Vehicle control methods, devices, electronic equipment and vehicles

Abstract

This application relates to the field of vehicle technology and discloses a vehicle control method, device, electronic device, and vehicle. The method includes: in response to detecting an authorized user approaching the vehicle, acquiring visual information of the authorized user and the luggage carried by the authorized user; determining the outer geometric dimensions of the luggage based on the visual information, and comparing the outer geometric dimensions with the preset loading space dimensions of the vehicle's trunk; if the outer geometric dimensions are larger than the preset loading space dimensions of the trunk, controlling the rear seats to fold down and opening the trunk lid. The technical solution of this application solves the problems of difficult trunk opening operation and poor user experience in related technologies, improving the convenience of trunk opening and the user experience.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, specifically to vehicle control methods, devices, electronic equipment, and vehicles. Background Technology

[0002] In related technologies, vehicle trunk opening methods mainly include manual switches, remote keys, and "kick-to-open" sensors. These operations are extremely inconvenient when the user's hands are occupied or when carrying large luggage. Furthermore, the "kick-to-open" method suffers from problems such as difficulty in locating the sensor and instability when standing on one leg. While some related technologies propose automatically opening the trunk via mobile signal or image recognition, they can only determine if luggage is being carried, not its specific dimensions. When luggage is too large, the user still needs to manually fold down the seats to load it, making the process cumbersome.

[0003] In other words, the relevant technology suffers from problems such as difficulty in opening the trunk and a poor user experience. Summary of the Invention

[0004] This application provides a vehicle control method, device, electronic device, and vehicle to solve the problems of difficult trunk opening and poor user experience in related technologies.

[0005] In a first aspect, this application provides a vehicle control method, the method comprising: In response to detecting an authorized user approaching the vehicle, visual information about the authorized user and the luggage carried by the authorized user is obtained; The external geometric dimensions of the luggage are determined based on visual information, and the external geometric dimensions are compared with the preset loading space dimensions of the vehicle's trunk. If the external geometric dimensions are larger than the preset loading space dimensions of the trunk, the rear seats will be folded down and the trunk lid will be opened.

[0006] In one alternative implementation, detecting an authorized user approaching the vehicle includes: Control the vehicle to emit detection signals; In response to the authorized user's sensing device receiving the detection signal and sending a response signal, the location and device identification of the sensing device are confirmed; The distance between the location and the vehicle's parking position is calculated as the sensing distance. If the sensing distance is less than or equal to a preset distance threshold and the device identifier is valid, an authorized user is detected approaching the vehicle.

[0007] In one alternative implementation, obtaining visual information about the authorized user and the luggage carried by the authorized user includes: The system uses a binocular camera system to capture stereo images of the authorized user and their luggage.

[0008] In one alternative implementation, determining the external geometric dimensions of the luggage based on visual information includes: Biometric identification is performed based on facial image information from 3D image alignment to verify the user's authorized identity for a secondary purpose; Based on stereo image pairs, the target items corresponding to luggage in the image are identified by an object recognition model; The stereoscopic dimensions of the target object are calculated based on the baseline distance of the binocular camera system, and the stereoscopic dimensions are used as the outer geometric dimensions.

[0009] In one alternative implementation, after comparing the external geometry with the vehicle's preset cargo space dimensions, the method further includes: If the external geometric dimensions are less than or equal to the preset loading space dimensions of the trunk, the trunk lid will be opened and the vehicle's height will be lowered.

[0010] In one alternative implementation, controlling the rear seats to fold down and open the trunk lid includes: The vehicle's cabin domain controller sends a folding command to the rear seat control unit to fold down the rear seats, creating a flat surface with the trunk carpet for loading large items. The vehicle's body domain controller sends an opening command to the trunk control unit to drive the trunk lid open.

[0011] In one alternative implementation, before acquiring visual information about the authorized user and the luggage carried by the authorized user, the method further includes: The environmental conditions, including ambient brightness and rainfall, are detected by a light sensor and / or a rain sensor. If the environmental conditions meet at least one of the following conditions: ambient brightness is less than a first threshold or rainfall is greater than a second threshold, then the vehicle's body domain controller sends a light-on command to turn on the lights.

[0012] Secondly, this application provides a vehicle control device, the device comprising: The acquisition module is used to acquire visual information about the authorized user and the luggage carried by the authorized user in response to the detection that an authorized user is approaching the vehicle; The comparison module is used to determine the external geometric dimensions of luggage based on visual information and compare the external geometric dimensions with the preset loading space dimensions of the vehicle's trunk; The trunk adjustment module is used to fold down the rear seats and open the trunk lid if the external geometric dimensions are larger than the preset loading space dimensions of the trunk.

[0013] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle control method of the first aspect or any corresponding embodiment described above.

[0014] Fourthly, this application provides a vehicle including a controller, the controller including a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the vehicle control method of the first aspect or any corresponding embodiment described above.

