WO2021218180A1

WO2021218180A1 - Method and apparatus for controlling unlocking of vehicle door, and vehicle, device, medium and program

Info

Publication number: WO2021218180A1
Application number: PCT/CN2020/136253
Authority: WO
Inventors: 王飞; 钱晨
Original assignee: 北京市商汤科技开发有限公司
Priority date: 2020-04-29
Filing date: 2020-12-14
Publication date: 2021-11-04
Also published as: CN111540090A; KR20210146354A; JP2022534284A; JP7281562B2

Abstract

A method and apparatus for controlling the unlocking of a vehicle door, and a vehicle, a device, a medium and a program. The method comprises: in response to the image acquisition module of a vehicle being awakened, obtaining an image acquired by the image acquisition module of the vehicle (S101); performing quality inspection on the face image in the obtained image (S102); when the result of the quality inspection meets a preset condition, performing face detection on the basis of the face image (S103); and when the face detection of the face image is passed, controlling at least one vehicle door lock of the vehicle to be unlocked (S104). In this way, according to the method for controlling the unlocking of a vehicle door, a user does not need to perform any operation throughout the entire process, and the device loss is low. A vehicle door can be automatically unlocked when a vehicle owner approaches a vehicle, and use is more convenient.

Description

Method, device, vehicle, equipment, medium and program for controlling unlocking of vehicle door

Cross-references to related applications

The present disclosure is filed based on a Chinese patent application with an application number of 202010355699.9 and an application date of April 29, 2020, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is incorporated herein by reference.

Technical field

The present disclosure relates to the field of image processing technology, and in particular, to a method, device, vehicle, equipment, medium, and program for controlling unlocking of a vehicle door.

Background technique

The current automotive electronics industry is developing rapidly, and the convenient and comfortable riding experience has attracted more and more attention from users. Among them, intelligent door unlocking is a highlight of the current riding experience. In related technologies, it is often inconvenient for the user to control the unlocking of the vehicle door.

Summary of the invention

The embodiments of the present disclosure provide at least a method, device, vehicle, equipment, medium, and program for controlling unlocking of a vehicle door.

The embodiment of the present disclosure provides a method for controlling unlocking of a vehicle door, including:

In response to the image acquisition module of the car being awakened, acquiring the image collected by the image acquisition module of the car;

Performing quality detection on the face image in the acquired image;

In the case that the result of the quality detection meets the preset condition, performing face detection based on the face image;

In the case where the face detection of the face image passes, at least one door lock of the vehicle is controlled to be unlocked. In this way, in response to the car's image acquisition module being awakened, the image collected by the car's image acquisition module is acquired, and the quality of the face image in the acquired image is inspected; if the result of the quality inspection meets the preset conditions In this case, face detection is performed based on the face image; if the face detection of the face image passes, at least one door lock of the car is unlocked; the user does not need to perform any operation throughout the process, and the equipment loss is small. The door can be unlocked in the process of the vehicle, which is more convenient to use.

In some embodiments, the method further includes:

In response to that no human face image is detected in the image collected within the first preset time after the image acquisition module is awakened, the image acquisition module is controlled to enter a sleep state.

In some embodiments, the method further includes:

In the case that the result of the quality inspection does not meet the preset condition, a prompt message is output.

In some embodiments, the method further includes:

In response to that none of the quality detection results meet the preset conditions within the second preset time, the image acquisition module is controlled to enter a dormant state.

In some embodiments, the method further includes:

In response to the failure of the face detection of the face images in the acquired image within the third preset time after the image acquisition module is awakened, the image acquisition module is controlled to enter the dormant state.

In some embodiments, the image acquisition module of the vehicle is awakened in at least one of the following situations:

It is detected that the distance between the human body and the vehicle is less than the preset distance;

Receiving a door unlocking instruction;

The Bluetooth module placed in the car searches for a Bluetooth device with a preset logo;

The Bluetooth module placed in the car searches for a Bluetooth device with a preset identification and is successfully paired.

In some embodiments, the quality detection includes at least one of the following: brightness detection, head posture detection, blur degree detection, resolution detection, and occlusion degree detection.

In some embodiments, for the case where the quality detection includes brightness detection, the quality detection on the acquired face image includes:

Determining the average brightness value of the plurality of pixels based on the pixel value of each of the plurality of pixels in the face image;

In the case that the average brightness value is greater than the first brightness threshold and less than the second brightness threshold, it is determined that the brightness detection result of the face image meets the brightness condition in the preset condition; wherein, the first brightness threshold Less than the second brightness threshold.

In some embodiments, for the case where the quality detection includes head posture detection, the quality detection on the acquired face image includes:

Performing head posture detection on the face image to obtain head posture information of the face in the face image; the head posture information includes: the pitch angle and the yaw angle of the face;

In the case where the absolute value of the pitch angle is less than the pitch angle threshold and the absolute value of the yaw angle is less than the yaw angle threshold, it is determined that the head posture detection result of the face image meets the preset conditions. Head posture conditions.

In some embodiments, for the case where the quality detection includes the blur degree detection, the quality detection on the acquired face image includes:

Performing key point detection on the face image to obtain position information of multiple key points in the face image in the face image;

Determine the sharpness value of the face image according to the position information of each key point in the plurality of key points;

In the case that the sharpness value of the face image is greater than the sharpness threshold value, it is determined that the blur degree detection result of the face image meets the sharpness condition in the preset condition.

In some embodiments, the determining the sharpness value of the face image according to the position information of each key point in the plurality of key points includes:

For each key point, determine a plurality of target pixels adjacent to the key point position according to the position information of each key point;

Determine the sharpness value of each key point based on the pixel value of each target pixel point corresponding to each key point;

The sharpness value of the face image is determined according to the sharpness value of each key point in the plurality of key points.

In some embodiments, for the case where the quality detection includes the detection of the degree of occlusion, the quality detection of the acquired face image includes:

Performing key point detection on the face image to obtain key point detection results corresponding to multiple key points in the face image;

Determine the occlusion degree value of the face image based on the key point detection results respectively corresponding to the multiple key points;

In the case that the occlusion degree value is less than the occlusion degree value threshold, it is determined that the occlusion degree detection result of the face image meets the occlusion degree condition in the preset condition.

In some embodiments, the performing face detection based on the face image includes:

The face detection is performed on the face image by using the face detection model loaded offline.

In some embodiments, the following method is used to load the face detection model offline:

Converting the face detection model from an encryption mode to a plain text mode, and writing the face detection model converted to the plain text mode into a header file of the car lock control system;

The header file is statically compiled to load the face detection model offline.

