A door control method, device, storage medium and equipment

Abstract

This invention belongs to the field of automotive technology and provides a vehicle door control method, device, storage medium, and equipment, including: acquiring an image to be recognized; sequentially performing human detection, facial recognition, and facial feature extraction on the image to be recognized, and comparing the extracted facial features with pre-stored facial information of persons; if the comparison results match, then based on the image to be recognized, performing luggage size recognition to obtain a trunk opening command; determining the number of persons in the image to be recognized and the permissions of each person according to the comparison results; if the comparison results match, acquiring voice, gestures, and / or human distance to recognize and obtain vehicle door opening commands and / or trunk opening commands; and further subdividing the vehicle door opening commands according to the number of persons, the permissions of each person, the distance between the vehicle door and obstacles, and the location of the persons. This achieves automatic opening and closing of vehicle doors and trunk, improving the convenience and safety of entering and exiting the vehicle.

Description

Technical Field

[0001] This invention belongs to the field of automotive technology, and in particular relates to a door control method, device, storage medium and equipment. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] In modern society, vehicles have become an indispensable part of people's daily lives. With the continuous development of technology, the functions of automobiles are becoming increasingly diverse, gradually transforming from traditional means of transportation into intelligent mobility tools. In the field of intelligent vehicles, technologies such as autonomous driving, vehicle networking, artificial intelligence, and voice recognition have gradually matured, providing vehicles with a more convenient, safe, and comfortable travel experience.

[0004] As people's living standards improve, their demands for car comfort are also increasing. However, in terms of automotive intelligence, the level of intelligence in door control is relatively low. This is mainly reflected in the fact that the opening and closing of doors still relies on traditional methods such as keys or remote controls, which cannot adequately meet users' needs for convenience and security, nor can they satisfy modern people's requirements for car comfort. Summary of the Invention

[0005] To address the technical problems mentioned above, this invention provides a vehicle door control method, device, storage medium, and equipment. Utilizing facial recognition, it can automatically identify individuals and recognize luggage dimensions. By combining voice, gestures, distance to other individuals, number of people, and permissions for each person, it sets logic for opening and closing the vehicle doors and trunk, achieving automatic opening and closing of the doors and trunk. Furthermore, by considering the distance between the door and obstacles, as well as the location of individuals, it avoids door collisions and obstruction of passengers, improving the convenience and safety of entering and exiting the vehicle.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] The first aspect of the present invention provides a door control method.

[0008] A door control method, comprising:

[0009] Acquire the image to be recognized;

[0010] The image to be identified is subjected to human detection, face recognition and facial feature extraction in sequence, and the extracted facial features are compared with the pre-stored facial information of the person.

[0011] If the comparison results match, the luggage size is identified based on the image to be identified, and when the luggage size exceeds the preset value, a trunk opening command is obtained;

[0012] Based on the comparison results, determine the number of people in the image to be identified and the permissions of each person;

[0013] If the comparison results match, the voice, gesture and / or human distance are obtained to identify the door opening command and / or trunk opening command; and the door to be opened is determined based on the number of people and the permissions of each person.

[0014] For car doors that need to be opened, the door opening command is further subdivided based on the distance between the car door and the obstacle and the location of the person.

[0015] Furthermore, the image to be identified is acquired when the car door is closed and a human body is detected.

[0016] Furthermore, the step of further refining the door opening command includes:

[0017] When the distance between the car door and the obstacle is less than the first threshold, the door opening command is to keep it closed, and a voice prompt is given that the door cannot be opened;

[0018] When the distance between the car door and the obstacle is greater than the first threshold and less than the second threshold, it is determined whether the person is in the designated position. If so, the door opening command is half-open; otherwise, the door opening command is to keep closed until the person is detected to be in the designated position.

[0019] When the distance between the car door and the obstacle is greater than the second threshold and less than the third threshold, it is determined whether the person is in the designated position. If so, the door opening command is to open the door fully; otherwise, the door opening command is to keep the door closed until the person is detected to be in the designated position.

[0020] When the distance between the car door and the obstacle is greater than the third threshold, the door opening command is to open the door fully.

