CN116189337A

CN116189337A - Child lock control method and device based on facial recognition and vehicle

Info

Publication number: CN116189337A
Application number: CN202310174981.0A
Authority: CN
Inventors: 柯晓萌
Original assignee: Chongqing Changan Automobile Co Ltd
Current assignee: Chongqing Changan Automobile Co Ltd
Priority date: 2023-02-28
Filing date: 2023-02-28
Publication date: 2023-05-30

Abstract

The application provides a child lock control method and device based on facial recognition and a vehicle, and relates to the technical field of vehicle-mounted child lock control. The method comprises the following steps: collecting a target image in the vehicle; determining a first facial feature of the acquisition object in the target image according to the target image; comparing the first facial features with preset second facial features to obtain a comparison result representing whether the first facial features and the second facial features are matched; collecting in-vehicle environment information of the vehicle; obtaining an analysis result representing whether the vehicle interior environment is dangerous or not according to the vehicle interior environment information; and controlling the child lock to execute locking or unlocking actions according to the comparison result and the analysis result. Therefore, the problems that the existing mode of controlling the child lock through face recognition is imperfect, the control mode is inflexible, emergency environments cannot be handled, and safety risks are caused can be solved.

Description

Child lock control method and device based on facial recognition and vehicle

Technical Field

The invention relates to the technical field of vehicle-mounted child lock control, in particular to a child lock control method and device based on facial recognition and a vehicle.

Background

The vehicle-mounted child lock is an active safety device for ensuring the safety of children in a vehicle, and prevents the danger caused by the false door opening of the children in the vehicle in the running process of the vehicle. Under the locking condition of the child safety lock, even if the child safety device is unlocked electrically through the central control lock, the child safety device is still in a locking state, the vehicle door can only be opened from the outside, and the door handle in the vehicle temporarily loses the door opening function.

At present, two control methods for the child lock are mainly adopted, one is that the weight of a passenger is taken as a parameter basis in the traditional method, and then the locking or unlocking of the child lock is controlled; the other is to collect face images of passengers in the car in real time, judge whether the rear seats in the car have children passengers or not, and then control locking or unlocking of the child locks. The method for controlling the child lock through face recognition is not perfect, and the problem that the control mode is inflexible, the emergency environment cannot be dealt with, and safety risks are caused exists. For example, in winter and summer, a vehicle is temporarily parked at a roadside and a child is often left in the vehicle, and when the temperature in the vehicle is constant without an air conditioner, the temperature in the vehicle is rapidly changed, and the child lock is automatically locked, so that the child with small age but self-movement capability cannot automatically open a door from the vehicle, and safety accidents are easily caused.

Disclosure of Invention

In view of the foregoing, an object of the embodiments of the present application is to provide a method, a device and a vehicle for controlling a child lock based on face recognition, which can improve the problems that the current method for controlling the child lock through face recognition is imperfect, the control method is inflexible, the emergency environment cannot be dealt with, and the safety risk is further caused.

In order to achieve the technical purpose, the technical scheme adopted by the application is as follows:

in a first aspect, an embodiment of the present application provides a child lock control method based on face recognition, where the method includes:

collecting a target image in the vehicle, wherein the target image is a facial image of a collected object in the vehicle, and the collected object comprises passengers or pets sitting in a rear seat in the vehicle;

determining a first facial feature of the acquisition object in the target image according to the target image, wherein the first facial feature comprises first facial feature information corresponding to the target image;

comparing the first facial features with preset second facial features to obtain a comparison result representing whether the first facial features and the second facial features are matched, wherein the second facial features comprise second facial feature information corresponding to a preset facial image;

Collecting in-vehicle environment information of the vehicle, wherein the in-vehicle environment information comprises at least one of temperature information, humidity information, oxygen concentration information and carbon monoxide concentration information;

obtaining an analysis result representing whether the vehicle interior environment is dangerous or not according to the vehicle interior environment information;

and controlling the child lock to execute locking or unlocking actions according to the comparison result and the analysis result.

