Map data collection method, device and computer-readable storage medium

Abstract

The present application discloses a map data collection method, device, and computer-readable storage medium. The present application relates to the field of electronic map technology. The method includes: determining a starting position identifier when a data collection vehicle passes the starting point of a pre-collected road, and determining an ending position identifier when the data collection vehicle passes the end point of the pre-collected road; determining target map data corresponding to the pre-collected road from a map data set collected by the data collection vehicle based on at least the starting position identifier and the ending position identifier; wherein the map data set is a collection of map data collected by the data collection vehicle while traveling along a data collection track, and the data collection track includes the pre-collected road. The present application can improve the integrity of map data collected by the vehicle, thereby improving the accuracy of maps constructed or updated based on the map data.

Description

Technical Field

[0001] The present application relates to the technical field of electronic maps, and in particular to a map data acquisition method, device, and computer-readable storage medium. Background Art

[0002] With the rapid development of autonomous driving technology and intelligent transportation systems, accurate vehicle trajectory data is crucial for building and maintaining high-precision maps (HD maps or lightweight maps).

[0003] At present, the commonly used map data collection method is to monitor the location information of the vehicle used to collect road data through the cloud. When it is detected that the vehicle enters a specific road section, the cloud matches the specific road section where the vehicle is currently located with the track to be collected indicated by the collection task to be executed. After matching the corresponding track to be collected, a data collection instruction is sent to the vehicle, instructing the vehicle to start road data collection to perform the collection task, and return the collected road data to the cloud after the vehicle completes the driving of the specific road section. However, in this process, since the vehicle starts collecting data after receiving the data collection instruction issued by the cloud and the vehicle is always driving, the road data corresponding to the distance between the entry point of the vehicle into the specific road section and the position where the vehicle is when the data collection instruction is received will be missing, thereby affecting the accuracy of the map constructed or updated based on the partially missing data.

[0004] Therefore, how to improve the integrity of map data collected by vehicles to improve the accuracy of maps built or updated based on the map data is a problem that urgently needs to be solved. Summary of the Invention

[0005] The main purpose of this application is to provide a map data collection method, device and computer-readable storage medium, aiming to improve the integrity of map data collected by vehicles and to improve the accuracy of maps constructed or updated based on the map data.

[0006] To achieve the above objectives, the present application provides a map data collection method, which includes:

[0007] Determine a starting position marker of the data collection vehicle when it passes the starting point of the pre-collection road, and determine an ending position marker of the data collection vehicle when it passes the end point of the pre-collection road;

[0008] Determining target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based at least on the starting position identifier and the ending position identifier;

[0009] The map data set is a set of map data collected by the data collection vehicle while traveling along a data collection track, and the data collection track includes the pre-collected road.

[0010] In one embodiment, the map data set is a video collected by the data collection vehicle during driving, the map data in the map data set is a video frame in the video, the starting position identifier is a timestamp of the video frame corresponding to the starting point, and the ending position identifier is a timestamp of the video frame corresponding to the end point.

[0011] In one embodiment, the steps of determining a starting position marker when the data collection vehicle passes the starting point of the pre-collection road, and determining a termination position marker when the data collection vehicle passes the end point of the pre-collection road, include:

[0012] Monitoring the real-time position information of the data collection vehicle while the data collection vehicle is traveling along the data collection track;

[0013] In response to monitoring that the data collection vehicle enters the pre-collection road from the starting point of the pre-collection road, triggering a starting position marker; and

[0014] In response to monitoring that the data collection vehicle travels along the pre-collection road to an end point of the pre-collection road, triggering a termination position marker; or

[0015] In response to monitoring that the data collection vehicle exits the pre-collection road from a non-end point of the pre-collection road, the process returns to the step of monitoring the real-time position information of the data collection vehicle.

[0016] In one embodiment, before the step of determining the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on at least the starting location identifier and the ending location identifier, the method further includes:

[0017] Determining a target driving trajectory of the data collection vehicle on the pre-collection road;

[0018] Determining whether a map data acquisition condition is met based on a match between the target driving trajectory and a reference trajectory indicated by the data collection task to be executed;

[0019] When the map data acquisition condition is met, the target map data corresponding to the pre-collected road is determined from the map data set collected by the data collection vehicle based at least on the starting position identifier and the ending position identifier.

[0020] In one embodiment, before the step of determining whether a map data acquisition condition is satisfied based on a match between the target driving trajectory and a reference trajectory indicated by the data collection task to be executed, the method further includes:

[0021] In a case where the data collection task to be executed indicates a first road, determining a trajectory corresponding to the first road as a reference trajectory of the data collection task;

[0022] In a case where the data collection task to be executed indicates a first lane, determining a trajectory corresponding to the first lane as a reference trajectory of the data collection task;

[0023] In a case where the data collection task to be executed indicates a task type and collection trajectory information, a reference trajectory corresponding to the data collection task is determined according to the task type and the collection trajectory information.

[0024] In one embodiment, the task type is a road-level collection task or a lane-level collection task, and the collected trajectory information is a second road or a second lane;

[0025] The step of determining the reference trajectory corresponding to the data collection task according to the task type and the collection trajectory information includes:

[0026] When the task type is a road-level collection task and the collection trajectory information is a second road, determining the trajectory corresponding to the second road as a reference trajectory of the data collection task;

[0027] When the task type is a road-level collection task and the collection trajectory information is for the second lane, determining the trajectory corresponding to the third road where the second lane is located as the reference trajectory for the data collection task, wherein the starting point of the second lane is the same as the starting point of the third road, and the end point of the second lane is the same as the end point of the third road;

[0028] When the task type is a lane-level collection task and the collection trajectory information is for the second lane, determining the trajectory corresponding to the second lane as the reference trajectory corresponding to the data collection task;

[0029] When the task type is a road-level data collection task and the collected trajectory information is of a second road, a trajectory corresponding to a target lane in the second road is determined as a reference trajectory corresponding to the data collection task.

