A vehicle-based semantic mapping method and related devices

Abstract

The application provides a vehicle-based semantic mapping method and related equipment, and the method comprises the following steps: acquiring current image information of a position currently occupied by a target vehicle; acquiring current road surface information based on the current image information; acquiring pitch angle posture information of the target vehicle; determining first target image information of the position currently occupied by the target vehicle according to the pitch angle posture information and the current road surface information; and acquiring first semantic mapping information based on the first target image information and the position currently occupied by the target vehicle. By collecting the pitch angle posture information of the vehicle, the image information is corrected based on the pitch angle posture information and the collected current road surface information, so as to eliminate the color difference between the current road surface information and the actual road surface caused by the different light environments of the image collection device due to the different vehicle pitch postures, and the accuracy and practicability of semantic mapping can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a semantic mapping method based on a vehicle and related equipment. BACKGROUND

[0002] In public places, for example, on the ground of a gas station or a highway, various pavement markings are drawn to indicate changes in road conditions, speed limit information and driving behavior restriction information, etc. With the development of science and technology and the progress of society, semantic mapping is performed through visual means, and semantic segmentation is performed on road images collected by a vehicle during driving, and combined with positioning information of the vehicle during driving, map information of pavement markings within the current driving range can be constructed.

[0003] However, due to the existence of a slope road section in the mapping range, when the vehicle drives to the slope, the light direction of the image acquisition device may cause a color difference between the collected image and the actual situation, which may further cause the result of semantic segmentation to be inaccurate. In addition, due to the different meanings of pavement markings of different colors, the color difference may also cause the user to misunderstand. The current semantic mapping method cannot solve the above problems, thereby reducing the accuracy and practicability of semantic mapping and affecting the user's experience. SUMMARY

[0004] The present application provides a semantic mapping method based on a vehicle and related equipment to solve the problem that the current semantic mapping method cannot correct the image, the collected image and the actual road surface exist a color difference, which reduces the accuracy of semantic segmentation, affects the expression of pavement markings, reduces the accuracy and practicability of semantic mapping, and affects the user's experience.

[0005] In a first aspect, the present application provides a semantic mapping method based on a vehicle, comprising:

[0006] obtaining current image information of a position currently occupied by a target vehicle;

[0007] obtaining current road surface information based on the current image information;

[0008] obtaining pitch angle posture information of the target vehicle;

[0009] determining first target image information of the position currently occupied by the target vehicle according to the pitch angle posture information and the current road surface information;

[0010] obtaining first semantic mapping information based on the first target image information and the position currently occupied by the target vehicle.

[0011] Optionally, the semantic mapping method based on a vehicle further comprises:

[0012] obtain roll angle pose information of the target vehicle;

[0013] determine second target image information of a current position of the target vehicle based on the roll angle pose information and the first target image information;

[0014] obtain second semantic mapping information based on the second target image information and the current position of the target vehicle.

[0015] Optionally, the obtaining of the current road surface information based on the current image information comprises:

[0016] obtain target road surface feature information of the target vehicle;

[0017] obtain current road surface image information according to the target road surface feature information and the current image information.

[0018] Optionally, the obtaining of the current road surface information based on the current image information comprises:

[0019] obtain parameter information of an image acquisition device of the target vehicle, wherein the parameter information comprises at least one of intrinsic information, extrinsic information and distortion parameter information of the image acquisition device;

[0020] determine mapping information of pixel coordinates and three-dimensional coordinates of the image acquisition device according to the parameter information;

[0021] determine current road coordinate information based on the current road surface image information and the mapping relationship.

[0022] Optionally, the determining of the first target image information of the current position of the target vehicle based on the pitch angle pose information and the current road surface information comprises:

[0023] obtain illumination information of the position of the target vehicle, wherein the illumination information comprises illumination direction information and illumination intensity information of light relative to the target vehicle at the position of the target vehicle;

[0024] obtain relative position information of the image acquisition device relative to the target vehicle;

[0025] determine current illumination influence information of the image acquisition device based on the relative position information and the illumination intensity information;

[0026] determine first corrected road surface information according to the current illumination influence information and the current road surface image information;

[0027] determine the first target image information based on the first corrected road surface information.