Perform face identity authentication and living body detection based on the face image.

The embodiment of the present disclosure also provides a device for controlling unlocking of a vehicle door, including:

The response module is used to obtain the image collected by the image acquisition module of the car in response to the image acquisition module of the car being awakened;

A quality detection module, configured to perform quality detection on the face image in the acquired image;

A face detection module, configured to perform face detection based on the face image when the result of the quality detection meets a preset condition;

The vehicle lock control module is used to control the unlocking of at least one door lock of the vehicle when the face detection of the face image passes.

In some embodiments, the device for controlling unlocking of a vehicle door further includes:

The first control module is configured to control the image acquisition module to enter the dormant state in response to that no face image is detected in the image collected within the first preset time after the image acquisition module is awakened.

The prompt module is used to output prompt information when the result of the quality inspection does not meet the preset condition.

The second control module is configured to control the image acquisition module to enter the dormant state in response to the quality inspection results failing to meet the preset conditions within the second preset time.

The third control module is configured to control the image acquisition module in response to the failure of the face detection of the facial image in the acquired image within the third preset time after the image acquisition module is awakened Go to sleep.

Received the door lock unlock command;

In some embodiments, for the case where the quality detection includes brightness detection, the quality detection module is configured to perform quality detection on the acquired face image based on multiple pixels in the face image. The pixel value of each pixel in, determine the average brightness value of the multiple pixels;

In some embodiments, for the case where the quality detection includes head posture detection, the quality detection module is used to perform head-level detection on the face image when performing quality detection on the acquired face image. Posture detection to obtain the head posture information of the face in the face image; the head posture information includes: the pitch angle and the yaw angle of the face;

In some embodiments, for the case where the quality detection includes the detection of the degree of blurring, the quality detection module is configured to perform a key function on the face image when performing quality detection on the acquired face image. Point detection to obtain position information of multiple key points in the face image in the face image;

In some embodiments, the quality detection module is configured to determine the sharpness value of the face image according to the position information of each key point in the plurality of key points, , According to the position information of each key point, determine a plurality of target pixels adjacent to the key point position;

In some embodiments, for the case where the quality detection includes detection of the degree of occlusion, the quality detection module is used to perform key point detection on the face image when performing quality detection on the acquired face image , To obtain the key point detection results corresponding to multiple key points in the face image;

In some embodiments, the face detection module is configured to perform face detection on the face image by using a face detection model loaded offline when performing face detection based on the face image.

The loading module is used to load the face detection model offline using the following method:

In some embodiments, the face detection module is used to perform face identity authentication and living body detection based on the face image when performing face detection based on the face image.

The embodiment of the present disclosure provides a vehicle, including: a vehicle body and an image acquisition module provided on the vehicle body; the vehicle body is also provided with a vehicle control system;

The image acquisition module is used to acquire images;

The vehicle control system is used to control the unlocking of the door lock on the vehicle body by using the method for controlling the unlocking of the vehicle as described in any one of the above embodiments.

An embodiment of the present disclosure also provides an electronic device, including a processor and a memory, the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the machine-readable instructions stored in the memory. When the machine-readable instruction is executed by the processor, the machine-readable instruction executes the steps in the foregoing embodiment or any possible implementation of the foregoing embodiment when the machine-readable instruction is executed by the processor.

The present disclosure also provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and the computer program executes the steps in the above-mentioned embodiment or any possible implementation of the above-mentioned embodiment when the computer program is run. .

The embodiment of the present disclosure provides a computer program, the computer program includes computer-readable code, in the case that the computer-readable code runs in a computer, the computer is caused to execute any of the above-mentioned methods for controlling unlocking of a vehicle door .

The present disclosure provides a method, a device, a vehicle, equipment, a medium, and a program for controlling unlocking of a car door; the method includes: in response to a car's image collection module being awakened, acquiring an image collected by the car's image collection module; Perform quality detection on the face image in the image; when the result of the quality detection meets the preset conditions, perform face detection based on the face image; when the face detection of the face image passes, control the car’s At least one door lock is unlocked. In this way, in the embodiment of the present disclosure, the method for controlling the unlocking of the vehicle door does not require the user to perform any operation throughout the entire process, and the equipment is low in loss. The vehicle door can be automatically unlocked when the vehicle owner approaches the vehicle, which is more convenient to use.

In order to make the above objectives, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with accompanying drawings are described in detail as follows.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present disclosure more clearly, the following will briefly introduce the drawings that need to be used in the embodiments. The drawings here are incorporated into the specification and constitute a part of the specification. The figure shows an embodiment conforming to the present disclosure, and is used together with the description to explain the technical solution of the present disclosure. It should be understood that the following drawings only show certain embodiments of the present disclosure, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, they can also Obtain other related drawings based on these drawings.

Fig. 1 shows a flowchart of a method for controlling unlocking of a vehicle door provided by an embodiment of the present disclosure;

FIG. 2 shows a schematic diagram of a system architecture applying the method for controlling unlocking of a vehicle door according to an embodiment of the present disclosure;

FIG. 3 shows an exemplary diagram of the relationship between an image acquisition module and a human body provided by an embodiment of the present disclosure;

FIG. 4 shows a specific example diagram of a method for controlling unlocking of a vehicle door provided by an embodiment of the present disclosure;

FIG. 5 shows a schematic structural diagram of a device for controlling unlocking of a vehicle door provided by an embodiment of the present disclosure;

Fig. 6 shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed ways

In order to make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only These are a part of the embodiments of the present disclosure, but not all of the embodiments. The components of the embodiments of the present disclosure generally described and illustrated in the drawings herein may be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed present disclosure, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of the present disclosure.

Studies have found that the current automotive electronics industry is developing rapidly, and users are paying more and more attention to the convenient and comfortable riding experience; among them, intelligent door unlocking is a highlight of the current riding experience. There are currently two ways to unlock the door:

1) Unlock the car key; for example, the car owner carries a car key that can wirelessly control the car lock; when the car owner is close to the car for a certain distance, the car key is used to wirelessly control the unlocking of the car door. This method requires the car owner to carry the car key with him, and once the car key is lost, the car lock cannot be unlocked; and the car key is usually large and cumbersome to carry; and this method is not convenient for the user to use.

2) Fingerprint unlocking; set up a fingerprint recognition device on the car; pre-enter the fingerprint of the car owner through the fingerprint recognition device, and during authentication, the car owner uses the fingerprint recognition device to perform fingerprint authentication matching. Although this unlocking method does not require the owner to carry the car key, the fingerprint identification device is easy to wear, and the device wears a lot during use. As the number of uses increases, the user may not be able to unlock it at one time, requiring the user to repeatedly input fingerprints for verification. It is not convenient for users to use.

