Vehicle terrain mode switching method and apparatus, and device and medium

Abstract

A vehicle terrain mode switching method, comprising: when a driver has not selected a physical knob for switching, turning on a vehicle-mounted camera of a vehicle, and collecting a terrain image of the current traveling environment of the vehicle (S101); inputting the terrain image into a pre-trained terrain recognition model, and outputting the terrain type of the current traveling environment of the vehicle (S102); and on the basis of the recognized terrain type, controlling the vehicle to be switched to a traveling mode corresponding to the recognized terrain type (S103). The method can enable a vehicle to autonomously perform switching or recommendation switching of driving modes, so that a user is not required to be familiar with terrain environment types, and also is not required to be familiar with switching modes, thereby greatly facilitating user operations, and thus improving the vehicle driving convenience. In addition, compared with a scheme in which parameters fed back by a vehicle body are used as a determination basis, terrain type recognition is more accurate, and mode switching is more accurate. Further provided are a vehicle terrain mode switching apparatus, a computer device and a computer-readable storage medium.

Description

Vehicle terrain mode switching method, device, equipment and medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on January 2, 2024, with application number 202410004388.6 and invention name “A vehicle terrain mode switching method, device, equipment and medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of artificial intelligence technology, and in particular to a vehicle terrain mode switching method, device, equipment and medium. Background Art

[0004] As a means of transportation, cars provide immense convenience for people. As the use cases diversify, so too do the environments in which cars are used. Cars no longer operate solely on paved roads, but now also in complex road conditions such as mud, sand, and snow. Different terrains place varying demands on car control systems. Improving car performance requires adaptability to diverse terrains, providing a superior driving experience in diverse road conditions, and extending the life of the car.

[0005] Currently, there are all-terrain vehicle control systems that can select a driving mode for different terrain environments. Each mode can be adjusted to the corresponding road conditions to improve the vehicle's driving, braking, body stability and passing performance on various road surfaces, thereby meeting users' expectations for safe and smooth driving in various complex road conditions.

[0006] Due to the different types of terrain environments, vehicles are usually equipped with multiple terrain modes. However, the inventors found that the existing car mode switching method can only be switched by the driver using a knob. This physical button control solution has high requirements for the driver and is relatively complicated to operate the vehicle. The driver needs to accurately judge the type of terrain environment in which they are currently driving and take appropriate actions. If the driver is not familiar with the switching method or terrain, it will be difficult to make the corresponding judgment and operation, which will affect the driving experience of the vehicle and even cause vehicle failure or shorten the service life. Summary of the Invention

[0007] One of the purposes of the present application is to provide a vehicle terrain mode switching method, device, equipment and medium to solve the problem in the prior art that the vehicle terrain mode switching method is complex and has high requirements for the driver.

[0008] In order to achieve the above objectives, the technical solutions adopted in this application are as follows:

[0009] In the first aspect, the present application provides a vehicle terrain mode switching method, which is applicable to a vehicle, and the method includes: when the driver does not select the physical knob switch, turning on the vehicle's on-board camera to collect a terrain image of the vehicle's current driving environment; inputting the terrain image into a pre-trained terrain recognition model, and outputting the terrain type of the vehicle's current driving environment; based on the identified terrain type, controlling the vehicle to switch to the driving mode corresponding to the identified terrain type.

[0010] In an optional embodiment, if the vehicle is currently in a fully automatic mode switch, the vehicle is controlled to switch to a driving mode corresponding to the identified terrain type based on the identified terrain type, including: automatically controlling the vehicle to switch to a driving mode corresponding to the identified terrain model.

[0011] In an optional embodiment, if the vehicle is currently in a state of actively recommended mode switching, the vehicle is controlled to switch to a driving mode corresponding to the identified terrain type based on the identified terrain type, including: sending a mode recommendation request to the central control screen of the vehicle, the mode recommendation request being used to request the driver to switch to a driving mode corresponding to the identified terrain type; and responding to the driver's operating instructions to determine whether to switch the vehicle to the driving mode corresponding to the identified terrain type.

[0012] In an optional embodiment, inputting the terrain image into a pre-trained terrain recognition model to output the terrain type of the vehicle's current driving environment includes: obtaining multiple continuous terrain images within a preset time period; inputting the multiple terrain images into the terrain recognition model in sequence to obtain the terrain type of each terrain image within the preset time period; if the terrain type in which the vehicle is located within the preset time period is the same type, determining that type as the terrain type of the vehicle's current driving environment.