[0021] Furthermore, the luggage size recognition step includes:

[0022] For each person, retain a human-shaped detection frame;

[0023] Within the human detection frame, baggage is identified to obtain the baggage outline;

[0024] Based on the luggage outline, the difference between the maximum and minimum pixel values ​​in the luggage outline is taken as the actual height of the luggage, and the difference between the pixel coordinates corresponding to the maximum and minimum pixel values ​​is taken as the pixel height of the luggage. The luggage size is calculated by using the ratio of the actual height of the luggage to the pixel height of the luggage.

[0025] Furthermore, if the distance between the human body at multiple consecutive time points is less than a set value, a door opening command is obtained.

[0026] Furthermore, if the distance between the human body and the car owner is less than a set value at a certain point in time during the owner's usual car usage period, a door opening command will be received.

[0027] Furthermore, the gesture is obtained by performing gesture recognition on the image to be recognized.

[0028] A second aspect of the present invention provides a door control device.

[0029] A door control device, comprising:

[0030] The image acquisition module is configured to acquire the image to be recognized.

[0031] The personnel identification module is configured to: sequentially perform human detection, face recognition, and facial feature extraction on the image to be identified, and compare the extracted facial features with the pre-stored facial information of the personnel;

[0032] The luggage recognition module is configured to: if the comparison results are consistent, perform luggage size recognition based on the image to be recognized, and when the luggage size exceeds the preset value, obtain a trunk opening command;

[0033] The personnel identification module is configured to determine the number of people in the image to be identified and the permissions of each person based on the comparison results.

[0034] The door control module is configured to: if the comparison results are consistent, acquire voice, gesture and / or human distance, and identify door opening command and / or trunk opening command; and determine the door to be opened based on the number of people and the permissions of each person; for the door to be opened, further subdivide the door opening command based on the distance between the door and the obstacle and the position of the person.

[0035] A third aspect of the present invention provides a computer-readable storage medium.

[0036] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a door control method as described in the first aspect above.

[0037] A fourth aspect of the present invention provides a computer device.

[0038] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of a door control method as described in the first aspect above.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] This invention utilizes facial recognition to automatically identify individuals and recognize luggage size. It combines voice, gestures, distance to people, number of people, and permissions for each person to set the logic for opening and closing car doors and the trunk, thereby achieving automatic opening and closing of car doors and the trunk and improving the convenience and safety of entering and exiting the vehicle.

[0041] This invention automatically detects the distance between the vehicle door and obstacles and avoids collisions, protecting the safety of vehicles and pedestrians.

[0042] This invention determines whether a person is in a designated location and further subdivides the door opening command, which can effectively prevent the distance between the door and an obstacle from preventing the person from passing through and thus blocking the person from the door.

[0043] This invention breaks down the steps of the door opening command into smaller steps, effectively integrating the judgment of the distance between the door and the obstacle and the judgment of whether the person is in the designated position, so as to give the door command quickly and accurately.

[0044] This invention uses the difference between the maximum and minimum pixel values ​​in the luggage outline as the luggage height, and the difference between the corresponding pixel coordinates as the luggage pixel height. Using this as a ratio, the luggage size can be calculated, which can roughly estimate the luggage size and save calculation time. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating a door control method according to Embodiment 1 of the present invention;

[0047] Figure 2 This is a structural diagram of a door control device shown in Embodiment 2 of the present invention;

[0048] Figure 3This is a schematic diagram of the structure of a computer device shown in Embodiment 4 of the present invention. Detailed Implementation

[0049] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0050] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0051] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0052] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and apparatuses according to various embodiments of the present invention. It should be noted that each block in a flowchart or block diagram may represent a module, segment, or portion of code, which may include one or more executable instructions for implementing the logical functions specified in the various embodiments. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, may be implemented using dedicated hardware-based apparatus that performs the specified functions or operations, or may be implemented using a combination of dedicated hardware and computer instructions.

[0053] Example 1

[0054] This embodiment provides a door control method.

[0055] This embodiment provides a vehicle door control method that uses technologies such as facial recognition and voice recognition to intelligently recognize the user's operating intentions and autonomously complete operations such as opening and closing the vehicle doors and trunk.

