CN114619993B - Automobile control method based on face recognition, system, equipment and storage medium thereof - Google Patents
Automobile control method based on face recognition, system, equipment and storage medium thereof Download PDFInfo
- Publication number
- CN114619993B CN114619993B CN202210258115.5A CN202210258115A CN114619993B CN 114619993 B CN114619993 B CN 114619993B CN 202210258115 A CN202210258115 A CN 202210258115A CN 114619993 B CN114619993 B CN 114619993B
- Authority
- CN
- China
- Prior art keywords
- face
- automobile
- information
- face detection
- recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a car control method based on face recognition, which comprises the steps of obtaining a first face detection result and a first face recognition result through a first face detection and recognition network, and determining an unlocking mode of a car according to the first face recognition result; after the automobile is successfully unlocked, a second face detection result is obtained, and comparison operation is carried out on the second face detection result and pre-stored face information so as to determine the identity of the automobile driver; and acquiring a second face detection result, performing comparison operation on the second face detection result and pre-stored face information to determine the identity of the automobile driver, and adjusting the corresponding driving part of the automobile according to the driving part adjusting information after determining the identity of the automobile driver as a user. The automobile unlocking device improves the safety and convenience of automobile unlocking, intelligently adjusts driving parts of the automobile, and provides convenience for automobile users. The invention also provides a system, equipment and storage medium for realizing the automobile control method based on face recognition.
Description
Technical Field
The utility model relates to the field of automobile control, in particular to an automobile control method based on face recognition, a system, equipment and a storage medium thereof.
Background
Along with the continuous improvement of living conditions, private cars become a main transportation means for people to travel, and bring convenience to the life of people. Meanwhile, traffic accidents, especially drunk driving, become a culprit of endangering lives and property. More and more drivers are aware of the hazards of drunk driving, and in this context, drive generations have emerged as an emerging industry.
Although the driving of the driver brings convenience to the vehicle owner, the driver brings trouble at the same time. Because each driver has different driving habits, the driving components such as the seat, the left and right rearview mirrors, the steering wheel height and the like are adjusted according to the driving habits before driving. After the modern driving service is finished, the driving part of the automobile cannot return to the original state of the automobile, the automobile user needs to manually adjust the driving part again according to own habit, and the position of the driving part adjusted again is difficult to adjust to the optimal position adjusted by the user at the last time, so that the trouble and the trouble are caused to the automobile user.
The Chinese patent with publication number CN203637689U discloses an automobile rearview mirror steering gear and a memory component thereof, wherein the memory component comprises a memory unit bracket, a carbon film plate, a carbon film brush piece and a potentiometer gear which are connected in sequence, and the joint of the memory unit bracket, the carbon film plate, the carbon film brush piece and the potentiometer gear is coaxially arranged. The automobile rearview mirror steering gear is provided with the memory component. The utility model realizes the adjustment of the rearview mirror of the vehicle owner through the memory component so as to restore the rearview mirror to the position and the angle which are set before the vehicle owner. Since the memory unit stores limited part information when the vehicle has a plurality of users, the position information of the driving parts of all the users cannot be stored well. However, the utility model does not solve the problem of requiring manual adjustment of the driving part after the replacement of the driver of the vehicle.
Therefore, it is necessary to provide a car control method based on face recognition, a system, a device and a storage medium thereof, so as to solve the above-mentioned problems in the prior art.
Disclosure of Invention
The invention aims to provide a face recognition-based automobile control method, a face recognition-based automobile control system, face recognition-based automobile control equipment and a face recognition-based automobile storage medium, so that the problem that a driver needs to manually adjust driving parts every time an automobile is replaced is solved.
In order to achieve the above purpose, the face recognition-based automobile control method of the present invention comprises the steps of:
s1: acquiring a first face detection result through a first face detection and recognition network, performing comparison operation on the first face detection result and pre-stored face information to acquire a first face recognition result, and determining an unlocking mode of the automobile according to the first face recognition result;
s2: after the automobile is successfully unlocked in the unlocking mode of the automobile, a second face detection result is obtained through a second face detection and recognition network, and comparison operation is carried out on the second face detection result and the pre-stored face information so as to determine the identity of an automobile driver;
s3: after the identity of the automobile driver is determined to be a user, driving part adjusting information corresponding to pre-stored face information matched with the user is extracted, and the driving part of the automobile is adjusted according to the driving part adjusting information.
The automobile control method based on face recognition has the beneficial effects that:
the first face detection result is obtained through the first face detection and recognition network, and comparison operation is carried out on the first face detection result and the pre-stored face information to obtain a first face recognition result, and an unlocking mode of the automobile is determined according to the first face recognition result, so that the safety and convenience of automobile unlocking are improved; after the automobile is successfully unlocked, a second face detection result is obtained through a second face detection and recognition network, and comparison operation is carried out on the second face detection result and the pre-stored face information so as to determine the identity of the driver; after the identity of the automobile driver is determined to be a user, driving part adjusting information corresponding to pre-stored face information matched with the user is extracted, and the driving part of the automobile is adjusted according to the driving part adjusting information. According to the invention, the safety and convenience of unlocking the automobile are improved by detecting the face information and determining the unlocking mode of the automobile, the identity of the driver of the automobile is determined by the comparison result of the face similarity and the similarity threshold value, and if the driver of the automobile is a user, the adjusting information of the driving part is determined according to the internal face information matched with the user, so that the driving part of the automobile is intelligently adjusted, the problem that the driving part needs to be manually adjusted every time the driver is replaced is solved, the trouble of the user of the automobile is reduced, and convenience is provided for the user of the automobile.