[0015] This application provides a vehicle control method that, compared to existing technologies, achieves the following beneficial technical effects: In response to detecting an authorized user approaching the vehicle, visual information of the authorized user and their luggage is acquired, enabling intelligent perception of the user's journey from approaching the vehicle to carrying luggage, providing accurate visual basis for subsequent identification of luggage size and user identity; based on the visual information, the external geometric dimensions of the luggage are determined, and these dimensions are compared with the vehicle's preset loading space dimensions in the trunk, enabling precise measurement of the luggage's three-dimensional dimensions. By comparing these dimensions with the trunk's volume, loading requirements are predicted, allowing for dynamic expansion of the trunk's loading capacity; if the external geometric dimensions are larger than the preset loading space dimensions in the trunk, the rear seats are folded down and the trunk lid is opened, realizing an intelligent welcoming function for the trunk. The vehicle's status is automatically adjusted according to the luggage size (opening the trunk, lowering the vehicle body, or folding down the seats), eliminating the need for manual operation or specific actions by the user, significantly improving the convenience and user experience of loading luggage. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a vehicle control method according to an embodiment of this application; Figure 2 This is a flowchart of another vehicle control method according to an embodiment of this application; Figure 3 This is a schematic diagram of another vehicle control process according to an embodiment of this application; Figure 4 This is a structural block diagram of a vehicle control device according to an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0021] As automotive intelligence continues to improve, users are placing increasingly higher demands on the ease of use of vehicle trunks. As the primary storage space in a vehicle, the ease of opening the trunk directly impacts the user experience.

[0022] Currently, trunk opening methods in related technologies mainly include manual switch start, remote key start, and millimeter-wave radar sensor start (commonly known as "one-kick start"). However, these traditional opening methods have many inconveniences in practical use. When the user's hands are occupied (e.g., carrying large luggage, shopping bags, etc.), manually opening the trunk or finding the remote key in their pocket becomes extremely difficult. For "one-kick" sensor start, the user not only needs to make an accurate kicking motion in a specific area, but also often fails to open the trunk due to difficulty in finding the sensor location; more importantly, when the user is carrying large items, standing on one leg and maintaining balance is a challenge in itself, making this function difficult to use when the user needs it most.

[0023] To address the aforementioned issues, some intelligent trunk control solutions have been proposed in related technologies. For example, one solution uses the signal from a mobile device carried by the user to determine the user's distance and automatically opens the trunk when the user approaches the vehicle; another solution uses an onboard camera to capture images and identify whether the user is carrying luggage, thus automatically opening the trunk. However, these solutions can only determine if the user is "carrying luggage," but cannot determine the specific size of the luggage. When the luggage is large and exceeds the trunk's capacity, the user still needs to manually adjust and fold down the rear seats after the trunk is opened before placing the luggage in, making the process cumbersome. Furthermore, these technical solutions cannot adaptively adjust the vehicle's configuration according to the user's actual loading needs, such as lowering the vehicle height to facilitate the transport of heavy items, leaving considerable room for improvement in trunk space utilization and ease of use.

[0024] It is evident that the trunk control methods in related technologies suffer from operational difficulties, insufficient intelligence, and poor user experience when users are carrying luggage, making it difficult to meet the growing user demands.

[0025] According to an embodiment of this application, a vehicle control method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] This embodiment provides a vehicle control method that can be used in the vehicle's central domain controller. Figure 1 This is a flowchart of a vehicle control method according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps: Step S101: In response to detecting that an authorized user is approaching the vehicle, visual information about the authorized user and the luggage carried by the authorized user is obtained.

[0027] Specifically, an authorized user refers to a user who has been authorized and authenticated by the vehicle, such as a vehicle owner or authorized user carrying a valid smart key and passing facial recognition. Visual information includes image data containing the user and their luggage acquired through image acquisition devices, such as stereo image pairs acquired by a binocular camera system, which can be used for subsequent identity verification and luggage size measurement.

[0028] In this step, visual information is actively collected when an authorized user is detected approaching the vehicle, enabling initial perception of the user and luggage. This timely capture of the user's approach provides a foundation for accurate identification of luggage size and user identity, avoiding the inconvenience of manual operation by the user.

[0029] In one possible implementation, the vehicle continuously transmits detection signals via a low-frequency antenna while locked. When the smart key carried by the user enters the sensing range and returns a response signal, the key is confirmed to be valid and the distance meets a preset threshold. Then, the binocular camera system is activated to collect image information containing the user and luggage.

[0030] Step S102: Determine the outer geometric dimensions of the luggage based on visual information, and compare the outer geometric dimensions with the preset loading space dimensions of the vehicle's trunk.

[0031] Specifically, the external geometric dimensions refer to the three-dimensional spatial dimensions of luggage calculated using visual information, including the length, width, and height of the luggage. For example, by combining triangulation with a binocular camera system and deep learning algorithms, the length, width, and height data of items such as suitcases and backpacks can be accurately calculated. The preset loading space dimensions of the trunk refer to the usable loading space dimensions of the vehicle's trunk in its default state, as well as the expanded loading space dimensions after the rear seats are folded down. For example, the standard trunk volume length, width, and height preset at the factory, and the expanded space dimensions formed by the rear seats folded down and the trunk carpet.

[0032] In this step, based on the collected visual information, a stereo vision algorithm is used to accurately calculate the three-dimensional dimensions of the luggage and compare them with the pre-stored loading space dimensions in the vehicle's trunk. Through precise size measurement and intelligent comparison, it is possible to accurately predict whether the luggage can fit in the trunk, providing a basis for decision-making for subsequent differentiated control and avoiding secondary operations caused by excessively large luggage.