[0013] In an optional embodiment, the terrain recognition model adopts a 34-layer residual network structure, wherein the terrain image is input into a pre-trained terrain recognition model to output the terrain type of the vehicle's current driving environment, including: extracting the features of the terrain image through a single convolution layer and a maximum pooling layer; after parsing the features using the residual network layer structure, the features are again subjected to maximum pooling to obtain the terrain type of the vehicle's current driving environment.

[0014] In an optional embodiment, the terrain recognition model is trained by the following steps: collecting terrain images corresponding to each terrain type and annotating them to obtain sample training sets corresponding to different terrain types; using the sample training sets to train the initial terrain recognition model to obtain the terrain recognition model.

[0015] In an optional embodiment, the collecting of terrain images corresponding to each terrain type and labeling thereof include: using an experimental vehicle equipped with a camera to drive in a terrain environment corresponding to each terrain type, and controlling the experimental vehicle to be in a form mode corresponding to the terrain type; controlling the camera of the experimental vehicle to collect a terrain image at a preset period, and marking the corresponding terrain type label on the terrain image.

[0016] In the second aspect, the present application provides a vehicle terrain mode switching method and a vehicle terrain mode switching device, the device comprising: an acquisition module, for turning on the vehicle's on-board camera to acquire a terrain image of the vehicle's current driving environment when the driver does not select the physical knob switch; an identification module, for inputting the terrain image into a pre-trained terrain recognition model and outputting the terrain type of the vehicle's current driving environment; and a switching module, for controlling the vehicle to switch to a driving mode corresponding to the identified terrain type based on the identified terrain type.

[0017] In a fourth aspect, the present application provides a computer device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the above-mentioned vehicle terrain mode switching method by executing the computer instructions.

[0018] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the above-mentioned vehicle terrain mode switching method.

[0019] Beneficial effects of this application:

[0020] By collecting the terrain image of the vehicle's current driving environment, and then using the pre-trained terrain recognition model to identify and process the terrain image, the terrain type of the current driving environment is determined, and then the corresponding terrain type is switched. Compared with the knob switching method used in the existing technology, this system allows the vehicle to autonomously switch driving modes or recommend switching. The user does not need to be familiar with the terrain environment type or the switching method, which greatly facilitates the user's operation and improves the convenience of vehicle driving. At the same time, since the terrain image of the current driving environment is directly collected and the terrain type of the vehicle is directly identified from the terrain image, compared with the solution that uses the parameters fed back by the vehicle body as the basis for judgment, the terrain type recognition is more accurate and the mode switching is more precise. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] FIG1 is a flow chart of a method for switching a vehicle terrain mode according to an embodiment of the present application;

[0023] FIG2 is an overall schematic diagram of a switching solution according to an embodiment of the present application;

[0024] FIG3 is a schematic diagram of a residual learning module according to an embodiment of the present application;

[0025] FIG4 is a schematic diagram of the network structure of a terrain recognition model according to an embodiment of the present application;

[0026] FIG5 is a schematic diagram of a vehicle terrain mode switching device according to an embodiment of the present application;

[0027] FIG6 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will describe the embodiments of the present application with reference to the accompanying drawings and optional embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the optional embodiments are only for the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0029] The embodiments of the present application provide a method, apparatus, device, and medium for switching vehicle terrain modes. The technical solutions provided in the embodiments of the present application are primarily applicable to automobiles (or vehicles), and are particularly applicable to vehicles equipped with cameras and multiple terrain modes. The configured camera can be used to capture images of the vehicle's front route, or it can be a device for capturing 360° images of the vehicle. It can be a built-in camera on the vehicle, or it can be a device configured elsewhere to capture images of the ground environment. There is no specific limit on the number of multiple terrain modes configured on the vehicle, and it can be three, four, or even six. In an optional embodiment, the vehicle's configured terrain modes may include six: standard mode, ice and snow mode, mud mode, pothole mode, sand mode, and wading mode. Optionally, terrain mode switching methods may include a knob switch method, a fully automatic mode switch method, and an active recommended mode switch method. When the driver selects the knob switch method, the vehicle switches modes based on the knob signal. When the driver selects the fully automatic mode switch method, the vehicle's onboard camera captures a terrain image, inputs the image into a terrain recognition model, and upon successful recognition, directly switches to the corresponding mode. When the driver chooses to actively recommend a mode switch, the vehicle's onboard camera captures a terrain image and inputs the image into a terrain recognition model. Upon successful recognition, a mode switch request is sent to the central control screen for driver confirmation. If the driver chooses to switch, the system switches to the corresponding mode. If the driver chooses not to switch, the system remains in its original state. The following describes the technical solution of the embodiment of this application in detail.