Optionally, the first face detection recognition network includes a first face detection network and a first face recognition network;
the first face detection network is used for detecting a face, outputting face classification information, face frame regression information and a plurality of face key point regression information, and outputting a face detection result to the first face recognition network;
the first face recognition network is used for outputting the first face recognition result after processing the first face detection result. The face detection system has the advantages that the first face detection network is used for detecting faces and outputting face classification information, face frame regression information and a plurality of face key point regression information so as to improve the accuracy of face detection and avoid interference of non-faces; the first face recognition network is used for processing the first face detection result and outputting the first face recognition result, and the first face detection network and the first face recognition network are used for respectively detecting and recognizing faces, so that the functions of the first face detection and recognition network are more perfect, and the detection and recognition are more accurate.
Optionally, the second face detection and recognition network includes a second face detection network and a second face recognition network;
The second face detection network is used for acquiring a second face detection result and transmitting the second face detection result to the second face recognition network;
the second face recognition network is used for judging whether the second face detection result is matched with the pre-stored face information or not. The face detection method has the advantages that a second face detection result is obtained through the second face detection network and is transmitted to the second face detection network; and comparing the second face detection result with the pre-stored face information through the second face recognition network, judging whether the second face detection result is matched with the pre-stored face information or not so as to determine whether an automobile driver is a user or not, and judging efficiency is high.
Optionally, in the step S1, the step of determining the unlocking mode of the automobile according to the first face recognition result includes:
and when the first face detection result is matched with the pre-stored face information, determining that the automobile driver is a user, and automatically unlocking the automobile. The automobile unlocking device has the beneficial effects that after the automobile driver is determined to be a user, the automobile is automatically unlocked, so that the automobile unlocking efficiency of the user is improved, the automobile is unlocked without using a key by the user, and the automobile unlocking convenience of the user is improved.
Optionally, in the step S1, the step of determining the unlocking mode of the automobile according to the first face recognition result includes:
when the first face detection result is not matched with the pre-stored face information, determining that the automobile driver is a guest;
and after the guest unlocks the automobile through the key and successfully unlocks the automobile, executing the step S2.
Optionally, determining that the automobile driver is a guest, further performing the steps of:
and when the guest does not unlock the automobile through the key or does not unlock the automobile and touches related parts of the automobile, an alarm is sent out. After determining that the automobile driver is the guest, if the guest does not unlock the automobile through a key or does not unlock the automobile and touches related parts of the automobile, an alarm is sent out to remind a user that someone is maliciously unlocking the automobile or damaging the automobile, so that the safety of the automobile is improved.
Optionally, in the step S2, the step of performing a comparison operation on the second face detection result and the pre-stored face information to determine the identity of the driver of the automobile includes:
when the second face detection result is matched with the pre-stored face information, determining the identity of the automobile driver as the user;
And when the second face detection result is not matched with the pre-stored face information, determining that the automobile driver is a guest, and ending the step S2. The method has the advantages that the step S3 is executed after the identity of the automobile driver is determined to be the user; after determining that the automobile driver is a guest, the step S2 is ended, so that the step S3 is ended in advance, that is, the step of intelligently adjusting the driving part of the automobile is omitted, the information of the driving part adjusted by the guest is not recorded, the storage of excessive disposable information in an information base is avoided, the congestion of the information and the unnecessary information storage are avoided, and the high-efficiency face detection and face recognition of the first face detection and recognition module and the second face detection and recognition module are ensured.
Optionally, the face recognition-based automobile control method further includes step S4: and after each driving is finished, updating the face information of the user to acquire the face information of the last user.
Optionally, in the step S3, the step of adjusting the driving part of the automobile according to the driving part adjustment information includes:
performing a comparison operation on the second face detection result and the face information of the last user, and keeping the position of the driving part of the automobile unchanged when the second face detection result is matched with the face information of the last user;
And when the second face detection result is not matched with the face information of the last user and the second face detection result is matched with the pre-stored face information, extracting driving part adjusting information corresponding to the pre-stored face information, and adjusting the driving part of the automobile according to the driving part adjusting information. The method has the advantages that step 3 is combined with the face information of the last user in step 4 to judge whether the current driver is the last user, if the current driver is the last driver, the position of the driving part of the automobile is kept unchanged, and the energy and the adjustment time of the automobile are saved; readjusting the driving part if the driver is not the last user but another user; the intelligent control adjusts or does not adjust the driving part of the automobile, thereby providing convenience for users, and when the current user of the automobile and the last user of the automobile are the same person, the driving part of the automobile is not adjusted, and the adjusting time is saved.