[0033] In one possible implementation, the external geometric dimensions of the luggage are calculated using triangulation based on stereo image pairs acquired by a binocular camera system. Simultaneously, the pre-stored preset loading space dimensions of the trunk are retrieved from the vehicle information computing center. The external geometric dimensions are compared with the preset loading space dimensions of the trunk, and the comparison result is output for subsequent control decisions.

[0034] Step S103: If the outer geometric dimensions are greater than the preset loading space dimensions of the trunk, then control the rear seats to fold down and open the trunk lid.

[0035] Specifically, the trunk lid refers to the cover structure at the rear of a vehicle used to close and open the trunk storage space, usually driven by an electric strut or hydraulic rod to achieve automatic opening and closing. Rear seats refer to the seats in the back of a vehicle for passengers, typically designed to fold down to form a continuous flat surface with the trunk carpet, thus expanding loading space.

[0036] In this step, differentiated vehicle control is implemented based on a comparison between the luggage's external geometric dimensions and the preset loading space dimensions in the trunk: when the external geometric dimensions exceed the preset loading space dimensions in the trunk, the rear seats are folded down first to expand the space, and then the trunk lid is opened. This achieves dynamic adjustment of the vehicle's loading status according to the size of the luggage, allowing users to obtain a suitable loading space without manual operation, significantly improving the user experience.

[0037] In one possible implementation, when the outer geometry is determined to be larger than the preset loading space size of the trunk, the intelligent driving domain controller first sends a folding command to the rear seat control unit, so that the rear seats automatically fold flat to form an extended plane with the trunk carpet, and then triggers the trunk lid to open.

[0038] In response to the detection of an authorized user approaching the vehicle, the system acquires visual information about the authorized user and their luggage, enabling intelligent perception of the user's journey from approaching the vehicle to carrying luggage. This provides accurate visual information for subsequent identification of luggage size and user identity. Based on the visual information, the system determines the external geometric dimensions of the luggage and compares these dimensions with the preset loading space dimensions in the trunk. This allows for precise measurement of the luggage's three-dimensional dimensions and prediction of loading needs by comparing them with the preset loading space dimensions, enabling dynamic expansion of the trunk's loading capacity. If the external geometric dimensions are larger than the preset loading space dimensions in the trunk, the system controls the rear seats to fold down and the trunk lid to open, achieving an intelligent welcome function for the trunk. The system automatically adjusts the vehicle's status (opening the trunk, lowering the vehicle body, or folding down the seats) according to the size of the luggage, without requiring manual operation or specific actions from the user, significantly improving the convenience and user experience of loading luggage.

[0039] This embodiment provides a vehicle control method that can be used in the vehicle's central domain controller. Figure 2 This is a flowchart of another vehicle control method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps: Step S201: In response to detecting that an authorized user is approaching the vehicle, visual information about the authorized user and the luggage carried by the authorized user is obtained.

[0040] Specifically, the detection of an authorized user approaching the vehicle in step S201 above includes the following steps: Step S2011: Control the vehicle to transmit a detection signal.

[0041] Specifically, the detection signal refers to the wireless signal actively emitted by the vehicle to identify authorized users, used to wake up and locate the sensing devices carried by the user. For example, the vehicle continuously emits a 125kHz low-frequency detection signal through a low-frequency antenna arranged inside the vehicle, forming a specific sensing area.

[0042] In this step, the vehicle actively emits detection signals to search for the presence of sensors in the surrounding area. This enables proactive detection of authorized users approaching the vehicle, providing a foundation for subsequent identity verification and distance determination, without requiring any active user intervention.

[0043] In one possible implementation, when the vehicle is locked, it periodically emits low-frequency detection signals through low-frequency antennas around the vehicle body, forming a sensing area with a radius of about 5-10 meters around the vehicle. When the user enters the area with the smart key, the key is activated and ready to respond.

[0044] Step S2012: In response to the authorized user's sensing device receiving the detection signal and sending a response signal, the location and device identifier of the sensing device are confirmed.

[0045] Specifically, a sensing device refers to an authentication device carried by the user that can wirelessly communicate with the vehicle, such as a smart key or a digital key module in a smartphone. A response signal is a wireless signal, typically a radio frequency signal, that the sensing device sends back to the vehicle after receiving a detection signal, containing device information and status data. Location refers to the relative coordinates of the sensing device relative to the vehicle, calculated using techniques such as signal strength, time of arrival, or angle of arrival. Device identification is a unique identifier built into the sensing device, used by the vehicle to verify the device's legitimacy and authorization level; examples include a key identification number (ID) or a digital certificate.

[0046] In this step, the response signal returned by the sensing device is received, and the device identifier and location information are extracted from it. This verifies the legitimacy of the user's identity and accurately locates their position, ensuring that subsequent visual data acquisition is only triggered when an authorized user is within a specific area, thus avoiding false triggering.

[0047] In one possible implementation, after receiving a low-frequency signal, the smart key sends a response signal containing the key ID and status information to the vehicle via a radio frequency link. The vehicle key's response signal is received by the communication module of the central domain controller, which calculates the key's current location based on signal strength or arrival time and verifies whether the key ID is in the registered list. If the verification is successful and the location is within a preset range, a trigger signal is sent to the intelligent driving domain controller to activate the binocular camera system.

[0048] Step S2013: Calculate the distance between the location and the vehicle's parking location as the sensing distance. If the sensing distance is less than or equal to a preset distance threshold and the device identifier is valid, then an authorized user is detected approaching the vehicle.

