Methods, devices, and electronic equipment for processing autonomous driving data
By processing autonomous driving data through methods of identifying and constructing virtual scenes, the problem of data anonymization in surveying and mapping was solved, achieving data anonymization and authenticity matching.
Patent Information
- Application Number
- CN202211008613.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-08-22
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2042-08-22
AI Technical Summary
There is a lack of effective means in the current technology to desensitize sensitive data such as mapping data in autonomous driving data.
By acquiring raw data from autonomous vehicles, identifying real-world environmental information, constructing virtual scenes that do not include sensitive information such as facial information, license plate information, and building information, and collecting environmental and vehicle operation information from the virtual scenes, processed autonomous driving data is generated.
It has achieved desensitization processing of personal privacy data and surveying data in autonomous driving data, ensuring that the processed data contains no sensitive information and that the virtual scene is highly matched with the real environment.
Smart Images

Figure CN115422576B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous driving, and more specifically, to a method for processing autonomous driving data, a processing device, a computer-readable storage medium, a processor, and an electronic device. Background Technology
[0002] As regulations tighten their control over autonomous driving data, real-world autonomous driving data must undergo anonymization before it can be used in compliance with regulations. Sensitive data includes personal privacy data and mapping data. Personal privacy data includes facial, license plate, and vehicle body data; mapping data includes maps, terrain, building, and location information.
[0003] Existing technologies use deep learning to identify sensitive image data and then perform desensitization operations such as blurring. However, there are no effective methods for mapping-related data such as maps and sensor data.
[0004] Therefore, there is an urgent need for a solution to the problem that existing technologies lack the ability to desensitize sensitive data such as mapping data in autonomous driving data.
[0005] The information disclosed above in the background section is only intended to enhance the understanding of the background art of the art described herein. Therefore, the background art may contain certain information that does not constitute prior art known to those skilled in the art in this country. Summary of the Invention
[0006] The main objective of this application is to provide a method, apparatus, computer-readable storage medium, processor, and electronic device for processing autonomous driving data, in order to solve the problem that the prior art lacks desensitization processing for sensitive data such as mapping data in autonomous driving data.
[0007] According to one aspect of the present invention, a method for processing autonomous driving data is provided, comprising: acquiring raw data collected by an autonomous driving vehicle; identifying the raw data to obtain real environment information, wherein the real environment information is the environment information in which the autonomous driving vehicle is located; constructing a virtual scene matching the real environment information based on the real environment information, wherein the virtual scene does not include at least facial information, license plate information, building information, and road sign information; and collecting the environmental information of the virtual scene and / or the corresponding vehicle operation information of the autonomous driving vehicle to obtain processed autonomous driving data.
[0008] Optionally, constructing a virtual scene matching the real environment information based on the real environment information includes: describing the real environment information using a scene description language to obtain a logical scene that does not include the license plate information, the building information, and the road sign information, wherein the logical scene includes road condition information and obstacle information; acquiring multiple pre-constructed scene simulation maps; determining a first simulation map based on the logical scene and the multiple scene simulation maps, wherein the first simulation map is the scene simulation map that matches the scene information of the logical scene; and adding the obstacle information of the logical scene to the first simulation map to obtain the virtual scene.
[0009] Optionally, constructing a virtual scene matching the real environment information based on the real environment information includes: describing the real environment information using a scene description language to obtain a logical scene that does not include the license plate information, the building information, and the road sign information; constructing a scene simulation map based on the scene information of the logical scene to obtain a second simulation map; and adding obstacle information of the logical scene to the second simulation map to obtain the virtual scene.
[0010] Optionally, the raw data includes image data and radar data. Identifying the raw data to obtain real environment information includes: using environmental recognition technology to identify and process the image data and the radar data to obtain the real environment information.
[0011] Optionally, collecting environmental information of the virtual scene includes: using an image acquisition device and a radar device that simulate the autonomous vehicle to collect environmental information of the virtual scene, thereby obtaining the environmental information of the virtual scene.
