Intelligent cabin, control method, autonomous vehicle and storage medium

Abstract

The invention provides an intelligent cabin, a control method, an automatic driving vehicle and a storage medium. The control method of the intelligent cabin comprises the following steps: acquiring and analyzing a first sign image of a target user outside the cabin to determine first physical features of the target user in multiple dimensions; analyzing the first physical feature through a pre-trained first model to determine at least one preference tag of the target user; and according to the at least one preference label, carrying out personalized setting on the plurality of devices in the intelligent cabin. The personal preference of the user is speculated by analyzing the physical sign image of the user outside the cabin, and equipment such as a seat, lamplight, an air conditioner and an information entertainment system in the intelligent cabin can be individually set in advance, so that the individual setting conforming to the personal preference of the user is completed in advance before the user enters the intelligent cabin, and the user experience of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a control method for an intelligent cockpit, an intelligent cockpit, an autonomous driving vehicle, and a computer-readable storage medium. Background Art

[0002] In recent years, vehicles have been continuously developing towards intelligence. As the most direct carrier connecting users and vehicles, smart cockpits have become an important entry point for the development of vehicle intelligence.

[0003] In the prior art, the settings of seats, lights, air conditioning, infotainment systems and other equipment in smart cockpits are mainly achieved through manual settings or pre-configured parameters. Although some improved smart cockpits have been equipped with on-board cameras to perform facial recognition on users, facial features are not sufficient to fully and objectively represent the needs and preferences of users in all aspects. Therefore, it is generally necessary to pre-bind the user's facial information and personalized setting parameters to achieve personalized settings of smart cockpits, and it is impossible to fully and intelligently provide friendly cockpit settings for users who have not bound facial information.

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a control technology for a smart cockpit, which infers the personal preferences of users outside the cabin by analyzing their vital signs images, so as to personalize the seats, lights, air conditioning, infotainment system and other equipment in the smart cockpit in advance, thereby completing the personalized settings that meet the personal preferences of the users before they enter the smart cockpit, thereby improving their user experience. Summary of the invention

[0005] A brief summary of one or more aspects is given below to provide a basic understanding of these aspects. This summary is not an exhaustive overview of all conceived aspects, and is neither intended to identify the key or decisive elements of all aspects nor to define the scope of any or all aspects. Its only purpose is to give some concepts of one or more aspects in a simplified form as a prelude to a more detailed description that will be given later.

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a control method of a smart cockpit, a smart cockpit, an autonomous driving vehicle, and a computer-readable storage medium, which can infer the personal preferences of users outside the cabin by analyzing their vital signs images, so as to personalize the seats, lights, air conditioning, infotainment system and other equipment in the smart cockpit in advance, thereby completing the personalized settings that meet the personal preferences of the users before they enter the smart cockpit, so as to improve their user experience.

[0007] Specifically, the control method of the above-mentioned smart cockpit provided according to the first aspect of the present invention includes the following steps: acquiring and parsing a first physical sign image of a target user outside the cabin to determine a first physical feature of the target user in multiple dimensions; parsing the first physical feature via a pre-trained first model to determine at least one preference tag of the target user; and personalizing multiple devices in the smart cockpit according to the at least one preference tag.

[0008] Preferably, in one embodiment of the present invention, the step of acquiring and parsing a first vital sign image of a target user outside the cabin to determine first physical features of the target user in multiple dimensions includes: acquiring and parsing a first vital sign image of a person outside the cabin to determine motion trend features of the person outside the cabin; judging the intention of the person outside the cabin to enter the smart cockpit based on the motion trend features; in response to the person outside the cabin having the intention to enter the smart cockpit, determining the person outside the cabin as the target user, and parsing the first vital sign image to determine first physical features of the target user in multiple dimensions.

[0009] Preferably, in one embodiment of the present invention, at least one external camera is provided on the outside of the smart cockpit. The step of acquiring and parsing the first vital sign image of the person outside the cabin to determine the motion trend characteristics of the person outside the cabin includes: performing moving object detection in a first detection range outside the cabin via a vehicle-mounted radar; in response to the detection result that there is a moving object in the first detection range, starting the external camera to collect the image of the moving object; extracting the motion trend characteristics of the human body from the image of the moving object; and determining the image containing at least one of the motion trend characteristics as the first vital sign image of the person outside the cabin, and determining the at least one of the motion trend characteristics as the motion trend characteristics of the person outside the cabin.

