Tracing method and device based on point cloud map

Abstract

The invention discloses a tracing method and device based on a point cloud map, and relates to the technical field of automatic driving. According to the method, a global unique source tracing file in a JSON format is created, the file comprises original information of each batch of collected data, and the information is in global one-to-one correspondence with id introduced by point cloud elements. The traceability information of each point cloud element can be found through an id medium; the id field is introduced into the operation of merging the map tiles after the mapping is completed, so that the memory consumption caused by a tedious mapping algorithm process and introduction of more fields into a relatively long data chain can be greatly reduced, the program complexity improvement caused by processing the custom field point cloud can be greatly reduced, and meanwhile, the robustness of the whole system is enhanced.

Description

TECHNICAL FIELD

[0001] The application discloses a point cloud map-based tracing method and device, and relates to the technical field of automatic driving. BACKGROUND

[0002] In the field of automatic driving, a large-scale high-precision point cloud map built in advance plays an important role in positioning of vehicles.

[0003] However, when it comes to a large-scale point cloud map containing extensive spatial information and multiple data layers, it is often very difficult to identify the source of point cloud data at these specific locations and the attribute information thereof in the map construction process. With the continuous increase of point cloud map data, such uncertainty and complexity also increase accordingly, making it increasingly difficult to perform addition, deletion, modification and query operations on the point cloud map in a given small-scale area.

[0004] Current methods mainly include the following three types: a point cloud marking method based on metadata, a point cloud management method based on a database, and a point cloud marking method based on fields.

[0005] Method 1 requires adding and updating metadata tags at each step of point cloud data collection and processing, increasing the complexity of data processing. As the amount of data increases, the number of metadata tags will also increase significantly, resulting in increased storage space requirements, which may affect the overall performance and storage cost of the system; method 2 requires careful design and continuous maintenance, especially when facing a constantly changing and expanding data set. For application scenarios with high real-time requirements, database queries may become a bottleneck, resulting in reduced system response speed; method 3 adds a new field to each point cloud element during the construction of a point cloud map. The field carries the tracing information of the point cloud.

[0006] Currently, the methods used by the industry are mostly based on method 2 and method 3. The main problem solved by the present application is that when using method 3, not all tracing information is added to each point cloud element, but only a globally unique integer field with a small memory footprint is introduced for each point cloud element.

[0007] In the prior art, point cloud tracing information is directly added to the original point cloud data collected and intermediate data in the mapping process, which inevitably introduces more fields into the lengthy mapping algorithm process and longer data chain, resulting in memory consumption and destruction of the simplicity of the original algorithm. Therefore, the present application provides a point cloud map-based tracing method and device to solve the above problems. SUMMARY

[0008] To solve the problems of the prior art, the application provides a point cloud map-based tracing method and device, which employs the following technical solutions:

[0009] In a first aspect, a point cloud map-based traceability method is provided, and the method comprises:

[0010] Collecting original data packets and generating a traceability file of the original data packets;

[0011] For a newly collected original data packet, determining whether a path of the newly collected original data packet exists in the traceability file; if not, generating corresponding traceability information according to the newly collected original data packet; if yes, generating a point cloud map according to the traceability file;

[0012] Merging mapping data into a map tile and updating the point cloud map.

[0013] In some implementations, the traceability file comprises a global_id field and a data_list field, the global_id field is used to indicate an id number of the traceability file, and the data_list field comprises structure data in a list form and is used to store traceability information of a point cloud map.

[0014] The data_list field comprises an obsdata_path field and an id field, the obsdata_path field is used to indicate a stored cloud address path of the original data packet, and the id field is used to indicate a unique number of the original data packet data.

[0015] In some implementations, the corresponding traceability information is generated according to the newly collected original data packet, and specifically comprises:

[0016] According to a cloud address of the newly collected original data packet, an obsdata_path field is added and a latest id field is generated;

[0017] The traceability information is added to the data_list field.

[0018] In some implementations, the mapping data is merged into the map tile according to the point cloud map, and specifically comprises:

[0019] According to mapping information of the point cloud map, a field corresponding to the traceability information is updated;

[0020] According to the mapping information, each point cloud element is inserted into an id field of the data traceability information.

[0021] The mapping data is merged into the map tile.