The defects in the above solutions are all the results of the inventors after practice and careful study. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure below for the above problems should be the inventors. Contributions made to this disclosure in the course of this disclosure.

Based on the above research, the present disclosure provides a method, device, vehicle, equipment, medium, and program for controlling unlocking of a car door. By responding to the car's image acquisition module being awakened, the image collected by the car's image acquisition module is acquired, and Perform quality inspection on the face image in the acquired image; if the result of the quality inspection meets the preset conditions, perform face detection based on the face image; if the face image of the face image passes the face detection, control At least one door lock of the vehicle is unlocked; in this way, the user does not need to perform any operation during the whole process, and the equipment loss is small. The door can be unlocked when the owner approaches the vehicle, which is more convenient to use.

It should be noted that similar reference numerals and letters indicate similar items in the following figures. Therefore, once a certain item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

In order to facilitate the understanding of this embodiment, first, a method for controlling unlocking of a vehicle door disclosed in an embodiment of the present disclosure will be introduced in detail. The execution subject of the method for controlling unlocking of a vehicle door provided by the embodiment of the present disclosure is generally a computer with certain computing capabilities. Equipment, the computer equipment includes, for example, terminal equipment, servers or other processing equipment. The terminal equipment may be User Equipment (UE), mobile equipment, user terminal, terminal, cellular phone, cordless phone, personal digital processing (Personal Digital Assistant, PDA), handheld devices, computing devices, wearable devices, etc.; other processing devices are, for example, a vehicle control system integrated with the vehicle. In some possible implementation manners, the method for controlling unlocking of a vehicle door may be implemented by a processor invoking a computer-readable instruction stored in a memory.

In a possible implementation manner, for the case where the execution subject is a server, the vehicle control system can communicate with the server wirelessly; after detecting that a person is approaching the vehicle, the vehicle control system controls the image acquisition module installed on the vehicle to acquire images, And send the image to the server; based on the acquired image, the server executes the method for controlling the unlocking of the vehicle door provided by the embodiment of the present disclosure, and controls the unlocking of the vehicle door by issuing an unlocking instruction to the vehicle control system. In this way, the door unlocking is realized through the interaction between the server and the vehicle control system, which is convenient for users; in addition, the main calculation task of controlling the unlocking of the vehicle door is executed on the server, which reduces the hardware requirements of the vehicle control system and effectively reduces the vehicle cost.

In another possible implementation manner, for the case where the execution subject is a terminal device, the terminal device can communicate with the vehicle control system wirelessly; the vehicle control system controls the image acquisition module installed on the vehicle after detecting that someone is approaching the vehicle The image is acquired and sent to the terminal device; the terminal device executes the method for controlling door unlocking provided by the embodiments of the present disclosure based on the image sent by the vehicle control system, and controls the unlocking of the door by issuing an unlock command to the vehicle control system.

Or, after the terminal device monitors that the distance between it and the vehicle is less than the preset distance, it controls the image acquisition module installed on the terminal device to acquire an image, and executes the method for controlling the unlocking of the door provided by the embodiment of the present disclosure based on the image; And by issuing an unlock command to the vehicle control system to control the unlocking of the door.

In this way, since the terminal device itself is a user's commonly used portable device, the door is unlocked based on the user's commonly used portable device, which not only does not require the user to carry an additional car key, but also facilitates the user to control the unlocking of the door at any time, which is more convenient to use.

In another possible implementation, for the case where the execution subject is the vehicle control system, the vehicle control system can monitor in real time whether the vehicle owner is close to the vehicle; after detecting that the vehicle owner is close to the vehicle, control the image acquisition module installed on the vehicle to acquire The method for controlling the unlocking of the vehicle door provided by the embodiment of the present disclosure is executed based on the image.

In this way, the unlocking of the door is controlled by the vehicle control system, and the user does not need to perform any operations, nor does it need to carry a key to control the unlocking of the door, which is convenient and quick to use.

In addition, it should be noted that the method for controlling the unlocking of the vehicle door provided by the embodiment of the present disclosure may also have other execution subjects, or the manner of interaction between the execution subject and other subjects to control the unlocking of the vehicle doors, which will not be repeated here.

Hereinafter, the method for controlling unlocking of the vehicle door provided by the embodiment of the present disclosure will be described by taking the execution subject as the vehicle control system as an example.

Referring to FIG. 1, it is a flowchart of a method for controlling unlocking of a vehicle door provided by an embodiment of the present disclosure. The method includes steps S101 to S104, wherein:

S101: In response to the image acquisition module of the car being awakened, acquire an image collected by the image acquisition module of the car.

S102: Perform quality detection on the face image in the acquired image.

S103: In the case that the result of the quality detection meets the preset condition, perform face detection based on the face image.

S104: Control the unlocking of at least one door lock of the vehicle when the face detection of the face image passes.

FIG. 2 is a schematic diagram of a system architecture that can apply the method for controlling unlocking of a vehicle door provided by an embodiment of the present disclosure; as shown in FIG. In order to support an exemplary application, the vehicle terminal 201 and the door unlocking terminal 203 establish a communication connection through the network 202. The vehicle terminal 201 reports the images collected by the image acquisition module to the door unlocking terminal device 203 through the network 202, and controls the door unlocking terminal. In response to the received image, the device 203 performs quality detection on the face image in the image based on the image; when the quality detection result meets the preset conditions, performs face detection based on the face image; When the face detection of the image passes, at least one door lock of the control car is unlocked. Finally, the door unlocking terminal 203 is controlled to upload the door unlocking information to the network 202, and send it to the vehicle terminal 201 via the network 202.

As an example, the vehicle terminal 201 may include a vehicle-mounted image acquisition device, and the control door unlocking terminal 203 may include a vehicle-mounted visual processing device or a remote server with visual information processing capabilities. The network 202 may adopt a wired connection or a wireless connection. Among them, when the control door unlocking terminal is a vehicle-mounted visual processing device, the vehicle terminal 201 can communicate with the vehicle-mounted visual processing device through a wired connection, such as data communication through a bus; when the control door unlocking terminal is a remote server, the vehicle terminal 201 can exchange data with a remote server through a wireless network.