[0028] Optionally, the vehicle-based semantic mapping method further comprises:

[0029] obtaining driving route information of the target vehicle;

[0030] obtaining a change type of the light source to which the illumination information belongs;

[0031] in a case where the light source is an invariable light source, determining illumination influence change information of the light source according to the driving route information;

[0032] obtaining second corrected road surface information based on the illumination influence change information.

[0033] Optionally, the vehicle-based semantic mapping method further comprises:

[0034] obtaining track road surface information according to the driving route information;

[0035] obtaining third semantic mapping information based on the track road surface information and the second corrected road surface information.

[0036] In a second aspect, the present application further provides a vehicle-based semantic mapping device, characterized in that comprising:

[0037] a first image acquisition module configured to acquire current image information of a position currently occupied by a target vehicle;

[0038] a second image acquisition module configured to acquire current road surface information based on the current image information;

[0039] a posture acquisition module configured to acquire a pitch angle posture information of the target vehicle;

[0040] a determination module configured to determine first target image information of the position currently occupied by the target vehicle according to the pitch angle posture information and the current road surface information;

[0041] a semantic mapping module configured to acquire first semantic mapping information based on the first target image information and the position currently occupied by the target vehicle.

[0042] In a third aspect, the present application further provides an electronic device comprising a memory and a processor, wherein the processor is configured to execute a computer program stored in the memory to implement steps of the vehicle-based semantic mapping method according to any one of the first aspect.

[0043] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is configured to be executed by a processor to implement steps of the vehicle-based semantic mapping method according to any one of the first aspect.

[0044] According to the technical scheme, the application provides a semantic mapping method based on a vehicle and a related device, the method comprising: acquiring current image information of a position currently occupied by a target vehicle; acquiring current road surface information based on the current image information; acquiring pitch angle posture information of the target vehicle; determining first target image information of the position currently occupied by the target vehicle according to the pitch angle posture information and the current road surface information; and acquiring first semantic mapping information based on the first target image information and the position currently occupied by the target vehicle. Since the current semantic mapping method cannot correct the image, there is a color difference between the collected image and the actual road surface, which reduces the accuracy of semantic segmentation, affects the expression of road marking, reduces the accuracy and practicability of semantic mapping, and affects the user experience. The embodiment of the application corrects the image information based on the pitch angle posture information and the collected current road surface information to eliminate the color difference between the current road surface information and the actual road surface caused by the different light environments of the image collection device caused by the different pitch angles of the vehicle, thereby improving the accuracy and practicability of semantic mapping. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical scheme of the application, the drawings required in the embodiments will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0046] Figure 1 A schematic flow chart of a semantic mapping method based on a vehicle provided by the embodiment of the application is shown in the figure.

[0047] Figure 2 A schematic structural diagram of a semantic mapping device based on a vehicle provided by the embodiment of the application is shown in the figure.

[0048] Figure 3 A schematic structural diagram of an electronic device provided by the embodiment of the application is shown in the figure.

[0049] Figure 4 A schematic structural diagram of a computer readable storage medium provided by the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0050] The embodiments will be described in detail below with reference to examples thereof as illustrated in the accompanying drawings. When the description below refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following embodiments are not meant to represent all implementations consistent with the present disclosure. Rather, they are merely examples of systems and methods consistent with some aspects of the present disclosure as detailed in the claims. In several embodiments provided by the present disclosure, it should be understood that the disclosed apparatus and methods can also be implemented in other manners. The embodiments described below are merely exemplary.

[0051] As shown in Figure 1 The present embodiments provide a vehicle-based semantic mapping method. The execution subject of the method can be a server and a controller, etc. The method comprises the following steps:

[0052] In step S110, current image information of a current position of a target vehicle is acquired.

[0053] In an example, the current image information of the current position of the target vehicle can be acquired by an image acquisition device.

[0054] In step S120, current road surface information is acquired based on the current image information.

[0055] In an example, the image processing algorithm can be used to remove the contours in the current image information that do not belong to the road surface information, such as the contours of grass, trees, pedestrians, and buildings on both sides of the road.