With reference to the first aspect, in some optional embodiments, comparing the first facial feature with a preset second facial feature to obtain a comparison result that characterizes whether the first facial feature and the second facial feature match, includes:

determining that the comparison result is facial feature matching when the similarity between at least one piece of first facial feature information and at least one piece of second facial feature information is greater than or equal to a first preset similarity threshold;

and when the similarity between any one of the first facial feature information and any one of the second facial feature information is smaller than a first preset similarity threshold value, determining that the comparison result is that the facial features are not matched.

With reference to the first aspect, in some optional embodiments, before controlling the child lock to perform the locking or unlocking action according to the comparison result and the analysis result, the method further includes:

When the comparison result is facial feature matching, the similarity is saved, so that historical similarity representing the change condition of the first facial feature is obtained;

when the values of the historical similarity are in a decreasing trend and the similarity is smaller than a second preset similarity threshold value on the premise that any comparison result is facial feature matching, counting the quantity of the first facial feature information corresponding to the first facial feature, wherein the historical similarity is a group of non-equally-spaced time sequences;

when the number of the first facial feature information is greater than or equal to a feature number threshold, the preset facial image is updated with the target image corresponding to the first facial feature.

With reference to the first aspect, in some optional embodiments, before collecting in-vehicle environment information of the host vehicle, the method further includes:

when the comparison result is that the facial features are not matched, acquiring an age bracket of the acquisition object through a preset age prediction model based on the target image;

and when the age bracket of the acquisition object is in a preset age bracket, changing the comparison result to be facial feature matching.

when the comparison result is that the facial features are matched, acquiring weight information of the acquisition object through a preset pressure sensor;

and when the weight information is larger than a preset weight threshold value, changing the comparison result to be that the facial features are not matched.

With reference to the first aspect, in some optional embodiments, obtaining an analysis result that characterizes whether the in-vehicle environment is dangerous according to the in-vehicle environment information includes:

when the in-vehicle environment information is in the corresponding preset environment information range, determining that the analysis result is in-vehicle environment safety;

when any one of the in-vehicle environmental information exceeds a first preset duration of a corresponding preset environmental information range, determining that the analysis result is in-vehicle environmental risk;

the preset environment information range comprises a preset temperature range, a preset humidity range, a preset oxygen concentration range and a preset carbon monoxide concentration range.

With reference to the first aspect, in some optional embodiments, controlling the child lock to perform locking or unlocking actions according to the comparison result and the analysis result includes:

When the comparison result is that the facial features are matched or the facial features are not matched and the analysis result is that the environment in the vehicle is dangerous, controlling the child lock to execute unlocking action;

when the comparison result is facial feature matching and the analysis result is in-car environment safety, controlling the child lock to execute locking action;

and when the comparison result is that the facial features are not matched and the analysis result is that the environment in the vehicle is safe, controlling the child lock to execute unlocking action.

With reference to the first aspect, in some optional embodiments, when the comparison result is that facial features match, and the analysis result is that the in-vehicle environment is safe, controlling the child lock to perform a locking action includes:

when the comparison result is facial feature matching and the analysis result is in-vehicle environment safety, determining the position information of the acquisition object according to the target image;

and controlling the child lock of the vehicle door on the corresponding side of the position information to execute locking action according to the position information.

In a second aspect, an embodiment of the present application further provides a child lock control device based on facial recognition, where the device includes:

the first acquisition unit is used for acquiring a target image in the vehicle, wherein the target image is a facial image of an acquisition object in the vehicle, and the acquisition object comprises passengers or pets sitting in a rear seat in the vehicle;

A determining unit, configured to determine, according to the target image, a first facial feature of the acquisition object in the target image, where the first facial feature includes first facial feature information corresponding to the target image;

the comparison unit is used for comparing the first facial features with preset second facial features to obtain comparison results representing whether the first facial features and the second facial features are matched or not, and the second facial features comprise second facial feature information corresponding to preset facial images;

the second acquisition unit is used for acquiring in-vehicle environment information of the vehicle, wherein the in-vehicle environment information comprises at least one of temperature information, humidity information, oxygen concentration information and carbon monoxide concentration information;

the analysis unit is used for obtaining an analysis result representing whether the vehicle interior environment is dangerous or not according to the vehicle interior environment information;

and the control unit is used for controlling the child lock to execute locking or unlocking actions according to the comparison result and the analysis result.