[0030] In one embodiment, the step of determining the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on at least the starting position identifier and the ending position identifier includes:

[0031] Determining target map data corresponding to the pre-collected road from a map data set collected by the data collection vehicle according to the starting position identifier and the ending position identifier, wherein the map data set is uploaded by the data collection vehicle; or

[0032] The starting position identifier and the ending position identifier are indicated to the data collection vehicle, and the target map data corresponding to the pre-collected road returned by the data collection vehicle according to the starting position identifier and the ending position identifier is received.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a map data collection method, which is applied to a data collection vehicle and includes:

[0034] collecting map data while the data collection vehicle is traveling along the data collection track, and determining a set of the collected map data as a map data set collected by the data collection vehicle;

[0035] The data collection trajectory includes a pre-collected road, and the map data set includes at least the starting position identifier of the data collection vehicle when it passes the starting point of the pre-collected road, and the ending position identifier of the data collection vehicle when it passes the end point of the pre-collected road.

[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a map data acquisition device, which includes:

[0037] An identification determination module is used to determine a starting position identification when the data collection vehicle passes the starting point of the pre-collection road, and to determine an ending position identification when the data collection vehicle passes the end point of the pre-collection road;

[0038] A data extraction module is used to determine the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on at least the starting position identifier and the ending position identifier; wherein the map data set is a collection of map data collected by the data collection vehicle while traveling along a data collection trajectory, and the data collection trajectory includes the pre-collected road.

[0039] In addition, to achieve the above-mentioned purpose, the present application further provides a map data acquisition device, which is applied to a data acquisition vehicle and includes:

[0040] A data collection module is used to collect map data while the data collection vehicle is traveling along a data collection track, and to determine a set of collected map data as a map data set collected by the data collection vehicle; wherein the data collection track includes a pre-collected road, and the map data set includes at least a starting position identifier of the data collection vehicle when it passes the starting point of the pre-collected road, and an ending position identifier of the data collection vehicle when it passes the end point of the pre-collected road.

[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer-readable storage medium, and the computer-readable storage medium stores a program for implementing the map data collection method. The program for implementing the map data collection method is executed by a processor to implement the steps of the map data collection method as described above.

[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned map data collection method when executed by a processor.

[0043] The present application provides a map data collection method, which determines a starting position identifier when a data collection vehicle passes the starting point of a pre-collected road, and determines an ending position identifier when the data collection vehicle passes the end point of the pre-collected road, and then determines target map data corresponding to the pre-collected road from a map data set collected by the data collection vehicle based on at least the starting position identifier and the ending position identifier, wherein the map data set is a collection of map data collected by the data collection vehicle during the process of traveling along a data collection track, and the data collection track includes the pre-collected road.

[0044] To sum up, compared with the traditional method of matching data collection tasks when a vehicle is detected entering a specific road section, and issuing data collection instructions to instruct the vehicle to start collecting data after the matching is successful, the data collection vehicle in the present application can start collecting map data before entering the pre-collected road without waiting for external instructions, and determine the starting position identifier and the ending position identifier when the data collection vehicle passes the starting point and end point of the pre-collected road, so as to obtain the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on the two position identifiers representing the location of the data collection vehicle, thereby avoiding the problem of partial loss of map data on the pre-collected road due to untimely issuance of instructions from the cloud, improving the integrity of the map data collected by the vehicle, and thus providing more reliable data support for map construction or map update, and improving the accuracy of maps constructed or updated based on map data. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 This is a flowchart of the first embodiment of the map data collection method of this application;

[0048] Figure 2 This is a first schematic diagram of vehicle position monitoring involved in an embodiment of the map data collection method of the present application;

[0049] Figure 3 This is a second schematic diagram of vehicle position monitoring involved in an embodiment of the map data collection method of the present application;

[0050] Figure 4 A third schematic diagram of vehicle position monitoring according to an embodiment of the map data collection method of the present application;

[0051] Figure 5 This is a fourth schematic diagram of vehicle position monitoring involved in an embodiment of the map data collection method of the present application;

[0052] Figure 6 This is a schematic diagram of a map data collection process involved in an embodiment of the map data collection method of the present application;

[0053] Figure 7 This is a schematic diagram of the device structure of the hardware operating environment involved in the map data collection method in the embodiment of the present application.

[0054] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] The main solution of the present application is: determining the starting position identifier of the data collection vehicle when it passes the starting point of the pre-collected road, and determining the ending position identifier of the data collection vehicle when it passes the end point of the pre-collected road; determining the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on at least the starting position identifier and the ending position identifier; wherein the map data set is a collection of map data collected by the data collection vehicle during the process of traveling along the data collection track, and the data collection track includes the pre-collected road.

[0058] At present, the commonly used map data collection method is to monitor the location information of the vehicle used to collect road data through the cloud. When it is detected that the vehicle enters a specific road section, the cloud matches the specific road section where the vehicle is currently located with the track to be collected indicated by the collection task to be executed. After matching the corresponding track to be collected, a data collection instruction is sent to the vehicle, instructing the vehicle to start road data collection to perform the collection task, and return the collected road data to the cloud after the vehicle completes the driving of the specific road section. However, in this process, since the vehicle starts collecting data after receiving the data collection instruction issued by the cloud and the vehicle is always driving, the road data corresponding to the distance between the entry point of the vehicle into the specific road section and the position where the vehicle is when the data collection instruction is received will be missing, thereby affecting the accuracy of the map constructed or updated based on the partially missing data.

