Control method and device for vehicle cabin

Abstract

This application relates to a control method and device for a vehicle cockpit. The method includes: acquiring multiple skeletal points of a driver or passenger outside the vehicle; determining the actual posture of the driver or passenger based on the multiple skeletal points; determining whether the actual posture matches any of at least one pre-set trigger posture in the vehicle; if the actual posture matches any trigger posture, determining the target position and target parameters in the vehicle cockpit corresponding to the trigger posture; and adjusting the cockpit adjustment device corresponding to the target position according to the target parameters, so as to complete the cockpit adjustment corresponding to the target position before the driver or passenger gets into the vehicle. This solves the problems of requiring users to manually adjust seats upon entering the vehicle, resulting in time-consuming and laborious adjustments, reducing the user's driving experience, decreasing customer loyalty, and impacting user experience. It improves vehicle comfort and safety, making it more intelligent and practical.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more specifically, to a method and apparatus for controlling a vehicle cockpit within the field of vehicle technology. Background Technology

[0002] With the development of high technology, automobiles are paying more and more attention to the convenience of drivers, and more and more intelligent technologies are being installed in vehicles, making the car cabin more intelligent and convenient.

[0003] The relevant technology adopts the following methods: 1. After the user gets into the vehicle, retrieve the user's memory parameters based on the user's manual operation; 2. Obtain the historical usage status of the seat that matches the memory parameters, and adjust the current usage status of the seat to the historical usage status.

[0004] However, the above method requires users to spend some time adjusting the seat after getting into the vehicle, which reduces the user's comfort and safety during driving. It cannot efficiently and quickly achieve personalized seat adjustments for different users, affecting the user experience. It lacks intelligence and practicality and urgently needs to be addressed. Summary of the Invention

[0005] This application provides a vehicle cabin control method and device to solve the problems that users need to spend a certain amount of time adjusting their seats after getting into the vehicle, which reduces the comfort and safety of users during the driving process, makes it impossible to efficiently and quickly realize personalized seat adjustments for different users, affects the user experience, and has insufficient intelligence and practicality.

[0006] Firstly, a method for controlling a vehicle cockpit is provided, the method comprising:

[0007] Obtain multiple skeletal points of the driver and passengers outside the vehicle;

[0008] The actual posture of the driver and passenger is determined based on the multiple skeletal points, and it is determined whether the actual posture matches any of the trigger postures in at least one of the vehicle's pre-set trigger postures.

[0009] If the actual posture matches any of the triggered postures, then the target position and target parameters in the vehicle cabin corresponding to the trigger postures are determined, and the cabin adjustment device corresponding to the target position is adjusted according to the target parameters to complete the cabin adjustment corresponding to the target position before the driver and passengers get into the vehicle.

[0010] By using the above technical solution, multiple skeletal points of the driver and passengers outside the vehicle are obtained to determine their actual posture. If the actual posture matches the triggered posture, it indicates that the driver or passenger has a need for automatic seat adjustment. The intelligent adjustment of the cabin is completed before the user gets in the vehicle according to the corresponding target position and target parameters. This enables efficient and rapid personalized seat adjustment for different users. A series of actions of the equipment in the cabin can be completed before the user gets in the vehicle, improving the comfort and safety of the vehicle, effectively enhancing the user experience, improving the interactive experience, and making it more intelligent and practical.

[0011] In conjunction with the first aspect, in some possible implementations, acquiring multiple skeletal points of the driver and passengers outside the vehicle includes:

[0012] Acquire human images of the occupants outside the vehicle;

[0013] The human image is input into a pre-trained skeletal point extraction model to obtain multiple skeletal points of the driver and passenger.

[0014] The above technical solution can acquire human images of drivers and passengers outside the vehicle, input the human images into a pre-trained skeletal point extraction model, and obtain multiple skeletal points of the drivers and passengers. This makes the multiple skeletal points of the drivers and passengers obtained by the vehicle more accurate and more intelligent, and can effectively meet the user's needs.

[0015] In combination with the first aspect and the above-described implementation methods, in some possible implementation methods, acquiring the human body image of the driver and passengers outside the vehicle includes:

[0016] Find the actual location of the vehicle key;

[0017] Calculate the actual distance between the vehicle key and the vehicle based on the actual location of the vehicle key;

[0018] When the actual distance is less than or equal to the preset power-on distance, the vehicle is powered on to collect human images of the driver and passengers outside the vehicle.

