High-precision Map Generation Method, Apparatus and Equipment

Abstract

This application relates to a high-precision map generation method, apparatus and device. The method includes: obtaining at least two pieces of image data collected by at least two camera devices for the same area during the driving of a vehicle; wherein, the orientations of the respective camera devices are different; obtaining positioning data collected by the positioning device of the vehicle during the image data collection; generating at least two pieces of initial high-precision map data corresponding to each piece of the image data according to the positioning data and the at least two pieces of image data; and generating a high-precision map according to the average result of the at least two pieces of initial high-precision map data. The solution provided by this application can improve the generation stability of the high-precision map.

Description

Technical Field

[0001] This application relates to the field of navigation technology, and in particular, to a high-precision map generation method, apparatus, and device. Background Art

[0002] High-precision maps have been widely used in the field of navigation technology, providing support for the realization of autonomous driving functions of vehicles. The generation of high-precision maps usually requires the use of environmental data and vehicle positioning data collected by vehicles. The acquisition schemes for environmental data include: fusion acquisition using multiple types of sensors, and acquisition using a single type of sensor (such as lidar, monocular camera). Currently, for the acquisition scheme of environmental data using a single type of sensor, a monocular camera is usually used to collect environmental data. Monocular cameras are inexpensive and easy to configure, and have been widely adopted.

[0003] In related technologies, vehicle-mounted monocular cameras are usually used to collect out-of-vehicle image data, and vehicle-mounted RTK (Real-time kinematic) positioning devices are used to obtain vehicle positioning data, and then high-precision maps are generated based on the image data and the positioning data.

[0004] However, in related technologies, a single monocular camera is used for high-precision map generation operations. Since the orientation of the camera is fixed, while the direction of sunlight irradiation changes, the amount of light entering the camera may be different under different lighting directions, which will in turn change the exposure time of the camera, resulting in differences in the high-precision maps generated under different lighting directions, affecting the stability of high-precision map generation. In addition, at the same moment, since the direction of sunlight irradiation is constant, the amount of light entering the cameras of vehicles traveling in two opposite directions on the road will be different, and ultimately, the high-precision maps generated by the cameras of vehicles in different directions in the same area will be different, affecting the stability of high-precision map generation and making it difficult to guarantee the stability of high-precision map generation. Here, stability means that when a vehicle performs multiple acquisitions of environmental data in the same area, the high-precision maps generated each time using the collected environmental data should be relatively stable, that is, the relative error distance of the high-precision maps generated in different batches for the position of the same target location is within a preset value (such as 10 centimeters). Summary of the Invention

[0005] To solve or partially solve the problems existing in related technologies, this application provides a high-precision map generation method, apparatus, and device, which can improve the stability of high-precision map generation.

[0006] The first aspect of this application provides a high-precision map generation method, including:

[0007] Acquire at least two sets of image data collected by at least two camera devices respectively for the same area during the driving of the vehicle; wherein the directions of the camera devices are different;

[0008] Acquiring positioning data collected by the positioning device of the vehicle during the image data collection process;

[0009] Generate at least two initial high-precision map data corresponding to each of the image data according to the positioning data and the at least two image data;

[0010] A high-precision map is generated based on the average result of the at least two initial high-precision map data.

[0011] In one embodiment, before acquiring at least two sets of image data respectively collected by at least two camera devices of the same area during the driving of the vehicle, the method further includes:

[0012] The positioning device of the vehicle is started, and the acquisition frequencies of at least two camera devices on the vehicle are respectively aligned with the acquisition frequency of the positioning device.

[0013] In one implementation, the at least two camera devices include two camera devices.

[0014] In one embodiment, among the two camera devices, one camera device faces the front of the vehicle, and the other camera device faces the rear of the vehicle.

[0015] In one embodiment, generating a high-precision map according to an average result of the at least two initial high-precision map data includes:

[0016] After determining that the comparison results of any two initial high-precision map data are within preset conditions, a high-precision map is generated based on the average results of the at least two initial high-precision map data.