[0059] Compared with the traditional method of matching data collection tasks when a vehicle is detected entering a specific road section, and issuing data collection instructions to instruct the vehicle to start collecting data after the match is successful, the data collection vehicle in this application can start collecting map data before entering the pre-collected road without waiting for external instructions, and determine the starting position identifier and the ending position identifier when the data collection vehicle passes the starting point and end point of the pre-collected road, so as to obtain the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on the two position identifiers representing the location of the data collection vehicle, thereby avoiding the problem of partial loss of map data on the pre-collected road due to untimely issuance of instructions from the cloud, improving the integrity of the map data collected by the vehicle, and thus providing more reliable data support for map construction or map update, and improving the accuracy of maps constructed or updated based on map data.

[0060] It should be noted that the execution entity of the methods in each embodiment of the map data collection method of this application can be the cloud, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an Internet of Things or Internet of Vehicles terminal with computing and processing capabilities, or a distributed system capable of implementing the above functions, etc. This embodiment does not specifically limit this. The following describes this embodiment and the following embodiments using the cloud as the execution entity as an example.

[0061] Based on this, this application proposes a map data collection method of the first embodiment. The execution subject of the map data collection method is the cloud. For the convenience of description, the following content is described by omitting the execution subject. Figure 1 The map data collection method includes steps S10 to S20:

[0062] Step S10, determining a starting position identifier when the data collection vehicle passes the starting point of the pre-collection road, and determining an ending position identifier when the data collection vehicle passes the end point of the pre-collection road;

[0063] It should be noted that the map data collection method of the embodiments of the present application is applied to the cloud, which is in communication with multiple data collection vehicles. A data collection vehicle refers to a vehicle used to collect map data. The embodiments of the present application do not limit the specific type of data collection vehicle. Such vehicles include, but are not limited to, collection vehicles, crowdsourcing vehicles, surveying and mapping vehicles, non-operational vehicles using corresponding electronic maps, and third-party professional vehicles. Crowdsourcing vehicles, for example, have characteristics such as irregular trajectories and large scale, which can meet the needs of local map updates. After startup, the data collection vehicles collect map data and their own location information (hereinafter referred to as real-time location information for clarity) in real time. Road sections requiring map data collection, namely the aforementioned pre-collected roads, are pre-configured in the cloud. It should be understood that the cloud is in communication with the data collection vehicles and selects the pre-collected roads in the map based on user instructions or pending data collection tasks. The cloud can also obtain the real-time location information of the data collection vehicles to monitor their real-time locations. The starting location marker represents the location of the data collection vehicle at the start of the pre-collected road, and the ending location marker represents the location of the data collection vehicle at the end of the pre-collected road. That is, it should be understood that there is a corresponding relationship between the location information of the data collection vehicle and the map data collected by the data collection vehicle.

[0064] Step S20, determining target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based at least on the starting position identifier and the ending position identifier;

[0065] It should be noted that a map dataset is a collection of map data collected by a data collection vehicle while traveling along a data collection track, and the data collection track includes pre-collected roads. In other words, a map dataset includes map data collected by the data collection vehicle on pre-collected roads.

[0066] Since there is a corresponding relationship between the starting position identifier of the data collection vehicle when it passes the starting point of the pre-collected road and the map data collected by the data collection vehicle at the starting point, and a corresponding relationship between the ending position identifier of the data collection vehicle when it passes the ending point of the pre-collected road and the map data collected by the data collection vehicle at the ending point, the map data corresponding to the starting position identifier and the ending position identifier can be determined from the map data set collected by the data collection vehicle based on the corresponding relationship between the starting position identifier, the ending position identifier, and the vehicle position identifier, and the map data collected by the data collection vehicle. This allows the starting map data of the map data corresponding to the pre-collected road (hereinafter referred to as target map data for distinction) to be determined as the map data corresponding to the starting position identifier, and the ending map data of the target map data to be determined as the map data corresponding to the ending position identifier. The vehicle position identifier includes at least the starting position identifier and the ending position identifier. Furthermore, the target map data includes the map data collected by the data collection vehicle at various locations on the pre-collected road.

[0067] In this way, compared with the traditional method of matching data collection tasks when a vehicle is detected entering a specific road section, and issuing data collection instructions to instruct the vehicle to start collecting data after the match is successful, the data collection vehicle in the embodiment of the present application can start collecting map data before entering the pre-collected road without waiting for external instructions, and determine the starting position identifier and the ending position identifier when the data collection vehicle passes the starting point and end point of the pre-collected road, so as to obtain the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on the two position identifiers representing the location of the data collection vehicle, thereby avoiding the problem of partial loss of map data on the pre-collected road due to untimely issuance of instructions from the cloud, improving the integrity of the map data collected by the vehicle, and thus providing more reliable data support for map construction or map update, and improving the accuracy of maps constructed or updated based on map data.

[0068] In one feasible embodiment, the map dataset is a collection of map data collected by the data collection vehicle during driving, wherein the map data can be image data, point cloud data, or other data types. Since the data collection vehicle collects map data and its own real-time location information in real time during driving, the data collection vehicle can record the collection location of the map data when collecting map data and save the mapping relationship between the map data and the collection location. The collection location recorded by the data collection vehicle is, for example, the GPS positioning point (track point) of the data collection vehicle. In this way, based on the starting position identifier and the end position identifier, the cloud can request the map data corresponding to each collection location on the pre-collected road from the data collection vehicle, that is, obtain the target map data of the pre-collected road in the map dataset from the vehicle.