[0012] Optionally, the real environment information includes static object information and dynamic object information. The static object information includes road surface information, building information, road sign information, and traffic sign and marking information. The dynamic object information includes vehicle information, pedestrian information, vehicle and pedestrian movement trajectory information, and traffic light information.
[0013] According to another aspect of the present invention, an autonomous driving data processing apparatus is also provided, including an acquisition unit, an identification unit, a construction unit, and a collection unit, wherein the acquisition unit is used to acquire raw data collected by an autonomous driving vehicle; the identification unit is used to identify the raw data to obtain real environment information of the autonomous driving vehicle; the construction unit is used to construct a virtual scene matching the real environment information based on the real environment information, wherein the virtual scene does not include at least facial information, license plate information, building information, and road sign information; and the collection unit is used to collect environmental information of the virtual scene and / or vehicle operation information of the corresponding autonomous driving vehicle to obtain processed autonomous driving data.
[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes any one of the methods described.
[0015] According to another aspect of the present invention, a processor is also provided, the processor being configured to run a program, wherein the program, when running, executes any of the methods described.
[0016] According to another aspect of the present invention, an electronic device is also provided, the electronic device including one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.
[0017] The technical solution of this application describes a method for processing autonomous driving data. First, raw data collected by the autonomous vehicle is acquired. Then, the raw data is identified to obtain information about the real environment in which the autonomous vehicle is located. Next, based on the obtained real environment information, a virtual scene is constructed that excludes sensitive information such as facial information, license plate information, building information, and road sign information. This virtual scene matches the real environment information. Finally, environmental information is collected from the virtual scene, and / or the operational information of the autonomous vehicle in the virtual scene is collected to obtain processed autonomous driving data. This application achieves desensitization processing of personal privacy data and mapping data in the autonomous driving data, ensuring that the processed autonomous driving data contains no personal privacy data or mapping data. This solves the problem in existing technologies of lacking desensitization processing for sensitive data such as mapping data in autonomous driving data. Furthermore, the virtual scene is constructed based on real environment information, possessing a high degree of realism, ensuring that the final processed autonomous driving data closely matches the actual environment. Attached Figure Description
[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0019] Figure 1 A flowchart illustrating a method for processing autonomous driving data according to an embodiment of this application is shown.
[0020] Figure 2 A flowchart illustrating another method for processing autonomous driving data according to an embodiment of this application is shown;
[0021] Figure 3 A flowchart illustrating another method for processing autonomous driving data according to an embodiment of this application is shown;
[0022] Figure 4 A schematic diagram of an apparatus for processing autonomous driving data according to an embodiment of this application is shown. Detailed Implementation
[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0026] It should be understood that when an element (such as a layer, film, region, or substrate) is described as being "on" another element, the element may be directly on the other element, or there may be an intermediate element present. Furthermore, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element, or "connected" to the other element via a third element.
[0027] As mentioned in the background section, the existing technology lacks desensitization processing for sensitive data such as mapping data in autonomous driving data. In order to solve the above problems, in a typical embodiment of this application, an autonomous driving data processing method, processing device, computer-readable storage medium, processor, and electronic device are provided.
[0028] According to an embodiment of this application, a method for processing autonomous driving data is provided.
[0029] Figure 1 This is a flowchart of a method for processing autonomous driving data according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:
[0030] Step S101: Obtain the raw data collected by the autonomous vehicle.
[0031] Autonomous vehicles are equipped with cameras and radar devices, including lidar and millimeter-wave radar. The raw data can be collected by the cameras, lidar, and millimeter-wave radar of the autonomous vehicle, including image data and radar data.
[0032] After obtaining the above raw data, it is necessary to perform perception and recognition on the raw data. The specific processing procedure is as follows:
[0033] Step S102: Identify the above-mentioned raw data to obtain real environmental information, which is the environmental information of the autonomous vehicle.