[0056] This embodiment provides a vehicle door control method that, by optimizing the design of the vehicle door and using noise reduction techniques, can improve the comfort inside the vehicle and provide users with a more comfortable riding experience.

[0057] This embodiment provides a vehicle door control method that applies the latest artificial intelligence technology and advanced sensor technology, including voice control, facial recognition, image recognition and intelligent sensors, which can automatically identify the identity of the person, unlock the vehicle door and trunk, and automatically open and close the vehicle door and trunk, thereby improving the convenience and safety of entering and exiting the vehicle.

[0058] This embodiment provides a door control method that uses a door sensor to detect whether the door is fully closed when closing, ensuring that the door is fully closed and improving safety.

[0059] This embodiment provides a door control method that automatically detects and avoids collisions, protecting the safety of vehicles and pedestrians.

[0060] The vehicle door control method provided in this embodiment can also control the opening and closing of the trunk via voice commands, and can be linked with the vehicle navigation system and smartphone to achieve a more intelligent operating experience.

[0061] This embodiment provides a door control method that improves the comfort and safety of automobiles, meeting modern people's requirements for the comfort and safety of automobiles.

[0062] The system architecture of the door control method provided in this embodiment includes a processor, a body domain controller, a motor, an image acquisition device, a sensor, an audio acquisition device, a door noise reduction processing device, and a door power supply.

[0063] Among them, the sensors include door sensors, which are used to determine the open / closed status of the doors.

[0064] The sensors include temperature sensors, humidity sensors, and distance sensors. One temperature sensor is installed inside and one outside the vehicle to collect temperature data inside and outside the doors. One humidity sensor is also installed inside and one outside the vehicle to collect humidity data inside and outside the doors. One distance sensor is installed on the outside of each door to collect the distance between the door and obstacles.

[0065] Among them, the sensors also include human body sensors, one of which is installed on the outside of each door and the outside of the trunk, to detect human dynamics around the doors and trunk, including information such as the approach and departure of people, and the time people stay near the doors.

[0066] Each door, the outside of the trunk, and the front of the vehicle are equipped with an image acquisition device for continuous image capture. The image acquisition device on the outside of the trunk is mounted on the top of the trunk to capture images of the trunk area. These image acquisition devices use high-definition sensors to capture clear images.

[0067] The audio acquisition device is located on the outside of the vehicle and is used to collect voice data from the outside of the vehicle.

[0068] Among them, the door noise reduction device can effectively reduce the noise generated when the door is closed by using noise reduction technology (speed reducer), thereby improving the ride comfort.

[0069] Each door is equipped with a motor that drives the door to rotate, thus opening and closing the door. The processor controls the motor speed, thereby dynamically adjusting the door closing speed to prevent the door from closing too quickly or too slowly, and to improve the stability of the door closing.

[0070] The processor can intelligently manage the power supply of the car doors based on the door status and the owner's needs, saving energy and extending battery life.

[0071] This embodiment provides a door control method, such as... Figure 1 As shown, it includes the following steps:

[0072] Step 1: The processor acquires the door opening and closing status collected by the door sensor. When the door is closed, the processor controls the human body sensor to detect human bodies around the door and trunk in real time. When a human body is detected, a human body approach command is sent to the processor.

[0073] Step 2: In response to the human body approach command, the processor sends an image acquisition device start command. In response to the image acquisition device start command, the image acquisition device continuously acquires the image to be identified and sends it to the processor.

[0074] Step 3: The processor acquires the image to be recognized and performs human detection, face recognition, and facial feature extraction on the image in sequence. The extracted facial features are compared with the pre-stored facial information of the person. If the comparison results are consistent, data acquisition commands are sent to the audio acquisition device, the image acquisition device, and the human body sensor respectively.

[0075] The pre-deposited personnel include the car owner and authorized personnel (family members).

[0076] Step 4: Based on the comparison results, the processor determines the number of people in the image to be identified (i.e., the number of people whose facial information matches the pre-stored information) and the permissions of each person.

[0077] In addition to storing facial information, the system also stores the person's permissions (i.e., whether the person has driving privileges).