[0069] In another feasible embodiment, the map data set is a video collected by the data collection vehicle during driving, the map data in the map data set is a video frame in the video, the starting position identifier is a timestamp of the video frame corresponding to the starting point, and the ending position identifier is a timestamp of the video frame corresponding to the end point.

[0070] It should be noted that the map dataset is a video captured by the data collection vehicle while driving, and the map data in the map dataset is a video frame from the video. The data type of the map data collected in real time by the data collection vehicle while in the startup state is video data. When the map dataset is video, the video encoding method used by the data collection vehicle can be H.26X (such as H.264, H.265, or H.266), AVSX (AVS1, AVS2, or AVS3), or other video encoding methods. The starting position identifier is the timestamp of the video frame captured by the data collection vehicle at the starting point of the pre-collected road, i.e., the time information when the data collection vehicle is at the starting point of the pre-collected road. The ending position identifier is the timestamp of the video frame captured by the data collection vehicle at the end point of the pre-collected road, i.e., the time information when the data collection vehicle is at the end point of the pre-collected road. In other words, there is a correspondence between the vehicle position identifier and the map data, and the vehicle position identifier represents the location information of the data collection vehicle. Therefore, the correspondence between the data collection vehicle's location information and the map data can be determined based on the vehicle position identifier to determine the target map data corresponding to the pre-collected road from the map dataset.

[0071] Thus, compared to the traditional method of collecting image data and saving it on the vehicle side, the embodiment of the present application compresses the map data of the video data type and saves it on the vehicle side, which can save two-thirds of the storage space and, to a certain extent, improve the efficiency of data storage, extend the life cycle of the data collection vehicle, and thus achieve the purpose of reducing operating costs. And compared to the traditional data collection method of uploading image data to the cloud, the embodiment of the present application uploads map data to the cloud in the form of video streams, saving bandwidth resources. In addition, it should be understood that collecting map data by video can reduce redundant data storage, save traffic, and video supports complete data storage throughout the day.

[0072] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated hereafter. On this basis, the step S10 may include:

[0073] Step S101, monitoring the real-time position information of the data collection vehicle while the data collection vehicle is traveling along the data collection track;

[0074] The data collection vehicle detects its own location information, i.e., the aforementioned real-time location information, in real time while driving. Specifically, this application does not limit how the cloud monitors the real-time location information of the data collection vehicle. In one feasible embodiment, the data collection vehicle feeds back its real-time location information to the cloud in real time. In another feasible embodiment, the cloud sends a location request command to the data collection vehicle, which then returns its real-time location information based on the location request command.

[0075] As the data collection vehicle travels along the data collection track, the cloud can monitor the real-time location information of the data collection vehicle.

[0076] Step S102, in response to monitoring that the data collection vehicle enters the pre-collection road from the starting point of the pre-collection road, triggering a starting position marker;

[0077] When the cloud monitors that the data collection vehicle enters the pre-collected road from the starting point of the pre-collected road, the starting position mark is automatically triggered.

[0078] In one feasible embodiment, the starting location marker represents the starting location information of the pre-collected road. After the starting location marker is triggered, a mapping relationship between the starting location marker and the map data collected when the data collection vehicle enters the pre-collected road from the starting point of the pre-collected road is recorded. In another feasible embodiment, the step of triggering the starting location marker specifically includes determining the timestamp of when the data collection vehicle enters the pre-collected road from the starting point of the pre-collected road as the starting location marker, so that the mapping relationship between the corresponding starting location marker and the map data can be subsequently determined based on the timestamp.

[0079] Step S103, in response to monitoring that the data collection vehicle travels along the pre-collection road to the end point of the pre-collection road, triggering a termination position marker;

[0080] When the cloud monitors that the data collection vehicle is driving along the pre-collected road to the end of the pre-collected route, the starting position mark is automatically triggered.

[0081] In one feasible embodiment, the end location marker represents the end location information of the pre-collected road. After the end location marker is triggered, a mapping relationship between the end location marker and the map data collected when the data collection vehicle exits the pre-collected road from the end point of the pre-collected road is recorded. In another feasible embodiment, the step of triggering the start location marker specifically includes determining the timestamp of the time when the data collection vehicle exits the pre-collected road from the end point as the start and end location marker, so that the mapping relationship between the corresponding end location marker and the map data can be subsequently determined based on the timestamp.

[0082] Step S104 , in response to monitoring that the data collection vehicle has driven out of the pre-collection road from a non-end point of the pre-collection road, returning to the step of monitoring the real-time position information of the data collection vehicle.

[0083] It should be noted that all locations on the pre-collected road, excluding the end point of the pre-collected road, are referred to as non-end points. Furthermore, the end point of the pre-collected road is the location of the other end of the pre-collected road, excluding the end where the data collection vehicle enters.

[0084] When the cloud monitors that the data collection vehicle leaves the pre-collected road from a non-end point on the pre-collected road, the step of detecting the real-time position information of the data collection vehicle is returned to.

[0085] For example, Figure 2 The first schematic diagram of vehicle position monitoring is shown. The data collection vehicle is located at the starting point of the pre-collected road selected in the box and drives into the pre-collected road from the starting point of the pre-collected road; Figure 3 The second schematic diagram of vehicle position monitoring is shown, where the data collection vehicle is traveling on the pre-collection road; Figure 4 The third schematic diagram of vehicle position monitoring is shown in FIG. 1 , where the data collection vehicle is located at the end of the pre-collection road and drives out of the pre-collection road from the end of the pre-collection road. Figure 5 FIG. 4 is a fourth schematic diagram of vehicle position monitoring, in which the data collection vehicle drives out of the pre-collection road from a non-end point of the pre-collection road.