[0034] Specifically, the aforementioned real-world environmental information includes static object information and dynamic object information. The static object information includes road surface information, building information, road sign information, and traffic sign and marking information. The dynamic object information includes vehicle information, pedestrian information, vehicle and pedestrian movement trajectory information, and traffic light information.
[0035] The aforementioned road surface information includes whether it is an intersection, whether it is a straight-ahead lane, and the shape of the intersection (crossroads, T-junctions, etc.). The aforementioned traffic light information includes, but is not limited to, the current color of the traffic light, the duration of the current color, and the time interval between color changes. The aforementioned vehicle information includes, but is not limited to, license plate information, vehicle shape, vehicle dimensions, and movement trajectory of four-wheeled, three-wheeled, and two-wheeled vehicles.
[0036] Of course, in order to more realistically reflect the scenario in which the autonomous vehicle is located, the above-mentioned real environment information is not limited to the static object information and dynamic object information mentioned above. It may also include external environment information such as weather, light and season, as well as other information. Those skilled in the art can flexibly set the content of the above-mentioned real environment information according to the actual situation.
[0037] To further ensure the accuracy of the obtained real-world environmental information and its consistency with the environment in which the autonomous vehicle operates, in one embodiment of this application, the raw data includes image data and radar data. Identifying the raw data to obtain real-world environmental information includes: using environmental recognition technology to identify and process the image data and radar data to obtain the real-world environmental information. By using environmental recognition technology to perceive and identify the image data and radar data, more accurate real-world environmental information can be obtained.
[0038] Step S103: Based on the above real environment information, construct a virtual scene that matches the above real environment information. The virtual scene shall not include facial information, license plate information, building information, or road sign information.
[0039] In practical applications, those skilled in the art can use any suitable method to construct a virtual scene that does not include sensitive information such as facial information, license plate information, building information, and road sign information, based on the aforementioned real-world environmental information. In one embodiment of this application, such as... Figure 2 As shown, the specific process of constructing a virtual scene that matches the aforementioned real-world environment information is as follows:
[0040] Step S201: Based on the above real environment information, use scene description language to describe the above real environment information to obtain a logical scene that does not include the above license plate information, the above building information and the above road sign information. The above logical scene includes road condition information and obstacle information.
[0041] Step S202: Obtain multiple pre-built scene simulation maps;
[0042] Step S203: Based on the above logical scenario and multiple above scenario simulation maps, determine the first simulation map, wherein the first simulation map is the above scenario simulation map that matches the scenario information of the above logical scenario.
[0043] Step S204: Add obstacle information of the above logical scene to the first simulation map to obtain the above virtual scene.
[0044] In this embodiment, a scene description language is first used to describe the real environment information, that is, a non-image logical language is used to describe it, ensuring that the resulting logical scene does not include facial information. Furthermore, during the description of the real environment using the scene description language, the aforementioned license plate information, building information, and road sign information are removed, ensuring that the resulting logical scene does not include actual maps, terrain, buildings, and location information, etc., as mapping data. Then, from multiple pre-built scene simulation maps, a scene simulation map that matches the scene information of the aforementioned logical scene is selected as the first simulation map. Finally, obstacle information of the logical scene is added to the first simulation map to obtain the aforementioned virtual scene, further achieving desensitization of personal privacy data and mapping data, further ensuring that the virtual scene does not contain the aforementioned personal privacy data and mapping data. Simultaneously, the aforementioned virtual scene includes scene information and obstacle information of the logical scene where the autonomous vehicle is located, ensuring a high degree of matching between the virtual scene and the real scene, that is, ensuring that the virtual scene is relatively realistic.
[0045] In one specific embodiment, the above logical scenario is scenario data in text format.