[0030] The present application provides a method for switching a vehicle terrain mode. The method is applicable to a vehicle and can be controlled by a controller on the vehicle. As shown in FIG1 , the method includes:

[0031] Step S101: If the driver does not select the physical knob switch, the vehicle's onboard camera is turned on to collect a terrain image of the vehicle's current driving environment;

[0032] As described above, the vehicle in the embodiment of the present application can support multiple terrain modes, and the terrain mode switching methods may include knob switching, fully automatic mode switching, and proactively recommended mode switching. Among them, the knob switching method has a higher priority than other modes. In other words, when the driver chooses to use the knob switching method, that is, physical knob switching, the vehicle cannot automatically switch modes. In this case, it is not within the scope of protection of this application.

[0033] The embodiment of the present application is applicable to the vehicle autonomously identifying or switching the corresponding terrain mode when the driver does not select the physical knob switch.

[0034] If the driver does not select the physical knob to switch, or the driver selects the fully automatic mode switch or the actively recommended mode switch, the vehicle is controlled to turn on the on-board camera to collect terrain images of the vehicle's current driving environment. The current driving environment is photographed so that the terrain environment currently located by the terrain image can be identified.

[0035] Step S102: input the terrain image into a pre-trained terrain recognition model, and output the terrain type of the vehicle's current driving environment.

[0036] In an embodiment of the present application, a corresponding terrain recognition model is pre-trained for terrain recognition. The terrain recognition model can adopt a neural network model. The terrain type of the current driving environment is identified by the pre-trained terrain recognition model to facilitate timely mode switching.

[0037] In the embodiment of the present application, the terrain recognition model can be deployed on the cloud. After uploading the collected terrain image to the cloud, the cloud will perform the terrain type identification. In this way, the vehicle only needs to have a camera to collect terrain images. There is no need to configure higher processing performance equipment on the vehicle, and there is even no need to change the original vehicle system. It only needs to upload the image, receive the judgment result on the cloud, and then switch or recommend switching in the vehicle system. On the other hand, in the embodiment of the present application, the terrain recognition model can also be deployed directly on the vehicle. After collecting the terrain image, the vehicle itself directly identifies the corresponding terrain type. In this way, when the vehicle is off the grid, it can autonomously identify the terrain type without being restricted by the network environment, while improving the response speed and efficiency.

[0038] Step S103 , based on the identified terrain type, controlling the vehicle to switch to a driving mode corresponding to the identified terrain type.

[0039] In the embodiment of the present application, after the terrain recognition model identifies the terrain type of the current driving environment, the driving mode can be switched based on the terrain type. In the embodiment of the present application, how to switch the driving mode can be determined based on the specific control scheme of the switching mode.

[0040] According to an embodiment of the present application, by collecting a terrain image of the vehicle's current driving environment, and then using a pre-trained terrain recognition model to identify and process the terrain image, the terrain type of the current driving environment is determined, and then the corresponding terrain type is switched. Compared with the knob switching method used in the prior art, the vehicle can autonomously switch driving modes or recommend switching. The user does not need to be familiar with the terrain environment type or the switching method, which greatly facilitates the user's operation and improves the convenience of vehicle driving. At the same time, since the terrain image of the current driving environment is directly collected and the terrain type of the vehicle is directly identified from the terrain image, compared with the solution that uses the parameters fed back by the vehicle body as the basis for judgment, the terrain type recognition is more accurate and the mode switching is more precise.

[0041] The switching scheme of the embodiment of the present application is shown in Figure 2. In the knob switching mode, no detailed introduction is given. If the vehicle is currently in full-automatic mode switching, based on the identified terrain type, the vehicle is controlled to switch to the driving mode corresponding to the identified terrain type, including: automatically controlling the vehicle to switch to the driving mode corresponding to the identified terrain model.

[0042] As mentioned above, when the driver selects fully automatic mode switching, the onboard camera captures a terrain image, feeds the image into the terrain recognition model, and upon successful recognition, directly switches to the corresponding mode. In other words, when in fully automatic mode switching, once the vehicle recognizes the terrain type of the current driving environment, it directly switches to the driving mode, achieving adaptive control switching and improving vehicle operation convenience.

[0043] On the other hand, if the vehicle is currently in an active recommended mode switch, based on the identified terrain type, the vehicle is controlled to switch to the driving mode corresponding to the identified terrain type, including: sending a mode recommendation request to the vehicle's central control screen, the mode recommendation request is used to request the driver to switch to the driving mode corresponding to the identified terrain type; responding to the driver's operating instructions to determine whether to switch the vehicle to the driving mode corresponding to the identified terrain type.