[0019] The above technical solution can obtain the actual position of the vehicle key, calculate the actual distance between the vehicle key and the vehicle based on the actual position of the vehicle key, and control the vehicle to power on when the actual distance is less than or equal to the preset power-on distance, so as to collect the human body image of the driver and passengers outside the vehicle. This allows the vehicle to obtain the human body image of the driver and passengers, thereby further improving the automation level of the vehicle and making it more intelligent.

[0020] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the target parameters include the adjustment parameters of the cabin adjustment devices corresponding to the seats, air conditioning, lights, instrument panel, central control screen, vehicle network, voice recognition device and gesture recognition device in the vehicle cabin.

[0021] The above technical solutions enable the use of vehicle cabin seats, air conditioning, lighting, instrument panel, central control screen, vehicle networking, voice recognition device and gesture recognition device to form target parameter settings, realize personalized cabin adjustments before users get in the car, ensure the user's driving experience in multiple dimensions, and effectively meet the user's multi-faceted needs.

[0022] In combination with the first aspect and the above-described implementation methods, in some possible implementation methods, obtaining multiple skeleton points of the driver and passengers outside the vehicle includes:

[0023] Collect the identification of the drivers and passengers outside the vehicle;

[0024] Based on the identity identifier, determine whether the driver or passenger has cabin adjustment authority, so as to obtain multiple skeletal points of the driver or passenger outside the vehicle if the driver or passenger has cabin adjustment authority.

[0025] The above technical solution can collect the identity information of the driver and passengers outside the vehicle and determine whether the driver and passengers have the right to adjust the cabin based on the identity information. If they have the right to adjust the cabin, multiple skeletal points of the driver and passengers outside the vehicle can be obtained, thereby effectively preventing false triggering of cabin control and further enhancing the comprehensiveness of the cabin control process.

[0026] In combination with the first aspect and the above implementation methods, in some possible implementation methods, after determining the actual posture of the driver and passenger based on the plurality of skeletal points, the method further includes:

[0027] Obtain the duration of the actual posture;

[0028] If the duration is greater than or equal to the preset effective duration, the actual posture is determined to be valid.

[0029] The above technical solution can obtain the duration of the actual posture; if the duration is greater than or equal to the preset effective duration, the actual posture is determined to be valid, thereby enabling the vehicle to accurately capture the actual posture of the driver and passengers, preventing the cockpit control from failing to execute smoothly due to incorrect acquisition of the actual posture, and further improving the accuracy and reliability of the cockpit control.

[0030] In combination with the first aspect and the above implementation methods, in some possible implementation methods, before determining whether the actual posture matches any of the at least one trigger posture preset by the vehicle, the method further includes:

[0031] Receive the setting instructions from the driver and passengers;

[0032] The vehicle is controlled to enter the attitude setting mode, and at least one trigger attitude and corresponding target position and target parameters are generated according to the setting instructions of the driver and passengers.

[0033] Secondly, a control device for the vehicle cockpit is provided, the device comprising:

[0034] The acquisition module is used to acquire multiple skeletal points of the driver and passengers outside the vehicle;

[0035] The judgment module is used to determine the actual posture of the driver and passenger based on the multiple skeletal points, and to determine whether the actual posture matches any of the trigger postures in at least one of the pre-set trigger postures of the vehicle.

[0036] The control module is used to determine the target position and target parameters in the vehicle cabin corresponding to the triggering posture when the actual posture matches the triggering posture, and adjust the cabin adjustment device corresponding to the target position according to the target parameters, so as to complete the cabin adjustment corresponding to the target position before the driver and passengers get into the vehicle.

[0037] In conjunction with the second aspect, in some possible implementations, the acquisition module includes:

[0038] The first acquisition unit is used to acquire human images of the drivers and passengers outside the vehicle;

[0039] The recognition unit is used to input the human body image into a pre-trained skeletal point extraction model to obtain multiple skeletal points of the driver and passenger.