[0086] In this embodiment, before step S20, the map data collection method of this application further includes:

[0087] Step A10, determining a target driving trajectory of the data collection vehicle on the pre-collection road;

[0088] Determine the driving trajectory of the data collection vehicle on the pre-collected road (hereinafter referred to as the target driving trajectory for distinction). It should be understood that the starting point of the target driving trajectory coincides with the starting point of the pre-collected road, the end point of the target driving trajectory coincides with the end point of the pre-collected road, and the target driving trajectory is distributed within the range of the pre-collected road.

[0089] Step A20, judging whether a map data acquisition condition is met based on a match between the target driving trajectory and a reference trajectory indicated by the data collection task to be executed;

[0090] It should be noted that each data collection task to be executed corresponds to an area to be collected, and the area to be collected indicated by the data collection task is called a reference trajectory.

[0091] Based on the match between the target driving trajectory and the reference trajectory indicated by the pending data collection task, a determination is made as to whether the map data acquisition conditions are met. Specifically, if the target driving trajectory and the reference trajectory are identical, the match between the target driving trajectory and the reference trajectory is considered successful, and the map data acquisition conditions are determined to be met.

[0092] Step A30 : When a map data acquisition condition is met, target map data corresponding to the pre-collected road is determined from the map data set collected by the data collection vehicle based at least on the starting position identifier and the ending position identifier.

[0093] When the data acquisition conditions are met, target map data corresponding to the pre-collected road is determined from the map data set collected by the data collection vehicle based at least on the starting position identifier and the ending position identifier.

[0094] In this embodiment, before step A20, the map data collection method of this application further includes:

[0095] Step B10: when the data collection task to be executed indicates a first road, determining a trajectory corresponding to the first road as a reference trajectory for the data collection task;

[0096] If the area to be collected indicated by the pending data collection task is a road (hereinafter referred to as the first road for distinction), the trajectory corresponding to the first road is determined as the reference trajectory indicated by the data collection task. It should be understood that the starting point of the trajectory corresponding to the road coincides with the starting point of the road, the end point of the trajectory corresponding to the road coincides with the end point of the road, and the trajectory corresponding to the road is distributed within the range of the road.

[0097] Step B20: when the data collection task to be executed indicates the first lane, determining the trajectory corresponding to the first lane as the reference trajectory of the data collection task;

[0098] If the area to be collected indicated by the pending data collection task is a lane (hereinafter referred to as the first lane for distinction), the trajectory corresponding to the first lane is determined as the reference trajectory indicated by the data collection task. It should be understood that the starting point of the trajectory corresponding to the lane coincides with the starting point of the lane, the end point of the trajectory corresponding to the lane coincides with the end point of the lane, and the trajectory corresponding to the lane is distributed within the lane range.

[0099] Step B30: When the data collection task to be executed indicates a task type and collection trajectory information, a reference trajectory corresponding to the data collection task is determined according to the task type and the collection trajectory information.

[0100] It should be noted that the task types indicated by the data collection task include road-level collection tasks and lane-level collection tasks. The collection trajectory information indicated by the data collection task includes roads and lanes.

[0101] In a case where the data collection task to be executed indicates a task type and collection trajectory information, a reference trajectory indicated by the data collection task is determined according to the task type and the collection trajectory information.

[0102] In a specific embodiment, the task type is a road-level collection task or a lane-level collection task, and the collected trajectory information is a second road or a second lane. Step B30 may include:

[0103] Step B301: when the task type is a road-level data collection task and the collected trajectory information is a second road, determining the trajectory corresponding to the second road as a reference trajectory for the data collection task;

[0104] It should be noted that, when the data collection task indicates the task type and the collected trajectory information, the road in the collected trajectory information is referred to as the second road for distinction, and the lane in the collected trajectory information is referred to as the second lane for distinction.

[0105] When the task type indicated by the data collection task is a road-level collection task and the collection trajectory information is the second road, the trajectory corresponding to the second road is determined as the reference trajectory indicated by the data collection task.

[0106] Step B302: When the task type is a road-level data collection task and the collected trajectory information is for the second lane, determine the trajectory corresponding to the third road where the second lane is located as a reference trajectory for the data collection task, wherein the starting point of the second lane is the same as the starting point of the third road, and the end point of the second lane is the same as the end point of the third road;

[0107] When the task type indicated by the data collection task is a road-level collection task and the collection trajectory information is the second lane, the accumulation corresponding to the road where the second lane is located (hereinafter referred to as the third road for distinction) is determined as the reference trajectory of the data collection task, wherein the starting point of the second lane is the same as the starting point of the third road, and the end point of the second lane is the same as the end point of the third road.

[0108] Step B303: When the task type is a lane-level collection task and the collection trajectory information is for the second lane, determine the trajectory corresponding to the second lane as a reference trajectory corresponding to the data collection task;

[0109] When the task type indicated by the data collection task is a lane-level collection task and the collection trajectory information is for the second lane, the trajectory corresponding to the second lane is determined as the reference trajectory indicated by the data collection task.

[0110] Step B304 : When the task type is a road-level data collection task and the collected trajectory information is of a second road, a trajectory corresponding to a target lane in the second road is determined as a reference trajectory corresponding to the data collection task.

[0111] When the task type indicated by the data collection task is a road-level collection task and the collection trajectory information is the second road, the trajectory corresponding to the lane included in the second road (hereinafter referred to as the target lane for distinction) is determined as the reference trajectory corresponding to the data collection task.