[0078] Step 5: If the comparison results are consistent, the processor performs luggage recognition and luggage size recognition based on the image to be recognized. When the luggage size exceeds the preset value, it issues a trunk opening command to the vehicle domain controller; or when the luggage size exceeds the preset value, it asks a voice question whether to open the trunk. If yes, it issues a trunk opening command to the vehicle domain controller.

[0079] Step 501: In step 3, for each image to be identified acquired by different image acquisition devices at the same time, human detection is performed to obtain several human detection boxes. For each human detection box, facial recognition, facial feature extraction, and facial information comparison are used to obtain the person corresponding to each human detection box. One human detection box is retained for each person.

[0080] Step 502: Within the human detection frame, perform baggage recognition to obtain the baggage outline and crop out the baggage image.

[0081] In this embodiment, the image acquisition device uses a depth camera, so the luggage image is a depth image.

[0082] Step 503: Calculate the luggage dimensions based on the luggage outline.

[0083] First, the difference between the maximum and minimum pixel values ​​in the luggage outline is taken as the luggage height h1 (actual luggage height). Assuming the pixel coordinates corresponding to the maximum pixel value are (x1, y1) and the pixel coordinates corresponding to the minimum pixel value are (x2, y2), the difference between y1 and y2 is taken as h2 (luggage pixel height). Then, the minimum bounding rectangle of the luggage outline is determined. The length of the minimum bounding rectangle is taken as the luggage pixel length l2, and the width of the minimum bounding rectangle is taken as the luggage pixel width w2. Therefore, the actual length l1 and actual width w1 of the luggage are: l1 = l2 * h1 / h2; w1 = w2 * h1 * kw / (kl * h2); where kl and kw represent pixel length and width, respectively. Finally, the luggage dimensions are approximately: l1 * w1 * h1.

[0084] This embodiment provides a door control method that proposes to use the difference between the maximum and minimum pixel values ​​in the luggage outline as the luggage height, and the difference between the corresponding pixel coordinates as the luggage pixel height. Using this as a ratio, the luggage size can be calculated, which can roughly estimate the luggage size and save calculation time.

[0085] Step 6: The audio acquisition unit, image acquisition device, and human body sensor respond to the data acquisition command, simultaneously acquire data, identify user commands (open door command, open trunk command), and send them to the vehicle domain controller.

[0086] Step 601: The audio acquisition device acquires voice and sends it to the processor; or, the image acquisition device continuously acquires the image to be recognized and sends it to the processor; or, the human body sensor acquires the distance to the human body and sends it to the processor.

[0087] Step 602: The processor acquires the voice and obtains voice commands through voice recognition.

[0088] Voice commands include, but are not limited to, commands to open the car door and commands to open the trunk.

[0089] Step 603: The processor continuously acquires the image to be recognized and obtains gesture commands through gesture recognition.

[0090] The gesture command can be 1, which is the command to open the car door; the gesture command can be 2, which is the command to open the trunk.

[0091] Step 604: The processor obtains the distance of the human body at multiple consecutive time points and determines the user's intent.

[0092] For example, if the distance between the human body and the set value d is less than the set value d at n consecutive time points, the user's intention is to open the car door; or, if the distance between the human body and the set value d is less than the set value d at a certain time point during the owner's usual car usage time (such as commuting time), the user's intention is to open the car door.

[0093] Among them, the car owners' habitual car usage time periods were obtained using machine learning and data mining techniques.

[0094] Step 605: For the door opening command, based on the number of people and the permissions of each person obtained in Step 4, determine which door needs to be opened and subdivide the door opening command into the following categories: open driver's side door, open passenger side door, open left rear door, and open right rear door.

[0095] Step 7: After the processor obtains the door that needs to be opened, it activates the distance sensor. The distance sensor collects the distance between the door and the obstacle. Based on the distance between the door and the obstacle and the location of the person, the door opening command is divided into keeping closed, fully opening the door, and half opening the door.

[0096] The location of the person is obtained by processing the image to be recognized.

[0097] Specifically, when the distance between the car door and the obstacle is less than a first threshold, the door opening command is to keep the door closed, and a voice prompt "The door cannot be opened at this time" is given; the first threshold is the required visibility of the door when it is half-open. In this embodiment, the first threshold is... L is the width of the car door;

[0098] When the distance between the car door and the obstacle is greater than the first threshold and less than the second threshold (which can be L), it is determined whether the person is in the designated position. If so, the door opening command is half-open; otherwise, the door opening command is to keep closed until the person is detected to be in the designated position.