[0040] In conjunction with the second aspect and the above implementation methods, in some possible implementations, the acquisition module further includes:

[0041] The second acquisition unit is used to acquire the actual location of the vehicle key;

[0042] The calculation unit is used to calculate the actual distance between the vehicle key and the vehicle based on the actual position of the vehicle key;

[0043] The first acquisition unit is used to control the vehicle to power on when the actual distance is less than or equal to a preset power-on distance, so as to acquire human images of the driver and passengers outside the vehicle.

[0044] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the target parameters include the adjustment parameters of the cabin adjustment devices corresponding to the seats, air conditioning, lights, instrument panel, central control screen, vehicle networking, voice recognition device and gesture recognition device in the vehicle cabin.

[0045] In combination with the second aspect and the above implementation methods, in some possible implementations, the acquisition module includes:

[0046] The second data acquisition unit is used to collect the identification of the drivers and passengers outside the vehicle;

[0047] The first determination unit is used to determine whether the occupant has cockpit adjustment permissions based on the identity identifier, so as to obtain multiple skeleton points of the occupant outside the vehicle if the occupant has cockpit adjustment permissions. In combination with the second aspect and the above implementation, in some possible implementations, the determination module includes:

[0048] The third acquisition unit is used to acquire the duration of the actual posture after determining the actual posture of the driver and passenger based on the multiple skeletal points.

[0049] The second judgment unit is used to determine that the actual posture is valid when the duration is greater than or equal to the preset effective duration.

[0050] Combining the second aspect and the above implementation methods, in some possible implementations, the judgment module may also include:

[0051] The setting unit is used to receive the setting instruction from the driver or passenger before determining whether the actual posture matches any of the trigger postures in at least one of the pre-set trigger postures of the vehicle.

[0052] The generation unit is used to control the vehicle to enter the posture setting mode and generate at least one trigger posture and corresponding target position and target parameters according to the setting instructions of the driver and passengers.

[0053] Thirdly, a cockpit controller is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle cockpit control method as described in the above embodiments.

[0054] Fourthly, a vehicle is provided that includes the aforementioned cockpit controller. Attached Figure Description

[0055] Figure 1 This is a flowchart of the vehicle cockpit control method according to an embodiment of the present invention;

[0056] Figure 2 This is a schematic diagram illustrating the detection effect of the model described in an embodiment of the present invention;

[0057] Figure 3 This is a schematic diagram of the model structure described in an embodiment of the present invention;

[0058] Figure 4 This is a schematic diagram of the vehicle cabin control device according to an embodiment of the present invention;

[0059] Figure 5 This is a schematic diagram of the cockpit controller according to an embodiment of the present invention. Detailed Implementation

[0060] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0061] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0062] During vehicle operation, users often have personalized needs for the in-vehicle environment. The comfort of the vehicle cabin environment is an important factor in determining the driving experience of drivers and passengers. A cabin setting that meets the needs of passengers can better realize human-vehicle interaction.

[0063] Currently, once passengers board the vehicle, the system remembers the user's preferred cabin settings based on manual operation records and matches the most suitable cabin state for the user based on historical data.

[0064] However, this technology requires a certain amount of time to wait for the vehicle to automatically adjust the seat, which affects the driver's safety and comfort. Furthermore, it is inefficient at personalized seat adjustments for different users, significantly diminishing the passenger experience. Therefore, achieving fast and effective personalized seat adjustments to improve the riding experience and optimize intelligence and practicality are problems we urgently need to solve. Before explaining the vehicle cabin control method provided in the embodiments of this application, the structure of the vehicle cabin control involved in the embodiments of this application will be described first.

[0065] Figure 1 This is a schematic flowchart of a vehicle cockpit control method provided in an embodiment of this application.

[0066] like Figure 1 As shown, the vehicle cockpit control method according to an embodiment of the present invention includes the following steps:

[0067] In step S101, multiple skeletal points of the driver and passengers outside the vehicle are obtained.

[0068] It is understood that in the embodiments of this application, multiple skeletal points of the driver and passengers near the vehicle’s perimeter can be obtained. The vehicle’s perimeter can be a specified area or location, or it can be the area around the vehicle itself, and is not specifically limited here.

[0069] Optionally, in some embodiments, obtaining multiple skeletal points of the driver and passengers outside the vehicle includes: obtaining a human image of the driver and passengers outside the vehicle; inputting the human image into a pre-trained skeletal point extraction model to obtain multiple skeletal points of the driver and passengers.