The invention also provides an automobile control system based on face recognition, which comprises:
the first face detection and recognition module is arranged on the outer side of the automobile and is used for acquiring a first face detection result through a first face detection and recognition network, and performing comparison operation on the first face detection result and pre-stored face information to acquire a first face recognition result;
The unlocking module is used for determining an unlocking mode of the automobile according to the first face recognition result and successfully unlocking the automobile through the unlocking mode of the automobile;
the second face detection and recognition module is arranged in a cab of the automobile and is used for acquiring a second face detection result through a second face detection and recognition network, performing comparison operation on the second face detection result and the pre-stored face information and performing comparison operation on the second face detection result and the pre-stored face information to determine the identity of an automobile driver;
and the driving part control module is used for extracting driving part adjusting information corresponding to the pre-stored face information matched with the user after determining the identity of the automobile driver as the user, and adjusting the driving part of the automobile according to the driving part adjusting information.
The automobile control system based on face recognition has the beneficial effects that:
acquiring a first face detection result through the first face detection and recognition module, and performing comparison operation on the first face detection result and the pre-stored face information to acquire a first face recognition result; the unlocking module determines an unlocking mode of the automobile according to a first face recognition result, and safety and rapidness of automobile unlocking are guaranteed; acquiring a second face recognition result through the second face detection and recognition module to determine the identity of the automobile driver; after the identity of the automobile driver is determined to be a user, the driving part control module extracts driving part adjusting information corresponding to pre-stored face information matched with the user, and adjusts the driving part of the automobile according to the driving part adjusting information. The automobile control system based on face recognition determines the unlocking mode of the automobile based on the detection and recognition of the face, determines whether the driver is a user or not through the detection and recognition of the face, intelligently adjusts the driving part of the automobile according to the driving part adjusting information corresponding to the pre-stored face information of the user, saves the time for adjusting the driving part of the user, improves the convenience of the user, and improves the comfort and experience of the user.
The invention also provides equipment, which comprises a memory and a processor, wherein the memory stores a program, and when the program is executed by the processor, the automobile control method based on face recognition is realized.
The invention also provides a storage medium, wherein the storage medium stores a program, and when the program is executed by the processor, the automobile control method based on face recognition is realized.
The device and the storage medium of the invention have the advantages that:
the safety and the convenience of unlocking the automobile are improved, and the driving part of the automobile is intelligently adjusted, so that the problem that the driving part needs to be manually adjusted when a driver is replaced every time is solved, and convenience is brought to the user.
Drawings
Fig. 1 is a flowchart of a first implementation of a car control method based on face recognition according to an embodiment of the present invention;
FIG. 2 is a flowchart of a second implementation of a face recognition-based vehicle control method according to an embodiment of the present invention;
fig. 3 is a block diagram of an automobile control system based on face recognition according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. Unless otherwise defined, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. As used herein, the word "comprising" and the like means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof without precluding other elements or items.
Aiming at the problems existing in the prior art, the embodiment of the invention provides a car control method based on face recognition, and fig. 1 is a flowchart of a first implementation of the car control method based on face recognition.
In a first embodiment, referring to fig. 1, the face recognition-based automobile control method of the present invention includes the steps of:
s1: acquiring a first face detection result through a first face detection and recognition network, performing comparison operation on the first face detection result and pre-stored face information to acquire a first face recognition result, and determining an unlocking mode of the automobile according to the first face recognition result;
s2: after the automobile is successfully unlocked in the unlocking mode of the automobile, a second face detection result is obtained through a second face detection and recognition network, and comparison operation is carried out on the second face detection result and the pre-stored face information so as to determine the identity of an automobile driver;
s3: after the identity of the automobile driver is determined to be a user, driving part adjusting information corresponding to pre-stored face information matched with the user is extracted, and the driving part of the automobile is adjusted according to the driving part adjusting information.
In some embodiments, the pre-stored face information and the driving part adjustment information are saved by a storage information base;
when the user of the automobile is unique, the number of the pre-stored face information of the user in the storage information base is one, and the number of the pre-stored face information of the user and the number of the driving part adjusting information are both one;
when a plurality of users of the automobile, such as the users of the automobile comprise owners of the automobile and families of the owners of the automobile or the users of the corporate buses comprise a plurality of corporate staff, the number of the pre-stored face information of the users in the storage information base is more than two, and the number of the pre-stored face information of the users and the number of the driving part adjusting information are more than two; and the pre-stored face information of each user corresponds to the driving part adjusting information of the user one by one.
In some alternative embodiments, the driving components of the automobile include a cabin seat, a center mirror, a left side mirror, a right side mirror, and a steering wheel of the automobile;
the driving part adjustment information includes adjustment information of an angle or a height of a seat, adjustment information of an angle of a center mirror, adjustment information of an angle and a fold of a left side mirror, adjustment information of an angle and a fold of a right side mirror, and adjustment information of a height of a steering wheel.