In a third aspect, embodiments of the present application further provide a vehicle, where the vehicle includes a processor and a memory coupled to each other, and the memory stores a computer program, where the computer program, when executed by the processor, causes the vehicle to perform the method described above.

In a fourth aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes a processor and a memory coupled to each other, where the memory stores a computer program, and when the computer program is executed by the processor, causes the electronic device to perform the method described above.

In a fifth aspect, embodiments of the present application further provide a computer readable storage medium, where a computer program is stored, which when run on a computer, causes the computer to perform the above-mentioned method.

The invention adopting the technical scheme has the following advantages:

in the technical scheme provided by the application, the first facial features of the acquisition object in the target image are determined by acquiring the target image in the vehicle and according to the target image, and then the first facial features and the preset second facial features are compared to obtain a comparison result representing whether the first facial features and the second facial features are matched or not; after the comparison result is obtained, the in-car environment information of the vehicle is collected, an analysis result representing whether the in-car environment is dangerous or not is obtained according to the in-car environment information, and finally the child lock is controlled to execute locking or unlocking actions according to the comparison result and the analysis result. Therefore, the problems that the existing mode of controlling the child lock through face recognition is imperfect, the control mode is inflexible, emergency environments cannot be handled, and safety risks are caused can be solved.

Drawings

The present application may be further illustrated by the non-limiting examples given in the accompanying drawings. It is to be understood that the following drawings illustrate only certain embodiments of the present application and are therefore not to be considered limiting of its scope, for the person of ordinary skill in the art may derive other relevant drawings from the drawings without inventive effort.

Fig. 1 is a flow chart of a child lock control method based on face recognition according to an embodiment of the present application.

Fig. 2 is a historical similarity line graph provided in an embodiment of the present application.

Fig. 3 is a block diagram of a child lock control device based on face recognition according to an embodiment of the present application.

Icon: 200-a child lock control based on facial recognition; 210-a first acquisition unit; 220-a determination unit; 230-a comparison unit; 240-a second acquisition unit; 250-an analysis unit; 260-control unit.

Detailed Description

The present application will be described in detail below with reference to the drawings and the specific embodiments, and it should be noted that in the drawings or the description of the specification, similar or identical parts use the same reference numerals, and implementations not shown or described in the drawings are in a form known to those of ordinary skill in the art. In the description of the present application, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.

The embodiment of the application provides an electronic device which can comprise a processing module and a storage module. The memory module stores a computer program which, when executed by the processing module, enables the electronic device to perform the respective steps in the face recognition based child lock control method described below.

In this embodiment, the electronic device may be an overall vehicle controller disposed on the host vehicle, and is configured to implement image or data processing, obtain a comparison result and an analysis result, and control the child lock to execute a locking or unlocking action according to the comparison result and the analysis result. It can be understood that, when the whole vehicle controller controls the child lock to execute the locking or unlocking action, the initial state of the child lock can be a locking state or an unlocking state, that is, when the whole vehicle controller controls the child lock to execute the locking action and the initial state of the child lock is a locking state, the child lock can not execute any action after receiving the control command of the whole vehicle controller; or when the whole vehicle controller controls the child lock to execute the unlocking action and the initial state of the child lock is the unlocking state, the child lock can not execute any action after receiving the control command of the whole vehicle controller.

Referring to fig. 1, the present application further provides a child lock control method based on facial recognition, where the method may be applied to the above-mentioned electronic device, and the electronic device executes or implements each step of the method. The child lock control method based on face recognition can comprise the following steps:

step 110, acquiring a target image in the vehicle, wherein the target image is a facial image of an acquisition object in the vehicle, and the acquisition object comprises passengers or pets sitting in a rear seat in the vehicle;

step 120, determining a first facial feature of the acquisition object in the target image according to the target image, wherein the first facial feature comprises first facial feature information corresponding to the target image;

step 130, comparing the first facial feature with a preset second facial feature to obtain a comparison result representing whether the first facial feature and the second facial feature are matched, wherein the second facial feature comprises second facial feature information corresponding to a preset facial image;

step 140, acquiring in-vehicle environment information of the vehicle, wherein the in-vehicle environment information comprises at least one of temperature information, humidity information, oxygen concentration information and carbon monoxide concentration information;

Step 150, obtaining an analysis result representing whether the vehicle interior environment is dangerous or not according to the vehicle interior environment information;

and step 160, controlling the child lock to execute locking or unlocking actions according to the comparison result and the analysis result.