Or, in some scenarios, the vehicle terminal 201 may be a vehicle-mounted vision processing device with a vehicle-mounted image acquisition module, which is specifically implemented as a vehicle-mounted host with a camera. At this time, the method for controlling the unlocking of the vehicle door in the embodiment of the present disclosure may be executed by the vehicle terminal 201, and the above-mentioned system architecture may not include the network 202 and the terminal 203 for controlling the unlocking of the vehicle door.

The above S101 to S104 are respectively described in detail below.

I: In the above S101, the image acquisition module of the car is awakened under at least one of the following conditions a1 to a4:

a1: It is detected that the distance between the human body and the vehicle is less than the preset distance.

In this case, for example, an infrared sensor, a distance measuring sensor, etc. may be provided on the vehicle, and the infrared sensor and/or the distance measuring sensor sensor can detect whether the distance between the human body and the vehicle is less than the preset distance.

For another example, short-range wireless communication technologies, such as Zigbee, Radio Frequency Identification (RFID), etc., can be used to monitor in real time whether the mobile terminal carried by the vehicle owner, such as mobile phones, smart bracelets, etc., can be detected; Since the communication distance of short-range communication is usually relatively limited, when the smart device of the vehicle owner can be detected, it means that the smart device of the vehicle owner has entered within a certain distance of the vehicle; at this time, the distance between the vehicle owner and the vehicle is considered to be less than the preset distance. In this way, detecting that the distance between the human body and the vehicle is less than the preset distance can activate the door lock unlocking process, and can perform targeted detection of the vehicle owner, and reduce the detection when people other than the vehicle owner are approaching the vehicle.

The specific preset distance can be set according to actual needs.

a2: Received a door lock unlock command.

Here, the door lock unlocking instruction is, for example, a voice instruction; the user can record the voice in the vehicle control system in advance; after receiving the voice instruction that matches the voice, it is considered that the image acquisition module of the car is to be awakened; the voice instruction is again For example, it is a preset voice; for example, the user can set a name for the vehicle; the vehicle control system will monitor the external voice in real time; when the detected voice contains the name of the vehicle, it is considered that the image collection module of the car should be awakened.

The voice instruction is, for example, an instruction sent through other devices, such as an instruction sent by a user through a portable mobile terminal, such as a mobile phone, smart bracelet, etc.; in this way, receiving a door lock unlocking instruction can facilitate the user to unlock the car lock. control.

There are other ways to receive specific vehicle lock control commands, and the details are not repeated here.

a3: The Bluetooth module placed in the car searches for a Bluetooth device with a preset logo.

Here, the Bluetooth device is, for example, a mobile terminal carried by the user, such as a mobile phone, a smart bracelet, and the like. The Bluetooth search module installed in the car will periodically search for nearby Bluetooth devices with a preset identifier, and if found, wake up the car's image acquisition module.

a4: The Bluetooth module placed in the car has searched for a Bluetooth device with a preset logo and paired successfully.

Here, after the Bluetooth module placed on the car searches for a Bluetooth device with a preset logo and the pairing is successful, the image acquisition module of the car is awakened, and the vehicle control system acquires the image through the image acquisition module installed on the vehicle; At this time, the acquired image may or may not include human faces. Therefore, in a possible implementation manner, first perform face interception processing on the acquired image; if the face image can be obtained therefrom, perform the subsequent steps; if the face image cannot be intercepted from it, control the image acquisition again The module acquires the image. Here, the image acquisition module includes, for example, at least one of a binocular camera and a three-dimensional camera. The installation location of the image acquisition module is, for example, a car B-pillar; in this way, searching for a Bluetooth device with a preset identifier through the Bluetooth module placed on the car can facilitate the vehicle to accurately identify the owner.

In another possible implementation manner, the vehicle control system obtains a video with a preset duration through an image acquisition module installed on the vehicle; the video includes multiple images; the image in the multiple videos can be processed Screening, for example, face interception processing is performed on multiple images in the video; in this case, for example, at least one face image can be obtained; when there are multiple face images (may be from the same image) The intercepted image may also be intercepted from different images), and each obtained image is used as the face image in S102 to perform subsequent processing.

In a possible implementation manner, the embodiment of the present disclosure also provides an example of a specific installation method of the image capture module on the vehicle; as shown in FIG. 3, the coverage of the image capture module's shooting angle of view is in the vertical direction, To cover people with a height of 1.4 meters to 1.9 meters; the installation height of the image acquisition module is 1.5 meters; the angle of the optical axis of the image acquisition module and the plane of the vehicle chassis is up to 2.5 degrees, and the angle to the vertical is 75 Degrees; the resolution of the obtained image is 1280×960; where 1280 is the size of the image in the vertical direction.

It should be noted that the above example only shows an installation method of the image acquisition module; the image acquisition module can also be installed in other ways according to the vehicle model, the height of the vehicle, and the vehicle facing the crowd, etc., which will not be repeated here.

In another embodiment of the present disclosure, in response to that no face image is detected in the image collected within the first preset time after the image acquisition module is awakened, the image acquisition module is controlled to enter the dormant state. In this way, the power consumption of the image acquisition module in the working state for a long time is saved, and at the same time, the image acquisition module can be quickly shut down after performing an incorrect acquisition operation.

After that, other methods can be used to control the unlocking of the door, such as fingerprint retrieval, and the user can control the unlocking of the door through a smart terminal.

II: In the above S102, the quality inspection includes but is not limited to at least one of the following b1 to b5:

b1: Brightness detection.

In a specific embodiment, for example, the following methods may be used to detect the brightness of a face image:

Based on the pixel value of each of the multiple pixels in the face image, the average brightness value of the multiple pixels is determined.

When the average brightness value is greater than the first brightness threshold and less than the second brightness threshold, it is determined that the brightness detection result of the face image meets the brightness condition in the preset condition; wherein the first brightness threshold is less than the second brightness threshold.

Here, for example, all pixels in the face image can be traversed, and the brightness value of the traversed pixel can be determined according to the pixel value of the traversed pixel; and then the average brightness can be determined according to the brightness value of all the traversed pixels .

Exemplarily, the average brightness value face _pixel of multiple pixels in the face image satisfies the following formula (1):

Among them, W represents the width of the face image; H represents the height of the face image; C represents the number of color channels of the face image; (left, top) represents the coordinate value of the pixel at the upper left corner of the face image; I(·) Represents the brightness formula of any pixel of the image.

Exemplarily, the brightness value of any pixel is the weighted sum of the pixel values of the pixel in different color channels.

For example, when the face image is an RGB format image, the weight corresponding to the R channel is 0.3; the weight corresponding to the G channel is 0.59; and the weight corresponding to the B channel is 0.11.