The automobile control method based on face recognition has the advantages that: according to the invention, the safety and convenience of unlocking the automobile are improved by detecting the face information and determining the unlocking mode of the automobile; the identity of the driver of the automobile is determined through the comparison result of the face similarity and the similarity threshold value, if the automobile driver is a user, the driving part adjusting information is determined according to the internal face information matched with the user, so that the driving part of the automobile is intelligently adjusted, the problem that the driving part needs to be manually adjusted by the driver every time is solved, the trouble of the automobile user is reduced, and convenience is brought to the automobile user.
Fig. 2 is a flowchart of a second implementation of a face recognition-based automobile control method according to an embodiment of the present invention.
In a second embodiment, referring to fig. 2, the face recognition-based automobile control method of the present invention further performs step S0 before performing step S1, based on the above steps S1 to S3:
face information of a user is detected and stored as pre-stored face information, and use information of the user on a driving part is recorded to obtain driving part adjusting information. The method has the advantages that the method records the driving part adjusting information of the user by detecting the face information of the user and storing the pre-stored face information, and provides reference information for the face comparison operation of the follow-up first face recognition network and the second face recognition network;
Referring to fig. 2, after step S3 is performed, step S4 is also performed:
and after each driving is finished, updating the face information of the user to acquire the face information of the last user.
In some optional embodiments, a first face detection and recognition module and a second face detection and recognition module are provided, where the first face detection and recognition network is provided in the first face detection and recognition module, and the second face detection and recognition network is provided in the second face detection and recognition module.
As an optional implementation manner of the present invention, the first face detection network is configured to detect a face and output face classification information, face frame regression information, and a plurality of face key point regression information, and the first face detection network is further configured to output a face detection result to the first face recognition network;
the first face recognition network is used for outputting the first face recognition result after processing the first face detection result. The first face detection network and the first face recognition network are obtained through training, and the first face detection network is used for detecting faces and outputting face classification information, face frame regression information and a plurality of face key point regression information so as to improve the accuracy of face detection and avoid interference of non-faces; the first face recognition network is used for processing the first face detection result and outputting the first face recognition result, and the first face detection network and the first face recognition network are used for respectively detecting and recognizing faces, so that the functions of the first face detection and recognition network are more perfect, and the detection and recognition are more accurate.
As an optional embodiment of the present invention, the second face detection and recognition network includes a second face detection network and a second face recognition network;
the second face detection network is used for acquiring a second face detection result and transmitting the second face detection result to the second face recognition network;
the second face recognition network is used for judging whether the second face detection result is matched with the pre-stored face information or not. The face detection method has the advantages that a second face detection result is obtained through the second face detection network and is transmitted to the second face detection network; and comparing the second face detection result with the pre-stored face information through the second face recognition network, judging whether the second face detection result is matched with the pre-stored face information or not so as to determine whether an automobile driver is a user or not, and judging efficiency is high.
In some specific embodiments of the present invention, the specific step of training the first face detection network includes:
providing a face detection Mnet network, wherein the face detection Mnet network is an improved version based on a face recognition Retinaface network; the difference between the human face detection Mnet network and the human face recognition Retinaface network is that a main network of the human face detection Mnet network uses a mobilent to lighten a model, and an SSH detection module consisting of SSH (Single Stage Headless) context modules is further added at the tail detection head position of the human face detection Mnet network; the size of the input of the face detection Mnet network is a 3-channel RGB image, and the output of the face detection Mnet network comprises three parts: face classification information, face frame regression information and a plurality of face key point regression information;
Under the caffe frame, 20.4 ten thousand images are used as a training data set and 3.5 thousand data are used as a verification set to be input into the face detection Mnet network, and a random gradient descent (Stochastic Gradient Descent, SGD) optimizer is used for training the face detection Mnet network, wherein training parameters are set as follows: the momentum (momentum) of the SGD optimizer was 0.9, the weight decay (weight decay) was 0.0005, the batch size (batch size) was 8×4, the initial learning rate was 0.001, the learning rate was modified to 0.01 after 5 epochs were completed, and finally the modification rate was modified to 0.001 at 55 th and 68 th epochs, respectively.
It is noted that when all training data sets are input into the network model, a complete training is performed, and this process is called an epoch.
In some optional embodiments of the present invention, the face recognition network of the present invention employs a face recognition MobileFaceNet network, and the face recognition MobileFaceNet network employs mobilenet v2 as a baseline model.
In some specific embodiments of the present invention, the specific step of training the first face recognition network includes:
before training the face recognition MobileFaceNet network, cleaning the Glint360K public data set, namely, reducing the original 361K data to 215K data, inputting the data into the face recognition MobileFaceNet network for training from scratch, wherein training parameters comprise:
The loss function adopts a face recognition loss function (ArcFace), the momentum of the SGD optimizer is 0.9, the weights of the global operation layer are calculated as 4e-4, the weights of the other layers except the global operation layer are calculated as 4e-5, the batch size is 512, the initial learning rate is 0.1, the learning rate is modified to be 0.01 when the iteration times (iteration times) of 36K, 52K and 58K are respectively carried out, and the learning rate is still 0.1 in the time period except the iteration times of 36K, 52K and 58K; and training the face recognition MobileFaceNet network through an SGD optimizer, and stopping training when training is completed to 60 tests.