[0070] It is understood that, in the embodiments of this application, the human body image of the driver and passengers outside the vehicle can be captured by an onboard camera to obtain a body image of the driver and passengers near the perimeter of the vehicle. This human body image is then input into a pre-trained skeletal point extraction model, which identifies the corresponding joints in the human body image and outputs the corresponding joints as skeletal points. The multiple skeletal points of the driver and passengers output by the model are as follows: Figure 2 As shown.

[0071] For example, as occupants approach the vehicle, external cameras can be used to capture their images. Front, rear, left, right, or all four sides of the vehicle can also be used for recording to avoid missed shots or incomplete images due to random movement of the occupants. The resulting human images are then input into a pre-built Openpose extraction model to obtain multiple skeletal points of the occupants. The Openpose model's structure is as follows: Figure 3 As shown, the ResNet architecture used in the original backbone of the Openpose model can be replaced with the Mobilenetv2 architecture to form a lightweight network, thereby reducing the computational load of the model. Furthermore, knowledge distillation can be performed using a model compression scheme. If the in-vehicle system allows, TensorRT can be deployed in the car for acceleration to meet the real-time requirements of the algorithm.

[0072] Based on the embodiments of this application, it is possible to acquire human images of drivers and passengers outside the vehicle, input the human images into a pre-trained skeletal point extraction model, and obtain multiple skeletal points of the drivers and passengers, thereby making the multiple skeletal points of the drivers and passengers obtained by the vehicle more accurate and more intelligent, which can effectively meet the user's needs.

[0073] Optionally, in some embodiments, acquiring human images of occupants outside the vehicle includes: acquiring the actual position of the vehicle key; calculating the actual distance between the vehicle key and the vehicle based on the actual position of the vehicle key; and controlling the vehicle to power on when the actual distance is less than or equal to a preset power-on distance, so as to acquire human images of occupants outside the vehicle.

[0074] Specifically, the location information of the vehicle key can be obtained by detecting its Bluetooth signal, thereby calculating the actual distance between the vehicle key and the vehicle, and powering on the vehicle when the actual distance is less than or equal to a preset power-on distance. For example, when the vehicle key's Bluetooth signal is detected to be within 15 meters of the vehicle, the vehicle is powered on to activate the vehicle's camera, allowing the vehicle to capture images of the occupants.

[0075] Alternatively, the key signal information can be transmitted to the vehicle via Bluetooth signal emitted by the vehicle key or network signal emitted by the driver's or passenger's mobile terminal, so as to obtain the power-on information emitted by the driver or passenger, power on the vehicle, and enable the vehicle camera to start normally to obtain human images of the driver or passenger.

[0076] Based on the embodiments of this application, it is possible to obtain the actual position of the vehicle key, calculate the actual distance between the vehicle key and the vehicle based on the actual position of the vehicle key, and control the vehicle to power on when the actual distance is less than or equal to a preset power-on distance, so as to collect human images of the driver and passengers outside the vehicle, thereby enabling the vehicle to obtain human images of the driver and passengers, so as to further improve the automation level of the vehicle and make it more intelligent.

[0077] Optionally, in some embodiments, acquiring multiple skeleton points of the driver and passengers outside the vehicle includes: collecting the identity identifier of the driver and passengers outside the vehicle; determining whether the driver and passengers have cockpit adjustment permissions based on the identity identifier, so as to acquire multiple skeleton points of the driver and passengers outside the vehicle if they have cockpit adjustment permissions.

[0078] It is understood that, in the embodiments of this application, the identity of the driver and passenger can be the driver and passenger's facial information. By collecting facial information, it can be determined that the detection target is the driver and passenger of the vehicle, so as to confirm that the detection target has the right to adjust the cabin, and then further obtain the information corresponding to multiple skeletal points of the detection target.

[0079] For example, after the vehicle is powered on, the external camera can be used to capture images of target A and target B around the vehicle. The facial features of target A and target B can be identified using the obtained human images to obtain corresponding facial information. Based on the obtained facial information, it can be determined whether target A and target B have cabin adjustment permissions. If the identity of target A corresponds to cabin adjustment permissions, while the identity of target B does not, then multiple skeletal points of target A can be further identified, while the identification of skeletal point information of target B can be stopped.