[0017] In one embodiment, the high-precision map generation method further includes:

[0018] After determining that the comparison results of any two copies of the initial high-precision map data exceed the preset conditions, the initial high-precision map data corresponding to the abnormal camera device is eliminated, and a high-precision map is generated based on the average results of the remaining copies of the initial high-precision map data; or,

[0019] After determining that the comparison result of any two initial high-precision map data exceeds the preset conditions, a high-precision map is generated based on the initial high-precision map data corresponding to a normally operating camera device.

[0020] A second aspect of the present application provides a high-precision map generation device, comprising:

[0021] A first acquisition module, configured to acquire at least two pieces of image data collected by at least two camera devices for the same area during the driving of the vehicle; wherein, the orientations of the respective camera devices are different;

[0022] A second acquisition module, configured to acquire positioning data collected by the positioning device of the vehicle during the acquisition of the image data;

[0023] A first generation module, configured to generate at least two pieces of initial high-precision map data corresponding to each piece of the image data according to the positioning data acquired by the second acquisition module and the at least two pieces of image data acquired by the first acquisition module;

[0024] A second generation module, configured to generate a high-precision map according to the average result of the at least two pieces of initial high-precision map data generated by the first generation module.

[0025] In an implementation manner, the high-precision map generation device further includes:

[0026] A setting module, configured to start the positioning device of the vehicle and align the acquisition frequencies of at least two camera devices on the vehicle with the acquisition frequency of the positioning device.

[0027] A third aspect of the present application provides an electronic device, including:

[0028] A processor; and

[0029] A memory, on which executable code is stored, and when the executable code is executed by the processor, the processor is caused to execute the method as described above.

[0030] A fourth aspect of the present application provides a computer-readable storage medium, on which executable code is stored, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0031] The technical solution provided by the present application may include the following beneficial effects:

[0032] The method provided by the present application uses at least two camera devices to collect image data, generates at least two pieces of initial high-precision map data corresponding to each piece of the image data according to the positioning data and the at least two pieces of image data collected by the at least two camera devices, and then generates a high-precision map according to the average result of the at least two pieces of initial high-precision map data. In this way, the influence of different sunlight irradiation directions on the generated high-precision map is avoided, random errors can be reduced, and the generation stability of the high-precision map can be improved.

[0033] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit the present application. Brief Description of the Drawings

[0034] The above and other objects, features, and advantages of the present application will become more apparent by describing the exemplary embodiments of the present application in more detail in conjunction with the accompanying drawings, wherein, in the exemplary embodiments of the present application, the same reference numerals generally represent the same components.

[0035] Figure 1 is a schematic flowchart of the high-precision map generation method shown in the embodiments of the present application;

[0036] Figure 2 is another schematic flowchart of the high-precision map generation method shown in the embodiments of the present application;

[0037] Figure 3 is a schematic structural diagram of the high-precision map generation device shown in the embodiments of the present application;

[0038] Figure 4 is another schematic structural diagram of the high-precision map generation device shown in the embodiments of the present application;

[0039] Figure 5 is a schematic structural diagram of the electronic device shown in the embodiments of the present application. Detailed Description of the Embodiments

[0040] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0041] The terms used in the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0042] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of this application, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0043] In the related art, a single monocular camera is used to perform high-precision map generation operations. Since the orientation of the camera is fixed while the direction of sunlight irradiation changes, the amount of light entering the camera may vary under different lighting directions, which will in turn change the exposure time of the camera, resulting in differences in the high-precision maps generated under different lighting directions and affecting the stability of high-precision map generation. Additionally, even at the same moment, since the direction of sunlight irradiation remains unchanged, the amount of light entering the cameras of vehicles traveling in two opposite directions on the road will be different, ultimately causing differences in the high-precision maps generated by the cameras of vehicles in different directions in the same area and affecting the stability of high-precision map generation, making it difficult to ensure the stability of high-precision map generation.

[0044] In view of the above problems, an embodiment of this application provides a high-precision map generation method, which can improve the stability of high-precision map generation.

[0045] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0046] Figure 1 is a schematic flowchart of the high-precision map generation method shown in the embodiments of this application.

[0047] See Figure 1 , the method includes:

[0048] Step S101, obtain at least two pieces of image data collected by at least two imaging devices for the same area during the driving process of the vehicle; wherein, the orientations of the respective imaging devices are different.