[0010] Preferably, in one embodiment of the present invention, a plurality of external cameras are provided on the outside of the smart cockpit, wherein each of the external cameras corresponds to a second detection range, and the step of starting the external camera to capture the image of the moving object in response to the detection result of the presence of a moving object within the first detection range includes: in response to the detection result of the presence of a moving object within the first detection range, starting the corresponding external camera to capture the image of the corresponding second detection range according to the position of the moving object.

[0011] Preferably, in one embodiment of the present invention, the external camera is respectively arranged on the left rearview mirror, the right rearview mirror, the left B-pillar and / or the right B-pillar of the smart cockpit to respectively capture images of a second detection range close to the left front door, the right front door, the left rear door and / or the right rear door of the smart cockpit, and / or the external camera is selected from a 3D TOF camera, or a combination of a 2D camera and a TOF sensor, to capture images with depth information.

[0012] Preferably, in one embodiment of the present invention, the motion trend characteristics include the planar position, depth and / or posture of the person outside the cabin in the first vital sign image of the current frame, and / or the planar position change, depth change and / or posture change of the person outside the cabin relative to the first vital sign image of at least one previous historical frame. The step of judging the intention of the person outside the cabin to enter the smart cockpit based on the motion trend characteristics includes: predicting the motion trajectory of the person outside the cabin based on the motion trend characteristics; and judging that the person outside the cabin has the intention to enter the smart cockpit in response to the motion trajectory pointing to any door of the smart cockpit.

[0013] Preferably, in one embodiment of the present invention, the first vital sign image includes RGB information and corresponding depth information of multiple pixels, and the step of parsing the first vital sign image to determine the first physical features of the target user in multiple dimensions includes: performing feature extraction on the RGB information and depth information of each pixel in the first vital sign image through a pre-trained second model to determine the first physical features of the target user in multiple dimensions, wherein the first physical features of the multiple dimensions are selected from at least one of height, weight, body proportions, gender, age, clothing, and personal belongings.

[0014] Preferably, in one embodiment of the present invention, the multiple devices in the smart cockpit include at least one of seats, lights, air conditioning, and infotainment systems, and the step of parsing the first physical feature via a pre-trained first model to determine at least one preference tag of the target user includes: determining at least one preference tag of the target user regarding seat settings based on the first physical feature in height dimension, weight dimension, body proportion dimension and / or personal belongings dimension; and / or determining at least one preference tag of the target user regarding lighting settings, air conditioning settings and / or infotainment system settings based on the first physical feature in gender dimension, age dimension and / or clothing dimension.

[0015] Preferably, in an embodiment of the present invention, the first physical feature of the carry-on dimension includes item type information and / or item size information, wherein the item type information indicates luggage and / or pets, and the item size information indicates the space size of the corresponding carry-on.

[0016] Preferably, in one embodiment of the present invention, at least one preference tag regarding the seat setting is selected from at least one of a front-to-rear position offset tag, an up-and-down height offset tag, and a backrest tilt angle tag, and / or at least one preference tag regarding the lighting setting is selected from at least one of a lighting position tag, a lighting frequency tag, a color temperature tag, and a brightness tag, and / or at least one preference tag regarding the air conditioning setting is selected from at least one of a temperature tag, a wind speed tag, a wind direction tag, and a cycle mode tag, and / or at least one preference tag regarding the infotainment system setting is selected from at least one of a recommended playlist tag, a recommended video tag, a recommended game tag, and a volume tag.

[0017] Preferably, in one embodiment of the present invention, the smart cockpit is configured with a cockpit domain controller and a body domain controller, and the step of personalizing the seats, lights, air conditioning and / or infotainment system in the smart cockpit according to the at least one preference tag includes: personalizing the infotainment system in the smart cockpit according to at least one preference tag set for the infotainment system via the cockpit domain controller; and / or personalizing the air conditioning in the smart cockpit according to at least one preference tag set for the air conditioning via the cockpit domain controller; and / or personalizing the seats in the smart cockpit according to at least one preference tag set for the seats via the body domain controller; and / or personalizing the lights in the smart cockpit according to at least one preference tag set for the lights via the body domain controller.