[0049] Specifically, the parking location refers to the vehicle's current spatial coordinates, usually based on the vehicle's center point or antenna position. The sensing distance is the calculated straight-line distance between the location and the parking location, used to determine if the user has entered the preset trigger area. The preset distance threshold is a pre-set distance limit for determining if a user is "approaching" the vehicle; for example, it can be set to 1.5 meters to 3 meters, and the specific value can be adjusted according to the vehicle model or user habits.

[0050] In this step, the calculated sensing distance is compared with a preset threshold, and the validity of the device identifier is considered to ultimately confirm whether the authorized user has approached the vehicle. This dual approach of distance threshold and authentication ensures that subsequent services are only triggered when the authorized user is actually close, avoiding false triggers and invalid wake-ups, thus improving system accuracy and user experience.

[0051] In one possible implementation, after the vehicle key enters the vehicle's sensing range, the distance between the smart key's current position and the vehicle is calculated to be 2 meters, while the preset distance threshold is 2.5 meters. At the same time, if the key ID verification is successful, it is determined that an authorized user has been detected approaching the vehicle, and the visual acquisition module is then triggered to start working.

[0052] Specifically, the visual information of the authorized user and the luggage carried by the authorized user in step S201 above includes the following steps: Step S2014: Acquire stereoscopic image pairs containing the authorized user and the luggage carried by the authorized user through a binocular camera system.

[0053] Specifically, a binocular camera system refers to a stereoscopic vision acquisition device composed of two independent cameras installed at a certain distance, simulating the principle of human binocular vision to acquire depth information of a scene. For example, a binocular camera module installed at the rear or roof of a vehicle can acquire stereoscopic images of the area behind the vehicle in real time. A stereoscopic image pair refers to a pair of images simultaneously acquired by the binocular camera system from the left and right perspectives. By calculating the parallax between these two images, the three-dimensional information of objects in the scene can be reconstructed.

[0054] In this step, a binocular camera system simultaneously acquires left and right-view images of the user and their luggage, forming a stereo image pair to provide raw data for subsequent stereoscopic dimension measurements. Utilizing the principle of binocular vision to obtain depth information allows for accurate reconstruction of the luggage's three-dimensional shape, providing a high-precision foundation for dimension calculations.

[0055] In one possible implementation, after receiving a trigger signal, the intelligent driving domain controller activates the binocular camera system at the rear of the vehicle. The left and right cameras simultaneously capture images of the user and their luggage, generating a pair of stereo images with a resolution of 1920x1080, which are then transmitted in real time to the image processing unit for subsequent analysis.

[0056] It should be noted that obtaining visual information about authorized users and their luggage can be achieved not only through binocular camera systems, but also through other image acquisition methods capable of acquiring depth information. For example, a Time-of-Flight (ToF) camera can directly acquire a depth map by emitting infrared light pulses and measuring the reflection time. Alternatively, a depth camera can be used to acquire 3D point cloud data through structured light or infrared speckle projection, or a fusion scheme combining a monocular camera with millimeter-wave radar / ultrasonic radar can be used to estimate object dimensions using radar ranging data assisted by the monocular image. All these methods can acquire visual information and depth information about the user and luggage, and all fall within the scope of protection of this application.

[0057] Step S202: Determine the external geometric dimensions of the luggage based on visual information, and compare the external geometric dimensions with the preset loading space dimensions of the vehicle's trunk.

[0058] Specifically, in this step, based on the visual information obtained in step S201, the three-dimensional dimensions of the luggage are accurately calculated using image processing and stereo vision algorithms. This data is then compared with the preset loading space dimensions of the trunk stored in the vehicle system. By utilizing the depth perception capability of binocular vision to obtain the precise length, width, and height dimensions of the luggage, and through intelligent comparison with the trunk volume, it is possible to accurately predict whether the luggage can be accommodated, providing a reliable basis for subsequent differentiated control and avoiding invalid operations or secondary adjustments due to size misjudgments.

[0059] In one possible implementation, after receiving stereo image pairs from a binocular camera system, the intelligent driving domain controller first identifies the luggage area in the image using a deep learning model. Then, it uses triangulation to calculate the disparity of each pixel in the luggage area, thereby reconstructing the three-dimensional point cloud data of the luggage and extracting its maximum length, width, and height. Subsequently, the controller retrieves the vehicle's factory-preset standard trunk volume dimensions (e.g., 100cm x 80cm x 50cm) and the expanded volume dimensions after folding down the rear seats (e.g., 150cm x 80cm x 50cm) from the information computing center. It then compares the calculated luggage dimensions with the sum of these two volume dimensions and outputs the comparison result.

[0060] Specifically, step S202 above, which determines the external geometric dimensions of the luggage based on visual information, includes the following steps: Step S2021: Perform biometric identification based on the facial image information in the stereo image pair to verify the user's authorized identity for a second time.

[0061] Specifically, based on facial image information from a 3D image pair containing the user's image, facial recognition technology extracts facial features and compares them with pre-stored authorized user information to confirm whether the current user is a legitimate authorized user. This adds an identity verification step before triggering the trunk control, ensuring that only authorized users can enjoy the intelligent welcome service, preventing unauthorized triggering by strangers, and improving vehicle security and user experience.