[0056] In step S130, pitch attitude information of the target vehicle is acquired.

[0057] In an example, the pitch attitude information of the target vehicle can be acquired by an inertial sensor of the target vehicle.

[0058] In step S140, first target image information of the current position of the target vehicle is determined according to the pitch attitude information and the current road surface information.

[0059] In an example, the position and the collection angle of an image sensor of the target vehicle relative to the target vehicle can be acquired. At least one of the brightness and the contrast information of the current image information can be acquired. The image correction information of the current image information can be determined based on the pitch attitude information. The current image information can be corrected according to the image correction information. The corrected current image information can be subjected to semantic segmentation to acquire the first target image information.

[0060] In step S150, first semantic mapping information is acquired based on the first target image information and the current position of the target vehicle.

[0061] The pitch attitude of the vehicle and the position of the image acquisition device relative to the vehicle both have an impact on the current image information. For example, when the vehicle is on an uphill slope and the image acquisition device is located at the rear of the vehicle, the light environment at the position of the image acquisition device is different from that without vehicle obstruction, which results in poor brightness and contrast of the current image information, difficulty in semantic segmentation, low accuracy, and obvious color difference. By collecting the pitch attitude information of the vehicle, the image information is corrected based on the pitch attitude information and the collected current road surface information, so as to eliminate the color difference between the current road surface information and the actual road surface caused by the different light environments of the image acquisition device due to different vehicle pitch attitudes, thereby improving the accuracy and practicality of semantic mapping.

[0062] According to some embodiments, the above-mentioned semantic mapping method based on a vehicle further comprises:

[0063] Obtaining the roll attitude information of the target vehicle;

[0064] Based on the roll attitude information and the first target image information, determining the second target image information of the position currently occupied by the target vehicle;

[0065] Based on the second target image information and the current position of the target vehicle, obtaining the second semantic mapping information.

[0066] For example, the roll attitude information can be obtained by the inertial sensor of the target vehicle. The correction information of the first target image information can be obtained according to the roll direction of the target vehicle and the position of the image acquisition device relative to the target vehicle, and the second target image information can be determined according to the correction information. For example, the line connecting the midpoint of the front of the target vehicle and the midpoint of the tail can be determined, when the image acquisition device is not on the line, the correction information of the first target image information can be determined according to the direction of the image acquisition device and the roll attitude relative to the line, and when the image acquisition device is on the line, the correction information of the first target image information can be determined according to at least one of the brightness distribution and the contrast distribution in the current position image.

[0067] By collecting the roll attitude information of the vehicle, the image information is corrected based on the roll attitude information and the collected current road surface information, so as to eliminate the color difference between the current road surface information and the actual road surface caused by the different light environments of the image acquisition device due to different roll attitudes caused by the vehicle being at a turning point, thereby improving the accuracy and practicality of semantic mapping.

[0068] According to some embodiments, the above-mentioned obtaining of the current road surface information based on the current image information comprises:

[0069] Obtaining target road surface feature information of the target vehicle;

[0070] According to the target road surface feature information and the current image information, current road surface image information is obtained.

[0071] According to the target road surface feature, semantic segmentation can be performed in the collected image, and road surface feature information without recognition features or actual use is removed, thereby improving the quality and practicality of semantic mapping.

[0072] According to some embodiments, the current road surface information is obtained based on the current image information, including:

[0073] Obtaining parameter information of the image acquisition device of the target vehicle, wherein the parameter information includes at least one of intrinsic information, extrinsic information, and distortion parameter information of the image acquisition device;

[0074] Determining mapping information of the pixel coordinates and the three-dimensional coordinates of the image acquisition device according to the parameter information;

[0075] Determining current road coordinate information based on the current road surface image information and the mapping relationship.