[0018] Preferably, in one embodiment of the present invention, at least one internal camera is further provided inside the smart cockpit, and the control method further includes the following steps: in response to the target user entering the smart cockpit, acquiring a second vital sign image of the target user via the at least one internal camera; updating at least one preference tag of the target user based on the second vital sign image; and during driving of the smart cockpit, dynamically adjusting the personalized settings of the seat, the light, the air conditioning and / or the infotainment system based on the updated at least one preference tag.

[0019] Preferably, in one embodiment of the present invention, the step of dynamically adjusting the personalized settings of the seats, the lights, the air conditioning and / or the infotainment system according to at least one updated preference tag during the driving of the smart cockpit includes: acquiring driving data of the smart cockpit; correcting at least one updated preference tag according to the driving data; and dynamically adjusting the personalized settings of the seats, the lights, the air conditioning and / or the infotainment system according to at least one corrected preference tag during the driving of the smart cockpit.

[0020] Preferably, in one embodiment of the present invention, the step of correcting and updating at least one preference label based on the driving data includes: in response to the driving data indicating that the smart cockpit is in a bumpy state, reducing the value of the up and down height offset label of the seat setting; and / or in response to the driving data indicating that the smart cockpit is in a high-speed state, increasing the value of the brightness label of the light setting; and / or in response to the driving data indicating that the smart cockpit is in a state close to a sharp turn, activating the strobe mode label of the light setting, and adjusting the value of the lighting frequency label according to the vehicle speed and / or critical distance.

[0021] In addition, the smart cockpit provided according to the second aspect of the present invention includes a memory and a processor. The memory stores computer instructions. The processor is connected to the memory and is configured to execute the computer instructions stored in the memory to implement the control method of the smart cockpit provided in any one of the above embodiments.

[0022] In addition, the above-mentioned autonomous driving vehicle provided according to the third aspect of the present invention is configured with a smart cockpit provided in any one of the above-mentioned embodiments.

[0023] In addition, the computer-readable storage medium provided according to the fourth aspect of the present invention stores computer instructions. When the computer instructions are executed by the processor, the control method of the smart cockpit provided by any one of the above embodiments is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above features and advantages of the present invention can be better understood after reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily drawn to scale, and components with similar related properties or features may have the same or similar reference numerals.

[0025] Figure 1 A schematic diagram of the architecture of a smart cockpit provided according to some embodiments of the present invention is shown.

[0026] Figure 2A schematic flow chart of a method for controlling a smart cockpit according to some embodiments of the present invention is shown.

[0027] Figure 3 A schematic diagram of parsing a first vital sign image according to some embodiments of the present invention is shown. DETAILED DESCRIPTION

[0028] The following specific embodiments illustrate the implementation of the present invention, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Although the description of the present invention will be introduced in conjunction with the preferred embodiment, this does not mean that the features of this invention are limited to this implementation. On the contrary, the purpose of introducing the invention in conjunction with the implementation is to cover other options or modifications that may be extended based on the claims of the present invention. In order to provide a deep understanding of the present invention, the following description will include many specific details. The present invention can also be implemented without using these details. In addition, in order to avoid confusion or blurring the focus of the present invention, some specific details will be omitted in the description.

[0029] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] In addition, the terms "upper", "lower", "left", "right", "top", "bottom", "horizontal" and "vertical" used in the following description should be understood as the directions shown in the paragraph and the related drawings. Such relative terms are only used for the convenience of description and do not mean that the device described therein must be manufactured or operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0031] It is understood that although the terms "first", "second", "third", etc. may be used herein to describe various components, regions, layers and / or parts, these components, regions, layers and / or parts should not be limited by these terms, and these terms are only used to distinguish different components, regions, layers and / or parts. Therefore, the first component, region, layer and / or part discussed below may be referred to as a second component, region, layer and / or part without departing from some embodiments of the present invention.

[0032] As mentioned above, in the prior art, the settings of seats, lights, air conditioning, infotainment systems and other equipment in smart cockpits are mainly achieved through manual settings or pre-configured parameters. Although some improved smart cockpits have been equipped with on-board cameras to perform facial recognition on users, facial features are not sufficient to fully and objectively represent the needs and preferences of users in all aspects. Therefore, it is generally necessary to pre-bind the user's facial information and personalized setting parameters to achieve personalized settings of smart cockpits, and it is impossible to fully and intelligently provide friendly cockpit settings for users who have not bound facial information.