[0046] The aforementioned scene simulation map consists of roads and traffic lights of different shapes and quantities, as well as buildings of different shapes and quantities. For example, the scene simulation map... Figure 1 It consists of a straight road, traffic lights on the straight road, two buildings on one side of the straight road, and three buildings on the other side of the road, creating a simulated scene. Figure 2 It consists of a crossroads, two traffic lights at the crossroads, and buildings surrounding the crossroads. Of course, the objects in the above-described scene simulation map are not limited to those described above; those skilled in the art can freely add objects to the scene simulation map according to actual needs. It should be noted that the above-described scene simulation map does not reflect the actual geographical information of the buildings and roads.
[0047] The scene simulation map that matches the scene information of the above logical scenario is the scene simulation map that is basically consistent with the scene information of the logical scenario. For example, if the scene information of the logical scenario is a T-junction with a traffic light and two buildings on each side of the side road of the T-junction, then the scene simulation map that matches the scene information of the above logical scenario also includes the above objects, and the relative positional relationship between the objects is consistent with the logical scenario.
[0048] In practical applications, in order to obtain the scene simulation map with a high degree of matching with the scene information of the above logical scenario, and to further ensure the high realism of the final virtual scene, as many scene simulation maps as possible can be built in advance so that all the above scene simulation maps can be adapted to different actual scenarios.
[0049] Of course, the specific process of constructing a virtual scene that matches the aforementioned real-world environment information is not limited to the process described above. In other embodiments of this application, the process of constructing a virtual scene that matches the aforementioned real-world environment information is as follows: Figure 3 As shown, the specific implementation steps are as follows:
[0050] Step S301: Based on the above real environment information, use scene description language to describe the above real environment information to obtain a logical scene that does not include the above license plate information, the above building information and the above road sign information.
[0051] Step S302: Based on the scene information of the above logical scenario, construct a scene simulation map to obtain a second simulation map;
[0052] Step S303: Add obstacle information of the above logical scene to the above second simulation map to obtain the above virtual scene.
[0053] Compared with the previous embodiment, this embodiment does not require pre-constructing a scene simulation map. Instead, it directly constructs a scene simulation map that matches the scene information of the logical scene to obtain a second simulation map. Then, it adds corresponding obstacle information to the second simulation map to obtain the virtual scene.
[0054] It should be noted that the scene simulation map constructed based on the scene information of the above logical scenario does not reflect the real geographical information of buildings and roads. The construction of the scene simulation map in this embodiment is the same as that in the above embodiment, and will not be repeated here.
[0055] The aforementioned obstacle information includes object information and location information of pedestrians, vehicles, and roadblocks on the road.
[0056] Step S104: Collect the environmental information of the virtual scene and / or the vehicle operation information of the corresponding autonomous vehicle to obtain the processed autonomous driving data.
[0057] Specifically, the aforementioned vehicle operation information may include the vehicle's throttle status, brake status, steering wheel position, vehicle location, vehicle orientation, vehicle speed, vehicle acceleration, and wheel speed. Of course, the aforementioned vehicle operation information is not limited to the above information; it may also include other operation information of the vehicle in this scenario.
[0058] In one specific embodiment, the processed autonomous driving data consists of the environmental information of the virtual scene and the vehicle operation information.
[0059] To further ensure the high authenticity of the processed autonomous driving data, according to another specific embodiment of this application, environmental information of the virtual scene is collected, specifically including: simulating the image acquisition device and radar device of the autonomous vehicle to collect the environmental information of the virtual scene, thereby obtaining the environmental information of the virtual scene.
[0060] The autonomous driving data processing method of this application first acquires raw data collected by an autonomous vehicle; then, it identifies the raw data to obtain the real-world environmental information of the autonomous vehicle; next, based on the obtained real-world environmental information, it constructs a virtual scene that excludes sensitive information such as facial information, license plate information, building information, and road sign information, and this virtual scene matches the real-world environmental information; finally, it collects environmental information from the virtual scene and / or collects the operational information of the autonomous vehicle in the virtual scene to obtain processed autonomous driving data. This application achieves desensitization processing of personal privacy data and mapping data in the autonomous driving data, ensuring that the processed autonomous driving data contains no personal privacy data or mapping data, thus solving the problem in the prior art of lacking desensitization processing for sensitive data such as mapping data in autonomous driving data. Furthermore, the virtual scene is constructed based on real-world environmental information and has a high degree of realism, ensuring that the final processed autonomous driving data closely matches the actual environment.