[0099] When the distance between the car door and the obstacle is greater than the second threshold and less than the third threshold (L+D, where D is a specified value, which can be the width of a human body), it is determined whether the person is in the specified position. If so, the door opening command is to open the door fully; otherwise, the door opening command is to keep the door closed until the person is detected to be in the specified position.

[0100] When the distance between the car door and the obstacle is greater than the third threshold, the door opening command is to open the door fully.

[0101] Judging the distance between the car door and an obstacle can prevent damage or safety issues caused by external environmental factors.

[0102] In this embodiment, the designated location is within a certain distance to the side and rear of the vehicle door that needs to be opened. The reason for determining whether the person is in the designated location is to prevent the distance between the vehicle door and the obstacle from being too great for the person to pass through after the door is opened, thus preventing the door from obstructing the person.

[0103] As one implementation method, when the temperature difference or humidity difference between the inside and outside of the car door exceeds a threshold, the door opening command can also be set to remain closed.

[0104] Step 8: The vehicle domain controller responds to the door opening command or trunk opening command and controls the door or trunk to open.

[0105] Step 801: After receiving the trunk opening command from step 6 or step 5, the vehicle domain controller controls the trunk to open.

[0106] Step 802: The vehicle domain controller receives the door opening command from step 7 and controls the door to open.

[0107] In one implementation, the vehicle domain controller locks and unlocks the doors by controlling the opening and closing of the door locks.

[0108] Step 9: The processor obtains the command to close the door or the command to close the trunk through the audio acquisition device, button or gesture, and controls the door or trunk to close through the body domain controller.

[0109] As one implementation method, when closing the car door, a door sensor is used to detect whether the door is fully closed, ensuring that the door is completely closed and improving safety.

[0110] In one implementation, the processor can also connect to a remote terminal to obtain commands to open the car door or open the trunk, or to close the car door or close the trunk, making it convenient for car owners to use and manage.

[0111] The remote terminal can be a mobile phone, computer, or car key, etc., and can communicate wirelessly with the processor via Bluetooth or Wi-Fi.

[0112] Example 2

[0113] This embodiment provides a vehicle door control device.

[0114] A door control device, such as Figure 2 As shown, it includes:

[0115] The image acquisition module is configured to acquire the image to be recognized.

[0116] The personnel identification module is configured to: sequentially perform human detection, face recognition, and facial feature extraction on the image to be identified, and compare the extracted facial features with the pre-stored facial information of the personnel;

[0117] The luggage recognition module is configured to: if the comparison results are consistent, perform luggage size recognition based on the image to be recognized, and when the luggage size exceeds the preset value, obtain a trunk opening command;

[0118] The personnel identification module is configured to determine the number of people in the image to be identified and the permissions of each person based on the comparison results.

[0119] The door control module is configured to: if the comparison results are consistent, acquire voice, gesture and / or human distance, and identify door opening command and / or trunk opening command; and determine the door to be opened based on the number of people and the permissions of each person; for the door to be opened, further subdivide the door opening command based on the distance between the door and the obstacle and the position of the person.

[0120] It should be noted that the vehicle door control device provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the electronic device can be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle occupant detection device and the vehicle occupant detection method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0121] Example 3

[0122] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of a door control method as described in Embodiment 1 above.

[0123] Example 4

[0124] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the door control method described in Embodiment 1 above.

[0125] Figure 3 A schematic diagram of the structure of a computer device provided in an exemplary embodiment of this application is shown. The computer device includes a processor and a memory.

[0126] The processor may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), or PLA (Programmable Logic Array). The processor may also include a main processor and coprocessors. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0127] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory are used to store at least one computer program, which is configured by a processor to implement the in-vehicle occupant detection method provided in the method embodiments of this application.