[0033] In order to overcome the above-mentioned defects of the prior art, the present invention provides a control method of a smart cockpit, a smart cockpit, an autonomous driving vehicle, and a computer-readable storage medium, which can infer the personal preferences of users outside the cabin by analyzing their vital signs images, so as to personalize the seats, lights, air conditioning, infotainment system and other equipment in the smart cockpit in advance, thereby completing the personalized settings that meet the personal preferences of the users before they enter the smart cockpit, so as to improve their user experience.

[0034] In some non-limiting embodiments, the control method of the smart cockpit provided in the first aspect of the present invention can be implemented via the smart cockpit provided in the second aspect of the present invention. Specifically, the smart cockpit can be configured in the autonomous driving vehicle provided in the third aspect of the present invention, which is provided with a memory and a processor. The memory includes but is not limited to the computer-readable storage medium provided in the fourth aspect of the present invention, on which computer instructions are stored. The processor is connected to the memory and is configured to execute the computer instructions stored on the memory to implement the control method of the smart cockpit provided in the first aspect of the present invention.

[0035] First, please refer to Figure 1 , Figure 1 A schematic diagram of the architecture of a smart cockpit provided according to some embodiments of the present invention is shown.

[0036] exist Figure 1 In the illustrated embodiment, the processor of the smart cockpit provided by the present invention may be implemented by a cockpit domain controller (Cockpit Domain Controller) cooperating with a body domain controller (Body Domain Controller).

[0037] Specifically, in some embodiments, the first end of the cockpit domain controller can be connected to a vehicle-mounted radar, an external camera, an internal camera and other sensing devices via a low voltage differential signal (LVDS) data line to collect a first physical sign image of the user, and thereby determine the first physical features of the user in multiple dimensions, so as to determine a personalized setting scheme for at least one device such as a seat, a light, an air conditioner, and an in-vehicle infotainment (IVI) system in the smart cockpit. The second end of the cockpit domain controller can be connected to the in-vehicle infotainment (IVI) system via a high definition multimedia interface (HDMI), and / or connected to the air conditioning device via a local interconnect network (LIN) bus of the smart cockpit, so as to transmit setting instructions to the IVI system and / or the air conditioning system respectively, so as to realize the personalized setting of the IVI system and / or the air conditioning device.

[0038] Furthermore, the third end of the cockpit domain controller can also be connected to the vehicle body domain controller. The vehicle body domain controller can also be connected to the lighting equipment of the smart cockpit via the above-mentioned LIN bus, and / or connected to the seat equipment of the smart cockpit via the controller area network bus (CAN) of the smart cockpit, so as to transmit setting instructions to the lighting equipment and / or the seat equipment respectively via the vehicle body domain controller to realize personalized settings of the lighting equipment and / or the seat equipment.

[0039] The working principle of the above-mentioned smart cockpit and autonomous driving vehicle will be described below in conjunction with an embodiment of the smart cockpit control method. Those skilled in the art will understand that the embodiments of these control methods are only some non-limiting implementation methods provided by the present invention, which are intended to clearly demonstrate the main concept of the present invention and provide some specific solutions that are convenient for the public to implement, rather than to limit all functions or all working modes of the smart cockpit. Similarly, the smart cockpit and autonomous driving vehicle are only a non-limiting implementation method provided by the present invention, and do not constitute a limitation on the execution subject and execution order of each step in the control method of these smart cockpits.

[0040] Please refer to Figure 1 and Figure 2 , Figure 2 A schematic flow chart of a method for controlling a smart cockpit according to some embodiments of the present invention is shown.

[0041] like Figure 1 and Figure 2As shown, in the process of personalizing the smart cockpit, the cockpit domain controller can first obtain and analyze the first physical sign image of the target user outside the cabin to determine the first physical features of the target user in multiple dimensions. Here, the target user can include the driver user in the driving seat, and can also include the passenger users in the co-pilot seat and the back seat.

[0042] Specifically, the cockpit domain controller can turn off the external camera when the vehicle is parked and / or turned off, and turn on the vehicle radar to detect moving objects in the first detection range outside the cabin (for example, 10 meters around the vehicle). Here, the vehicle radar can be selected from at least one or a combination of millimeter wave radar, laser radar, 4D radar, ultra wide band (UWB) sensor, and Bluetooth Low Energy (BLE) sensor.