In the above embodiment, by acquiring the target image in the host vehicle, determining the first facial feature of the acquisition object in the target image according to the target image, and comparing the first facial feature with the preset second facial feature, a comparison result representing whether the first facial feature and the second facial feature are matched is obtained; after the comparison result is obtained, the in-car environment information of the vehicle is collected, an analysis result representing whether the in-car environment is dangerous or not is obtained according to the in-car environment information, and finally the child lock is controlled to execute locking or unlocking actions according to the comparison result and the analysis result. Therefore, the problems that the existing mode of controlling the child lock through face recognition is imperfect, the control mode is inflexible, emergency environments cannot be handled, and safety risks are caused can be solved.

The following will describe in detail the steps of the child lock control method based on face recognition, as follows:

in step 110, the target image may be a face image or a pet face image acquired in real time through a preset vehicle-mounted camera, that is, the vehicle-mounted camera is kept in a working state after the whole vehicle is started, and when the vehicle-mounted camera senses that a passenger or a pet enters a rear space of the vehicle for a second preset time period (for example, 30 seconds), the face image of the passenger or the pet is acquired as the target image.

In step 120, the first facial feature may be understood as a set of facial features of the passenger or the pet in the target image acquired in real time, and the first facial feature information may be understood as specific feature information, such as texture feature information, shape feature information, five-sense organ feature information, and the like, of the facial image of the passenger or the pet. It will be appreciated that under the first facial features of the same acquisition object, a plurality of types of first facial feature information may be included.

In step 130, the preset facial image may be a template image stored in advance by the user on an in-vehicle terminal connected to the in-vehicle controller or a server interconnected with the in-vehicle terminal according to personal needs, for example, a facial template image of a passenger in a regular manner, or a facial template image of a family pet. It is understood that the template image may include a front face, a side face, a facial feature close-up image, etc. of the frequent passenger or the home pet, so as to clearly and comprehensively express facial feature information of the frequent passenger or the home pet, and the content of the template image is not particularly limited herein. The face image described in the template image is not limited to the child for which the child lock functions, and may be a person with weak self-behavior such as the elderly or disabled. The second facial features may be a set of facial features of the frequent passenger or the home pet extracted from the template image according to a preset template image, and the second facial feature information may be understood as specific feature information such as texture feature information, shape feature information, five sense organ feature information, etc. possessed by the facial image of the frequent passenger or the home pet.

In this embodiment, comparing the first facial feature with a preset second facial feature to obtain a comparison result that characterizes whether the first facial feature and the second facial feature match may include:

It can be appreciated that, in practical applications, the target image acquired by the camera may not include all facial feature information of the acquired object, for example, when the target image includes only the side face of the passenger, the facial feature information may include only the side face shape feature, the ear shape feature, and the like of the passenger; but each individual has unique facial features, whether it be a person or a pet. Therefore, in the first facial feature and the second facial feature, only one piece of first facial feature information and one piece of second facial feature information are required to be the same or highly similar (the similarity is greater than or equal to a first preset similarity threshold value) respectively, and the comparison result can be determined to be facial feature matching, namely the same person or pet is recorded in the target image and the preset facial image acquired in real time; otherwise, in the first facial feature and the second facial feature, the fact that any first facial feature information and second facial feature information are identical or highly similar does not exist can be determined, and the comparison result is that facial features are not matched, namely the target image acquired in real time and the preset facial image are not recorded with the same person or pet.

In this embodiment, the similarity threshold may be flexibly set according to practical situations, for example, when the similarity representing that the first facial feature and the second facial feature are identical is 100%, the similarity threshold may be set to a value close to 100%, such as 95%, 90%, 85%, and the like, which is 90% in this embodiment.