[0080] This application embodiment can collect the identity identifiers of drivers and passengers outside the vehicle, and determine whether the drivers and passengers have cockpit adjustment permissions based on the identity identifiers. If they have cockpit adjustment permissions, multiple skeletal points of the drivers and passengers outside the vehicle can be obtained, thereby effectively preventing false triggering of cockpit control and further enhancing the comprehensiveness of the cockpit control process.

[0081] In step S102, the actual posture of the driver and passengers is determined based on multiple skeletal points, and it is determined whether the actual posture matches any of the trigger postures in at least one of the vehicle's pre-set trigger postures.

[0082] It is understood that, in the embodiments of this application, the skeletal points can be the results of human image recognition of drivers and passengers by a pre-trained skeletal point extraction model. The model can determine the posture features of the driver's and passengers' body parts by judging multiple skeletal points, and analyze the extracted posture features to obtain the actual posture of the driver and passengers after combining the posture features. It can then determine whether the obtained actual posture matches the pre-set trigger posture.

[0083] For example, for a human image of a driver or passenger captured by an external camera, posture features ① and ② can be extracted based on multiple skeletal points, and the actual posture a of the driver or passenger can be generated based on the obtained posture features. It can then be determined whether any of the preset trigger postures A, B, and C match the actual human posture a.

[0084] Optionally, in some embodiments, after determining the actual posture of the driver or passenger based on multiple skeletal points, the method further includes: obtaining the duration of the actual posture; and determining that the actual posture is valid if the duration is greater than or equal to a preset effective duration.

[0085] Specifically, the system can capture images of the driver and passengers using external cameras. After identifying the actual posture of the driver and passengers, it can obtain the duration of the time the driver and passengers maintain the actual posture and determine whether the duration meets the condition of being greater than or equal to a preset effective duration. If the condition is met, the actual posture of the driver and passengers is determined to be a valid posture, and a matching process between the actual posture and the actual posture is performed. If the condition is not met, the posture is deemed invalid, and the matching process between the actual posture and the actual posture is stopped.

[0086] It should be noted that the preset effective duration can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0087] The embodiments of this application can obtain the duration of the actual posture; if the duration is greater than or equal to the preset effective duration, the actual posture is determined to be valid, thereby enabling the vehicle to accurately capture the actual posture of the driver and passengers, preventing the cockpit control from failing to execute smoothly due to incorrect acquisition of the actual posture, and further improving the accuracy and reliability of the cockpit control.

[0088] In step S103, if the actual posture matches any trigger posture, the target position and target parameters in the vehicle cabin corresponding to any trigger posture are determined, and the cabin adjustment device corresponding to the target position is adjusted according to the target parameters so as to complete the cabin adjustment corresponding to the target position before the driver and passengers get into the vehicle.

[0089] It is understood that, in the embodiments of this application, when the actual posture of the occupant C is identified as matching the trigger posture, the target position and target parameters corresponding to the trigger posture can be obtained, namely, the vehicle cabin preference settings of the occupant C and the vehicle position set by the preference settings. Based on the specific settings, the intelligent adjustment of the driver's cabin at the corresponding vehicle position is completed before the occupant C gets into the vehicle. Each trigger posture corresponds to a unique occupant and includes the target position and target parameters corresponding to that occupant. The trigger posture can be, for example, the left hand resting on the right shoulder or the left hand clenched into a fist and raised high.

[0090] For example, a human body image can be captured by a vehicle camera to obtain the actual posture of the driver / passenger, and it can be determined that the actual posture corresponds to trigger posture 1. Then, the vehicle target position of the driver / passenger corresponding to trigger posture 1 can be obtained as the co-driver position. The cockpit adjustment device corresponding to the co-driver position can be adjusted according to the target parameters of the driver / passenger corresponding to the cockpit position.

[0091] For example, human images can be captured by a vehicle camera to obtain the actual postures of driver and passenger D and driver and passenger E. Then, it can be determined that the actual posture of driver and passenger D corresponds to trigger posture 1 and the actual posture of driver and passenger E corresponds to trigger posture 2. Then, the vehicle target position corresponding to the trigger posture 1 of driver D is obtained as the passenger position, and the cabin adjustment device corresponding to the passenger position is adjusted according to the target parameters of driver and passenger D corresponding to the cabin position. Similarly, the vehicle target position corresponding to the trigger posture 2 of driver and passenger E is obtained as the driver position, and the cabin adjustment device corresponding to the driver position is adjusted according to the target parameters of driver and passenger E corresponding to the cabin position.