[0076] For example, the current image processing region can be determined according to the processing region of the historical collected image information, and the current image to be processed can be obtained based on the current image processing region and the current image information. The target pixel coordinates of the current image can be determined according to the current image to be processed and the current image processing region. The physical size represented by each pixel can be determined through the intrinsic information, so as to realize the conversion between the image physical coordinate system and the pixel coordinate system. The extrinsic information can be used to realize the conversion between the world coordinate system and the camera coordinate system. The distortion parameter information can be used to correct the distorted image information. The mapping model of the pixel coordinates and the three-dimensional coordinates of the image acquisition device can be established through at least one of the intrinsic information, the extrinsic information, and the distortion parameter information of the image acquisition device. The current road surface image information collected can be input into the mapping model to determine the current road coordinate information.

[0077] Based on the intrinsic, extrinsic, and distortion parameters of the image acquisition device, any point in the image can be restored in the three-dimensional space, so as to determine the coordinates of any pixel point in the image in the real world, and then the road coordinate information can be restored in the road position, thereby improving the accuracy and practicality of semantic mapping.

[0078] According to some embodiments, the first target image information of the position currently occupied by the target vehicle is determined according to the pitch angle posture information and the current road surface information, including:

[0079] obtain illumination information of a position where the target vehicle is located, wherein the illumination information comprises illumination direction information and illumination intensity information of light at the position where the target vehicle is located relative to the target vehicle;

[0080] obtain relative position information of the image acquisition device relative to the target vehicle;

[0081] determine current illumination influence information of the image acquisition device based on the relative position information and the illumination intensity information;

[0082] determine first corrected road surface information according to the current illumination influence information and the current road surface image information;

[0083] determine the first target image information based on the first corrected road surface information.

[0084] For example, the illumination information of the position where the target vehicle is located can be obtained by a light sensor, and the relative position information of the light sensor and the image acquisition device can be obtained. The light sensor and the image acquisition device can be arranged at the same position. The illumination shielding condition at the image acquisition device can be determined based on the relative position information, and the current illumination influence information of the image acquisition device can be determined according to the illumination shielding condition and the illumination information obtained by the light sensor. The influence of illumination on the color of the image can be determined based on the current illumination influence information and the current road surface image information, and the first corrected road surface information can be determined according to the color influence condition by correcting the current road surface image information. The first corrected road surface information can be subjected to semantic segmentation to determine the first target image information.

[0085] By combining the direction and intensity of illumination, the color difference of the image can be determined, so that the color of the current road surface image information can be corrected, the image quality can be improved, and the accuracy of semantic segmentation can be improved. In addition, in the case where the color of the road surface has an indication function, reducing the color difference can assist the user in driving judgment and improve the practicability of semantic mapping.

[0086] According to some embodiments, the semantic mapping method based on a vehicle further comprises:

[0087] obtain driving route information of the target vehicle;

[0088] obtain a change type of a light source to which the illumination information belongs;

[0089] in the case where the light source is an invariable light source, determine illumination influence change information of the light source according to the driving route information;

[0090] obtain second corrected road surface information based on the illumination influence change information.

[0091] Exemplarily, the image information of the light source can be acquired according to the light direction by other image acquisition devices of the vehicle, the change type of the light source is determined, and the light source can be divided into an invariable light source and a variable light source according to the light intensity change information and the light source position change information of the light source. In the case of the invariable light source, the position of the light source relative to the target vehicle during the driving of the target vehicle according to the driving route can be determined according to the driving route information and the light source position, and the light influence change information can be determined, wherein the light influence change information includes the light direction change information and the light intensity change information.

[0092] In the case of the invariable light source, such as a street lamp, the influence of the light source on the image acquisition device can be determined according to the driving route of the vehicle, and the image can be corrected, thereby avoiding repeated measurement of the light information, simplifying the processing steps, improving the processing speed, and further improving the practicability and convenience of semantic mapping.

[0093] According to some embodiments, the above-mentioned vehicle-based semantic mapping method further comprises:

[0094] According to the driving route information, the track road surface information is acquired.

[0095] Based on the track road surface information and the second corrected road surface information, the third semantic mapping information is acquired.

[0096] Exemplarily, the track road surface information is the road surface information collected by the target vehicle when driving along the driving route.

[0097] In the case of the invariable light source, the track road surface information of the vehicle on the driving route is acquired, and the second corrected road surface information is combined to directly acquire the semantic mapping information, thereby simplifying the mapping steps.