[0062] In one possible implementation, the left eye image from the stereo image pair acquired by the binocular camera system is input into the face recognition module. The module first detects the face region in the image, extracts the face feature vector, and then compares the feature vector with the authorized user face database pre-stored in the information computing center. If the similarity exceeds a preset threshold (e.g., 95%), the current user's authorized identity is confirmed, and their corresponding permission level and personal settings preferences are obtained.

[0063] Step S2022: Based on the stereo image pair, the target item corresponding to the luggage in the image is identified by the object recognition model.

[0064] Specifically, an object recognition model refers to a deep learning neural network model trained on a large number of labeled images, capable of identifying and locating target objects of a specific category from images, such as luggage, backpacks, and suitcases. The target object refers to the image region identified by the object recognition model as luggage carried by the user, typically marked with bounding boxes or segmentation masks.

[0065] In this step, the stereo image is compared with the input object recognition model, which automatically identifies and selects the target item area belonging to luggage in the image. Utilizing the powerful recognition capabilities of deep learning models, luggage targets can be accurately separated from complex backgrounds, providing a precise input area for subsequent accurate size measurements and avoiding background interference.

[0066] In one possible implementation, stereo images captured by a binocular camera system are input into a pre-trained YOLO or Faster R-CNN object recognition model. The model detects items such as suitcases, backpacks, and cardboard boxes in the images and outputs the location coordinates and confidence score of each target item in the form of a bounding box. The system filters based on the confidence score, selecting the target with the highest confidence score as the user's luggage, and extracts the corresponding region of this target in the left and right images for subsequent size calculations.

[0067] Step S2023: Calculate the three-dimensional size of the target object based on the baseline distance of the binocular camera system, obtain the three-dimensional size of the target object, and use the three-dimensional size as the outer geometric size.

[0068] Specifically, the baseline distance of a binocular camera system refers to the horizontal straight-line distance between the optical centers of the left and right cameras. Based on the baseline distance of the binocular camera system, triangulation is used to calculate the three-dimensional dimensions of a target object. Triangulation is a method based on the principle of binocular vision, utilizing the parallax created when the left and right cameras capture the same object, and calculating the object's three-dimensional spatial coordinates through geometric relationships. Specifically, given the focal lengths and baseline distance of the two cameras, by matching the pixel coordinate differences (i.e., parallax) of the same object point in the left and right images, the depth information of that point can be calculated, thereby reconstructing the object's three-dimensional dimensions.

[0069] In this step, for the identified luggage target area, feature points are matched in the stereo image pair, the disparity value of each point is calculated, and the three-dimensional point cloud or outline of the luggage is reconstructed using the principle of triangulation, thereby calculating the length, width, and height dimensions of the luggage. Obtaining accurate stereo dimensions of the luggage provides reliable data for comparison with the trunk volume and is a core technological support for realizing intelligent loading decisions.

[0070] In one possible implementation, for the luggage area selected in step S2022, scale-invariant feature transform (SIFT) or oriented fast and rotated brief (ORB) feature points are extracted from the left and right images and stereo matching is performed to obtain the disparity of the matched point pairs. Based on the calibration parameters (focal length, baseline distance) of the binocular cameras, the 3D coordinates of each matched point are calculated using the principle of similar triangles. Statistical analysis is performed on the 3D coordinates of all points within the luggage area. After removing outliers, the differences between the maximum and minimum values ​​of the coordinates in the X, Y, and Z directions are taken as the length, height, and width of the luggage, respectively, to obtain the final stereo dimensions.

[0071] Specifically, step S202, which compares the external geometric dimensions with the preset loading space dimensions of the vehicle's trunk, is step S2024. For details of this step, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0072] In step S203, if the outer geometric dimensions are greater than the preset loading space dimensions, the rear seats are folded down and the trunk lid is opened.

[0073] Specifically, step S203 above, which involves folding down the rear seats and opening the trunk lid, includes the following steps: In step S2031, the vehicle's cabin domain controller sends a folding command to the rear seat control unit to control the rear seats to fold down, forming a flat surface with the trunk carpet for loading large items.

[0074] Specifically, the cockpit domain controller refers to the electronic control unit that integrates the vehicle's intelligent cockpit functions, responsible for managing and coordinating cabin comfort and interactive functions such as the in-vehicle infotainment system, instrument display, rear seat controls, air conditioning, and ambient lighting. The rear seat control unit is a dedicated actuator controller for controlling the electric adjustment, folding, and repositioning of the rear seats, typically integrated within the seat or directly driven by the cockpit domain controller. A folding command is a control signal sent from the cockpit domain controller to the rear seat control unit to trigger the folding action of the rear seats, usually containing target angle and speed parameters. The trunk carpet is a cover laid at the bottom of the trunk; when the rear seats are folded down, it forms a continuous, flat surface with the trunk carpet, facilitating the loading of extra-long or large items.

[0075] In this step, when the luggage size is determined to be larger than the trunk volume, a folding command is sent to the rear seat control unit via the cabin domain controller. This controls the rear seats to automatically fold down, creating an expanded loading surface with the trunk carpet. This automatic expansion of the trunk loading space allows users to obtain greater loading capacity without manually folding down the seats. It is particularly suitable for transporting large luggage that exceeds the standard trunk volume, significantly improving loading convenience and space utilization.