[0061] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0062] This application also provides an autonomous driving data processing apparatus. It should be noted that the autonomous driving data processing apparatus of this application can be used to execute the autonomous driving data processing method provided in this application. The autonomous driving data processing apparatus provided in this application will be described below.
[0063] Figure 4 This is a schematic diagram of an autonomous driving data processing apparatus according to an embodiment of this application. Figure 4 As shown, the device includes:
[0064] Acquisition unit 10 is used to acquire raw data collected by autonomous vehicles.
[0065] Autonomous vehicles are equipped with cameras and radar devices, including lidar and millimeter-wave radar. The raw data can be collected by the cameras, lidar, and millimeter-wave radar of the autonomous vehicle, including image data and radar data.
[0066] The identification unit 20 is used to identify the above-mentioned raw data to obtain the real environment information of the autonomous vehicle.
[0067] Specifically, the aforementioned real-world environmental information includes static object information and dynamic object information. The static object information includes road surface information, building information, road sign information, and traffic sign and marking information. The dynamic object information includes vehicle information, pedestrian information, vehicle and pedestrian movement trajectory information, and traffic light information.
[0068] The aforementioned road surface information includes whether it is an intersection, whether it is a straight-ahead lane, and the shape of the intersection (crossroads, T-junctions, etc.). The aforementioned traffic light information includes, but is not limited to, the current color of the traffic light, the duration of the current color, and the time interval between color changes. The aforementioned vehicle information includes, but is not limited to, license plate information, vehicle shape, vehicle dimensions, and movement trajectory of four-wheeled, three-wheeled, and two-wheeled vehicles.
[0069] Of course, in order to more realistically reflect the scenario in which the autonomous vehicle is located, the above-mentioned real environment information is not limited to the static object information and dynamic object information mentioned above. It may also include external environment information such as weather, light and season, as well as other information. Those skilled in the art can flexibly set the content of the above-mentioned real environment information according to the actual situation.
[0070] To further ensure the accuracy of the obtained real-world environmental information and its consistency with the environment in which the autonomous vehicle operates, in one embodiment of this application, the original data includes image data and radar data, and the identification unit includes a processing module. This processing module is used to identify and process the image data and radar data using environmental identification technology to obtain the real-world environmental information. By using environmental identification technology to perceive and identify the image data and radar data, more accurate real-world environmental information can be obtained.
[0071] The construction unit 30 is used to construct a virtual scene that matches the real environment information based on the real environment information mentioned above. The virtual scene does not include facial information, license plate information, building information, or road sign information.
[0072] In practical applications, those skilled in the art can use any suitable method to construct a virtual scene that does not include sensitive information such as facial information, license plate information, building information, and road sign information based on the aforementioned real environment information. In one embodiment of this application, the aforementioned construction unit specifically includes a first description module, an acquisition module, a determination module, and a first addition module. The first description module is used to describe the aforementioned real environment information using a scene description language to obtain a logical scene that does not include the aforementioned license plate information, building information, and road sign information. The logical scene includes road condition information and obstacle information. The acquisition module is used to acquire multiple pre-built scene simulation maps. The determination module is used to determine a first simulation map based on the aforementioned logical scene and the multiple aforementioned scene simulation maps. The first simulation map is the scene simulation map that matches the scene information of the aforementioned logical scene. The first addition module is used to add the obstacle information of the aforementioned logical scene to the aforementioned first simulation map to obtain the aforementioned virtual scene.