[0098] As shown in Figure 2 , a schematic structural diagram of a vehicle-based semantic mapping device provided by an embodiment of the present application. Figure 2 A schematic structural diagram of a vehicle-based semantic mapping device provided by an embodiment of the present application.

[0099] An embodiment of the present application provides a vehicle-based semantic mapping device 200, which comprises:

[0100] The first image acquisition module 201 is configured to acquire current image information of a position currently occupied by the target vehicle.

[0101] The second image acquisition module 202 is configured to acquire current road surface information based on the current image information.

[0102] The attitude acquisition module 203 is configured to acquire the pitch angle attitude information of the target vehicle.

[0103] The determining module 204 is configured to determine first target image information of a current position of the target vehicle according to the pitch angle posture information and the current road surface information.

[0104] The semantic mapping module 205 is configured to obtain first semantic mapping information based on the first target image information and the current position of the target vehicle.

[0105] The semantic mapping device 200 based on the vehicle can implement Figure 1 The processes implemented in the method embodiments are not repeated here to avoid repetition.

[0106] Please refer to Figure 3 , Figure 3 for the schematic structural diagram of the electronic device provided in the embodiments of the present application.

[0107] The embodiments of the present application provide an electronic device 300, which comprises a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and capable of running on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0108] Obtain current image information of a current position of a target vehicle;

[0109] Obtain current road surface information based on the current image information;

[0110] Obtain pitch angle posture information of the target vehicle;

[0111] Determine first target image information of the current position of the target vehicle according to the pitch angle posture information and the current road surface information;

[0112] Obtain first semantic mapping information based on the first target image information and the current position of the target vehicle.

[0113] In the specific implementation process, when the processor 320 executes the computer program 311, any embodiment in the corresponding embodiments can be implemented. Figure 1

[0114] Since the electronic device introduced in the embodiments is the device used to implement the device in the embodiments of the present application, the specific implementation of the electronic device in the embodiments and its various forms can be understood by those skilled in the art based on the method introduced in the embodiments of the present application. Therefore, how the electronic device implements the method in the embodiments of the present application is not described in detail here. As long as the device used by those skilled in the art to implement the method in the embodiments of the present application belongs to the scope of protection of the present application.

[0115] As Figure 4 ​As shown, Figure 4 An illustrative structural diagram of a computer readable storage medium provided by an embodiment of the present application.

[0116] The embodiment provides a computer readable storage medium 400, and the computer readable storage medium 400 stores a computer program 411. The computer program 411 is executed by a processor to implement the following steps.

[0117] Obtain current image information of a current position of a target vehicle;

[0118] Obtain current road surface information based on the current image information;

[0119] Obtain a pitch angle posture information of the target vehicle;

[0120] Determine first target image information of the current position of the target vehicle according to the pitch angle posture information and the current road surface information;

[0121] Obtain first semantic mapping information based on the first target image information and the current position of the target vehicle.

[0122] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product in the form of being implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0123] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The function of one flow or multiple flows and / or blocks Figure 1 The function of one flow or multiple flows and / or blocks

[0124] These computer program instructions can also be stored in a computer readable storage medium capable of guiding a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1one or more processes and / or blocks Figure 1 the function specified in the one or more blocks.

[0125] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operational steps are performed on the computer or other programmable data processing device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide a process for implementing the flow Figure 1 one or more processes and / or blocks Figure 1 the function specified in the one or more blocks.

[0126] The embodiments of the present application also provide a computer program product, which includes computer software instructions, when the computer software instructions are run on a processing device, so that the processing device executes the flow or function as described above. ​ the flow in the vehicle-based semantic mapping method in the corresponding embodiments.

[0127] The computer program product described above includes one or more computer instructions. When the computer program instructions described above are loaded and executed on a computer, the flow or function as described above according to the embodiments of the present application is generated in whole or in part. The computer described above can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions described above can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions described above can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer-readable storage medium described above can be any available medium that can be stored by a computer or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available medium described above can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)) and the like.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only 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 an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0130] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0131] Furthermore, the functional units in the various embodiments of this application 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.