[0049] Among them, the imaging device may be a monocular camera. The imaging device is installed on the vehicle. The imaging device may be installed on the top of the vehicle, or on the front or rear of the vehicle. This application does not make any limitations in this regard.

[0050] Among them, different imaging devices may collect image data for the same area at different time periods during the driving process of the vehicle.

[0051] Among them, the image data can be multiple images continuously captured by a camera device. That is to say, the image data can be video data composed of frames of images.

[0052] In this step, at least two camera devices are used to collect image data of the same area. Each camera device collects a portion of image data, and multiple camera devices correspond to multiple portions of image data one by one. It can be understood that during driving, after the vehicle travels a certain section of the road, even if the orientations of the camera devices are different, each camera device can still collect image data of the same area. For example, two cameras on the vehicle are respectively oriented towards the front and the rear of the vehicle. When the vehicle is driving towards the target area, the camera oriented towards the front of the vehicle can collect image data. When the vehicle leaves the target area, the camera oriented towards the rear of the vehicle can collect image data, so that both cameras can collect image data of the target area.

[0053] Step S102: Obtain the positioning data collected by the vehicle's positioning device during the image data collection process.

[0054] Among them, the positioning device can be an RTK (Real-time kinematic) positioning device. The positioning device can also be a GPS (Global Positioning System) positioning device.

[0055] In this step, the obtained positioning data is collected by the vehicle's positioning device during the image data collection process. That is to say, during the vehicle's driving, when the vehicle's camera device is collecting image data, the vehicle's positioning device is also collecting the vehicle's positioning data at the same time. The positioning data can include the vehicle's position information during the image data collection process.

[0056] Step S103: Generate at least two initial high-precision map data corresponding to each portion of image data based on the positioning data and at least two portions of image data.

[0057] In this step, one portion of initial high-precision map data is generated based on the positioning data and one portion of image data. That is to say, each portion of initial high-precision map data corresponds to the image data collected by a camera device, and each portion of initial high-precision map data can be used to generate a high-precision map.

[0058] Using a deep learning perception algorithm and visual SLAM (simultaneous localization and mapping) technology, an initial high-precision map data can be generated based on the positioning data and a piece of image data, and then a high-precision map can be generated. For the specific implementation process and principle of generating the high-precision map based on the positioning data and the image data, reference can be made to the description in the related technology, which will not be elaborated here.

[0059] It should be noted that each piece of initial high-precision map data corresponds one-to-one with each piece of image data. Since multiple different pieces of image data are respectively collected by different camera devices, and the orientations of each camera device are different, resulting in different light intakes of each camera device, so that the exposure times and imaging times of each camera device are different, and the image data collected by different camera devices will be slightly different. It can be understood that due to the different imaging times of each camera device after exposure, the images collected by each camera device each time and the vehicle position information collected by each positioning device each time are not synchronized. In this way, for each piece of initial high-precision map data corresponding to each piece of image data respectively, the geographical location information of the same target in each piece of initial high-precision map data will be slightly different, and there will be errors in the high-precision maps generated by different initial high-precision map data.

[0060] Step S104: Generate a high-precision map according to the average result of at least two pieces of initial high-precision map data.

[0061] In this step, each piece of initial high-precision map data can be averaged to obtain the average result of each piece of initial high-precision map data, and then a high-precision map can be generated.

[0062] It can be understood that for a camera device, since the sunlight irradiation direction is determined, for the same moment, the image data collected by camera devices with different orientations for the same area will be different, thus making the high-precision maps generated using different image data different, which affects the generation stability of the high-precision map. In the embodiment of the present application, since multiple camera devices with different orientations are used to collect image data, and then a high-precision map is generated according to the average result of each piece of initial high-precision map data corresponding one-to-one with each piece of image data. In this way, even if the sunlight irradiation direction changes, there will not be a large change in the average result. Through the averaging process, random errors can be effectively reduced, and the difference in the generated high-precision map caused by different light directions can be avoided, and the generation stability of the high-precision map can be improved.