[0128] Those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0129] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A door control method, characterized in that, include: Acquire the image to be recognized; The image to be identified is subjected to human detection, face recognition and facial feature extraction in sequence, and the extracted facial features are compared with the pre-stored facial information of the person. If the comparison results match, the luggage size is identified based on the image to be identified, and when the luggage size exceeds the preset value, a trunk opening command is obtained; Based on the comparison results, determine the number of people in the image to be identified and the permissions of each person; If the comparison results match, the voice, gesture and / or human distance are obtained to identify the door opening command and / or trunk opening command; and the door to be opened is determined based on the number of people and the permissions of each person. For the car door that needs to be opened, the door opening command is further subdivided according to the distance between the car door and the obstacle and the location of the people; The steps for further refining the door opening command include: when the distance between the door and the obstacle is less than a first threshold, the door opening command is to remain closed, and a voice prompt indicates that the door cannot be opened; when the distance between the door and the obstacle is greater than the first threshold but less than a second threshold, it is determined whether the person is in a designated position; if so, the door opening command is to partially open the door; otherwise, the door opening command is to remain closed until the person is detected to be in a designated position; when the distance between the door and the obstacle is greater than the second threshold but less than a third threshold, it is determined whether the person is in a designated position; if so, the door opening command is to fully open the door; otherwise, the door opening command is to remain closed until the person is detected to be in a designated position; when the distance between the door and the obstacle is greater than a third threshold, the door opening command is to fully open the door. If the distance between the human body and the set value is less than the set value at multiple consecutive time points, a door opening command is obtained; If the distance between the human body and the car owner is less than a set value at a certain point in time during the owner's usual car usage period, a door opening command will be received.

2. The door control method according to claim 1, characterized in that, The image to be identified is acquired when the car door is closed and a human body is detected.

3. The door control method according to claim 1, characterized in that, The steps for luggage size identification include: For each person, retain a human-shaped detection frame; Within the human detection frame, baggage is identified to obtain the baggage outline; Based on the luggage outline, the difference between the maximum and minimum pixel values ​​in the luggage outline is taken as the actual height of the luggage, and the difference between the pixel coordinates corresponding to the maximum and minimum pixel values ​​is taken as the pixel height of the luggage. The luggage size is calculated by using the ratio of the actual height of the luggage to the pixel height of the luggage.

4. The door control method according to claim 1, characterized in that, The gesture is obtained by performing gesture recognition on the image to be recognized.

5. A vehicle door control device, characterized in that, include: The image acquisition module is configured to acquire the image to be recognized. The personnel identification module is configured to: sequentially perform human detection, face recognition, and facial feature extraction on the image to be identified, and compare the extracted facial features with the pre-stored facial information of the personnel; The luggage recognition module is configured to: if the comparison results are consistent, perform luggage size recognition based on the image to be recognized, and when the luggage size exceeds the preset value, obtain a trunk opening command; The personnel identification module is configured to determine the number of people in the image to be identified and the permissions of each person based on the comparison results. The door control module is configured to: if the comparison results are consistent, acquire voice, gesture and / or human distance, and identify door opening command and / or trunk opening command; and determine the door to be opened based on the number of people and the permissions of each person; for the door to be opened, further subdivide the door opening command based on the distance between the door and the obstacle and the position of the person. The steps for further refining the door opening command include: when the distance between the door and the obstacle is less than a first threshold, the door opening command is to remain closed, and a voice prompt indicates that the door cannot be opened; when the distance between the door and the obstacle is greater than the first threshold but less than a second threshold, it is determined whether the person is in a designated position; if so, the door opening command is to partially open the door; otherwise, the door opening command is to remain closed until the person is detected to be in a designated position; when the distance between the door and the obstacle is greater than the second threshold but less than a third threshold, it is determined whether the person is in a designated position; if so, the door opening command is to fully open the door; otherwise, the door opening command is to remain closed until the person is detected to be in a designated position; when the distance between the door and the obstacle is greater than a third threshold, the door opening command is to fully open the door. If the distance between the human body and the set value is less than the set value at multiple consecutive time points, a door opening command is obtained; If the distance between the human body and the car owner is less than a set value at a certain point in time during the owner's usual car usage period, a door opening command will be received.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of a door control method as described in any one of claims 1-4.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of a door control method as described in any one of claims 1-4.

Images