[0043] Afterwards, in response to the detection result of the presence of a moving object within the first detection range, the cockpit domain controller can activate an external camera to capture an image of the moving object, extract motion trend features of the human body from the image of the moving object, determine the image containing at least one motion trend feature as a first vital sign image of a person outside the cabin, and determine the at least one motion trend feature as a motion trend feature of a person outside the cabin.

[0044] In some embodiments, the external camera can be selected from a 3D TOF camera, or a combination of a 2D camera and a TOF sensor, for collecting images with depth information. The multiple external cameras can be respectively arranged on the left rearview mirror, the right rearview mirror, the left B-pillar and / or the right B-pillar of the smart cockpit to respectively collect images of the second detection range near the left front door, the right front door, the left rear door and / or the right rear door of the smart cockpit. In response to the detection result that there is a moving object within the first detection range, the cockpit domain controller can preferably start the corresponding external camera to collect the corresponding image of the second detection range according to the position of the moving object, so as to focus on improving the image quality of the corresponding area, thereby improving the recognition accuracy of motion trend characteristics and physical characteristics.

[0045] Furthermore, the second detection range can be a fan-shaped visible area with an angle range of 60° to 120° with the vehicle body. The motion trend characteristics include but are not limited to the plane position, depth and / or posture of the extravehicular personnel in the first vital sign image of the current frame, and / or the plane position change, depth change and / or posture change of the extravehicular personnel relative to the first vital sign image of at least one previous historical frame. The posture can be characterized by the plane position, depth and spatial angle of the torso and limbs. The specific steps of extracting motion trend characteristics from the image do not involve the technical improvements of the present invention and are not elaborated here.

[0046] In this way, by using a vehicle-mounted radar with low energy consumption and low data processing load to wake up the external camera for image acquisition and image analysis, the present invention can effectively reduce the energy consumption and data processing load of the smart cockpit for detecting moving objects outside the vehicle. By setting up multiple cameras and selectively activating the external cameras at corresponding positions, the present invention can not only cover the 360° detection range around the vehicle by combining various types of other sensors such as radar, but also effectively improve the imaging quality of the user's vital signs image and reduce the parameter requirements and costs of the camera.

[0047] After determining the motion trend characteristics of the people outside the cabin, the cockpit domain controller can judge whether the people outside the cabin have the intention to enter the smart cockpit based on the motion trend characteristics, and determine the people outside the cabin who have the intention to enter the smart cockpit as the target user, thereby analyzing the first vital sign image of the target user to determine the first physical characteristics of the target user in multiple dimensions.

[0048] Specifically, in the process of determining whether the person outside the cabin has the intention to enter the smart cockpit, the cockpit domain controller can first predict the motion trajectory of the person outside the cabin based on the motion trend characteristics of the first physical sign image taken continuously in multiple frames. In response to the prediction result that the motion trajectory points to any door of the smart cockpit, the cockpit domain controller can determine that the person outside the cabin has the intention to enter the corresponding door of the smart cockpit. By analyzing the motion trend characteristics of the person outside the cabin to screen potential target users, the present invention can further reduce the number of parsed objects, thereby eliminating the huge data processing load generated by extracting and parsing multi-dimensional first physical features.

[0049] Those skilled in the art will understand that the above-mentioned embodiment of determining the intention of a person outside the cabin to enter the smart cockpit by analyzing the motion trend characteristics of the first vital sign image of the person outside the cabin is only a preferred scheme provided by the present invention, which is intended to clearly demonstrate the main concept of the present invention and provide a specific scheme that is easy for the public to implement, but is not intended to limit the scope of protection of the present invention.

[0050] Optionally, in other embodiments, technicians in this field may also determine whether the person outside the cabin has the intention to enter the corresponding door of the smart cockpit by identifying the image of the user carrying the car key, receiving the unlocking signal of the car key, and / or receiving the remote start signal provided by the user, and similarly achieve the effect of eliminating the huge data processing load generated by extracting and parsing the multi-dimensional first physical features.

[0051] Please refer to further Figure 3 , Figure 3 A schematic diagram of parsing a first vital sign image according to some embodiments of the present invention is shown.