[0063] As can be seen from this embodiment, the method provided by the embodiments of the present application uses at least two imaging devices to collect image data, generates at least two initial high-precision map data corresponding to each piece of image data according to the positioning data and at least two pieces of image data collected by the at least two imaging devices, and then generates a high-precision map according to the average result of the at least two pieces of initial high-precision map data. In this way, the influence of different sunlight irradiation directions on the generated high-precision map is avoided, random errors can be reduced, and the generation stability of the high-precision map can be improved.

[0064] Figure 2 It is another flowchart of the high-precision map generation method according to the embodiments of the present application. Figure 2 Relatively Figure 1 Describes the solution of the present application in more detail.

[0065] See Figure 2 , the method includes:

[0066] Step S201, start the positioning device of the vehicle, and align the acquisition frequencies of at least two imaging devices on the vehicle with the acquisition frequency of the positioning device respectively.

[0067] Among them, the positioning device may be an RTK (Real-time kinematic) positioning device, and the imaging device may be a monocular camera. The imaging device collects image data, and the image data may be multiple images continuously captured by the imaging device. That is to say, the image data may be video data composed of frames of images. The positioning device may collect the positioning data of the vehicle, and the positioning data may include the position information of the vehicle during the process of collecting image data.

[0068] It should be noted that the positioning device generally collects positioning data according to a preset positioning frequency. For example, if the preset positioning frequency of the positioning device is 100HZ, the positioning device collects the position information of the vehicle 100 times per second. The imaging device generally collects image data according to a preset frame rate. For example, if the preset frame rate is 30fps, the imaging device captures 30 images per second.

[0069] In this step, align the acquisition frequency of the imaging device with that of the positioning device. That is to say, after the positioning device of the vehicle is started, when the vehicle's position information is collected for the first time, the cameras of each imaging device are triggered to expose simultaneously. In this way, the image imaging moment of the imaging device is synchronized with the moment when the positioning device collects the position information, so as to ensure the hard synchronization between the imaging device and the positioning device. In one implementation, according to the synchronization time difference between the imaging device and the positioning device, the imaging device and the positioning device can be synchronously triggered at intervals of a set time period. For example, if the positioning frequency of the positioning device is 90HZ and the frame rate of the imaging device is 30fps, the imaging device and the positioning device can be synchronously triggered every 0.033 seconds. In this way, it can be ensured that each time the imaging device collects an image and each time the positioning device collects the vehicle's position information are carried out simultaneously, thereby reducing random errors and improving the accuracy and stability of the high-precision map.

[0070] It can be understood that if the vehicle speed is 60km / h (i.e., 16.7m / s), the positioning frequency of the positioning device is 100HZ, and the frame rate of the imaging device is 30fps. Then, for each frame of image generated, the vehicle will move 50cm, and for each generation of vehicle position information (i.e., a vehicle positioning point), the vehicle will move 16.7cm. It can be seen that the generation of the image and the vehicle position information is discrete. However, the vehicle movement is continuous, so that within the 30-millisecond interval of generating the image, there is a random time difference between the currently obtained vehicle position information and the generated image, which will cause a deviation between the actual position of the vehicle when the image is generated and the vehicle position obtained by the positioning device, thus affecting the accuracy of the subsequent generated high-precision map and making the accuracy of the high-precision map unable to be guaranteed.

[0071] It should be noted that in the technical field of high-precision map production, for the position of the same target location, the relative error between the position information marked in the high-precision map and the position information measured by the professional surveying and mapping equipment needs to be less than the preset distance (for example, 10 centimeters) to meet the current requirements for the accuracy of the high-precision map in this field.

[0072] In order to meet the accuracy requirements of the high-precision map, in the embodiments of the present application, by aligning the acquisition frequency of each imaging device with the acquisition frequency of the positioning device respectively, it can be ensured that each time the imaging device collects an image and each time the positioning device collects the vehicle's position information are carried out simultaneously, so as to ensure that the actual position of the vehicle when the image is generated is consistent with the vehicle position obtained by the positioning device to the greatest extent, and further improve the accuracy of the subsequent generated high-precision map and ensure the generation accuracy of the high-precision map.

[0073] Further, before the camera device is started, the internal and external parameters of the camera device can be calibrated, including calibrating the internal parameters of the camera device and performing external parameter calibration of the target on the road, so as to eliminate distortion.