It can be stated that 4e-4 corresponds to 4X 10 -4 4e-5 corresponds to 4X 10 -5 。
In some optional embodiments of the present invention, the second face detection recognition network includes a second face detection network and a second face recognition network, and since the training steps of the second face detection network and the first face detection network are identical, the training steps of the second face recognition network and the first face recognition network are identical, so that a detailed description is omitted.
As an optional implementation manner of the present invention, in the step S1, the step of determining the unlocking mode of the automobile according to the first face recognition result includes:
And when the first face detection result is matched with the pre-stored face information, determining that the automobile driver is a user, and automatically unlocking the automobile. The automobile unlocking device has the advantages that after the automobile driver is determined to be a user, the automobile is automatically unlocked, so that the automobile unlocking efficiency of the user is improved, the automobile is unlocked without using a key by the user, and the automobile unlocking convenience of the user is improved.
As an optional implementation manner of the present invention, the step of determining the unlocking mode of the automobile according to the first face recognition result further includes:
when the first face detection result is not matched with the pre-stored face information, determining that the automobile driver is a guest;
after determining that the automobile driver is a guest, the steps are further performed:
when the guest unlocks the automobile through the key, executing the step S2 after the automobile is successfully unlocked;
and when the guest does not unlock the automobile through the key or does not unlock the automobile and touches related parts of the automobile, an alarm is sent out. The automobile safety control method has the advantages that after the automobile driver is determined to be the guest, if the guest does not unlock the automobile through the key or does not unlock the automobile and touches related parts of the automobile, an alarm is sent out to remind a user that someone is maliciously unlocking the automobile or damaging the automobile, and therefore the safety of the automobile is improved.
In some alternative embodiments, the specific steps of step S1 include:
before a driver gets on the vehicle, the first face detection and recognition module adjusts the image size of the current frame of the video stream into an initial image with the resolution of 320 multiplied by 320, and inputs the initial image into the face detection Mnet network, and finally the face detection Mnet network outputs all face classification information, face frames rectbox of all contained face positions and 5 key points of the face;
the first face detection and recognition module cuts out a face image ROIimage from the initial image according to the face frame rectbox, and adjusts the resolution of the face image ROIimage to 112×112 so as to obtain a faceimg image, wherein the first face detection result comprises the faceimg image;
illustratively, ROIimage is an abbreviation of region of interest image, where the text name is a region of interest image, and in the field of image processing, a region to be processed is outlined from the processed image in a square, circle, ellipse, and irregular pattern, which is referred to as a region of interest; the facemg image is the img format of the face image.
And inputting the faceimg image into the face recognition MobileFaceNet network, and outputting a similarity value of the faceimg image and each piece of prestored face information in the storage information base by the face recognition MobileFaceNet network. The first face recognition result comprises similarity values of the faceimg image and each piece of prestored face information in the storage information base.
The first face detection and recognition module outputs a plurality of similarity values to a system, and the system performs the following operations:
the system sorts the magnitude of the similarity values to obtain the maximum value max in all the similarity values, when the system judges that the max is more than or equal to 0.6, the system judges that the faceimg image is successfully matched with the prestored face information with the maximum similarity value, determines that the prestored face information corresponding to the maximum value max in the similarity is matched with the face information of the user, determines that an automobile driver is the user, and then sends a vehicle unlocking instruction to automatically unlock the vehicle;
when the system judges that max is less than 0.6, judging that the faceimg image is not successfully matched with the prestored face information in the storage information base, and determining that an automobile driver is an automobile guest, wherein the automobile guest can be unlocked only by a key;
if the guest does not unlock the vehicle by a key, or does not unlock the vehicle but touches the door or pulls the door handle, the system gives an alarm to alert the owner of the vehicle that someone is attempting to steal or destroy the vehicle.
As an optional embodiment of the present invention, in the step S2, the step of performing a comparison operation on the second face detection result and the pre-stored face information to determine the identity of the driver of the automobile includes:
When the second face detection result is matched with the pre-stored face information, determining the identity of the automobile driver as the user;
and when the second face detection result is not matched with the pre-stored face information, determining that the automobile driver is a guest, and ending the step S2. The method has the advantages that the step S3 is executed after the identity of the automobile driver is determined to be the user; after the automobile driver is determined to be the guest, the second face detection and recognition step is finished, so that the step of intelligently adjusting the driving part of the automobile is omitted, and the information of the driving part adjusted by the guest is not recorded, so that the storage of excessive disposable information in a storage information base is avoided, the congestion of the information and the unnecessary information storage are avoided, and the high-efficiency face detection and face recognition of the first face detection and recognition module and the second face detection and recognition module are ensured.