[0112] In this embodiment, step S30 may include:

[0113] Step S301, determining target map data corresponding to the pre-collected road from a map data set collected by the data collection vehicle according to the start position identifier and the end position identifier, wherein the map data set is uploaded by the data collection vehicle;

[0114] The cloud receives the map data set uploaded by the data collection vehicle, and then determines the target map data corresponding to the pre-collected road from the map data based on the starting position identifier and the ending position identifier.

[0115] Step S302 : indicating the starting position identifier and the ending position identifier to the data collection vehicle, and receiving the target map data corresponding to the pre-collected road returned by the data collection vehicle according to the starting position identifier and the ending position identifier.

[0116] The map dataset is stored on the data collection vehicle. The cloud indicates the starting location identifier and the ending location identifier to the data collection vehicle, and receives the target map data corresponding to the pre-collected road returned by the data collection vehicle based on the starting location identifier and the ending location identifier.

[0117] The embodiments of the present application do not limit the specific method of determining the target map data from the map data set based on the vehicle location identifier. For example, in one feasible implementation, when the data collection vehicle stops driving, it uploads the map data set collected during the current driving process to the cloud. The cloud receives the map data set uploaded by the data collection vehicle and determines the video frame corresponding to the vehicle location identifier in the map data set based on the starting location identifier and the ending location identifier. Then, the target map data of the pre-collected road is determined using the video frame corresponding to the starting location identifier as the starting frame and the video frame corresponding to the ending location identifier as the ending frame. For another example, in another feasible implementation, the cloud generates a data request instruction based on the starting location identifier and the ending location identifier, and sends the data request instruction to the data collection vehicle. After receiving the data request instruction, the data collection vehicle parses the data request instruction to obtain the starting location identifier and the ending location identifier, and determines the target map data corresponding to the pre-collected road based on the starting location identifier and the ending location identifier, and returns the target map data to the cloud.

[0118] For example, Figure 6 The figure shows a schematic diagram of the map data collection process, in which the cloud receives real-time location information uploaded by the data collection vehicle; based on the real-time location information, it determines whether the data collection vehicle is located at the starting point of the pre-collected road; if the data collection vehicle is detected at the starting point, the driving trajectory of the data collection vehicle is recorded; it monitors whether the data collection vehicle travels along the pre-collected road from the starting point of the pre-collected road to the end point of the pre-collected road; if so, a target driving trajectory of the data collection vehicle on the pre-collected road is generated; the target driving trajectory is then matched with the reference trajectory indicated by the data collection task to be executed to obtain a matching result; when the matching result is a successful match, a data request instruction containing the starting position identifier and the ending position identifier is sent to the data collection vehicle to obtain the target map data collected by the data collection vehicle on the pre-collected road.

[0119] In this embodiment, after step S30, the map data collection method of the present application further includes: determining the amount to be collected of the reference trajectory indicated by the data collection task to be executed, subtracting one from the amount to be collected to obtain a new amount to be collected; and when it is detected that the new amount to be collected is zero, determining that the data collection task is completed.

[0120] It should be noted that each pending data collection task corresponds to a pending collection area, which indicates the area and the amount to be collected. For example, a data collection task may specify a road as the pending collection area and require three trips on that road (i.e., the amount to be collected). The data collection task specifies the amount to be collected in the pending collection area. Each time a data collection vehicle is detected collecting map data along a reference trajectory, the amount to be collected is decremented by one to update the amount. This amount is considered complete until it reaches zero.

[0121] After obtaining the target map data collected by the target data collection vehicle, the amount to be collected of the reference trajectory indicated by the data collection task is determined, the amount to be collected of the data collection task is subtracted by one to obtain a new amount to be collected; and whether the new amount to be collected is zero is detected. When it is detected that the new amount to be collected is zero, it is determined that the data collection task is completed.

[0122] For example, a data collection task that successfully matches the target driving trajectory is a road-level collection task. The reference trajectory specified for this data collection task is the first road, and three trips are required to collect data on this first road. In other words, if the data collection vehicle is a crowdsourced vehicle, as long as three vehicles have completed the first road, the map data collected by each of these three vehicles on the first road can be obtained from these three vehicles to complete the data collection task. Due to the large number of crowdsourced vehicles, using crowdsourced vehicles as data collection vehicles for map data collection can shorten the data collection cycle and improve data collection efficiency. Furthermore, after obtaining the map data uploaded by each data collection vehicle for the road to be collected, a fusion analysis is performed on the map data to update the current electronic map based on the results of the fusion analysis.

[0123] The embodiment of the present application determines the location information of the data collection vehicle when it passes the starting point and end point of the pre-collected road, establishes a correspondence between map data and the collection location based on the starting location identifier corresponding to the starting point and the ending location identifier corresponding to the end point, and then determines the map data corresponding to the two location information from the map data set collected by the data collection vehicle based on the starting location identifier and the ending location identifier, thereby determining the target map data corresponding to the pre-collected road. In this way, the problem of incomplete map data collection is avoided and the accuracy of the map constructed or updated based on the target map data is improved.

[0124] It should be noted that the execution subject of the map data collection method of the present application is a data collection vehicle. Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those of the above-mentioned first and second embodiments can be referred to the above introduction and will not be repeated hereafter. On this basis, the map data collection method further includes:

[0125] Step C10, collecting map data while the data collection vehicle is traveling along the data collection track, and determining a set of the collected map data as a map data set collected by the data collection vehicle;

[0126] The data collection trajectory includes a pre-collected road, and the map data set includes at least the starting position identifier of the data collection vehicle when it passes the starting point of the pre-collected road, and the ending position identifier of the data collection vehicle when it passes the end point of the pre-collected road.