[0074] Step S202: Obtain at least two pieces of image data collected by at least two camera devices for the same area during the driving process of the vehicle; wherein, the orientations of the respective camera devices are different.

[0075] Among them, different camera devices can collect image data for the same area at different time periods during the driving process of the vehicle.

[0076] Among them, at least two camera devices can include two camera devices. The performance and model specifications of the two camera devices can be the same, and the two camera devices are fixedly installed on the top of the vehicle. Among the two camera devices, one camera device faces the front of the vehicle, and the other camera device faces the rear of the vehicle. For example, the two camera devices can be installed back-to-back on the top of the vehicle.

[0077] In this step, at least two camera devices are used to collect image data for the same area. Each camera device collects one piece of image data, and multiple camera devices correspond to multiple pieces of image data one by one. It can be understood that during the driving process, after the vehicle has traveled a section of the road, even if the orientations of the respective camera devices are different, each camera device can still collect image data for the same area. For example, the two cameras on the vehicle face the front and rear of the vehicle respectively. When the vehicle is driving towards the target area, the camera facing the front of the vehicle can collect image data. When the vehicle leaves the target area, the camera facing the rear of the vehicle can collect image data, so that both cameras can collect image data for the target area.

[0078] Step S203: Obtain the positioning data collected by the positioning device of the vehicle during the image data collection process.

[0079] In this step, the obtained positioning data is collected by the positioning device of the vehicle during the image data collection process. That is to say, during the driving process of the vehicle, when the camera device of the vehicle is collecting image data, the positioning device of the vehicle is also collecting the positioning data of the vehicle at the same time.

[0080] Step S204: Generate at least two pieces of initial high-precision map data corresponding to each piece of image data according to the positioning data and at least two pieces of image data.

[0081] In this step, an initial high-precision map data is generated based on the positioning data and an image data. That is to say, each initial high-precision map data corresponds to the image data collected by a camera device, and each initial high-precision map data can be used to generate a high-precision map.

[0082] Using the deep learning perception algorithm and the visual SLAM (simultaneous localization and mapping) technology, an initial high-precision map data can be generated based on the positioning data and an image data, and then a high-precision map can be generated. For the specific implementation process and principle of generating the high-precision map based on the positioning data and the image data, reference can be made to the descriptions in the related technologies, and details will not be elaborated here.

[0083] It should be noted that each initial high-precision map data corresponds one by one to each image data. Since multiple different image data are respectively collected by different camera devices, and the orientations of the camera devices are different, the light incident amounts of the camera devices are different, resulting in different exposure times and imaging times of the camera devices, and the image data collected by different camera devices will be slightly different. It can be understood that due to the different imaging times of the camera devices after exposure, the images collected by the camera devices each time and the vehicle position information collected by the positioning device each time are not synchronized. In this way, for each initial high-precision map data corresponding to each image data generated, the geographical location information of the same target in each initial high-precision map data will be slightly different, and there will be errors in the high-precision maps generated from different initial high-precision map data.

[0084] Step S205: After determining that the comparison results of any two initial high-precision map data are within the preset conditions, generate a high-precision map according to the average result of at least two initial high-precision map data.

[0085] In one implementation, that the comparison results of any two initial high-precision map data are within the preset conditions includes: the deviation of the geographical positions marked for the same target (such as a building) in any two initial high-precision map data is within a set value (such as 10 cm, 15 cm, etc.). That is to say, if the deviation of the geographical positions marked for the same target in any two initial high-precision map data is within the set value, it can be determined that the comparison results of any two initial high-precision map data are within the preset conditions.

[0086] In this step, after determining that the comparison results of any two initial high-precision map data are within the preset conditions, the average processing can be performed on each initial high-precision map data to obtain the average result of each initial high-precision map data, and then a high-precision map can be generated.

[0087] For example, at least two camera devices include two camera devices, one camera device facing the front of the vehicle and the other camera device facing the rear of the vehicle. The camera device facing the front of the vehicle corresponds to the initial high-precision map data of A, and the camera device facing the rear of the vehicle corresponds to the initial high-precision map data of B. Then, if the deviation between the geographical location (latitude and longitude) of the target X marked by the initial high-precision map data of A and the geographical location of the target X marked by the initial high-precision map data of B is within the set value, it can be determined that the comparison result of the two initial high-precision map data is within the preset conditions.