[0052] exist Figure 3In the illustrated embodiment, the first physical sign image may include RGB information of multiple pixels and corresponding depth information to improve the accuracy of its representation of the user's physical signs. Before parsing the first physical sign image to determine the first physical features of the target user in multiple dimensions, the technician may first use a large number of physical sign image samples and corresponding data labels to train YOLO models and other deep learning models based on convolutional neural networks (CNN) to obtain a second model. Here, the second model involves at least one physical feature dimension of height, weight, body proportions, gender, age, clothing, and personal belongings. The body proportions can be characterized by the length ratio of the user's arms, legs, and torso. The personal belongings include but are not limited to luggage and pets. The data label is used to indicate the true value of the physical features involved in the corresponding physical sign image sample. The specific steps of training the artificial intelligence model according to the image samples and data labels do not involve the technical improvements of the present invention and are not repeated here.

[0053] Afterwards, in the process of parsing the first vital sign image to determine the first physical features of the target user in multiple dimensions, the cockpit domain controller can input the first vital sign image of the target user into a pre-trained second model, and extract features of the RGB information and depth information of each pixel in the first vital sign image through the second model to determine the first physical features of the target user in multiple dimensions.

[0054] Specifically, the above-mentioned second model can be composed of a combination of multiple CNN networks such as the YOLO model, which can use traditional visual methods to detect the user's height characteristics and / or body proportion characteristics, use the CNN network to extract characteristics about the user's weight, gender, age and / or clothing, and use the CNN network to detect whether the user is carrying luggage, pets and other personal items.

[0055] Please continue to refer to Figure 2 After determining the first physical features of the target user in multiple dimensions, the cockpit domain controller can parse the first physical features via a first model such as a pre-trained support vector machine (SVM) to determine at least one preference tag of the target user, and then personalize at least one device in the smart cockpit according to the at least one preference tag.

[0056] For example, for the personalized setting of the above-mentioned seat equipment, in the process of parsing the first physical feature to determine at least one preference tag of the target user, the first model can determine at least one preference tag of the target user regarding the seat setting based on the first physical feature of the target user in the height dimension, weight dimension, body proportion dimension and / or personal belongings dimension. Here, the at least one preference tag for the seat setting can be selected from at least one of the front and rear position offset tag, the up and down height offset tag, and the backrest tilt angle tag. The cockpit domain controller can intelligently determine at least one preference tag for the seat setting based on the height, weight, body proportion dimension of the target user, and the size of personal belongings such as luggage and pets, and adjust the front and rear position offset, up and down height offset and / or backrest tilt angle of the seat in a personalized manner via the vehicle body domain controller.

[0057] For another example, with respect to the personalized settings of the above-mentioned lighting equipment, in the process of parsing the first physical feature to determine at least one preference tag of the target user, the first model can determine at least one preference tag of the target user regarding the lighting settings based on the first physical feature of the target user in the gender dimension, age dimension and / or clothing dimension. Here, the at least one preference tag regarding the lighting settings can be selected from at least one of a lighting position tag, a lighting frequency tag, a color temperature tag, and a brightness tag. The cockpit domain controller can intelligently determine at least one preference tag of the lighting settings based on the gender, age, and clothing type of the target user, and adjust the lighting position, lighting frequency, color temperature and / or brightness of the lights in a personalized manner via the vehicle body domain controller.

[0058] For another example, with respect to the personalized settings of the above-mentioned air-conditioning equipment, in the process of parsing the first physical feature to determine at least one preference tag of the target user, the first model can determine at least one preference tag of the target user regarding the air-conditioning settings based on the first physical feature of the target user in the gender dimension, age dimension and / or clothing dimension. Here, the at least one preference tag regarding the air-conditioning settings can be selected from at least one of a temperature tag, a wind speed tag, a wind direction tag, and a circulation mode tag. The cockpit domain controller can intelligently determine at least one preference tag for the air-conditioning settings based on the gender, age, and clothing type of the target user, and adjust the target temperature, wind speed, wind direction, and / or circulation mode of the air-conditioning in a personalized manner.

[0059] For another example, with respect to the personalized settings of the above-mentioned infotainment (IVI) system, in the process of parsing the first physical feature to determine at least one preference tag of the target user, the first model can determine at least one preference tag of the target user regarding the IVI system settings based on the first physical feature of the target user in the gender dimension, age dimension and / or clothing dimension. Here, at least one preference tag set for the infotainment (IVI) system can be selected from at least one of a recommended playlist tag, a recommended video tag, a recommended game tag, and a volume tag. The cockpit domain controller can intelligently determine at least one preference tag set for the infotainment (IVI) system based on the target user's gender, age, and clothing type, and personalize the infotainment (IVI) system's recommended playlist, recommended video, recommended game, and / or volume.