[0092] This application embodiment can determine the target position and target parameters in the vehicle cabin corresponding to any triggering posture when the actual posture matches any triggering posture. The cabin adjustment device corresponding to the target position is adjusted according to the target parameters so that the cabin adjustment corresponding to the target position can be completed before the driver and passengers get into the vehicle. This enables efficient and fast personalized seat adjustment for different users, improves the comfort and safety of the vehicle, and makes it more intelligent and practical.

[0093] Optionally, in some embodiments, before determining whether the actual posture matches any of the at least one trigger posture preset by the vehicle, the method further includes: receiving a setting instruction from the driver or passenger; controlling the vehicle to enter a posture setting mode; and generating at least one trigger posture and a corresponding target position and target parameters according to the setting instruction from the driver or passenger.

[0094] It is understandable that drivers and passengers can pre-set the trigger posture by issuing setting commands to the vehicle. The vehicle enters the posture setting mode upon receiving the setting command and obtains the target position and target parameters corresponding to the trigger posture based on the driver's and passengers' setting command.

[0095] In actual operation, users can operate on mobile devices or vehicle displays, and set or select the vehicle's default trigger posture, set the vehicle position corresponding to the trigger posture, and the cockpit parameters corresponding to the vehicle position, and finally achieve the matching connection between the trigger posture and the target position and target parameters.

[0096] Optionally, in some embodiments, the target parameters include the adjustment parameters of the cabin adjustment devices corresponding to the vehicle's seats, air conditioning, lights, instrument panel, central control screen, vehicle networking, voice recognition device, and gesture recognition device.

[0097] It is understandable that, in the implementation of this application, the cabin can be adjusted according to the specific parameters of different aspects such as the vehicle's seats, air conditioning, lights, instrument panel, central control screen, vehicle networking, voice recognition, and gesture recognition.

[0098] For example, users can adjust the seat height and angle settings, air conditioning temperature settings, and headlight color settings in the vehicle cabin. The automatic activation settings for the instrument panel, central control screen, vehicle networking, voice recognition, and gesture recognition devices are also saved as memory parameters. Before the user gets in the vehicle, the seat is adjusted to the corresponding height, the air conditioning is adjusted to a comfortable temperature, and the headlights are adjusted to the preferred color. The instrument panel, central control screen, vehicle networking, voice recognition, and gesture recognition are automatically activated, enabling personalized cabin adjustments before the user gets in the vehicle to ensure the actual needs of the driver and passengers are met.

[0099] Based on the embodiments of this application, the target parameter settings can be constructed using the seats, air conditioning, lights, instrument panel, central control screen, vehicle network, voice recognition device and gesture recognition device of the vehicle cabin, so as to realize personalized cabin adjustment before the user gets in the car, ensuring the user's driving experience in multiple dimensions and effectively meeting the user's multi-faceted needs.

[0100] According to the vehicle cockpit control method of this invention, multiple skeletal points of the driver and passengers outside the vehicle can be acquired to obtain the actual posture of the driver and passengers. If the actual posture matches the triggered posture, it indicates that the driver and passengers have a need for automatic seat adjustment. The intelligent cockpit adjustment is completed before the user gets into the vehicle according to the corresponding target position and parameters. This achieves efficient and rapid personalized seat adjustment for different users, completing a series of actions of the equipment in the cockpit before the user gets in the vehicle, improving vehicle comfort and safety, effectively enhancing the user experience, improving the interactive experience, and making it more intelligent and practical. Therefore, it solves the problems of requiring users to manually adjust the seat upon entering the vehicle, causing users to spend time waiting, which is time-consuming and laborious, reducing the user's driving experience, decreasing customer loyalty, and affecting the overall user experience. This method improves vehicle comfort and safety, making it more intelligent and practical.

[0101] Figure 4 This is a schematic diagram of the structure of the vehicle cabin control device provided in the embodiments of this application.

[0102] For example, such as Figure 4 As shown, the device 10 may include:

[0103] Acquisition Module 100: Used to acquire multiple skeletal points of the driver and passengers outside the vehicle.

