping relationship is established based on the time information of the scene database and the time information of the weather database, and a second mapping relationship is established based on the time information of the scene database and the time information of the tracking database.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Receive a scene library retrieval request sent by a user equipment, and determine user scene data from the scene library according to the scene library retrieval request; A user scenario library is generated based on the user scenario data, and the user scenario library is sent to the user device.

8. A scene library construction apparatus characterized by comprising: The device includes: The first acquisition module is used to acquire map information of the target area and tracking data of target vehicles collected by roadside equipment within the target area; The filtering module is used to filter scenes based on the map information and the tracking data to determine the scene information corresponding to the target vehicle. The construction module is used to build a scene library based on the scene information. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images