[0076] In one possible implementation, the intelligent driving domain controller determines that the seats need to be folded down based on size comparison results, and then sends a seat folding request to the cockpit domain controller via CAN or Ethernet. The cockpit domain controller, based on the current seat status and safety checks (such as detecting whether there are passengers or items in the rear seats), sends a folding command to the rear seat control unit after confirming safety. The seat control unit then drives the electric motor to fold the rear seat backs forward to a horizontal position, making the backrests flush with the trunk carpet, forming a continuous loading platform with extended length.

[0077] In step S2032, the vehicle's body domain controller sends an opening command to the trunk control unit to drive the trunk lid to open.

[0078] Specifically, a body domain controller refers to an electronic control unit that integrates vehicle body-related function controls, responsible for managing and coordinating the execution of body accessories such as doors, windows, trunk, and lights. Examples include the vehicle's Body Control Module (BCM) or a regionally integrated body domain controller. A trunk control unit is a dedicated actuator controller for controlling the opening and closing of the trunk lid, typically including a drive motor, strut controller, or lock mechanism controller. An opening command is a control signal sent from the body domain controller to the trunk control unit to trigger the trunk lid to open, usually transmitted via Controller Area Network (CAN) or Local Interconnect Network (LIN) bus protocols.

[0079] In this step, when the overall dimensions of the luggage are determined to be less than or equal to the preset loading space dimensions of the trunk, an opening command is sent to the trunk control unit via the vehicle domain controller, driving the trunk lid to open automatically. This achieves automatic opening of the trunk lid, eliminating the need for manual operation by the user and improving the convenience of loading luggage.

[0080] The vehicle control method of this application first detects and confirms the identity of an authorized user approaching the vehicle through low-frequency antenna detection and smart key response; then, it triggers a binocular camera system to acquire stereo images of the user and luggage; based on facial recognition to confirm user authorization, it locates the luggage area using an object recognition model, and accurately calculates the outer geometric dimensions of the luggage using triangulation based on the baseline distance of the binocular camera system; it compares the outer geometric dimensions with the preset loading space dimensions of the trunk; and it performs differentiated control based on the comparison results—if the outer geometric dimensions are less than or equal to the preset loading space dimensions of the trunk, it controls the trunk lid to open and simultaneously lowers the air suspension to reduce the vehicle height; if the outer geometric dimensions are greater than the preset loading space dimensions of the trunk, it first controls the rear seats to automatically fold down to form an extended loading surface with the trunk carpet, and then opens the trunk lid. Through multi-sensor fusion and cross-domain collaborative control, a fully intelligent service is achieved from the user's approach to luggage loading. It can accurately sense luggage size and predict loading needs, automatically adjusting the vehicle status to accommodate luggage of different sizes. Users can complete the loading of large luggage without manual operation or specific actions, significantly improving the convenience and intelligence of the trunk and optimizing the user experience.

[0081] In some optional implementations, prior to obtaining visual information about the authorized user and the luggage carried by the authorized user in step S201 above, the method further includes: Step a1: Detect the environmental conditions using a light sensor and / or a rain sensor. The environmental conditions include ambient brightness and rainfall.

[0082] Specifically, a light sensor is a photosensitive element installed on the inside of a vehicle's windshield or dashboard to detect ambient light intensity. Examples include photodiodes or photoresistors, which output a numerical value for the current illuminance. A rain sensor is an optical sensor typically integrated into the inside of the windshield. It uses the principle of infrared light reflection on the glass surface to detect the size and density of raindrops, thereby determining the rainfall intensity. Environmental conditions refer to the current external environmental parameters collected by the light and rain sensors, including ambient brightness (in lux) and rainfall (in mm / h or the level signal output by the sensor).

[0083] In this step, before performing visual information acquisition, the ambient environment around the vehicle is detected in real time using light and rain sensors to obtain data on ambient brightness and rainfall. This advance awareness of current environmental conditions provides a basis for determining whether auxiliary lighting needs to be activated later, ensuring the visual acquisition system can function normally even in harsh environments.

[0084] In one possible implementation, after the vehicle starts the trunk control system, the body domain controller first reads the illuminance value (e.g., 50 lux) output by the light sensor behind the windshield, and at the same time reads the rainfall intensity level (e.g., moderate rainfall, corresponding to the intermittent wiper setting) output by the rain sensor. These two data are temporarily stored as environmental state parameters for subsequent threshold determination.

[0085] Step a2: If the environmental conditions meet at least one of the following: ambient brightness is less than a first threshold and rainfall is greater than a second threshold, then the vehicle's body domain controller sends a light-on command to turn on the lights.

[0086] Specifically, the first threshold refers to a pre-set critical value used to determine whether the ambient brightness is too low, such as 50 lux or 100 lux. Below this value, it is determined that the light is insufficient and auxiliary lighting is needed. The second threshold refers to a pre-set critical value used to determine whether the rainfall is too heavy, such as the moderate rainfall intensity corresponding to the output signal of the rain sensor. Above this value, it is determined that the weather is severe and auxiliary lighting is needed. The light-on command refers to the control signal sent by the vehicle domain controller to the vehicle lighting control unit to trigger the external lights (such as headlights, fog lights, or welcome lights) to be turned on.

[0087] In this step, the detected environmental conditions are compared with preset thresholds. If the ambient brightness is lower than the first threshold or the rainfall is higher than the second threshold, indicating that the current ambient light is dim or the weather is bad, a light-on command is sent through the vehicle domain controller to automatically turn on the vehicle lights. This proactive illumination in adverse environments such as nighttime, underground parking lots, and rain / fog not only facilitates clear images for the binocular camera system but also provides users with a better field of vision when carrying luggage, improving safety and user experience.