[0104] Judgment module 200: used to determine the actual posture of the driver and passengers based on multiple skeletal points, and to determine whether the actual posture matches any of the trigger postures in at least one of the pre-set trigger postures of the vehicle.

[0105] Control module 300: When the actual posture matches any triggered posture, it determines the target position and target parameters in the vehicle cabin corresponding to any triggered posture, and adjusts the cabin adjustment device corresponding to the target position according to the target parameters, so as to complete the cabin adjustment corresponding to the target position before the driver and passengers get into the vehicle. Optionally, in some embodiments, the acquisition module 100 includes:

[0106] First acquisition unit: used to acquire human images of drivers and passengers outside the vehicle.

[0107] Recognition unit: Used to input human body images into a pre-trained skeletal point extraction model to obtain multiple skeletal points of the driver and passengers.

[0108] Optionally, in some embodiments, the acquisition module 100 further includes:

[0109] Second acquisition unit: used to acquire the actual location of the vehicle key.

[0110] Calculation unit: Used to calculate the actual distance between the vehicle key and the vehicle based on the actual position of the vehicle key.

[0111] First acquisition unit: used to control the vehicle to power on when the actual distance is less than or equal to the preset power-on distance, so as to acquire human images of the driver and passengers outside the vehicle.

[0112] Optionally, in some embodiments, the target parameters include the adjustment parameters of the cabin adjustment devices corresponding to the vehicle's seats, air conditioning, lights, instrument panel, central control screen, vehicle networking, voice recognition device, and gesture recognition device.

[0113] Optionally, in some embodiments, the acquisition module 100 further includes:

[0114] The second data collection unit is used to collect the identification information of the drivers and passengers outside the vehicle.

[0115] The first judgment unit is used to determine whether the driver or passenger has the right to adjust the cabin based on the identity identifier, so as to obtain multiple skeleton points of the driver or passenger outside the vehicle if the driver or passenger has the right to adjust the cabin.

[0116] Optionally, in some embodiments, the determination module 200 includes:

[0117] The third acquisition unit is used to acquire the duration of the actual posture after determining the actual posture of the driver and passengers based on multiple skeletal points.

[0118] The second judgment unit is used to determine that the actual posture is valid when the duration is greater than or equal to the preset effective duration.

[0119] Optionally, in some embodiments, the determination module 200 further includes:

[0120] Setting unit: Used to receive setting instructions from the driver or passenger before determining whether the actual posture matches any of the trigger postures in at least one of the vehicle's pre-set trigger postures.

[0121] Generation unit: Used to control the vehicle to enter the attitude setting mode, and generate at least one trigger attitude and corresponding target position and target parameters according to the setting instructions of the driver and passengers.

[0122] It should be noted that the specific implementation of the vehicle cockpit control device in this embodiment of the invention is similar to the specific implementation of the vehicle cockpit control method. To reduce redundancy, it will not be described in detail here.

[0123] In summary, this application can extract the human posture features of occupants outside the vehicle, obtain multiple skeletal points of the occupants, and determine their actual posture. If the actual posture matches the triggered posture, it indicates that the occupant has a need for automatic seat adjustment. The system then performs intelligent cabin adjustment before the user gets in the vehicle, based on the corresponding target position and parameters. This enables efficient and rapid personalized seat adjustment for different users, completing a series of actions of the cabin equipment before the user enters the vehicle. This improves vehicle comfort and safety, effectively enhances the user experience, improves the interactive experience, and makes the system more intelligent and practical. Therefore, it solves the problem that personalized seat adjustments previously required manual adjustment upon entering the vehicle, leading to waiting time, wasting time and effort, reducing the user's driving experience, decreasing customer loyalty, and impacting overall user experience. This approach improves vehicle comfort and safety, making the system more intelligent and practical.

[0124] Figure 5 This is a schematic diagram of the structure of a cockpit controller provided in an embodiment of this application.

[0125] It should be understood that the methods described above can be applied to... Figure 5 The cockpit controller with the structure shown.

[0126] Furthermore, embodiments of this application also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform the vehicle cockpit control method provided in embodiments of this application.