For any pixel (left+w, top+h, c), the brightness value of the pixel satisfies:

0.3×(left+w)+0.59×(top+h)+0.11×c

It should be noted that the foregoing method for calculating the brightness value is only an example of the amount of pixels, and other methods may also be used to calculate the brightness value of the pixel.

For another example, a preset number of pixels can be randomly confirmed in a face image, and then according to the pixel value of each pixel in the determined preset number of pixels, the value of each pixel in the preset number of pixels can be determined Brightness value; then according to the pixel values of all the preset number of pixels, the average brightness value corresponding to the face image is determined.

In another embodiment of the present disclosure, a fill light may also be provided on the vehicle; when it is detected that the average brightness value is greater than or equal to the second brightness threshold, the fill light is controlled to turn on to fill the user's face with light.

In this way, in the embodiments of the present disclosure, by detecting the brightness of the face image, the excessively bright and dark face images are reduced, and the subsequent increase in the difficulty of face detection caused by the over-exposure of the face image or the excessively dark face image is avoided. Improve the accuracy of face detection.

b2: head posture detection.

In specific implementation, for example, the following methods can be used to detect the head posture of a face image:

Head posture detection is performed on the face image to obtain the head posture information of the face in the face image; the head posture information includes: the pitch angle and the yaw angle of the face.

When the absolute value of the pitch angle is less than the pitch angle threshold and the absolute value of the yaw angle is less than the yaw angle threshold, it is determined that the head posture detection result of the face image meets the head posture condition in the preset condition.

Here, when the head pose is detected on the face image, for example, multiple face key points in the face image can be identified; then the rotation matrix of the head pose is determined according to the coordinates of the face key points in the face image And translate the matrix. Then, based on the rotation matrix and the translation matrix, the head posture information is determined.

Among them, the head posture information is expressed as: (yaw, pitch, roll).

Among them, yaw represents the pitch angle, that is, the angle at which a person raises or lowers his head; pitch represents the yaw angle, that is, the angle at which a person's head turns left and right; roll represents a roll angle, that is, the angle at which a person swings his head from side to side.

If the absolute value of the pitch angle is greater than or equal to the pitch angle threshold, or the absolute value of the yaw angle is greater than or equal to the yaw angle threshold, then the face appears in the face image less area; in this case, based on the person The accuracy and feasibility of the facial image to identify whether the person corresponding to the facial image is legal is low. Therefore, when the absolute value of the pitch angle is less than the pitch angle threshold and the absolute value of the yaw angle is less than the yaw angle threshold, the face recognition process in S103 is executed.

In this way, in the embodiment of the present disclosure, by detecting the head posture of the face image, the situation that the face appears in the face image is too small, and the face caused by the face appearing in the face image is too small. The problem of decreased detection accuracy.

b3: Blur degree detection.

In a specific embodiment, for example, the following method may be used to detect the degree of blurring of the face image:

The key point detection is performed on the face image, and the position information of multiple key points in the face image in the face image is obtained.

According to the position information of each key point in the multiple key points, the sharpness value of the face image is determined.

In the case that the sharpness value of the face image is greater than the sharpness threshold, it is determined that the detection result of the blur degree of the face image meets the sharpness condition in the preset condition.

Here, for example, the following method can be used to determine the sharpness value of the face image:

For each key point, according to the position information of each key point, multiple target pixels adjacent to the key point position are determined.

Based on the pixel value of each target pixel corresponding to each key point, the sharpness value of each key point is determined.

According to the sharpness value of each key point in the multiple key points, the sharpness value of the face image is determined.

Exemplarily, assuming that there are M key points of the face in the face image, the sharpness value blur of the face image satisfies the following formula (2):

Among them, landmarks _blur (m) represents the sharpness value of the m-th key point. And the landmarks _blur (m) satisfies the following formula (3):

landmarks _blur (m)=landmarks _blur (m)[x-1,y]+landmarks _blur (m)[x+1,y]

+landmarks _blur (m)[x,y-1]+landmarks _blur (m)[x,y+1] (3);

-4×landmarks _blur (m)[x,y]

landmarks _blur (m)[x,y] represents the coordinates of the m-th key point. landmarks _blur (m)[x-1,y], landmarks _blur (m)[x+1,y], landmarks _blur (m)[x,y-1], landmarks _blur (m)[x,y+1 ] Respectively represent the coordinates of the four target pixel points adjacent to the m-th key point position.

In this way, in the embodiments of the present disclosure, by detecting the degree of blur of the face image, the problem of the accuracy of face detection decreased due to the excessive blur of the face image is reduced. At the same time, the key points are used to accurately locate the face, and the position of the key points in the face image is used to calculate the degree of blurring of the approximate face in the Laplacian gradient, so as to avoid the background of the face image caused by the face definition value. Interference, improve the accuracy of the clarity value.

b4: Resolution detection.

In the specific implementation, after the face image is obtained, the resolution of the face image is detected; if the resolution of the face image is less than the preset resolution threshold, that is, the face is smaller, the face image contains There are fewer facial features; the accuracy of face recognition based on a face image with a smaller resolution will be reduced; therefore, in order to ensure the accuracy of face recognition, resolution detection must be performed on the face image.

b5: occlusion degree detection.

In specific implementation, for example, the following methods can be used to detect the degree of occlusion of a face image:

The key point detection is performed on the face image, and the key point detection results corresponding to multiple key points in the face image are obtained.

Based on the key point detection results corresponding to the multiple key points, the occlusion degree value of the face image is determined.

In a case where the occlusion degree value is less than the occlusion degree value threshold, it is determined that the detection result of the occlusion degree of the face image meets the occlusion degree condition in the preset condition.

Here, in the acquired human face image, the human face may be blocked by obstacles, such as buildings, clothing on the person, accessories, and so on. After the face in the face image is occluded to a certain extent, the accuracy of face recognition will decrease. In order to ensure the accuracy of face recognition, it is necessary to detect the degree of occlusion of the face image.

Exemplarily, suppose there are M key points of the face. For example, a pre-trained face key point detection model can be used to perform key point detection on the face image; the key point detection results obtained include: the key points that can be detected The coordinate value of the point in the face image. If the coordinate value of a certain key point exists, it means that the key point is not occluded; if the coordinate value of a certain key point is empty, it means that the key point is occluded.

The occlusion degree value occlusion of the face image satisfies the following formula (4), for example:

Among them, landmarks(m) satisfies the following formula (5):

Among them, m represents the m-th key point.