For example, when the first facial feature includes first eyebrow feature information and first lip feature information, and the second facial feature includes second face feature information, second eyebrow feature information and second lip feature information, the first facial feature and the second facial feature are compared, wherein the similarity of the first eyebrow feature information and the second eyebrow feature information is 93%, the similarity of the first lip feature information and the second lip feature information is 96%, and both the similarity exceeds a similarity threshold value of 90%, that is, two pieces of first facial feature information exist in the first facial feature, and the similarity between the two pieces of second facial feature information exceeds the similarity threshold value, and the comparison result is determined to be facial feature matching.

In step 140, in-vehicle environmental information is collected through a preset sensor assembly, which may be a temperature sensor, a humidity sensor, an oxygen concentration sensor, a carbon monoxide concentration sensor, or the like. It can be understood that the collection of the in-vehicle environment information can be performed at short time intervals with preset period (such as once every 1 second and once every 1 minute), or continuous real-time collection of uninterrupted operation.

In step 150, obtaining an analysis result representing whether the in-vehicle environment is dangerous according to the in-vehicle environment information may include:

In this embodiment, the preset environmental information range may represent a daily environment suitable for human and pet survival, for example, the preset temperature range may be between 10 ℃ and 30 ℃, the preset humidity range may be between 5% rh (Relative Humidity ) and 95% rh, the preset oxygen concentration range may be between 19.5% and 23.5%, and the preset carbon monoxide concentration may be between 0.6mg/m3 and 30mg/m 3.

In this embodiment, the first preset duration may be flexibly set according to actual requirements, for example, 1 minute, 2 minutes, 3 minutes, etc., to prevent the sensor assembly from short-term failure, so as to further cause false detection and false judgment.

The sensing component senses that the temperature in the vehicle is 36 ℃, the preset environment information range comprises a preset temperature range of 10 ℃ to 30 ℃, a preset humidity range of 5% RH to 95% RH, a preset oxygen concentration range of 19.5% to 23.5%, and a preset carbon monoxide concentration of 0.6mg/m < 3 > to 30mg/m < 3 >, and when the temperature in the vehicle is kept at 36 ℃ for more than 2 minutes, or the temperature in the vehicle is always higher than 30 ℃ within 2 minutes after the sensing component senses the temperature in the vehicle at 36 ℃, the analysis result is determined to be the risk of the environment in the vehicle.

In step 160, controlling the child lock to perform locking or unlocking actions according to the comparison result and the analysis result may include:

It can be understood that when the analysis result is that the environment in the vehicle is dangerous, the passengers or pets are threatened to life health if the children lock is in a locked state, the escape difficulty of the passengers or pets is increased, and serious safety accidents are easy to cause. Therefore, when the environment in the vehicle is dangerous, the unlocking of the child lock is controlled by the vehicle body controller immediately regardless of the comparison result. Or when the environment in the vehicle is safe, but the comparison result is that the facial features are not matched, namely, passengers in the vehicle have enough behavior cognitive ability, and danger caused by opening and closing the vehicle door at will is avoided, the unlocking of the child lock is controlled by the vehicle body controller. Or when the environment in the vehicle is safe and the comparison result is that the facial features are matched, namely, passengers in the vehicle have children, old people, disabled people and the like and do not have enough behavior cognitive ability, or pets in the vehicle are provided, the passengers or pets in the vehicle possibly bring danger to the driving process due to the random opening and closing of the vehicle door, and the locking of the child lock is controlled through the vehicle body controller.

In this embodiment, when the comparison result is that the facial features match, and the analysis result is that the environment inside the vehicle is safe, controlling the child lock to execute the locking action may include:

When the camera collects the target image, the specific position of the collected object on the back row is directly and clearly obtained from the original image shot by the camera, and when the collected object is located on the left seat of the back row, the child lock arranged on the door beside the left seat of the back row is controlled by the vehicle body controller to execute locking action; when the collection object is seated on the rear right seat, the vehicle body controller controls the child lock arranged on the vehicle door beside the rear right seat to execute locking action; when a plurality of collection objects are arranged and the collection objects are seated on the left side seat and the right side seat of the rear row, the child locks arranged on the vehicle doors beside the seats on the two sides of the rear row are controlled by the vehicle body controller to execute locking actions; or when the camera acquires the target image, the specific position of the acquisition object on the back row can not be directly and clearly obtained from the original image shot by the camera, and the child locks arranged on the vehicle doors beside the seats on the two sides of the back row are controlled by the vehicle body controller to execute locking actions. Therefore, when the child lock is needed to be locked, the child lock nearest to the acquisition object can be accurately controlled to execute the locking action, and inconvenience to other passengers sitting beside the vehicle door is avoided.