[0127] It should be noted that the executor of the embodiment of the present application is a data collection vehicle. The data collection vehicle collects map data while traveling along the data collection track, and determines the set of collected map data as the map data set collected by the data collection vehicle. The data collection track includes pre-collected roads, that is, the data collection vehicle can collect complete map data on the pre-collected roads. And the map data set at least includes the starting position identifier when the data collection vehicle passes the starting point of the pre-collected road, and the ending position identifier when the data collection vehicle passes the end point of the pre-collected road. In addition, it should be understood that the data collection vehicle records the correspondence between each collected map data and the collection position of the map data, that is, the map data set includes the position identifier of the data collection vehicle when it passes each position on the data collection track.

[0128] In a specific embodiment, the data collection vehicle is communicatively connected to the cloud. After stopping, the data collection vehicle returns the map data set collected that time to the cloud, so that the cloud can obtain target map data corresponding to the pre-collected road from the map data set based on the starting location identifier and the ending location identifier. Alternatively, the data collection vehicle receives a data request instruction issued by the cloud, parses the data request instruction, obtains the starting location identifier and the ending location identifier, and then determines the corresponding video frame from the map data set based on the starting location identifier and the ending location identifier. The video frame corresponding to the starting location identifier is used as the starting frame, and the video frame corresponding to the ending location identifier is used as the ending frame to determine the target map data corresponding to the pre-collected road, and the target map data is returned to the cloud in the form of a video stream. This saves bandwidth resources.

[0129] The data collection vehicle may collect map data using H264, H265, H266, AVS1, AVS2, AVS3, or other video technologies. It should be understood that, compared to the traditional method of collecting image data and storing it on the vehicle side, in the embodiment of the present application, the data collection vehicle compresses the map data of the video data type and stores it on the vehicle side, which can save two-thirds of the storage space and, to a certain extent, improve the efficiency of data storage, extend the life cycle of the data collection vehicle, and thus achieve the purpose of reducing operating costs.

[0130] Thus, embodiments of the present application are applied to a data collection vehicle. In this embodiment, map data is collected while the data collection vehicle travels along a data collection trajectory, and a collection of the collected map data is determined as a map dataset collected by the data collection vehicle. The data collection trajectory includes a pre-collected road, and the map dataset includes at least a starting location identifier when the data collection vehicle passes the starting point of the pre-collected road and an ending location identifier when the data collection vehicle passes the ending point of the pre-collected road. Thus, compared to the traditional method of matching data collection tasks via the cloud upon detecting a vehicle entering a specific road section and issuing a data collection instruction to instruct the vehicle to begin data collection after a successful match, the data collection vehicle in this embodiment can collect complete map data on the pre-collected road and record the location identifiers of the data collection vehicle when it passes the starting point and ending point of the pre-collected road. Based on these two location identifiers, the map data corresponding to the pre-collected road can be determined from the map dataset collected by the data collection vehicle. This avoids the problem of missing map data on the pre-collected road due to untimely instructions from the cloud, improves the integrity of the map data collected by the vehicle, and thus provides more reliable data support for map construction or map updates, thereby improving the accuracy of maps constructed or updated based on the map data.

[0131] This application provides a map data collection device, which is a cloud-based or data collection vehicle. The map data collection device includes: 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 perform the map data collection method described in the first embodiment.

[0132] Reference below Figure 7 , which shows a structural schematic diagram of a map data acquisition device suitable for implementing an embodiment of the present application. Figure 7 The map data collection device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0133] like Figure 7As shown, the map data acquisition device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the map data acquisition device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication devices 1009. The communication device 1009 can allow the map data collection device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a map data collection device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0134] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0135] The map data collection device provided in this application, utilizing the map data collection method of the aforementioned embodiment, can address the technical problem of improving the integrity of map data collected by a vehicle, thereby enhancing the accuracy of maps constructed or updated based on that map data. Compared to the prior art, the map data collection device provided in this application achieves the same beneficial effects as the map data collection method provided in the aforementioned embodiment. Other technical features of this map data collection device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0136] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0137] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0138] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the map data collection method in the above-mentioned embodiment.

[0139] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0140] The computer-readable storage medium may be included in the map data acquisition device; or it may exist independently without being assembled into the map data acquisition device.

[0141] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the map data acquisition device, the map data acquisition device is enabled to: determine the starting position identifier when the data acquisition vehicle passes the starting point of the pre-collected road, and determine the ending position identifier when the data acquisition vehicle passes the end point of the pre-collected road; determine the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on at least the starting position identifier and the ending position identifier; wherein the map data set is a collection of map data collected by the data collection vehicle during the process of traveling along the data collection trajectory, and the data collection trajectory contains the pre-collected road.

[0142] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0144] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0145] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned map data collection method. This computer-readable storage medium addresses the technical problem of improving the integrity of map data collected by vehicles, thereby enhancing the accuracy of maps constructed or updated based on this map data. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the map data collection method provided in the aforementioned embodiments and are not further elaborated here.

[0146] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the above-mentioned map data collection method when executed by a processor.

[0147] The computer program product provided in this application can improve the integrity of map data collected by vehicles, thereby improving the accuracy of maps constructed or updated based on this map data. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiments of this application are the same as those of the map data collection method provided in the above embodiments, and will not be further elaborated here.