[0088] If the geographical location of the target X marked in the initial high-precision map data of A is (x 1 , y 1 ), and the geographical location of the target X marked in the initial high-precision map data of B is (x 2 , y 2 ),

[0089] Then the average result of the geographical location of the target X is:

[0090] In the technical field of high-precision map production, stability means that the vehicle conducts multiple collections of environmental data (such as image data) for the same area, and the high-precision map generated each time using the collected environmental data should be relatively stable, that is, the relative error distance of the same target location in the high-precision maps generated in different batches is within the preset value (such as 10 centimeters).

[0091] It can be understood that for a camera device, since the direction of sunlight irradiation is determined, at the same moment, the image data collected by camera devices with different orientations for the same area will be different, resulting in differences in the high-precision maps generated using different image data and affecting the generation stability of the high-precision map. In the embodiments of the present application, since multiple camera devices with different orientations are used to collect image data, and then the high-precision map is generated according to the average result of each initial high-precision map data corresponding to each piece of image data one by one. In this way, even if the direction of sunlight irradiation changes, there will not be a large change in the average result. Through the averaging process, random errors can be effectively reduced, and differences in the generated high-precision map caused by different light directions can be avoided, improving the generation stability of the high-precision map.

[0092] For the sake of easy understanding, for example, at least two camera devices include two camera devices, one camera device facing the front of the vehicle and the other camera device facing the rear of the vehicle. Whether the vehicle is driving towards the direction of sunlight irradiation or away from the direction of sunlight irradiation, for the average result of the two initial high-precision map data, the differences in the finally generated high-precision maps should be extremely subtle or even the same. In this way, the generation stability of the high-precision map is effectively guaranteed.

[0093] On the contrary, in the related art, a vehicle has only one camera and generates a high-precision map based on the image data collected by one camera. Then, the image data collected when the vehicle travels in the direction of sunlight irradiation is different from the image data collected when the vehicle travels in the direction away from sunlight irradiation. Two different pieces of image data will generate two different high-precision maps, and the stability of generating the high-precision map cannot be guaranteed.

[0094] Step S206: After determining that the comparison result of any two pieces of initial high-precision map data exceeds the preset condition, eliminate the initial high-precision map data corresponding to the abnormal camera device, and generate a high-precision map according to the average result of the remaining pieces of initial high-precision map data.

[0095] Among them, the comparison result of any two pieces of initial high-precision map data exceeding the preset condition may include that the deviation of the geographical positions marked by any two pieces of initial high-precision map data for the same target (such as a building) is outside the set value (such as 10 cm, 15 cm, etc.).

[0096] It can be understood that the difference in the exposure time of the camera device has an extremely subtle impact on the subsequent generated initial high-precision map data. If the comparison result of any two pieces of initial high-precision map data exceeds the preset condition, it can be considered that one of the camera devices is abnormal. It can be seen that at least two camera devices provided in the embodiment of the present application also play a quality inspection role and can ensure the correctness of the finally generated high-precision map.

[0097] In this step, after determining that the comparison result of any two pieces of initial high-precision map data exceeds the preset condition, each camera device can be inspected, and then the initial high-precision map data corresponding to the abnormal camera device can be eliminated, and a high-precision map can be generated according to the average result of the remaining pieces of initial high-precision map data to ensure the stability and accuracy of generating the high-precision map.

[0098] Step S207: After determining that the comparison result of any two pieces of initial high-precision map data exceeds the preset condition, generate a high-precision map according to the initial high-precision map data corresponding to one camera device that operates normally.

[0099] In this step, after determining that the comparison result of any two pieces of initial high-precision map data exceeds the preset condition, each camera device can be inspected, and a high-precision map can be generated according to the initial high-precision map data corresponding to one camera device that operates normally to ensure the correctness and accuracy of the high-precision map.