[0044] As mentioned above, when a mode switch is proactively recommended, after the terrain type is identified, the terrain type will be sent to the vehicle's central control screen via a request, prompting the user to switch to the corresponding driving mode. Typically, after receiving the reminder, the user can independently choose whether to switch, either by pressing a button on the vehicle or on the central control screen. If the user confirms the switch, the vehicle directly switches to the driving mode corresponding to the identified terrain type; otherwise, if the user decides not to switch, the current driving mode remains.

[0045] Of course, in the embodiment of the present application, if the identified terrain type is consistent with the current driving mode of the vehicle, no mode switching or mode switching reminder will be performed.

[0046] Optionally, in an embodiment of the present application, when the vehicle uses a fully automatic mode switching method or an active recommendation mode switching method, if the knob is turned to switch the state, the system will switch the state and make an active recommendation the next time a terrain change is detected.

[0047] As an optional implementation, in an embodiment of the present application, a terrain image is input into a pre-trained terrain recognition model to output the terrain type of the vehicle's current driving environment, including: obtaining multiple continuous terrain images within a preset time period; inputting the multiple terrain images into the terrain recognition model in sequence to obtain the terrain type of each terrain image within the preset time period; if the terrain type in which the vehicle is located within the preset time period is the same type, then determining that type as the terrain type of the vehicle's current driving environment.

[0048] The preset time period can be set as needed, for example, 10 seconds. In the embodiment of the present application, multiple identifications and identifications of multiple terrain images are used before determining the final terrain type. For example, when using the fully automatic switching mode and the active recommendation switching mode, the terrain recognition model detects the terrain once every 2 seconds. When the detection results are the same for 10 seconds, it indicates that the user has entered the terrain type rather than sending a switching signal due to misidentification. This improves the error tolerance rate of terrain type recognition.

[0049] As an optional implementation, the terrain recognition model of the embodiment of the present application can use a residual learning module to build a network with a higher number of layers to better learn the target features. The residual learning module is shown in Figure 3. The terrain recognition model can adopt a 34-layer residual network structure, as shown in Figure 3. Specifically, the terrain image is input into the pre-trained terrain recognition model, and the terrain type of the vehicle's current driving environment is output, including: extracting the features of the terrain image through a convolution layer and a maximum pooling layer; after parsing the features using the residual network layer structure, it is again subjected to maximum pooling to obtain the terrain type of the vehicle's current driving environment.

[0050] After the terrain image is input, features are extracted through a single convolution and maximum pooling. The number of channels in the residual module is 64, 128, 256, and 512, respectively. The convolution stride of the three-layer network is 2, doubling the number of channels to 512. Maximum pooling is performed again before output, and the image is classified into six categories based on the terrain type.

[0051] In the embodiment of the present application, a pre-built initial model is used, as shown in Figure 4, and then a training set is constructed for model training. The terrain recognition model is trained by the following steps: terrain images corresponding to each terrain type are collected and annotated to obtain sample training sets corresponding to different terrain types; the sample training sets are used to train the initial terrain recognition model to obtain a terrain recognition model. The neural network used in the terrain recognition model of the embodiment of the present application is essentially a neural network classifier. The network is trained using a large amount of terrain data samples, enabling the network to accurately classify the input terrain images.

[0052] Among them, the collection of training samples can be carried out by collecting and annotating images while the vehicle is driving. Specifically, terrain images corresponding to each terrain type are collected and annotated, including: using an experimental vehicle equipped with a camera to drive in a terrain environment corresponding to each terrain type, and controlling the experimental vehicle to be in a form mode corresponding to the terrain type; controlling the camera of the experimental vehicle to collect a terrain image every preset period, and marking the corresponding terrain type label on the terrain image.

[0053] In this example, a test vehicle drives across the terrain to collect image data. The experimenter uses a knob to select the corresponding terrain type. Each captured image is automatically labeled. After a certain number of images of each terrain type are collected, they serve as training samples for model training.

[0054] The present application also provides a vehicle terrain mode switching device, applicable to a vehicle. The device corresponds to the method shown in FIG1 , and as shown in FIG5 , the device includes:

[0055] The acquisition module 501 is configured to activate the vehicle's onboard camera to acquire a terrain image of the vehicle's current driving environment when the driver does not select the physical knob switch;

[0056] The recognition module 502 is configured to input the terrain image into a pre-trained terrain recognition model and output the terrain type of the vehicle's current driving environment;

[0057] The switching module 503 is configured to control the vehicle to switch to a driving mode corresponding to the identified terrain type based on the identified terrain type.