[0088] In one possible implementation, the vehicle domain controller determines that the brightness value output by the light sensor is 30 lux, which is lower than a preset first threshold (50 lux), thus meeting the activation condition. It then sends a headlight activation command to the lighting control unit via the CAN bus to turn on the low beam headlights. If the rainfall is detected to exceed a second threshold at the same time, the fog lights can also be turned on or the light duration can be extended to ensure that the user and the camera system receive sufficient illumination.

[0089] In an optional implementation, after step S202, the method further includes: If the external geometric dimensions are less than or equal to the preset loading space dimensions of the trunk, the trunk lid will be opened and the vehicle's height will be lowered.

[0090] Specifically, vehicle height refers to the vertical distance between the vehicle chassis and the ground. It can be adjusted through the air suspension system to lower the vehicle height, making it easier for users to load and unload heavy objects.

[0091] If the external geometric dimensions of the luggage are less than or equal to the preset loading space dimensions of the trunk, it means that the current volume of the luggage can be accommodated in the trunk space. In this case, the trunk lid will be opened and the vehicle height will be lowered so that the user can put the luggage into the trunk more easily.

[0092] In one possible example, the intelligent driving domain controller sends the comparison result and the opening command to the body domain controller via the CAN bus. After parsing the command, the body domain controller sends a pulse width modulation (PWM) signal or a relay control signal to the trunk control unit to activate the trunk electric strut motor and drive the trunk lid to open smoothly to the preset height.

[0093] The chassis domain controller that controls the vehicle sends a lowering command to the air suspension control unit to trigger the air suspension system to lower the vehicle height.

[0094] When the luggage dimensions are determined to be less than or equal to the trunk volume, a lowering command is sent to the air suspension control unit via the chassis domain controller, triggering the air suspension system to actively lower the vehicle height. Lowering the vehicle height reduces the vertical distance between the trunk opening and the ground, making it easier for users to push or lift heavy items into the trunk, which is particularly suitable for scenarios involving transporting large luggage.

[0095] In another possible example, the intelligent driving domain controller sends a reduction command to the chassis domain controller via CAN or Ethernet. The chassis domain controller, after determining safety based on the current vehicle speed and status, sends a target height value to the air suspension control unit. The air suspension control unit then drives the compressor to expel some of the gas from the air springs, lowering the vehicle height by a preset value (e.g., 30-50mm), and maintains this position once the target height is reached.

[0096] The vehicle control method provided in this embodiment acquires visual information and accurately determines the three-dimensional dimensions of luggage. Combined with intelligent comparison with the trunk volume, it achieves the function of automatically adapting the vehicle's loading status according to the size of the luggage. Users can obtain optimal loading conditions (standard space and / or extended space) when approaching the vehicle without any manual operation or specific actions, greatly improving the convenience and intelligence of trunk use and optimizing the user experience.

[0097] Figure 3 This is a schematic diagram of another vehicle control process according to an embodiment of this application. Figure 3 As shown, the process includes the following steps: A user approaches the vehicle with luggage; the in-vehicle low-frequency antenna recognizes the smart key; the keyless entry system's electronic control unit sends a signal to the intelligent driving domain controller, triggering the binocular camera system to start working; the binocular camera system recognizes the user's face and confirms the owner's identity; the binocular camera system checks if the user is carrying large luggage; if not, the system stops recognizing; if carrying large luggage, the intelligent driving domain controller sends signals to the body domain control unit and the chassis domain control unit; the body domain control unit triggers the trunk lid to open, and the chassis domain control unit triggers the air suspension to lower the vehicle height; simultaneously, a deep learning algorithm is applied to calculate the three-dimensional dimensions of the large luggage, i.e., the luggage's external geometric dimensions; it is determined whether the external geometric dimensions are smaller than the preset loading space dimensions of the trunk; if so, the process ends; if not, the intelligent driving domain controller sends a signal to the rear seat control unit to control the rear seats to fold down to expand the loading space, and then the process ends. This process, through multi-sensor fusion and cross-domain collaborative control, realizes a trunk welcome function that automatically adjusts the vehicle's status according to the luggage size.

[0098] This embodiment also provides a vehicle control device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0099] This embodiment provides a vehicle control device, such as... Figure 4 As shown, it includes: The acquisition module 401 is used to acquire visual information about the authorized user and the luggage carried by the authorized user in response to detecting that an authorized user is approaching the vehicle; The comparison module 402 is used to determine the external geometric dimensions of the luggage based on visual information and compare the external geometric dimensions with the preset loading space dimensions of the vehicle's trunk. The trunk adjustment module 403 is used to control the rear seats to fold down and open the trunk lid if the external geometric dimensions are greater than the preset loading space dimensions of the trunk.

[0100] In some optional implementations, the acquisition module 401 includes: The signal transmitting unit is used to control the vehicle to transmit detection signals; The location confirmation unit is used to confirm the location and device identification of the sensing device in response to the authorized user's sensing device receiving the detection signal and sending a response signal. The distance judgment unit is used to calculate the distance between the location and the vehicle's parking position as the sensing distance. If the sensing distance is less than or equal to a preset distance threshold and the device identifier is valid, it detects that an authorized user is approaching the vehicle.