[0132] 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 this application, 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 this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0133] In summary, the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A vehicle-based semantic mapping method, characterized in that, include: Obtain current image information of the target vehicle's current location; Obtain current road surface information based on the current image information; Obtain the pitch angle attitude information of the target vehicle; Based on the pitch angle attitude information and the current road surface information, the first target image information of the current position of the target vehicle is determined; Based on the first target image information and the current location of the target vehicle, first semantic mapping information is obtained; The step of determining the first target image information of the current position of the target vehicle based on the pitch angle attitude information and the current road surface information includes: Based on the pitch angle attitude information, the illumination information of the target vehicle's location is obtained, wherein the illumination information includes the illumination direction information and illumination intensity information of the light source at the target vehicle's location relative to the target vehicle. Acquire the relative position information of the image acquisition device on the target vehicle relative to the target vehicle; Based on the relative position information and the light intensity information, the current light impact information of the image acquisition device is determined; Based on the current illumination impact information and the current road surface information, determine the first corrected road surface information; Based on the first corrected road surface information, the first target image information is determined.

2. The vehicle-based semantic mapping method as described in claim 1, characterized in that, Also includes: Obtain the roll angle attitude information of the target vehicle; Based on the flip angle attitude information and the first target image information, the second target image information is used to determine the current position of the target vehicle. Based on the second target image information and the current location of the target vehicle, second semantic mapping information is obtained.

3. The vehicle-based semantic mapping method as described in claim 1, characterized in that, The step of obtaining current road surface information based on the current image information includes: Obtain the target road surface feature information of the target vehicle; Based on the target road surface feature information and the current image information, obtain the current road surface image information.

4. The vehicle-based semantic mapping method as described in claim 3, characterized in that, The step of obtaining current road surface information based on the current image information includes: Obtain parameter information of the image acquisition device of the target vehicle, wherein the parameter information includes at least one of the intrinsic parameter information, extrinsic parameter information and distortion parameter information of the image acquisition device; The mapping relationship between pixel coordinates and three-dimensional coordinates of the image acquisition device is determined based on the parameter information; Based on the current road surface image information and the mapping relationship, the current road coordinate information is determined.

5. The vehicle-based semantic mapping method as described in claim 3, characterized in that, Also includes: Obtain the driving route information of the target vehicle; Obtain the change type of the light source to which the illumination information belongs; When the light source is a constant light source, the illumination effect change information of the light source is determined based on the driving route information; Based on the information on changes in illumination, second corrected road surface information is obtained.

6. The vehicle-based semantic mapping method as described in claim 5, characterized in that, Also includes: Based on the driving route information, obtain the track surface information; Based on the track road surface information and the second corrected road surface information, third semantic mapping information is obtained.

7. A vehicle-based semantic mapping device, characterized in that, include: The first image acquisition module is used to acquire current image information of the target vehicle's current location; The second image acquisition module is used to acquire current road surface information based on the current image information; The attitude acquisition module is used to acquire the pitch angle attitude information of the target vehicle; The determination module is used to determine the first target image information of the current position of the target vehicle based on the pitch angle attitude information and the current road surface information; A semantic mapping module is used to obtain first semantic mapping information based on the first target image information and the current location of the target vehicle; The step of determining the first target image information of the current position of the target vehicle based on the pitch angle attitude information and the current road surface information includes: Based on the pitch angle attitude information, the illumination information of the target vehicle's location is obtained, wherein the illumination information includes the illumination direction information and illumination intensity information of the light source at the target vehicle's location relative to the target vehicle. Acquire the relative position information of the image acquisition device on the target vehicle relative to the target vehicle; Based on the relative position information and the light intensity information, the current light impact information of the image acquisition device is determined; Based on the current illumination impact information and the current road surface information, determine the first corrected road surface information; Based on the first corrected road surface information, the first target image information is determined.

8. An electronic device, comprising a memory and a processor, characterized in that, When the processor executes a computer program stored in the memory, it implements the steps of the vehicle-based semantic mapping method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the vehicle-based semantic mapping method as described in any one of claims 1 to 6.

Images