[0058] According to an embodiment of the present application, by collecting a terrain image of the vehicle's current driving environment, and then using a pre-trained terrain recognition model to identify and process the terrain image, the terrain type of the current driving environment is determined, and then the corresponding terrain type is switched. Compared with the knob switching method used in the prior art, the vehicle can autonomously switch driving modes or recommend switching. The user does not need to be familiar with the terrain environment type or the switching method, which greatly facilitates the user's operation and improves the convenience of vehicle driving. At the same time, since the terrain image of the current driving environment is directly collected and the terrain type of the vehicle is directly identified from the terrain image, compared with the solution that uses the parameters fed back by the vehicle body as the basis for judgment, the terrain type recognition is more accurate and the mode switching is more precise.

[0059] For detailed description, please refer to the above method embodiment, which will not be repeated here.

[0060] The vehicle terrain mode switching device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0061] An embodiment of the present application also provides a computer device having the vehicle terrain mode switching device shown in FIG. 6 above.

[0062] Please refer to Figure 6, which is a structural diagram of a computer device provided by an optional embodiment of the present application. As shown in Figure 6, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 takes a processor 10 as an example.

[0063] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0064] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0065] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0066] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0067] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0068] The embodiments of the present application also provide a computer-readable storage medium. The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; optionally, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0069] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

Claims

1. A method for switching vehicle terrain modes, characterized in that, Applicable to a vehicle, the method includes: When the driver does not select physical knob switching, turn on the in-vehicle camera of the vehicle to collect a topographic image of the current driving environment of the vehicle; Input the topographic image into a pre-trained topographic recognition model, and output the topographic type of the current driving environment of the vehicle; Based on the recognized topographic type, control the vehicle to switch to the driving mode corresponding to the recognized topographic type.

2. The vehicle terrain mode switching method according to claim 1, wherein If the vehicle is currently in the case of fully automatic mode switching, the controlling the vehicle to switch to the driving mode corresponding to the recognized topographic type based on the recognized topographic type includes: Automatically control the vehicle to switch to the driving mode corresponding to the recognized topographic model.

3. The vehicle terrain mode switching method according to claim 1, characterized in that If the vehicle is currently in the case of active recommendation mode switching, the controlling the vehicle to switch to the driving mode corresponding to the recognized topographic type based on the recognized topographic type includes: Send a mode recommendation request to the central control screen of the vehicle, where the mode recommendation request is used to request the driver to switch to the driving mode corresponding to the recognized topographic type; Respond to the driver's operation instruction to determine whether to switch the vehicle to the driving mode corresponding to the recognized topographic type.

4. The vehicle terrain mode switching method according to claim 1, wherein The inputting the topographic image into a pre-trained topographic recognition model and outputting the topographic type of the current driving environment of the vehicle includes: Obtain multiple consecutive topographic images within a preset time period; Input the multiple topographic images into the topographic recognition model in sequence to obtain the topographic type of each topographic image within the preset time period; If the topographic types of the vehicle within the preset time period are all of the same type, determine this type as the topographic type of the current driving environment of the vehicle.

5. The vehicle terrain mode switching method according to claim 1, wherein The topographic recognition model adopts a 34-layer residual network structure. Among them, the inputting the topographic image into a pre-trained topographic recognition model and outputting the topographic type of the current driving environment of the vehicle includes: Extract the features of the topographic image through a convolutional layer and a max pooling layer; After parsing the features using the residual network layer structure and then passing through max pooling again, obtain the topographic type of the current driving environment of the vehicle.

6. The vehicle terrain mode switching method according to claim 1, characterized in that, The topographic recognition model is trained through the following steps: Collect topographic images corresponding to each topographic type and label them to obtain a sample training set corresponding to different topographic types; Use the sample training set to train an initial topographic recognition model to obtain the topographic recognition model.

7. The vehicle terrain mode switching method according to claim 1, characterized in that, The collecting topographic images corresponding to each topographic type and labeling them includes: Drive an experimental vehicle equipped with a camera in the topographic environment corresponding to each topographic type, and control the experimental vehicle to be in the driving mode corresponding to the topographic type; Control the camera of the experimental vehicle to collect a topographic image every preset period, and mark the corresponding topographic type label on the topographic image.

8. A vehicle terrain mode switching device, characterized in that, The device includes: The acquisition module is used to turn on the vehicle-mounted camera of the vehicle and acquire the topographic image of the current driving environment of the vehicle when the driver does not select physical knob switching; The recognition module is used to input the topographic image into a pre-trained topographic recognition model and output the topographic type of the current driving environment of the vehicle; The switching module is used to control the vehicle to switch to the driving mode corresponding to the recognized topographic type based on the recognized topographic type.

9. A computer device, characterized in that, It includes: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the vehicle topographic mode switching method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the vehicle topographic mode switching method according to any one of claims 1-7.

Images