[0060] In this way, by configuring an external camera on the outside of the smart cockpit and performing multi-dimensional physical feature analysis on it through the pre-trained first and second models, the present invention can accurately infer the personal preferences of any user and personalize the seats, lights, air conditioning, infotainment system and other equipment in the smart cockpit in advance, so as to complete the personalized settings that meet the user's personal preferences before the user enters the smart cockpit, thereby improving the user experience.

[0061] Further, in Figure 1 In the illustrated embodiment, the interior of the smart cockpit provided by the present invention may also be preferably provided with at least one internal camera. The internal camera may be installed at a location such as a steering wheel, the inside of an A-pillar, and / or a rearview mirror based on the configuration of a driver monitoring system (DMS) or an in-cabin monitoring system (IMS), and / or installed at a location such as the inside of a ceiling based on the configuration of an occupancy monitoring system (OMS).

[0062] Since the smart cockpit has a more unified and simple scene mode, the second vital sign image collected by the internal camera can more accurately reflect the physical characteristics of the target user in multiple dimensions. In response to the target user entering the smart cockpit, the cockpit domain controller can turn off the external camera and turn on at least one internal camera at the corresponding position to collect the second vital sign image of the target user, and update at least one preference tag of the target user based on the second vital sign image. The specific principle is similar to the above embodiment and will not be repeated here. Afterwards, during the driving process of the smart cockpit, the cockpit domain controller can dynamically adjust the personalized settings of the seat, lighting, air conditioning and / or infotainment system according to the updated at least one preference tag, thereby further improving the accuracy of the smart cockpit's inference of user preferences and further reducing the need for manual settings by the user.

[0063] Furthermore, during the driving process of the above-mentioned smart cockpit, the above-mentioned cockpit domain controller can also better obtain the driving data of the smart cockpit such as the driving speed and gyroscope information, and correct and update at least one preference tag according to the driving data to further adjust the personalized settings of the seats, lights, air conditioning and / or infotainment system.

[0064] For example, in response to the driving data indicating that the smart cockpit is in a bumpy state, the cockpit domain controller can reduce the value of the up and down height offset tag related to the seat setting, thereby reducing the bumps by lowering the seat height.

[0065] For another example, in response to driving data indicating that the smart cockpit is in a high-speed state, the cockpit domain controller can increase the value of the brightness tag related to the lighting setting, thereby preventing the driver from falling asleep by increasing the cabin brightness.

[0066] For another example, in response to driving data indicating that the smart cockpit is approaching a sharp turn, the cockpit domain controller can activate the strobe mode tag for the lighting setting, and adjust the value of the lighting frequency tag according to the vehicle speed and / or critical distance, thereby reminding the driver to slow down by strobing the interior lights. Afterwards, during the driving process of the smart cockpit, the seat, lighting, air conditioning and / or infotainment system are adjusted according to the modified at least one preference tag for personalized settings.

[0067] In summary, the control method of the smart cockpit, the smart cockpit, the autonomous driving vehicle and the computer-readable storage medium provided by the present invention can infer the personal preferences of the user outside the cabin by analyzing the vital signs of the user, so as to personalize the seats, lights, air conditioning, infotainment system and other equipment in the smart cockpit in advance, thereby completing the personalized settings that meet the user's personal preferences before the user enters the smart cockpit, and greatly reducing the need for manual settings of the smart cockpit, thereby improving the user experience.

[0068] Although the above methods are illustrated and described as a series of actions for simplicity of explanation, it should be understood and appreciated that these methods are not limited by the order of the actions, because according to one or more embodiments, some actions may occur in a different order and / or concurrently with other actions from those illustrated and described herein or not illustrated and described herein but understandable to those skilled in the art.

[0069] Those skilled in the art will appreciate that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips cited throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0070] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. The technician may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0071] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in cooperation with a DSP core, or any other such configuration.

[0072] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling a smart cockpit, characterized in that: The following steps are involved: Acquire and analyze a first physical sign image of a target user outside the cabin to determine first physical features of the target user in multiple dimensions; Parsing the first physical feature via a pre-trained first model to determine at least one preference tag of the target user; as well as According to the at least one preference tag, multiple devices in the smart cockpit are personalized.