As an optional embodiment of the present invention, in the step S3, the step of adjusting the driving part of the automobile according to the driving part adjustment information includes:
performing a comparison operation on the second face detection result and the face information of the last user, and keeping the position of the driving part of the automobile unchanged when the second face detection result is matched with the face information of the last user;
And when the second face detection result is not matched with the face information of the last user and the second face detection result is matched with the pre-stored face information, extracting driving part adjusting information corresponding to the pre-stored face information, and adjusting the driving part of the automobile according to the driving part adjusting information. The method has the advantages that step 3 is combined with the face information of the last user in step 4 to judge whether the current driver is the last user, if the current driver is the last driver, the position of the driving part of the automobile is kept unchanged, and the energy and the adjustment time of the automobile are saved; readjusting the driving part if the driver is not the last user but another user; the intelligent control adjusts or does not adjust the driving part of the automobile, thereby providing convenience for users, and keeping the position of the driving part of the automobile unchanged when the current user of the automobile and the last user of the automobile are the same, and saving the adjusting time.
In some alternative embodiments, the specific steps of steps S2, S3 and S4 include:
(1) The second face detection and recognition module adjusts the image size of the current frame of the video stream into an initial image with the resolution of 320 multiplied by 320, the initial image is input into the face detection Mnet network, and finally the face detection Mnet network outputs all face classification information, face frames rectbox of all face positions and 5 key points of the face;
Then the second face detection and recognition module cuts out a face image ROIimage from the initial image according to the face frame rectbox, and adjusts the resolution of the face image ROIimage to 112×112 so as to obtain a faceimg image, wherein the second face recognition result comprises the faceimg image;
and inputting the faceimg image into the face recognition MobileFaceNet network, and outputting a similarity value of the faceimg image and each piece of prestored face information in the storage information base by the face recognition MobileFaceNet network. The second face recognition result comprises a similarity value of the faceimg image and each piece of prestored face information in the storage information base.
(2) After the second face detection and recognition module outputs a plurality of similarity values, the system performs the following operations:
after the system receives the similarity values, the similarity values are ranked to obtain a maximum value max of all the similarities, and the system compares the max with a similarity threshold, which is set to 0.6 in some embodiments. When the system judges that max is less than 0.6, judging that the faceimg image is not successfully matched with the prestored face information in the storage information base, determining that the automobile driver is a guest by the system, and in the driving process of the guest, not storing the face information and the driving part adjusting information of the guest by the system, and after the driving is finished, automatically adjusting the position of the driving part to the position of the driving part corresponding to the driving part adjusting information of the first user by the system so as to facilitate the next user to drive the automobile;
When the system judges that the max is more than or equal to 0.6, judging that the faceimg image is successfully matched with the prestored face information with the maximum similarity value, determining that the automobile driver is a user, and after the automobile driver is determined to be the user, performing the following steps:
the system performs comparison operation on the faceimg image and the face information of the last user, if the similarity between the faceimg image and the face information of the last user is greater than 0.6, the faceimg image is matched with the face information of the last user, the system recognizes that the driver of the automobile is the same user as the last automobile driver, and the system controls the position of a driving part of the automobile to be unchanged;
if the similarity between the facemg image and the face information of the last user is smaller than 0.6, the facemg image is not matched with the face information of the last user, and the system determines that the driver of the automobile is different from the last automobile driver; when the second face detection result is matched with the pre-stored face information in the face library, driving part adjusting information is determined according to the pre-stored face information matched with the current user of the automobile, and the system adjusts the automobile driving part according to the driving part adjusting information so as to adjust the position of the driving part to be the position used by the current user.
(3) After each time the user finishes driving the vehicle, the system updates the face information of the user who drives the automobile last according to the face information detected and identified by the second face detection and identification module so as to obtain the face information of the last user.
In some embodiments, the system is the face recognition-based automobile control system.
In some alternative embodiments, when the pre-stored face information of the user is stored in the storage information base, but the driving component adjustment information corresponding to the pre-stored face information is not stored, for example, the step of starting the automatic recording of driving component adjustment for the first time the user drives the automobile, the steps include:
starting timing from the moment when the user adjusts the driving part, and taking the adjusted position of the driving part as driving part adjusting information corresponding to the pre-stored face information if the user keeps the adjusted position of the driving part all the time within the time of keeping the time t more than or equal to 15-20min, namely the user does not adjust the position of the driving part within the continuous time of 15-20 min;
if the user readjusts the position of the driving part within a holding time t <15-20min, i.e. the user readjust the position of the driving part within a continuous time less than 15-20min, the system does not update the driving part adjustment information of this user, while updating said holding time t.
The invention further provides a face recognition-based automobile control system, and fig. 3 is a structural diagram of the face recognition-based automobile control system in the embodiment of the invention.
Referring to fig. 3, the face recognition-based automobile control system of the present invention includes:
the first face detection and recognition module 1 is arranged on the outer side of the automobile and is used for acquiring a first face detection result through a first face detection and recognition network, and performing comparison operation on the first face detection result and pre-stored face information to acquire a first face recognition result;
the unlocking module 3 is used for determining an unlocking mode of the automobile according to the first face recognition result and successfully unlocking the automobile through the unlocking mode of the automobile;
the second face detection and recognition module 2 is arranged in a cab of the automobile and is used for acquiring a second face detection result through a second face detection and recognition network, performing comparison operation on the second face detection result and the pre-stored face information and performing comparison operation on the second face detection result and the pre-stored face information to determine the identity of an automobile driver;
and the driving part control module 4 is used for extracting driving part adjusting information corresponding to the pre-stored face information matched with the user after determining the identity of the automobile driver as the user, and adjusting the driving part of the automobile according to the driving part adjusting information.