[0073] In this embodiment, a scene description language is first used to describe the real environment information, that is, a non-image logical language is used to describe it, ensuring that the resulting logical scene does not include facial information. Furthermore, during the description of the real environment using the scene description language, the aforementioned license plate information, building information, and road sign information are removed, ensuring that the resulting logical scene does not include actual maps, terrain, buildings, and location information, etc., as mapping data. Then, from multiple pre-built scene simulation maps, a scene simulation map that matches the scene information of the aforementioned logical scene is selected as the first simulation map. Finally, obstacle information of the logical scene is added to the first simulation map to obtain the aforementioned virtual scene, further achieving desensitization of personal privacy data and mapping data, further ensuring that the virtual scene does not contain the aforementioned personal privacy data and mapping data. Simultaneously, the aforementioned virtual scene includes scene information and obstacle information of the logical scene where the autonomous vehicle is located, ensuring a high degree of matching between the virtual scene and the real scene, that is, ensuring that the virtual scene is relatively realistic.
[0074] In one specific embodiment, the above logical scenario is scenario data in text format.
[0075] The aforementioned scene simulation map consists of roads and traffic lights of different shapes and quantities, as well as buildings of different shapes and quantities. For example, the scene simulation map... Figure 1 It consists of a straight road, traffic lights on the straight road, two buildings on one side of the straight road, and three buildings on the other side of the road, creating a simulated scene. Figure 2 It consists of a crossroads, two traffic lights at the crossroads, and buildings surrounding the crossroads. Of course, the objects in the above-described scene simulation map are not limited to those described above; those skilled in the art can freely add objects to the scene simulation map according to actual needs. It should be noted that the above-described scene simulation map does not reflect the actual geographical information of the buildings and roads.
[0076] The scene simulation map that matches the scene information of the above logical scenario is the scene simulation map that is basically consistent with the scene information of the logical scenario. For example, if the scene information of the logical scenario is a T-junction with a traffic light and two buildings on each side of the side road of the T-junction, then the scene simulation map that matches the scene information of the above logical scenario also includes the above objects, and the relative positional relationship between the objects is consistent with the logical scenario.
[0077] In practical applications, in order to obtain the scene simulation map with a high degree of matching with the scene information of the above logical scenario, and to further ensure the high realism of the final virtual scene, as many scene simulation maps as possible can be built in advance so that all the above scene simulation maps can be adapted to different actual scenarios.
[0078] Of course, the above-mentioned construction unit is not limited to the modules mentioned above. In other embodiments of this application, the above-mentioned construction unit may also include a second description module, a construction module, and a second adding module. The second description module is used to describe the real environment information using a scene description language based on the real environment information to obtain a logical scene that does not include the license plate information, the building information, and the road sign information. The construction module is used to construct a scene simulation map based on the scene information of the logical scene to obtain a second simulation map. The second adding module is used to add obstacle information of the logical scene to the second simulation map to obtain the virtual scene.
[0079] Compared with the previous embodiment, this embodiment does not require pre-constructing a scene simulation map. Instead, it directly constructs a scene simulation map that matches the scene information of the logical scene to obtain a second simulation map. Then, it adds corresponding obstacle information to the second simulation map to obtain the virtual scene.
[0080] It should be noted that the scene simulation map constructed based on the scene information of the above logical scenario does not reflect the real geographical information of buildings and roads. The construction of the scene simulation map in this embodiment is the same as that in the above embodiment, and will not be repeated here.
[0081] The aforementioned obstacle information includes object information and location information of pedestrians, vehicles, and roadblocks on the road.
[0082] The acquisition unit 40 is used to acquire environmental information of the virtual scene and / or vehicle operation information of the corresponding autonomous vehicle to obtain processed autonomous driving data.
[0083] Specifically, the aforementioned vehicle operation information may include the vehicle's throttle status, brake status, steering wheel position, vehicle location, vehicle orientation, vehicle speed, vehicle acceleration, and wheel speed. Of course, the aforementioned vehicle operation information is not limited to the above information; it may also include other operation information of the vehicle in this scenario.
[0084] In one specific embodiment, the processed autonomous driving data consists of the environmental information of the virtual scene and the vehicle operation information.