In practical application, on the premise of ensuring safety, the method saves the operation resources of the vehicle-mounted terminal or the whole vehicle controller, shortens the operation period, and stops the acquisition of the target image and fixes the comparison result after the vehicle door is closed and the child lock performs the locking or unlocking action for the first time; and continuing to perform corresponding steps of in-vehicle environment information acquisition and analysis result judgment, and controlling the child lock to execute locking or unlocking actions according to the comparison result and the analysis result until the vehicle is flameout or the vehicle door is opened from the outside of the vehicle.

As an alternative embodiment, before controlling the child lock to perform the locking or unlocking action according to the comparison result and the analysis result, the method may further include:

It can be understood that the facial features must change correspondingly as time passes, and in order for the child lock control method based on facial recognition provided in this embodiment to adapt to the change, the timeliness of the preset facial image is ensured by monitoring the change condition of the first facial feature and using the target image acquired in real time as the material for updating the preset facial image when the change condition exceeds a certain extent.

In this embodiment, since the facial features of a person gradually change with the lapse of time, and there is a possibility that a certain time is suddenly changed in similarity due to makeup, facial trauma, or the like, and the time interval in which the camera captures the target image every two times is uncertain, the historical similarity can be understood as a set of time series, and has features of reduced tendency and unequal intervals. The time sequence is a sequence of the same statistics index values arranged according to the time sequence of the occurrence of the statistics index values.

In this embodiment, the second preset similarity threshold may be understood as a warning line, and when the similarity is lower than the warning line, the facial features of the passenger are greatly changed, and errors may occur in future target image acquisition and comparison result judgment processes. Therefore, when the similarity is lower than the guard line, each time the facial feature matching starts to be found, there is a target image in which the number of first facial feature information is large (greater than or equal to the threshold of the number of features), and the target image is taken as a material for updating the preset facial image.

In this embodiment, the preset face image may be updated with the target image corresponding to the first face feature, and the target image may be one of the new preset face images, or one of the preset face images may be replaced with the target image. The specific manner of updating the preset face image with the target image is not limited herein.

For example, referring to fig. 2, a line graph generated from a set of historical similarity, the historical similarity line graph shows that a passenger a is riding the vehicle and sitting on the rear seat 7 times during 10 months, the facial features of the passenger a gradually change over time, that is, the similarity of the target image corresponding to the passenger with the preset facial image is lower and lower, wherein the passenger a may be suddenly reduced compared with the relatively smooth reduction trend of the historical similarity line graph due to makeup in the period of 30 months of 2022, and therefore, the target image corresponding to the historical similarity is not used as a material for updating the preset facial image. Specifically, compared with a plurality of historical similarities, any historical similarity has a stable decreasing trend or a sudden decrease or increase, and can be judged by calculating the slope of a connecting line between every two points in a line graph generated by the historical similarity, and further calculating the absolute value of the difference between adjacent slopes. When the absolute value of the difference is larger than a preset difference (such as 0.3), determining that the historical similarity between adjacent slopes is suddenly reduced or increased; when the absolute value of the difference is less than or equal to a preset difference (e.g., 0.3), it is determined that the historical similarity between adjacent slopes has a steadily decreasing trend.

When the passenger a sits on the vehicle and is seated on the rear seat for the seventh time, the similarity is 94%, which is lower than a second preset similarity threshold (for example, 95%), and at this time, the number of first facial feature information corresponding to the similarity is counted, for example, when the first facial feature information includes facial shape feature information, eyebrow shape feature information, auricle shape feature information, and lip mark feature information, the number of first facial feature information is 4, which is greater than a preset feature number threshold (for example, 3), that is, the target image corresponding to the first facial feature information is clearer, has more facial features of the passenger a, and the target image can be added to the preset facial image by using the target image as a material for updating the preset facial image.

As an alternative embodiment, before collecting the in-vehicle environment information of the host vehicle, the method may further include:

In this embodiment, the age prediction model may be an offline model, which is obtained by training using a large number of images of different age groups as training samples, and is installed in an on-vehicle terminal connected to the vehicle controller. The age prediction model may be used to predict an age bracket of a person in an image from a person image acquired in real time.