[0022] In a second aspect, an embodiment of the present application provides a point cloud map-based traceability device, and the device comprises:

[0023] a data collection module configured to collect raw data packets and generate a trace file of the raw data packets;

[0024] a data processing module configured to, for a newly collected raw data packet, determine whether a path of the newly collected raw data packet exists in the trace file; if not, generate corresponding trace information according to the newly collected raw data packet; and if yes, generate a point cloud map according to the trace file;

[0025] a data merging module configured to merge mapping data into a map tile and update the point cloud map.

[0026] In some implementations, the data collection module, the trace file includes a global_id field and a data_list field, the global_id field is configured to indicate an id number of the trace file, and the data_list field includes structure data in a list form and is configured to store trace information of a point cloud map.

[0027] The data_list field includes an obsdata_path field and an id field, the obsdata_path field is configured to indicate a cloud address path of storage of the raw data packet, and the id field is configured to indicate a unique number of data of the raw data packet.

[0028] In some implementations, the data processing module specifically includes:

[0029] a field generation unit configured to generate a latest id field by adding an obsdata_path field according to a cloud address of a newly collected raw data packet;

[0030] a field update unit configured to add the trace information into the data_list field.

[0031] In some implementations, the data merging module includes:

[0032] a trace update unit configured to update a field corresponding to the trace information according to mapping information of the point cloud map;

[0033] a field insertion unit configured to insert each point cloud element into an id field of the data trace information according to the mapping information;

[0034] a tile update unit configured to merge the mapping data into the map tile.

[0035] In a third aspect, an electronic device is provided, comprising a memory and a processor, the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method in the first aspect.

[0036] In a fourth aspect, a computer storage medium is provided, the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method in the first aspect.

[0037] One or more embodiments of the present application can bring at least the following beneficial effects:

[0038] The method of the present application can create a globally unique JSON format traceability file, which contains the original information of each batch of collected data, and the information is globally one-to-one corresponding to the id introduced by the point cloud element. Through the medium of id, the traceability information of each point cloud element can be found;

[0039] Introducing the id field in the merging map tile operation after mapping completion can greatly reduce the memory consumption caused by introducing more fields in the long mapping algorithm process and the long data chain, and the increase of program complexity caused by processing custom field point cloud, and at the same time enhance the robustness of the whole system. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0041] Figure 1 is a flowchart of a traceability method based on a point cloud map provided by an embodiment of the present application;

[0042] Figure 2 is an implementation flowchart of a traceability device based on a point cloud map provided by an embodiment of the present application;

[0043] Figure 3 is a merging schematic diagram of newly created map data and map tiles provided by an embodiment of the present application. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0045] Embodiment one:

[0046] Figure 1 A point cloud map-based traceability method flowchart is shown, as Figure 1 indicated, the point cloud map-based traceability method provided by the present embodiment comprises:

[0047] S1, collecting original data packets to generate a traceability file of the original data packets;

[0048] S2, for newly collected original data packets, judging whether the path of the newly collected original data packets exists in the traceability file; if not, generating corresponding traceability information according to the newly collected original data packets; if yes, generating a point cloud map according to the traceability file;

[0049] S3, merging mapping data into a map tile to update the point cloud map.

[0050] First, according to S1, a globally unique JSON format traceability file is generated. The JSON file contains two fields: global_id and data_list. The global_id field represents the latest id number of the current traceability file. The data_list field uses a list form data structure to store all the traceability information of the point cloud map, and its sub-data structure includes: the obsdata_path field represents the storage cloud address path of the original data packet, which is unique; the id field represents the unique number of each original data packet data, which corresponds to the obsdata_path field one by one, that is, each obsdata_path field has and only has one id field number; the city_area field represents the city area number, for example, NanTongShi-ChongChuanQu; the base_version field represents the basic version number of constructing this map; the version field represents the latest map version number newly built this time;

[0051] The attributes field represents attributes, and the other field is a field that can be supplemented at any time later.