The higher the occlusion, the more severe the occlusion of the face; therefore, an occlusion threshold value is set. Only when the occlusion value is less than the occlusion threshold, the face recognition in S103 will be performed on the face image. process.

In the embodiments of the present disclosure, by detecting the degree of occlusion of the face image, the problem that the face detection accuracy is reduced due to the excessive occlusion of the face is reduced.

In this way, in the embodiments of the present disclosure, a variety of quality detection solutions are provided to avoid the phenomenon of misoperation in the quality detection, thereby improving the intelligence and reliability of the detection.

In another embodiment of the present disclosure, in response to that none of the quality inspection results meet the preset condition within the second preset time, the image acquisition module is controlled to enter the dormant state. In this way, the power consumption of the image acquisition module in the working state for a long time is saved, and at the same time, the image acquisition module can be quickly shut down after performing an incorrect acquisition operation.

III: In the above S103, after the result of the quality detection meets the preset condition, for example, the face detection model loaded offline may be used to perform face detection on the face image. In this way, in the embodiment of the present disclosure, the face detection model is pre-loaded offline, and when the vehicle lock is controlled to unlock, there is no need to load various models immediately, and the response speed is faster.

Specifically, the face detection model can be loaded offline using the following method, for example:

The face detection model is converted from the encryption mode to the plaintext mode, and the face detection model converted to the plaintext mode is written into the header file of the car lock control system.

Here, offline loading may be completed when the vehicle leaves the factory, or when the user sets the lock control system of the vehicle for the first time, or after the face detection model is updated. In this way, by writing the face detection model converted to the plaintext mode into the header file of the car lock control system and statically compiling it, the robustness of the offline loading process of the face detection model can be improved.

In this way, after the vehicle lock control system is awakened, there is no need to load the face detection model instantly, which speeds up the response speed of the vehicle control system.

In a specific implementation, the face detection of the face image includes, for example, performing face identity authentication and living body detection on the face image.

Exemplarily, a face template image of the vehicle owner is stored in the vehicle control system, and there is at least one face template image; and the angles of the faces in the face images of different templates are different. When the face image is authenticated, for example, multiple key points in the face image can be detected; then the key points of the face image are matched with the face key points in each face template image to obtain the person The matching degree between the face image and each face template image; if the matching degree between the face image and the preset number of face template images is greater than the preset matching degree, the face matching detection of the face image .

In addition, live detection of face images, for example, can obtain a video of a preset duration through an image acquisition module installed on a vehicle; then, for multiple images in the video, at least one person has multiple faces that are different; where Multiple face images belonging to the same person belong to different images in the video. For each person, the quality of the multiple face images of the person is tested separately, and at least two face images are determined from them, and based on at least two faces The difference feature between the images is used to determine whether the person corresponding to the two face images is alive. When it is confirmed as a living body, it passes the living body detection of the face image.

Here, for example, the life detection of the face image may be performed based on a pre-trained life detection model.

In this way, in the embodiment of the present disclosure, the verification of the legitimate user is achieved through face identity authentication, and the living body detection can effectively prevent the use of photo spoofing to attack the vehicle control system to steal the vehicle.

In another embodiment of the present disclosure, if the quality detection of the face image does not meet the preset conditions, prompt information is also output; for example, prompt information such as voice can be issued to the user according to the specific results of the quality detection, if The quality inspection includes the detection of the occlusion degree, and when the occlusion degree fails, the user is prompted "the area of the occlusion is too large"; if the quality detection includes the brightness detection and the brightness detection fails, the user is prompted "the current light is too dark", etc. Set according to actual needs. In this way, a prompt message is issued to the user based on the specific result of the quality inspection, so that the user can be informed of the failure of the inspection in time and take relevant measures.

In another embodiment of the present disclosure, the model used to obtain the face image and the model used in the quality detection process of the face image can be pre-loaded offline; the loading method is the same as the offline loading method of the face detection model described above Similar, I won't repeat it here.

In another embodiment of the present disclosure, in response to the face detection of the face image in the acquired image fails within the third preset time after the image acquisition module is awakened, the image acquisition module is controlled to enter sleep state. In this way, by controlling one or more of the above-mentioned image acquisition modules to enter the sleep state, the process of unlocking the door is restricted to a certain period of time, and the deadlock state is prevented from entering the unlocking process.

In the embodiment of the present disclosure, in response to the image acquisition module of the car to be awakened, the image acquired by the image acquisition module of the car is acquired, and the quality inspection of the face image in the acquired image is performed; the result of the quality inspection conforms to the preset Under the conditions, face detection is based on the face image; if the face detection of the face image is passed, at least one door lock of the car is unlocked; the user does not need to perform any operation throughout the process, and the equipment loss is small. When the owner approaches the vehicle, the door lock can be unlocked, which is more convenient to use.

Those skilled in the art can understand that in the above-mentioned methods of the specific implementation, the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process. The specific execution order of each step should be based on its function and possibility. The inner logic is determined.

Referring to FIG. 4, the embodiment of the present disclosure also provides a specific example of a method for controlling unlocking of a vehicle door, including:

S401: In response to the image acquisition module of the car being awakened, acquire an image collected by the image acquisition module of the car.

S402: Detect whether the face image can be detected in the image collected within the first preset time after the image collection module is awakened; if not, skip to S403; if yes, skip to S404.

S403: Control the image acquisition module to enter a sleep state. Finish.

S404: Perform quality detection on the face image in the acquired image; the quality detection includes: brightness detection, head posture detection, blur degree detection, resolution detection, and occlusion degree detection.

S405: Determine whether the result of the quality inspection meets the preset condition within the second preset time; if not, skip to S403; if yes, skip to S406.

S406: Perform face detection based on the face image.

S407: Determine whether the face detection of the face image in the acquired image is passed within the third preset time after the image acquisition module is awakened; if not, skip to S403; if yes, skip to S408.

S408: Control the unlocking of at least one door lock of the vehicle. Finish.

In this way, through the above process, a control process of unlocking the door is realized.

Based on the same inventive concept, the embodiment of the present disclosure also provides a device for controlling the unlocking of a vehicle door corresponding to the method for controlling the unlocking of a vehicle door. Because the device in the embodiment of the present disclosure solves the problem and the method for controlling the unlocking of the vehicle door described above in the embodiment of the present disclosure Similar, so the implementation of the device can refer to the implementation of the method, and the repetition will not be repeated.