It will be appreciated that the person, object or pet depicted in the preset face image is generally known to the driver, and in practice, a strange child or elderly passenger may sit in the vehicle in a rear row in addition to the person depicted in the preset face image. Therefore, when the comparison result is that the facial features are not matched, the age bracket of the acquisition object recorded in the target image is predicted by the preset age prediction model, and when the age bracket of the acquisition object is in the preset age bracket (such as 0-14 years old or 70-90 years old), the comparison result is changed to be that the facial features are matched. Thus, the application range of the child lock control method based on face recognition provided by the embodiment can be enlarged, and the child lock control method is not limited to the preset face image.

The age prediction model may be a CNN (convolutional neural network) model, a deep learning model, a gaussian mixture model, or the like.

In this embodiment, the preset weight threshold may be understood as a maximum value of common weights of children in the age range of 0-14 years, and the preset weight threshold may be flexibly set according to actual requirements, for example, light weights of 45kg, 40kg, and the like.

It can be understood that, for reasons such as congenital growth, maintenance, makeup of the face of a part of young or adult, the part of young or adult may be mistakenly identified as a child, when the comparison result is that the facial features match, the weight information of the object to be collected is obtained through a preset pressure sensor (for example, the weight of a passenger with a certain facial feature match is 55 kg), and when the weight information is greater than a preset weight threshold (for example, 45 kg), the comparison result is changed to be that the facial features do not match. Thus, the accuracy of the comparison result is further ensured by combining the facial features with the weight of the passengers.

Referring to fig. 3, the present application further provides a child lock control device 200 based on facial recognition, where the child lock control device 200 based on facial recognition includes at least one software function module that may be stored in a memory module in the form of software or Firmware (Firmware) or cured in an Operating System (OS) of an electronic device. The processing module is configured to execute executable modules stored in the storage module, such as software function modules and computer programs included in the child lock control device 200 based on face recognition.

The child lock control device 200 based on facial recognition includes a first acquisition unit 210, a determination unit 220, a comparison unit 230, a second acquisition unit 240, an analysis unit 250, and a control unit 260, and the functions of the respective units may be as follows:

a first collecting unit 210, configured to collect a target image in the host vehicle, where the target image is a facial image of a collected object in the host vehicle, and the collected object includes a passenger or a pet sitting in a rear seat in the host vehicle;

a determining unit 220, configured to determine, according to the target image, a first facial feature of the acquisition object in the target image, where the first facial feature includes first facial feature information corresponding to the target image;

a comparing unit 230, configured to compare the first facial feature with a preset second facial feature to obtain a comparison result that characterizes whether the first facial feature and the second facial feature match, where the second facial feature includes second facial feature information corresponding to a preset facial image;

the second collecting unit 240 is configured to collect in-vehicle environment information of the host vehicle, where the in-vehicle environment information includes at least one of temperature information, humidity information, oxygen concentration information, and carbon monoxide concentration information;

The analysis unit 250 is configured to obtain an analysis result that characterizes whether the vehicle interior is dangerous according to the vehicle interior environment information;

and the control unit 260 is used for controlling the child lock to execute locking or unlocking actions according to the comparison result and the analysis result.

Optionally, the comparing unit 230 is further configured to:

Optionally, the child lock control device 200 based on face recognition may further include:

a storage unit, configured to store the similarity when the comparison result is facial feature matching, so as to obtain a historical similarity representing a change situation of the first facial feature;

the statistics unit is used for counting the quantity of the first facial feature information corresponding to the first facial feature when the values of the plurality of historical similarity are in a decreasing trend and the similarity is smaller than a second preset similarity threshold value on the premise that any comparison result is facial feature matching, and the historical similarity is a group of time sequences with unequal intervals;

An updating unit configured to update the preset face image with the target image corresponding to the first face feature when the number of the first face feature information is greater than or equal to a feature number threshold.

a first obtaining unit, configured to obtain, when the comparison result is that the facial features are not matched, an age bracket of the acquisition object through a preset age prediction model based on the target image;

and the first changing unit is used for changing the comparison result into facial feature matching when the age bracket of the acquisition object is in a preset age bracket.

the second acquisition unit is used for acquiring the weight information of the acquisition object through a preset pressure sensor when the comparison result is that the facial features are matched;

and the second changing unit is used for changing the comparison result to be that the facial features are not matched when the weight information is larger than a preset weight threshold value.