[0052] Next, according to S2, before mapping is performed using a new collected raw data packet each time, it is determined whether the data packet path already exists in the traceability file, and if not, a traceability information of the data is generated; specifically including:

[0053] According to S21, based on the cloud address of the newly collected raw data packet, the obsdata_path field is added and the latest id field is generated;

[0054] According to S22, the traceability information is added to the data_list field;

[0055] According to S21 and S22, the cloud address of the raw data packet collected this time is added to the obsdata_path field, and the latest id is generated, and the remaining fields are temporarily empty. Finally, the traceability information of the data is added to the data_list field;

[0056] Next, according to S3, after the mapping of the newly collected data is completed, the mapping data this time needs to be merged into the entire map tile; specifically including:

[0057] S31, according to the mapping information of the point cloud map, the field corresponding to the traceability information is updated;

[0058] S32, according to the mapping information, each point cloud element is inserted into the id field of the data traceability information;

[0059] S33, the mapping data is merged into the map tile;

[0060] According to S31, the mapping information updates the field corresponding to the traceability information, such as the city_area field, the base_version field, the version field, etc. Then according to S32, for each point cloud element of this mapping, the id field of the data traceability information is inserted. Finally, according to S33, the mapping data this time is merged into the entire map tile. At this time, if it is necessary to obtain the traceability information of any point cloud element in the map, the technical personnel can query the id field of the point cloud through a script or manually, and in combination with the globally unique traceability file, it can be realized. In addition, adding the id field to the point cloud element occupies very small memory space and does not significantly increase the storage burden. And only in the operation of merging the map tile after mapping is completed, the id field is introduced, which can reduce the memory consumption caused by introducing more fields in the long mapping algorithm process and the long data chain.

[0061] Embodiment Two

[0062] On the basis of embodiment one, it is assumed that the area to be mapped this time is a certain section of a road in Wuxi Binhu District, and a globally unique JSON format traceability file has been generated in advance:

[0063] The collection personnel collect the original data package for mapping (assuming the cloud address of the data package is:

[0064] eos: / / neolix-fs / data_hd / WuXiShiBinHuQuWuXiBinHu-MeiYuanBuCai-20241121224209-X33712-1"), and upload it to the middle platform, which automatically triggers the mapping process;

[0065] The mapping script determines whether the data package path already exists in the traceability file. If it exists, the next step is performed. If it does not exist, the traceability information of the data is added, and the fields obsdata_path and id are filled in;

[0066] The mapping script maps the data;

[0067] According to the mapping situation, the remaining traceability information fields city_area, base_version, and version are automatically filled or updated.

[0068] Insert all point cloud elements of this mapping into the value of the id field of the data traceability information: 3284;

[0069] Merge the newly mapped data into the entire map tile. The complete effect is shown in Figure 3 The entire map tile area and the newly mapped point cloud area are shown, and a few points are randomly selected, with the id field showing 3284, which meets the expectation.

[0070] Embodiment three:

[0071] Figure 2 An implementation flowchart of a point cloud map based traceability device is shown. The embodiment of the present application provides a point cloud map based traceability device, which comprises:

[0072] A data collection module for collecting original data packages and generating a traceability file for the original data packages;

[0073] A data processing module for determining whether the path of the newly collected original data package exists in the traceability file. If it does not exist, corresponding traceability information is generated according to the newly collected original data package. If it exists, a point cloud map is generated according to the traceability file;

[0074] A data merging module is configured to merge the mapping data into a map tile, and update the point cloud map.

[0075] Further, in the data acquisition module, the traceability file includes a global_id field and a data_list field, the global_id field is configured to indicate the id number of the traceability file, and the data_list field includes structure data in a list form and is configured to store the traceability information of the point cloud map.

[0076] The data_list field includes an obsdata_path field and an id field, the obsdata_path field is configured to indicate the cloud address path of the storage of the original data packet, and the id field is configured to indicate the unique number of the original data packet.

[0077] Further, the data processing module specifically includes:

[0078] A field generation unit is configured to generate the latest id field by adding the obsdata_path field according to the cloud address of the newly-acquired original data packet.

[0079] A field updating unit is configured to add the traceability information into the data_list field.

[0080] Further, the data merging module includes:

[0081] A traceability updating unit is configured to update the field corresponding to the traceability information according to the mapping information of the point cloud map.

[0082] A field insertion unit is configured to insert each point cloud element into the id field of the data traceability information according to the mapping information.

[0083] A tile updating unit is configured to merge the mapping data into the map tile.

[0084] Embodiment four:

[0085] The embodiment also provides an electronic device including a memory and a processor, the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method of the embodiment one.