[0100] It can be seen from this embodiment that the method provided in the embodiments of the present application can ensure that each time the image is collected by the camera device and each time the vehicle position information is collected by the positioning device are carried out simultaneously by aligning the collection frequencies of the respective camera devices with the collection frequency of the positioning device, so as to ensure that the actual position of the vehicle when the image is generated is consistent with the vehicle position obtained by the positioning device to the greatest extent, thereby improving the accuracy of the subsequent generated high-precision map and ensuring the generation accuracy of the high-precision map. According to the average result of at least two initial high-precision map data, a high-precision map is generated to avoid differences in the generated high-precision map due to different light directions, which can improve the generation stability of the high-precision map.

[0101] Corresponding to the foregoing method embodiments for implementing application functions, the present application also provides a high-precision map generation device, an electronic device, and corresponding embodiments.

[0102] Figure 3 It is a schematic structural diagram of a high-precision map generation device shown in the embodiments of the present application.

[0103] See Figure 3 , a high-precision map generation device 30 includes: a first acquisition module 310, a second acquisition module 320, a first generation module 330, and a second generation module 340.

[0104] The first acquisition module 310 is configured to acquire at least two pieces of image data respectively acquired by at least two camera devices for the same area during the driving of the vehicle; wherein, the orientations of the respective camera devices are different.

[0105] The second acquisition module 320 is configured to acquire positioning data collected by the positioning device of the vehicle during the image data acquisition process.

[0106] The first generation module 330 is configured to generate at least two pieces of initial high-precision map data corresponding to each piece of image data according to the positioning data acquired by the second acquisition module 320 and the at least two pieces of image data acquired by the first acquisition module 310.

[0107] The second generation module 340 is configured to generate a high-precision map according to the average result of at least two pieces of initial high-precision map data generated by the first generation module 330.

[0108] It can be seen from this embodiment that the high-precision map generation device provided by the present application can avoid the influence of different sunlight irradiation directions on the generated high-precision map, can reduce random errors, and can improve the generation stability of the high-precision map.

[0109] Figure 4 It is another schematic structural diagram of a high-precision map generation device shown in the embodiments of the present application.

[0110] SeeFigure 4 , a high-precision map generation device 30, comprising: a first acquisition module 310, a second acquisition module 320, a first generation module 330, a second generation module 340, and a setting module 350.

[0111] Among them, the functions of the first acquisition module 310, the second acquisition module 320, the first generation module 330, the first generation module 330, and the second generation module 340 can be referred to Figure 4 the description in, which will not be elaborated here.

[0112] The setting module 350 is used to start the positioning device of the vehicle and align the acquisition frequencies of at least two camera devices on the vehicle with the acquisition frequency of the positioning device respectively.

[0113] Furthermore, the second generation module 340 is further used to generate a high-precision map according to the average result of at least two pieces of initial high-precision map data after determining that the comparison result of any two pieces of initial high-precision map data is within the preset conditions.

[0114] The second generation module 340 is further used to, after determining that the comparison result of any two pieces of initial high-precision map data exceeds the preset conditions, eliminate the initial high-precision map data corresponding to the abnormal camera device, and generate a high-precision map according to the average result of the remaining pieces of initial high-precision map data.

[0115] The second generation module 340 is further used to, after determining that the comparison result of any two pieces of initial high-precision map data exceeds the preset conditions, generate a high-precision map according to the initial high-precision map data corresponding to one normal operating camera device.

[0116] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0117] Figure 5 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.

[0118] See Figure 5 , the electronic device 500 includes a memory 510 and a processor 520.

[0119] The processor 520 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0120] The memory 510 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, the ROM may store static data or instructions required by the processor 520 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even when the computer is powered off. In some embodiments, the permanent storage device uses a mass storage device (such as a magnetic or optical disk, flash memory) as the permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as dynamic random access memory. The system memory may store some or all of the instructions and data required by the processor during operation. In addition, the memory 510 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and magnetic disks and / or optical disks may also be used. In some embodiments, the memory 510 may include a removable storage device that is readable and / or writable, such as a compact disc (CD), read-only digital versatile disc (such as DVD-ROM, dual-layer DVD-ROM), read-only Blu-ray disc, ultra density optical disc, flash memory card (such as SD card, min SD card, Micro-SD card, etc.), magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and instantaneous electronic signals transmitted wirelessly or by wire.