The automobile control system based on face recognition has the advantages that: the first face detection and recognition module 1 detects the face and acquires a first face recognition result, so that an unlocking mode of the automobile is determined, whether the driver is a user is determined through detection and recognition of the face by the second face detection and recognition module 2, and the driving part control module 4 intelligently adjusts the driving part of the automobile according to the driving part adjusting information corresponding to the pre-stored face information of the user, so that the time for adjusting the driving part by the user is saved, the convenience of the user is improved, and the comfort and experience of the user are improved.
In some embodiments, referring to fig. 3, the face recognition-based automobile control system further includes a recording module 5, configured to detect face information of a user and store the face information as pre-stored face information, and record usage information of a driving part by the user to obtain driving part adjustment information.
In some embodiments, referring to fig. 3, the recording module 5 includes a face input unit (not shown in the drawing, a driving part usage information and status information detection unit (not shown in the drawing) and a storage information base 50, detects a face by the face input unit to obtain face information of a user, and stores the face information of the user as the pre-stored face information by the storage information base 50, detects the usage information and status information of the driving part by the user during driving of the automobile by the driving part usage information and status information detection unit, and stores the driving part usage information and status information as the driving part adjustment information by the storage information base 50, and makes the pre-stored face information of each user correspond to the driving part adjustment information of the user.
In some optional embodiments, the first face detection and recognition module 1 is installed outside the automobile, and in particular, the first face detection and recognition module 1 is disposed at a position of 160cm from the ground of the left B-pillar or the right B-pillar of the automobile, so that the first face detection and recognition module 1 can perform face detection and recognition on a driver located outside the automobile to determine an unlocking mode of the automobile.
In some optional embodiments, the second face detection and recognition module 2 is installed inside the automobile, specifically, the second face detection and recognition module 2 is disposed in a cab of the automobile to facilitate detection and recognition of a position of a face of a driver to be driven, and after the driver enters the cab or sits on a driver seat, the second face detection and recognition module 2 performs face detection and recognition on the driver to be driven, so as to determine whether to adjust a driving component.
As an optional implementation manner of the present invention, a first face detection network and a first face recognition network are set in the first face detection and recognition module 1, where the first face detection network is used to detect a face and output face classification information, face frame regression information and a plurality of face key point regression information, and the first face detection network is also used to output a face detection result to the first face recognition network;
The first face recognition network is used for outputting the first face recognition result after processing the first face detection result.
In some optional embodiments, the first face detection network uses the face detection network described above, and the first face recognition network uses the face recognition network described above.
As an optional implementation manner of the present invention, a second face detection network and a second face recognition network are set in the second face detection and recognition module 2, where the second face detection network is configured to obtain a second face detection result, and transmit the second face detection result to the second face recognition network;
the second face recognition network is used for judging whether the second face detection result is matched with the pre-stored face information or not.
As an alternative embodiment of the present invention, referring to fig. 2, the face recognition-based automobile control system of the present invention further includes an alarm module 6, and after the first face detection and recognition module 1 recognizes that the automobile driver is a guest, if the guest unlocks the automobile through a key, the alarm module 6 is not started; if the guest does not unlock the car by a key or touches or pulls car parts such as a car door and a car door handle, the alarm module 6 starts an alarm to give an alarm to remind the car user.