2. The control method according to claim 1, characterized in that: The step of acquiring and analyzing the first physical sign image of the target user outside the cabin to determine the first physical features of the target user in multiple dimensions includes: Acquire and analyze a first vital sign image of a person outside the cabin to determine a motion trend characteristic of the person outside the cabin; According to the motion trend characteristics, determining the intention of the person outside the cabin to enter the smart cockpit; In response to the person outside the cabin having an intention to enter the smart cockpit, the person outside the cabin is determined as the target user, and the first vital sign image is analyzed to determine first physical features of the target user in multiple dimensions.

3. The control method according to claim 2, characterized in that: At least one external camera is disposed outside the smart cockpit, and the step of acquiring and analyzing a first vital sign image of a person outside the cabin to determine a motion trend feature of the person outside the cabin comprises: Detecting moving objects in a first detection range outside the cabin via the vehicle-mounted radar; In response to a detection result that a moving object exists within the first detection range, starting the external camera to capture an image of the moving object; Extracting motion trend features of a human body from the image of the moving object; and An image containing at least one of the motion trend features is determined as a first vital sign image of a person outside the cabin, and the at least one of the motion trend features is determined as a motion trend feature of the person outside the cabin.

4. The control method according to claim 3, characterized in that: The smart cockpit is provided with a plurality of external cameras outside, wherein each of the external cameras corresponds to a second detection range, and in response to a detection result that a moving object exists within the first detection range, the step of starting the external camera to collect an image of the moving object comprises: In response to a detection result indicating that a moving object exists within the first detection range, a corresponding external camera is activated to capture an image of a corresponding second detection range according to a position of the moving object.

5. The control method according to claim 4, characterized in that: The external cameras are respectively arranged on the left rearview mirror, the right rearview mirror, the left B-pillar and / or the right B-pillar of the smart cockpit to respectively collect images of a second detection range close to the left front door, the right front door, the left rear door and / or the right rear door of the smart cockpit, and / or The external camera is selected from a 3D TOF camera, or a combination of a 2D camera and a TOF sensor, and is used to capture images with depth information.

6. The control method according to claim 1, characterized in that: The first vital sign image includes RGB information of a plurality of pixels and corresponding depth information. The step of analyzing the first vital sign image to determine the first physical features of the target user in multiple dimensions includes: Through the pre-trained second model, feature extraction is performed on the RGB information and depth information of each pixel in the first vital sign image to determine the first physical features of the target user in multiple dimensions, wherein the first physical features in multiple dimensions are selected from at least one of height, weight, body proportions, gender, age, clothing, and personal belongings.

7. The control method according to claim 6, characterized in that: The plurality of devices in the smart cockpit include at least one of a seat, a light, an air conditioner, and an infotainment system. The step of parsing the first physical feature via a pre-trained first model to determine at least one preference tag of the target user includes: Determine at least one preference tag of the target user regarding seat settings based on a first physical feature in terms of height, weight, body proportions, and / or belongings; and / or At least one preference tag of the target user regarding lighting settings, air conditioning settings and / or infotainment system settings is determined based on the first physical features in gender dimension, age dimension and / or clothing dimension.

8. The control method according to claim 7, characterized in that: The first physical feature of the carry-on dimension includes item type information and / or item size information, wherein the item type information indicates luggage and / or pets, and the item size information indicates the space size of the corresponding carry-on.

9. The control method according to claim 7, characterized in that: At least one preference tag about the seat setting is selected from at least one of a front-to-back position offset tag, a top-to-bottom height offset tag, a backrest tilt angle tag, and / or At least one preference tag about the light setting is selected from at least one of a light position tag, a light frequency tag, a color temperature tag, and a brightness tag, and / or At least one preference tag for the air conditioning setting is selected from at least one of a temperature tag, a wind speed tag, a wind direction tag, a cycle mode tag, and / or At least one preference tag set for the infotainment system is selected from at least one of a recommended playlist tag, a recommended video tag, a recommended game tag, and a volume tag.

10. The control method according to claim 1, characterized in that: The interior of the smart cockpit is also provided with at least one internal camera, and the control method further comprises the following steps: In response to the target user entering the smart cockpit, acquiring a second vital sign image of the target user via the at least one internal camera; updating at least one preference tag of the target user according to the second vital sign image; and During the driving of the smart cockpit, the personalized settings of the seat, the lighting, the air conditioning and / or the infotainment system are dynamically adjusted according to the updated at least one preference tag.

Images