[0121] An executable code is stored on the memory 510, and when the executable code is processed by the processor 520, it may cause the processor 520 to execute some or all of the methods described above.

[0122] In addition, the method according to the present application can also be implemented as a computer program or a computer program product, which includes computer program code instructions for performing some or all of the steps in the above-mentioned method of the present application.

[0123] Alternatively, the present application can also be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium), on which executable code (or a computer program or computer instruction code) is stored. When the executable code (or the computer program or computer instruction code) is executed by a processor of an electronic device (or a server, etc.), the processor is caused to execute some or all of the steps of the above-mentioned method according to the present application.

[0124] The various embodiments of the present application have been described above. The above description is exemplary and not exhaustive, and is also not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, the practical application, or the improvement of the technology in the market, or to enable other ordinary skill in the art in the technical field to understand the disclosed embodiments.

Claims

1. A method for generating high-precision maps. It is characterized in that include: Acquire at least two sets of image data respectively collected by at least two camera devices of the same area during the driving process of the vehicle; wherein the directions of the camera devices are different; the at least two sets of image data are acquired by the at least two camera devices photographing the same area in a sequential order according to different directions and at different times; the at least two camera devices are installed on the vehicle; Acquiring positioning data collected by the positioning device of the vehicle during the image data collection process; Generate at least two initial high-precision map data corresponding to each of the image data according to the positioning data and the at least two image data; A high-precision map is generated based on the average result of the at least two initial high-precision map data.

2. The method according to claim 1, It is characterized in that Before acquiring at least two sets of image data respectively collected by at least two camera devices of the same area during the driving of the vehicle, the method further includes: The positioning device of the vehicle is started, and the acquisition frequencies of at least two camera devices on the vehicle are respectively aligned with the acquisition frequency of the positioning device.

3. The method according to claim 1, Features: The at least two camera devices include two camera devices.

4. The method according to claim 3, Features: Of the two camera devices, one camera device faces the front of the vehicle, and the other camera device faces the rear of the vehicle.

5. The method according to claim 1, It is characterized in that The step of generating a high-precision map according to an average result of the at least two initial high-precision map data comprises: After determining that the comparison results of any two initial high-precision map data are within preset conditions, a high-precision map is generated based on the average results of the at least two initial high-precision map data.

6. The method according to claim 5, It is characterized in that The method further comprises: After determining that the comparison results of any two copies of the initial high-precision map data exceed the preset conditions, the initial high-precision map data corresponding to the abnormal camera device is eliminated, and a high-precision map is generated based on the average results of the remaining copies of the initial high-precision map data; or, After determining that the comparison result of any two initial high-precision map data exceeds the preset conditions, a high-precision map is generated based on the initial high-precision map data corresponding to a normally operating camera device.

7. A high-precision map generation device, It is characterized in that include: A first acquisition module is used to acquire at least two sets of image data respectively collected by at least two camera devices of the same area during the driving process of the vehicle; wherein the directions of the camera devices are different; the at least two sets of image data are acquired by the at least two camera devices photographing the same area in a sequential order according to different directions and at different times; and the at least two camera devices are installed on the vehicle; A second acquisition module is used to acquire positioning data collected by the positioning device of the vehicle during the image data acquisition process; A first generation module, configured to generate at least two pieces of initial high-precision map data respectively corresponding to each piece of the image data according to the positioning data acquired by the second acquisition module and at least two pieces of image data acquired by the first acquisition module; A second generation module, configured to generate a high-precision map according to an average result of at least two pieces of initial high-precision map data generated by the first generation module.

8. The apparatus according to claim 7, wherein, the apparatus further comprises: a setting module, configured to activate a positioning device of the vehicle and align the acquisition frequencies of at least two camera devices on the vehicle with the acquisition frequency of the positioning device respectively.

9. An electronic device, wherein, it comprises: a processor; and a memory, storing executable code thereon, which when executed by the processor, causes the processor to execute the method according to any one of claims 1-6.

10. A computer-readable storage medium, storing executable code thereon, which when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1-6.

Images