[0085] To further ensure the high authenticity of the processed autonomous driving data, according to another specific embodiment of this application, the acquisition unit specifically includes a simulation module. The simulation module is used to simulate the image acquisition equipment and radar equipment of the autonomous vehicle to acquire environmental information of the virtual scene and obtain the environmental information of the virtual scene.
[0086] In the autonomous driving data processing apparatus of this application, the raw data collected by the autonomous driving vehicle is acquired by the acquisition unit; the raw data is identified by the identification unit to obtain the real environment information of the autonomous driving vehicle; a virtual scene is constructed by the construction unit based on the obtained real environment information, excluding sensitive information such as facial information, license plate information, building information, and road sign information, and the virtual scene matches the real environment information; the environmental information of the virtual scene is collected by the acquisition unit, and / or the operation information of the autonomous driving vehicle in the virtual scene is collected to obtain the processed autonomous driving data. This application achieves the desensitization processing of personal privacy data and mapping data in the autonomous driving data, ensuring that the processed autonomous driving data does not contain personal privacy data or mapping data, and solves the problem of the lack of desensitization processing for sensitive data such as mapping data in the prior art. Furthermore, the virtual scene is constructed based on real environment information and has a high degree of realism, ensuring that the final processed autonomous driving data matches the actual environment well.
[0087] The aforementioned autonomous driving data processing device includes a processor and a memory. The aforementioned acquisition unit, recognition unit, construction unit, and collection unit are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.
[0088] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the lack of anonymization processing for sensitive data such as mapping data in autonomous driving data, a problem present in current technologies.
[0089] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0090] This invention provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements the above-described method for processing autonomous driving data.
[0091] This invention provides a processor for running a program, wherein the program executes the method for processing autonomous driving data.
[0092] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:
[0093] Step S101: Obtain the raw data collected by the autonomous vehicle;
[0094] Step S102: Identify the above-mentioned raw data to obtain real environment information, which is the environment information of the autonomous vehicle.
[0095] Step S103: Based on the above real environment information, construct a virtual scene that matches the above real environment information. The virtual scene shall not include facial information, license plate information, building information, or road sign information.
[0096] Step S104: Collect the environmental information of the virtual scene and / or the vehicle operation information of the corresponding autonomous vehicle to obtain the processed autonomous driving data.
[0097] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.
[0098] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:
[0099] Step S101: Obtain the raw data collected by the autonomous vehicle;
[0100] Step S102: Identify the above-mentioned raw data to obtain real environment information, which is the environment information of the autonomous vehicle.
[0101] Step S103: Based on the above real environment information, construct a virtual scene that matches the above real environment information. The virtual scene shall not include facial information, license plate information, building information, or road sign information.
[0102] Step S104: Collect the environmental information of the virtual scene and / or the vehicle operation information of the corresponding autonomous vehicle to obtain the processed autonomous driving data.
[0103] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0104] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.
[0105] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0106] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0107] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0108] As can be seen from the above description, the embodiments of this application achieve the following technical effects:
[0109] 1) In the above-mentioned method for processing autonomous driving data, the raw data collected by the autonomous vehicle is first acquired; then, the raw data is identified to obtain the real environment information of the autonomous vehicle; then, based on the obtained real environment information, a virtual scene is constructed that does not include sensitive information such as facial information, license plate information, building information, and road sign information, and this virtual scene matches the real environment information; finally, environmental information is collected from the virtual scene, and / or the operating information of the autonomous vehicle in the virtual scene is collected to obtain the processed autonomous driving data. This application achieves the desensitization processing of personal privacy data and mapping data in the autonomous driving data, ensuring that the processed autonomous driving data does not contain personal privacy data or mapping data, solving the problem in the prior art of lacking desensitization processing for sensitive data such as mapping data in autonomous driving data. Furthermore, the virtual scene is constructed based on real environment information and has a high degree of realism, ensuring that the final processed autonomous driving data is relatively well matched with the actual environment.