[0101] In some optional implementations, the acquisition module 401 includes: The image acquisition unit is used to acquire stereo image pairs containing the authorized user and the luggage carried by the authorized user through a binocular camera system.

[0102] In some alternative implementations, the comparison module 402 includes: The identity verification unit is used to perform biometric identification based on facial image information in stereo image alignment, in order to verify the user's authorized identity a second time. The baggage recognition unit is used to identify the target item corresponding to the baggage in the image based on stereo image pairs and an object recognition model. The size calculation unit is used to calculate the three-dimensional size of the target object based on the baseline distance of the binocular camera system, obtain the three-dimensional size of the target object, and use the three-dimensional size as the outer geometric size.

[0103] The trunk adjustment module 403 also includes: The body adjustment unit is used to control the trunk lid to open and lower the vehicle's body height if the external geometric dimensions are less than or equal to the preset loading space dimensions of the trunk.

[0104] In some alternative implementations, the trunk adjustment module 403 includes: The seat folding unit is used to control the vehicle's cabin domain controller to send folding commands to the rear seat control unit to control the rear seats to fold down and form a flat surface with the trunk carpet for loading large items. The trunk opening unit is used to control the vehicle's body domain controller to send an opening command to the trunk control unit to drive the trunk lid to open.

[0105] In some optional implementations, the acquisition module 401 further includes: An environmental detection subunit is used to detect environmental conditions, including ambient brightness and rainfall, through a light sensor and / or a rain sensor. The light-on subunit is used to control the vehicle's body domain controller to send a light-on command to turn on the lights if the environmental conditions meet at least one of the following: ambient brightness is less than a first threshold and rainfall is greater than a second threshold.

[0106] The vehicle control device provided in this application embodiment can execute the vehicle control method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0107] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0108] The following is a detailed reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0109] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0110] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the vehicle control method of embodiments of this application.

[0111] Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0112] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the vehicle control method shown in the above embodiments is implemented.

[0113] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0114] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A vehicle control method, characterized in that, The method includes: In response to detecting an authorized user approaching the vehicle, visual information about the authorized user and the luggage carried by the authorized user is acquired; The external geometric dimensions of the luggage are determined based on the visual information, and the external geometric dimensions are compared with the preset loading space dimensions of the vehicle's trunk. If the external geometric dimensions are greater than the preset loading space dimensions of the trunk, then the rear seats are folded down and the trunk lid is opened.

2. The method according to claim 1, characterized in that, The detection of an authorized user approaching the vehicle includes: Control the vehicle to emit detection signals; In response to the authorized user's sensing device receiving the detection signal and sending a response signal, the location and device identifier of the sensing device are confirmed; The distance between the location and the vehicle's parking location is calculated as the sensing distance. If the sensing distance is less than or equal to a preset distance threshold and the device identifier is valid, then the authorized user is detected to be approaching the vehicle.

3. The method according to claim 1, characterized in that, The step of obtaining visual information about the authorized user and the luggage carried by the authorized user includes: A stereoscopic image pair containing the authorized user and the luggage carried by the authorized user is acquired through a binocular camera system.

4. The method according to claim 3, characterized in that, Determining the external geometric dimensions of the luggage based on the visual information includes: Biometric identification is performed based on the facial image information in the stereoscopic image pair to verify the user's authorized identity for a second time; Based on the stereo image pair, the target item corresponding to the luggage in the image is identified by the object recognition model; The stereoscopic dimensions of the target object are calculated based on the baseline distance of the binocular camera system, and the stereoscopic dimensions are used as the outer geometric dimensions.

5. The method according to claim 1, characterized in that, After comparing the external geometric dimensions with the preset loading space dimensions of the vehicle's trunk, the method further includes: If the external geometric dimensions are less than or equal to the preset loading space dimensions of the trunk, the trunk lid will be opened and the vehicle's body height will be lowered.

6. The method according to claim 1, characterized in that, The control of folding down the rear seats and opening the trunk lid includes: The vehicle's cockpit domain controller sends a folding command to the rear seat control unit to fold down the rear seats, forming a flat surface with the trunk carpet for loading large items. The vehicle's body domain controller sends an opening command to the trunk control unit to drive the trunk lid to open.

7. The method according to claim 1, characterized in that, Before obtaining visual information about the authorized user and the luggage carried by the authorized user, the method further includes: The environmental condition is detected by a light sensor and / or a rain sensor, the environmental condition including ambient brightness and rainfall. If the environmental conditions satisfy at least one of the following: the ambient brightness is less than a first threshold and the rainfall is greater than a second threshold, then the vehicle's body domain controller is controlled to send a light-on command to turn on the lights.

8. A vehicle control device, characterized in that, The device includes: The acquisition module is used to acquire visual information about the authorized user and the luggage carried by the authorized user in response to detecting that an authorized user is approaching the vehicle; A comparison module is used to determine the external geometric dimensions of the luggage based on the visual information, and compare the external geometric dimensions with the preset loading space dimensions of the vehicle's trunk; The trunk adjustment module is used to control the rear seats to fold down and open the trunk lid if the external geometric dimensions are greater than the preset loading space dimensions of the trunk.

9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the vehicle control method of any one of claims 1 to 7.

10. A vehicle, characterized in that, The vehicle includes a controller, which includes a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the vehicle control method of any one of claims 1 to 7.

Images