[0127] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0128] When the functional modules are divided according to their respective functions, the device may also include a data acquisition module, a judgment module, and a control module. It should be noted that all relevant content regarding the steps involved in the above method embodiments can be referenced to the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0129] It should be understood that the device provided in this embodiment is used to execute the above-described vehicle cockpit control method, and therefore can achieve the same effect as the above-described implementation method.

[0130] When using integrated units, the device may include a processing module and a storage module. When applied to an automobile, the processing module can be used to control and manage the vehicle's movements. The storage module can be used to support the vehicle in executing program code, etc.

[0131] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0132] In addition, the device provided in the embodiments of this application may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the vehicle cockpit control method provided in the above embodiments.

[0133] This embodiment also provides a vehicle that includes the aforementioned cockpit controller.

[0134] In this embodiment, the device, cockpit controller, computer program product or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0135] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0136] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units 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 device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0137] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for controlling a vehicle cockpit, characterized in that, Includes the following steps: As the driver and passengers approach the vehicle, the vehicle's front, rear, left, right, or all four sides cameras capture images of the driver and passengers outside the vehicle. These images are then input into a pre-built skeleton extraction model to obtain multiple skeleton points of the driver and passengers. The skeleton extraction model is created by replacing the ResNet architecture used in the original backbone of the Openpose model with the Mobilenetv2 architecture, thus creating a lightweight network. The actual posture of the driver and passenger is determined based on the multiple skeletal points, and it is determined whether the actual posture matches any of the trigger postures in at least one of the vehicle's pre-set trigger postures. If the actual posture matches any of the triggered postures, then the target position and target parameters in the vehicle cabin corresponding to the triggered posture are determined, and the cabin adjustment device corresponding to the target position is adjusted according to the target parameters to complete the cabin adjustment corresponding to the target position before the driver or passenger gets into the vehicle. Each triggered posture corresponds to a unique driver or passenger and includes the target position and target parameters in the vehicle cabin corresponding to the driver or passenger. The target position includes the driver's position and the front passenger position corresponding to the driver or passenger. The target parameters include the adjustment parameters of the cabin adjustment devices corresponding to the seats, air conditioning, lights, instrument panel, central control screen, vehicle networking, voice recognition device and gesture recognition device in the vehicle cabin; Before determining whether the actual posture matches any of the at least one trigger posture preset by the vehicle, the method further includes: Receive the setting instructions from the driver and passengers; The vehicle is controlled to enter the attitude setting mode, and at least one trigger attitude and corresponding target position and target parameters are generated according to the setting instructions of the driver and passengers.

2. The method according to claim 1, characterized in that, The acquisition of human images of the occupants outside the vehicle includes: Find the actual location of the vehicle key; Calculate the actual distance between the vehicle key and the vehicle based on the actual location of the vehicle key; When the actual distance is less than or equal to the preset power-on distance, the vehicle is powered on to collect human images of the driver and passengers outside the vehicle.

3. The method according to claim 1, characterized in that, After acquiring human images of the occupants outside the vehicle; Collect the identification of the drivers and passengers outside the vehicle; Based on the identity identifier, determine whether the driver or passenger has cabin adjustment authority, so as to obtain multiple skeletal points of the driver or passenger outside the vehicle if the driver or passenger has cabin adjustment authority.

4. The method according to claim 1, characterized in that, After determining the actual posture of the driver and passenger based on the multiple skeletal points, the method further includes: Obtain the duration of the actual posture; If the duration is greater than or equal to the preset effective duration, the actual posture is determined to be valid.

5. A control device for a vehicle cockpit, characterized in that, For implementing the vehicle cockpit control method as described in any one of claims 1-4, the apparatus comprises: The acquisition module is used to acquire multiple skeletal points of the driver and passengers outside the vehicle; The judgment module is used to determine the actual posture of the driver and passenger based on the multiple skeletal points, and to determine whether the actual posture matches any of the trigger postures in at least one of the pre-set trigger postures of the vehicle. The control module is used to determine the target position and target parameters in the vehicle cabin corresponding to the triggering posture when the actual posture matches the triggering posture, and adjust the cabin adjustment device corresponding to the target position according to the target parameters, so as to complete the cabin adjustment corresponding to the target position before the driver and passengers get into the vehicle.

6. A cockpit controller, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle cockpit control method as described in any one of claims 1-4.

7. A vehicle, characterized in that, include: The cockpit controller as described in claim 6.

Images