Optionally, the analysis unit 250 is further configured to:

Optionally, the control unit 260 is further configured to:

In this embodiment, the processing module may be an integrated circuit chip with signal processing capability. The processing module may be a general purpose processor. For example, the processor may be a central processing unit (Central Processing Unit, CPU), digital signal processor (Digital Signal Processing, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present application.

The memory module may be, but is not limited to, random access memory, read only memory, programmable read only memory, erasable programmable read only memory, electrically erasable programmable read only memory, and the like. In this embodiment, the storage module may be configured to store the target image, the comparison result, the analysis result, the first preset similarity threshold, the second preset similarity threshold, the historical similarity, the age prediction model, and the like. Of course, the storage module may also be used to store a program, and the processing module executes the program after receiving the execution instruction.

It should be noted that, for convenience and brevity of description, specific working processes of the electronic device described above may refer to corresponding processes of each step in the foregoing method, and will not be described in detail herein.

Embodiments of the present application also provide a computer-readable storage medium. The computer readable storage medium has stored therein a computer program which, when run on a computer, causes the computer to perform the child lock control method based on face recognition as described in the above embodiments.

From the foregoing description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented in hardware, or by means of software plus a necessary general hardware platform, and based on this understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disc, a mobile hard disk, etc.), and includes several instructions to cause a computer device (may be a personal computer, a server, or a network device, etc.) to perform the methods described in the respective implementation scenarios of the present application.

In summary, the embodiment of the application provides a child lock control method and device based on facial recognition and a vehicle. In the scheme, a first facial feature of an acquisition object in a target image is determined by acquiring the target image in the vehicle and according to the target image, and then the first facial feature and a preset second facial feature are compared to obtain a comparison result representing whether the first facial feature and the second facial feature are matched or not; after the comparison result is obtained, the in-car environment information of the vehicle is collected, an analysis result representing whether the in-car environment is dangerous or not is obtained according to the in-car environment information, and finally the child lock is controlled to execute locking or unlocking actions according to the comparison result and the analysis result. Therefore, the problems that the existing mode of controlling the child lock through face recognition is imperfect, the control mode is inflexible, emergency environments cannot be handled, and safety risks are caused can be solved.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus, system, and method may be implemented in other manners as well. The above-described apparatus, systems, and method embodiments are merely illustrative, for example, flow charts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. In addition, the functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.

The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method of child lock control based on facial recognition, the method comprising:

2. The method of claim 1, wherein comparing the first facial feature to a predetermined second facial feature to obtain a comparison result that characterizes whether the first facial feature and the second facial feature match, comprises:

3. The method of claim 1, wherein prior to controlling the child lock to perform a locking or unlocking action based on the comparison result and the analysis result, the method further comprises:

4. The method of claim 1, wherein prior to collecting in-vehicle environmental information of the host vehicle, the method further comprises:

5. The method of claim 4, wherein prior to collecting in-vehicle environmental information of the host vehicle, the method further comprises:

6. The method of claim 1, wherein obtaining an analysis of whether the vehicle interior environment is dangerous based on the vehicle interior environment information comprises:

7. The method of claim 1, wherein controlling the child lock to perform a locking or unlocking action based on the comparison result and the analysis result comprises:

8. The method of claim 7, wherein controlling the child lock to perform a locking action when the comparison result is facial feature matching and the analysis result is in-vehicle environmental safety comprises:

9. A child lock control device based on facial recognition, the device comprising:

10. A vehicle comprising a processor and a memory coupled to each other, the memory storing a computer program which, when executed by the processor, causes the vehicle to perform the method of any one of claims 1-8.

11. An electronic device comprising a processor and a memory coupled to each other, the memory storing a computer program that, when executed by the processor, causes the electronic device to perform the method of any of claims 1-8.

12. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when run on a computer, causes the computer to perform the method according to any of claims 1-8.