Referring to FIG. 5, a schematic diagram of a device 5 for controlling unlocking of a vehicle door provided by an embodiment of the present disclosure. The device 5 includes: a response module 51, a quality detection module 52, a face detection module 53, and a vehicle lock control module 54 ;in,

The response module 51 is configured to acquire images collected by the image acquisition module of the car in response to the image acquisition module of the car being awakened;

The quality detection module 52 is configured to perform quality detection on the face image in the acquired image;

The face detection module 53 is configured to perform face detection based on the face image when the result of the quality inspection meets a preset condition;

The vehicle lock control module 54 is configured to control the unlocking of at least one door lock of the vehicle when the face detection of the face image passes.

In the embodiment of the present disclosure, in response to the image acquisition module of the car to be awakened, the image acquired by the image acquisition module of the car is acquired, and the quality inspection of the face image in the acquired image is performed; the result of the quality inspection conforms to the preset Under the conditions, face detection is based on the face image; if the face detection of the face image is passed, at least one door lock of the car is unlocked; the user does not need to perform any operation throughout the process, and the equipment loss is small. When the owner approaches the vehicle, the door can be unlocked, which is more convenient to use.

In a possible implementation manner, the device 5 for controlling unlocking of a vehicle door further includes: a first control module 55, configured to respond to the images captured within the first preset time after the image capture module is awakened If no face image is detected, the image acquisition module is controlled to enter a sleep state.

In a possible implementation manner, the device 5 for controlling unlocking of a vehicle door further includes: a prompt module 56 for outputting prompt information when the result of the quality inspection does not meet a preset condition.

In a possible implementation manner, the device 5 for controlling unlocking of a vehicle door further includes: a second control module 57 for controlling the The image acquisition module enters a sleep state.

In a possible implementation manner, the device 5 for controlling unlocking of the vehicle door further includes: a third control module 58 for responding to the image acquired within the third preset time after the image acquisition module is awakened The face detection of the face image in the image fails, and the image acquisition module is controlled to enter the dormant state.

In a possible implementation manner, the image acquisition module of the vehicle is awakened in at least one of the following situations: it is detected that the distance between the human body and the vehicle is less than a preset distance; the door unlocking instruction is received; the Bluetooth is placed on the vehicle The module searches for a Bluetooth device with a preset identification; the Bluetooth module placed in the car searches for a Bluetooth device with a preset identification and the pairing is successful.

In a possible implementation manner, the quality detection includes at least one of the following: brightness detection, head posture detection, blur degree detection, resolution detection, and occlusion degree detection.

In a possible implementation manner, for the case where the quality detection includes brightness detection, the quality detection module 52 is configured to perform quality detection on the acquired face image based on the number of images in the face image. The pixel value of each pixel in the pixel points, determining the average brightness value of the multiple pixel points;

In a possible implementation manner, for the case where the quality detection includes head posture detection, the quality detection module 52 is configured to perform quality detection on the face image acquired when performing quality detection on the face image. Perform head posture detection to obtain head posture information of the face in the face image; the head posture information includes: the pitch angle and the yaw angle of the face;

In a possible implementation manner, for the case where the quality detection includes the detection of the degree of blurring, the quality detection module 52 is configured to perform the quality detection on the acquired face image. Perform key point detection on the image to obtain position information of multiple key points in the face image in the face image;

In a possible implementation manner, the quality detection module 52 is configured to determine the sharpness value of the face image according to the position information of each key point in the plurality of key points, and use it to target each key point. Key points, according to the position information of each key point, determine multiple target pixels adjacent to the key point position;

In a possible implementation manner, for the case where the quality detection includes detection of the degree of occlusion, the quality detection module 52 is configured to perform quality detection on the face image when performing quality detection on the face image. Key point detection, to obtain the key point detection results corresponding to multiple key points in the face image;

In a possible implementation manner, the face detection module 53 is configured to perform face detection on the face image by using a face detection model loaded offline when performing face detection based on the face image.

In a possible implementation manner, the device 5 for controlling unlocking of a vehicle door further includes: a loading module 59, configured to load the face detection model offline by using the following method:

In a possible implementation manner, the face detection module 53 is configured to perform face identity authentication and living body detection based on the face image when performing face detection based on the face image.

For the description of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant description in the above method embodiment, which will not be described in detail here.

The embodiment of the present disclosure also provides a vehicle, including: a vehicle body and an image acquisition module provided on the vehicle body; the vehicle body is also provided with a vehicle control system;

The image acquisition module is used to acquire images;

The vehicle control system is used to control the unlocking of the door lock on the vehicle body by adopting the method for controlling the unlocking of the vehicle according to any one of the embodiments of the present disclosure.

The embodiment of the present disclosure also provides an electronic device 6, as shown in FIG. 6, which is a schematic structural diagram of the computer device 6 provided by the embodiment of the present disclosure, including:

A processor 61 and a memory 62; the memory 62 stores machine-readable instructions executable by the processor 61, and when the computer device is running, the machine-readable instructions are executed by the processor to implement the following steps:

Performing quality detection on the face image in the acquired image;

In the case where the face detection of the face image passes, at least one door lock of the vehicle is controlled to be unlocked.

For the specific execution process of the foregoing instructions, reference may be made to the steps of the method for controlling the unlocking of the vehicle door described in the embodiments of the present disclosure, which will not be repeated here.

The embodiment of the present disclosure also provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and the computer program executes the steps of the method for controlling unlocking of a vehicle door described in the above method embodiment when the computer program is run by a processor . Wherein, the storage medium may be a volatile or non-volatile computer readable storage medium.

The computer program product of the method for controlling the unlocking of a vehicle door provided by the embodiment of the present disclosure includes a computer-readable storage medium storing a program code, and the instructions included in the program code can be used to execute the control of the unlocking of the vehicle door described in the foregoing method embodiment For details of the steps of the method, please refer to the above method embodiment, which will not be repeated here.

The embodiments of the present disclosure also provide a computer program, the computer program including computer readable code, when the computer readable code runs in an electronic device, the processor of the electronic device executes the method for realizing the method described in any of the foregoing embodiments. The method of controlling the unlocking of the car door described above. The computer program product can be specifically implemented by hardware, software, or a combination thereof. In some embodiments of the present disclosure, the computer program product is specifically embodied as a computer storage medium. In some embodiments of the present disclosure, the computer program product is specifically embodied as a software product, such as a software development kit (SDK). and many more.

Those skilled in the art can clearly understand that, for the convenience and conciseness of the description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device, and method may be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation. For example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some communication interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.