[0086] In practical applications, the processor can be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller (MCU), a microprocessor, or other electronic elements, which are used to execute the methods in the above embodiments.

[0087] The method implemented by the embodiment is as described in the content of Embodiment One.

[0088] Embodiment Five

[0089] The embodiment also provides a computer readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the method of Embodiment One is implemented.

[0090] The computer readable storage medium can be implemented by any type of volatile or non-volatile storage devices or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0091] The method implemented by the embodiment is as described in the content of Embodiment One.

[0092] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed system and method can also be implemented in other ways. The system and method embodiments described above are only illustrative.

[0093] It should be noted that, in the present document, the terms "first", "second", and the like, in the description and in the claims of the present application and in the above-described drawings, are intended to distinguish similar objects and not necessarily to describe a particular chronological or sequential order. The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by an indefinite article "a" does not exclude the existence, under the same conditions, of two or more identical elements.

[0094] Although the embodiments of the present application are disclosed as above, the above-described content is only for facilitating the understanding of the present application and is not intended to limit the present application. Any person skilled in the art of the present application can make any modification and change in the implementation form and details without departing from the spirit and scope of the present application, and the patent protection scope of the present application shall be subject to the scope defined by the appended claims.

Claims

1. A point cloud map based provenance method, the method comprising: The method comprises: collecting original data packets, and generating a traceability file of the original data packets; for a newly collected original data packet, determining whether a path of the newly collected original data packet exists in the traceability file; if not, generating corresponding traceability information according to the newly collected original data packet; if yes, generating a point cloud map according to the traceability file; merging mapping data into a map tile, and updating the point cloud map.

2. The method of claim 1, wherein, The traceability file comprises a global_id field and a data_list field, the global_id field is used for indicating an id number of the traceability file; and the data_list field comprises structure data in a list form, and is used for storing traceability information of a point cloud map. The data_list field comprises an obsdata_path field and an id field; the obsdata_path field is used for indicating a cloud address path of storage of the original data packet; and the id field is used for indicating a unique number of data of the original data packet.

3. The method of claim 2, wherein, According to the newly collected original data packet, the corresponding traceability information is generated, specifically comprising: according to a cloud address of the newly collected original data packet, adding an obsdata_path field and generating a latest id field; adding the traceability information into the data_list field.

4. The method of claim 3, wherein, According to the point cloud map, the mapping data is merged into the map tile, comprising: according to mapping information of the point cloud map, updating a field corresponding to the traceability information; according to the mapping information, inserting each point cloud element into the id field of the data traceability information; merging the mapping data into the map tile. 5.A traceability device based on a point cloud map, characterized in that, The device comprises: a data collection module, configured to collect original data packets, and generate a traceability file of the original data packets; a data processing module, configured to, for a newly collected original data packet, determine whether a path of the newly collected original data packet exists in the traceability file; if not, generate corresponding traceability information according to the newly collected original data packet; if yes, generate a point cloud map according to the traceability file; a data merging module, configured to merge mapping data into a map tile, and update the point cloud map.

6. The method of claim 5, wherein, In the data collection module, the traceability file comprises a global_id field and a data_list field, the global_id field is used for indicating an id number of the traceability file; and the data_list field comprises structure data in a list form, and is used for storing traceability information of a point cloud map. The data_list field comprises an obsdata_path field and an id field; the obsdata_path field is used for indicating a cloud address path of storage of the original data packet; and the id field is used for indicating a unique number of data of the original data packet.

7. The apparatus of claim 6, wherein, The data processing module specifically comprises: a field generation unit, configured to, according to a cloud address of the newly collected original data packet, add an obsdata_path field and generate a latest id field; A field updating unit is configured to add the provenance information into the data_list field.

8. The apparatus of claim 7, wherein, The data merging module comprises: A provenance updating unit is configured to update a field corresponding to the provenance information according to mapping information of the point cloud map. A field inserting unit is configured to insert each point cloud element into an id field of the data provenance information according to the mapping information. A tile updating unit is configured to merge the mapping data into the map tile.

9. An electronic device, comprising: The memory is configured to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the method in any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, The computer program is stored in the computer readable storage medium and is executed by the processor to implement the method in any one of claims 1-4.

Images