[0110] 2) In the aforementioned autonomous driving data processing device, the acquisition unit acquires the raw data collected by the autonomous vehicle; the recognition unit identifies the raw data to obtain the real environment information of the autonomous vehicle; the construction unit constructs a virtual scene based on the obtained real environment information, excluding sensitive information such as facial information, license plate information, building information, and road sign information, and the virtual scene matches the real environment information; the acquisition unit collects environmental information from the virtual scene and / or collects the operating information of the autonomous vehicle in the virtual scene to obtain processed autonomous driving data. This application achieves desensitization processing of personal privacy data and mapping data in the autonomous driving data, ensuring that the processed autonomous driving data does not contain personal privacy data or mapping data, solving the problem in the prior art of lacking desensitization processing of sensitive data such as mapping data in autonomous driving data. Furthermore, the virtual scene is constructed based on real environment information and has a high degree of realism, ensuring that the final processed autonomous driving data is well matched with the actual environment.
[0111] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A method for processing autonomous driving data, characterized in that, include: Obtain raw data collected by autonomous vehicles; The raw data is identified to obtain real environmental information, which is the environmental information of the autonomous vehicle. Based on the real environment information, a virtual scene matching the real environment information is constructed, wherein the virtual scene does not include at least facial information, license plate information, building information, and road sign information; Collect environmental information of the virtual scene and / or vehicle operation information of the corresponding autonomous driving vehicle to obtain processed autonomous driving data; Based on the real environment information, constructing a virtual scene that matches the real environment information includes: describing the real environment information using a scene description language to obtain a logical scene that does not include the license plate information, the building information, and the road sign information, wherein the logical scene includes road condition information and obstacle information; acquiring multiple pre-constructed scene simulation maps; determining a first simulation map based on the logical scene and the multiple scene simulation maps, wherein the first simulation map is the scene simulation map that matches the scene information of the logical scene; adding the obstacle information of the logical scene to the first simulation map to obtain the virtual scene.
2. The method according to claim 1, characterized in that, The raw data includes image data and radar data. Identifying the raw data yields real-world environmental information, including: The image data and radar data are processed using environmental recognition technology to obtain the real environmental information.
3. The method according to claim 1, characterized in that, Collect environmental information of the virtual scene, including: The image acquisition equipment and radar equipment of the simulated autonomous vehicle are used to collect environmental information of the virtual scene to obtain the environmental information of the virtual scene.
4. The method according to claim 1, characterized in that, The real-world environment information includes static object information and dynamic object information. The static object information includes road surface information, building information, road sign information, and traffic sign and marking information. The dynamic object information includes vehicle information, pedestrian information, vehicle and pedestrian movement trajectory information, and traffic light information.
5. A device for processing autonomous driving data, characterized in that, include: The acquisition unit is used to acquire raw data collected by autonomous vehicles. The identification unit is used to identify the raw data to obtain the real environment information of the autonomous vehicle. The construction unit is used to construct a virtual scene that matches the real environment information based on the real environment information, wherein the virtual scene does not include facial information, license plate information, building information, or road sign information. The acquisition unit is used to acquire environmental information of the virtual scene and / or vehicle operation information of the corresponding autonomous driving vehicle to obtain processed autonomous driving data. The construction unit specifically includes a first description module, an acquisition module, a determination module, and a first addition module. The first description module describes the real environment information using a scene description language to obtain a logical scene excluding license plate information, building information, and road sign information. The logical scene includes road condition information and obstacle information. The acquisition module acquires multiple pre-built scene simulation maps. The determination module determines a first simulation map based on the logical scene and the multiple scene simulation maps. The first simulation map is the scene simulation map that matches the scene information of the logical scene. The first addition module adds obstacle information of the logical scene to the first simulation map to obtain the virtual scene.
6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program performs the method according to any one of claims 1 to 4.
7. A processor, characterized in that, The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 4 when it runs.
8. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 4.
Citation Information
Patent Citations
Simulation method and system of a vehicle road virtual scene
CN109657355A