[0148] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A map data collection method, characterized in that: The map data collection method comprises: Monitoring the real-time position information of the data collection vehicle while the data collection vehicle is traveling along the data collection track; In response to monitoring that the data collection vehicle enters the pre-collection road from the starting point of the pre-collection road, triggering a starting position marker; and In response to monitoring that the data collection vehicle travels along the pre-collection road to an end point of the pre-collection road, triggering a termination position marker, or in response to monitoring that the data collection vehicle travels out of the pre-collection road from a non-end point of the pre-collection road, returning to the step of monitoring the real-time position information of the data collection vehicle; Determining a target driving trajectory of the data collection vehicle on the pre-collected road, wherein a starting point of the target driving trajectory coincides with a starting point of the pre-collected road, an end point of the target driving trajectory coincides with an end point of the pre-collected road, and the target driving trajectory is distributed within a range of the pre-collected road; determining whether a map data acquisition condition is satisfied based on a match between the target driving trajectory and a reference trajectory indicated by a data collection task to be executed, wherein the map data acquisition condition is that the target driving trajectory and the reference trajectory are identical; When a map data acquisition condition is met, target map data corresponding to the pre-collected road is determined from the map data set collected by the data collection vehicle based on the correspondence between the starting position identifier, the ending position identifier, and the vehicle position identifier and the map data collected by the data collection vehicle, wherein the vehicle position identifier includes the starting position identifier and the ending position identifier; The map data set is a set of map data collected by the data collection vehicle while traveling along a data collection track, and the data collection track includes the pre-collected road.

2. The method according to claim 1, wherein The map data set is a video collected by the data collection vehicle during driving, the map data in the map data set is a video frame in the video, the starting position identifier is a timestamp of the video frame corresponding to the starting point, and the ending position identifier is a timestamp of the video frame corresponding to the end point.

3. The method according to claim 1, wherein Before the step of determining whether a map data acquisition condition is satisfied based on a match between the target driving trajectory and a reference trajectory indicated by the data collection task to be executed, the method further includes: In a case where the data collection task to be executed indicates a first road, determining a trajectory corresponding to the first road as a reference trajectory of the data collection task; In a case where the data collection task to be executed indicates a first lane, determining a trajectory corresponding to the first lane as a reference trajectory of the data collection task; In a case where the data collection task to be executed indicates a task type and collection trajectory information, a reference trajectory corresponding to the data collection task is determined according to the task type and the collection trajectory information.

4. The method according to claim 3, wherein The task type is a road-level collection task or a lane-level collection task, and the collected trajectory information is a second road or a second lane; The step of determining the reference trajectory corresponding to the data collection task according to the task type and the collection trajectory information includes: When the task type is a road-level collection task and the collection trajectory information is a second road, determining the trajectory corresponding to the second road as a reference trajectory of the data collection task; When the task type is a road-level collection task and the collection trajectory information is for the second lane, determining the trajectory corresponding to the third road where the second lane is located as the reference trajectory for the data collection task, wherein the starting point of the second lane is the same as the starting point of the third road, and the end point of the second lane is the same as the end point of the third road; When the task type is a lane-level collection task and the collection trajectory information is for the second lane, determining the trajectory corresponding to the second lane as the reference trajectory corresponding to the data collection task; When the task type is a road-level data collection task and the collected trajectory information is of a second road, a trajectory corresponding to a target lane in the second road is determined as a reference trajectory corresponding to the data collection task.

5. The method according to claim 1, wherein The step of determining the target map data corresponding to the pre-collected road from the map data set collected by the data collection vehicle based on the correspondence between the starting position identifier, the ending position identifier, and the vehicle position identifier and the map data collected by the data collection vehicle comprises: determining target map data corresponding to the pre-collected road from a map data set collected by the data collection vehicle based on a correspondence between the starting position identifier, the ending position identifier, and the vehicle position identifier and map data collected by the data collection vehicle, wherein the map data set is uploaded by the data collection vehicle; or The starting position identifier and the ending position identifier are indicated to the data collection vehicle, and the target map data corresponding to the pre-collected road returned by the data collection vehicle according to the starting position identifier and the ending position identifier is received.

6. A map data collection method, characterized in that: The map data collection method is applied to a data collection vehicle, and the map data collection method includes: collecting map data while the data collection vehicle is traveling along the data collection track, and determining a set of the collected map data as a map data set collected by the data collection vehicle; The data collection trajectory includes a pre-collected road, and the map data set includes at least a starting position identifier when the data collection vehicle passes the starting point of the pre-collected road, an ending position identifier when the data collection vehicle passes the end point of the pre-collected road, and a correspondence between the vehicle position identifier and the map data collected by the data collection vehicle, wherein the vehicle position identifier includes the starting position identifier and the ending position identifier; The starting position identifier is triggered when the data collection vehicle is detected to enter the pre-collection road from the starting point of the pre-collection road during the process of the data collection vehicle traveling along the data collection track; the ending position identifier is triggered when the data collection vehicle is detected to travel along the pre-collection road to the end point of the pre-collection road during the process of the data collection vehicle traveling along the data collection track; The vehicle location identifier and the correspondence between the vehicle location identifier and the map data collected by the data collection vehicle are used to extract the target map data corresponding to the pre-collected road from the map data set when the target driving trajectory of the data collection vehicle on the pre-collected road matches the reference trajectory indicated by the data collection task to be executed, and when the map data acquisition condition is met, the starting point of the target driving trajectory coincides with the starting point of the pre-collected road, the end point of the target driving trajectory coincides with the end point of the pre-collected road, and the target driving trajectory is distributed within the range of the pre-collected road, and the map data acquisition condition is that the matching condition is that the target driving trajectory is the same as the reference trajectory.

7. A map data collection device, characterized in that: The map data collection device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the map data collection method according to any one of claims 1 to 5 or 6.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the map data collection method according to any one of claims 1 to 5 or 6.

Images