If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present disclosure essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present disclosure. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

Finally, it should be noted that the above-mentioned embodiments are only specific implementations of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than limit it. The protection scope of the present disclosure is not limited to this, although referring to the foregoing The embodiments describe the present disclosure in detail, and those of ordinary skill in the art should understand that any person skilled in the art can still modify the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present disclosure. Or it can be easily conceived of changes, or equivalent replacements of some of the technical features; and these modifications, changes or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered by the present disclosure. Within the scope of protection. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Industrial applicability

The present disclosure provides a method, device, vehicle, equipment, medium, and program for controlling unlocking of a car door; wherein, in response to the car's image collection module being awakened, the image collected by the car's image collection module is acquired; Perform quality detection on the face image in the image; perform face detection based on the face image if the result of the quality detection meets preset conditions; perform face detection on the face image In the case of passing, at least one door lock of the vehicle is controlled to be unlocked.

Claims

A method for controlling unlocking of a vehicle door includes:

In response to the image acquisition module of the car being awakened, acquiring the image collected by the image acquisition module of the car;

Performing quality detection on the face image in the acquired image;

In the case that the result of the quality detection meets the preset condition, performing face detection based on the face image;

In the case where the face detection of the face image passes, at least one door lock of the vehicle is controlled to be unlocked.
The method according to claim 1, further comprising:

In response to that no human face image is detected in the image collected within the first preset time after the image acquisition module is awakened, the image acquisition module is controlled to enter a sleep state.
The method according to claim 1, further comprising:

In the case that the result of the quality inspection does not meet the preset condition, a prompt message is output.
The method according to claim 3, further comprising:

In response to that none of the quality detection results meet the preset conditions within the second preset time, the image acquisition module is controlled to enter a dormant state.
The method according to claim 1, further comprising:

In response to the failure of the face detection of the face images in the acquired image within the third preset time after the image acquisition module is awakened, the image acquisition module is controlled to enter the dormant state.
According to the method of any one of claims 1 to 5, the image acquisition module of the car is awakened in at least one of the following situations:

It is detected that the distance between the human body and the vehicle is less than the preset distance;

Receiving a door unlocking instruction;

The Bluetooth module placed in the car searches for a Bluetooth device with a preset logo;

The Bluetooth module placed in the car searches for a Bluetooth device with a preset identification and is successfully paired.
The method according to any one of claims 1 to 6, wherein the quality detection includes at least one of the following: brightness detection, head posture detection, blur degree detection, resolution detection, and occlusion degree detection.
The method according to claim 7, for the case where the quality detection includes brightness detection, the quality detection on the acquired face image includes:

Determining the average brightness value of the plurality of pixels based on the pixel value of each of the plurality of pixels in the face image;

In the case that the average brightness value is greater than the first brightness threshold and less than the second brightness threshold, it is determined that the brightness detection result of the face image meets the brightness condition in the preset condition; wherein, the first brightness threshold Less than the second brightness threshold.
The method according to claim 7 or 8, for the case where the quality detection includes head posture detection, the quality detection on the acquired face image includes:

Performing head posture detection on the face image to obtain head posture information of the face in the face image; the head posture information includes: the pitch angle and the yaw angle of the face;

In the case where the absolute value of the pitch angle is less than the pitch angle threshold and the absolute value of the yaw angle is less than the yaw angle threshold, it is determined that the head posture detection result of the face image meets the preset conditions. Head posture conditions.
The method according to any one of claims 7 to 9, for the case where the quality detection includes the detection of the degree of blur, the quality detection of the acquired face image includes:

Performing key point detection on the face image to obtain position information of multiple key points in the face image in the face image;

Determine the sharpness value of the face image according to the position information of each key point in the plurality of key points;

In the case that the sharpness value of the face image is greater than the sharpness threshold value, it is determined that the blur degree detection result of the face image meets the sharpness condition in the preset condition.
The method according to claim 10, wherein the determining the sharpness value of the face image according to the position information of each key point in the plurality of key points comprises:

For each key point, determine a plurality of target pixels adjacent to the key point position according to the position information of each key point;

Determine the sharpness value of each key point based on the pixel value of each target pixel point corresponding to each key point;

The sharpness value of the face image is determined according to the sharpness value of each key point in the plurality of key points.
The method according to any one of claims 7 to 11, for the case where the quality detection includes the detection of the degree of occlusion, the quality detection of the acquired face image includes:

Performing key point detection on the face image to obtain key point detection results corresponding to multiple key points in the face image;

Determine the occlusion degree value of the face image based on the key point detection results respectively corresponding to the multiple key points;

In the case that the occlusion degree value is less than the occlusion degree value threshold, it is determined that the occlusion degree detection result of the face image meets the occlusion degree condition in the preset condition.
The method according to any one of claims 1 to 12, the performing face detection based on the face image comprises:

The face detection is performed on the face image by using the face detection model loaded offline.
According to the method of claim 13, the following method is adopted to load the face detection model offline:

Converting the face detection model from an encryption mode to a plain text mode, and writing the face detection model converted to the plain text mode into a header file of the car lock control system;

The header file is statically compiled to load the face detection model offline.
The method according to any one of claims 1 to 14, wherein the performing face detection based on the face image comprises:

Perform face identity authentication and living body detection based on the face image.
A device for controlling unlocking of a vehicle door includes:

The response module is used to obtain the image collected by the image acquisition module of the car in response to the image acquisition module of the car being awakened;

A quality detection module, configured to perform quality detection on the face image in the acquired image;

A face detection module, configured to perform face detection based on the face image when the result of the quality detection meets a preset condition;

The vehicle lock control module is used to control the unlocking of at least one door lock of the vehicle when the face detection of the face image passes.
A vehicle includes: a vehicle body and an image acquisition module arranged on the vehicle body; the vehicle body is also provided with a vehicle control system;

The image acquisition module is used to acquire images;

The vehicle control system is used to control the unlocking of the door lock on the vehicle body by using the method for controlling the unlocking of the vehicle according to any one of claims 1 to 15.
An electronic device comprising: a processor and a memory, the memory storing machine-readable instructions executable by the processor, the processor being used to execute the machine-readable instructions stored in the memory, the machine being able to When the read instruction is executed by the processor, the processor executes the steps of the method for controlling unlocking of a vehicle door according to any one of claims 1 to 15.
A computer-readable storage medium having a computer program stored on the computer-readable storage medium, and when the computer program is run by an electronic device, the electronic device executes the control door of any one of claims 1 to 15 Steps of unlocking method.
A computer program, the computer program comprising computer readable code, when the computer readable code runs in an electronic device, the processor of the electronic device executes for realizing any one of claims 1 to 15 The method of controlling the unlocking of the vehicle door as described in the item.