In some alternative embodiments of the present invention, referring to fig. 2, the operation steps of the face recognition-based automobile control system are as follows:
(1) When the first face detection and recognition module 1 detects a face, performing primary face detection and recognition, recording face information of the face to obtain a first face detection result, matching the first face detection result with pre-stored face information in the storage information base 50, and if the first face detection result fails to match with the pre-stored face information, determining that a driver to be tested is a guest, wherein the guest can unlock the car only by a key; if the guest does not unlock the automobile or touch or pull automobile parts such as the automobile door, the automobile door handle and the like through the key, the alarm module 6 starts an alarm and gives an alarm;
if the first face detection result is successfully matched with the pre-stored face information, determining that the driver of the automobile is a user, and controlling the unlocking module 3 to unlock the lock of the automobile so as to automatically unlock the automobile;
(2) After the automobile driver successfully unlocks the automobile and enters the cab, the second face detection and identification module 2 carries out secondary face detection and identification on the face, records the face information of the to-be-driven person to obtain a second face detection result, matches the second face detection result with pre-stored face information, and if the second face detection result fails to match with the pre-stored face information, determines that the to-be-driven person is a guest, at the moment, the driving part control module 4 does not adjust the driving part, keeps the position of the driving part of the automobile unchanged, and does not record or store the face information and driving part adjusting information of the guest in the process of driving the automobile by the guest;
If the second face detection result is successfully matched with the pre-stored face information, determining that the automobile driver to be tested is a user;
(3) After determining that the automobile driver is a user, if the driving part adjusting information corresponding to the user is not stored in the storage information base 50, the recording module 5 starts and executes a driving part adjusting automatic recording step to record new driving part adjusting information of the user, stores the recorded driving part adjusting information into the storage information base 50, and enables the driving part adjusting information to be correspondingly matched with pre-stored face information of the user; if the stored information base 50 stores the driving part adjusting information corresponding to the user, the second face detection and recognition module 2 compares the face information of the current user with the face information of the last user, if the face information of the current user is successfully matched with the face information of the last user, the current user and the last user of the automobile are the same person, and at the moment, the driving part control module 4 keeps the position of the driving part unchanged;
if the face information of the current user fails to match with the face information of the last user, comparing the face information of the current user with the pre-stored face information in the storage information base 50 through the second face detection and identification module 2, determining pre-stored face information matched with the current user, and then determining driving part adjusting information corresponding to the pre-stored face information, wherein at the moment, the driving part control module 4 adjusts the driving part of the automobile according to the driving part adjusting information so as to adjust the driving part to be used to by the current user;
(4) After each driving, if the second face detection and recognition module 2 detects and recognizes that the automobile driver is a user, the recording module 5 updates the face information of the last user according to the face information detected and recognized by the second face detection and recognition module 2, that is, the face information of the last user of the automobile is stored in the storage information base 50 as the face information of the last user.
The invention also provides equipment, which comprises a memory and a processor, wherein the memory stores a program, and when the program is executed by the processor, the automobile control method based on face recognition is realized.
The invention also provides a storage medium, wherein the storage medium stores a program, and when the program is executed by a processor, the automobile control method based on face recognition is realized.
The advantages of the device and the storage medium of the invention are: the safety and the convenience of unlocking the automobile are improved, and the driving part of the automobile is intelligently adjusted, so that the problem that the driving part needs to be manually adjusted when a driver is replaced every time is solved, and convenience is brought to the user.
While embodiments of the present invention have been described in detail hereinabove, it will be apparent to those skilled in the art that various modifications and variations can be made to these embodiments. It is to be understood that such modifications and variations are within the scope and spirit of the present invention as set forth in the following claims. Moreover, the invention described herein is capable of other embodiments and of being practiced or of being carried out in various ways.
Claims (6)
1. The automobile control method based on face recognition is characterized by comprising the following steps:
s1: acquiring a first face detection result through a first face detection and recognition network, performing comparison operation on the first face detection result and pre-stored face information to acquire a first face recognition result, and determining an unlocking mode of the automobile according to the first face recognition result;
s2: after the automobile is successfully unlocked in the unlocking mode of the automobile, a second face detection result is obtained through a second face detection and recognition network, and comparison operation is carried out on the second face detection result and the pre-stored face information so as to determine the identity of an automobile driver;
s3: after determining that the identity of the automobile driver is a user, extracting driving part adjusting information corresponding to pre-stored face information matched with the user, and adjusting the driving part of the automobile according to the driving part adjusting information, wherein the specific steps comprise:
performing comparison operation on the second face detection result and the face information of the last user, and keeping the position of the driving part of the automobile unchanged when the second face detection result is matched with the face information of the last user;
When the second face detection result is not matched with the face information of the last user and the second face detection result is matched with the pre-stored face information, extracting driving part adjusting information corresponding to the pre-stored face information, and adjusting the driving part of the automobile according to the driving part adjusting information;
s4: updating the face information of the user after driving to obtain the face information of the last user;
in the step S1, the step of determining the unlocking mode of the automobile according to the first face recognition result includes:
when the first face detection result is matched with the pre-stored face information, determining that the automobile driver is a user, and automatically unlocking the automobile;
when the first face detection result is not matched with the pre-stored face information, determining that the automobile driver is a guest;
after the guest unlocks the automobile through the key and successfully unlocks the automobile, executing the step S2;
after determining that the automobile driver is a guest, the steps are further performed:
when the guest does not unlock the automobile through the key or does not unlock the automobile and touches related parts of the automobile, an alarm is sent out;
in the step S2, the step of performing a comparison operation on the second face detection result and the pre-stored face information to determine the identity of the driver of the automobile includes:
When the second face detection result is matched with the pre-stored face information, determining the identity of the automobile driver as the user;
and when the second face detection result is not matched with the pre-stored face information, determining that the automobile driver is a guest, and ending the step S2.
2. The face recognition-based automotive control method of claim 1, wherein the first face detection recognition network comprises a first face detection network and a first face recognition network;
the first face detection network is used for detecting a face, outputting face classification information, face frame regression information and a plurality of face key point regression information, and outputting a face detection result to the first face recognition network;
the first face recognition network is used for outputting the first face recognition result after processing the first face detection result.
3. The face recognition-based automobile control method of claim 1 wherein the second face detection recognition network comprises a second face detection network and a second face recognition network;
the second face detection network is used for acquiring a second face detection result and transmitting the second face detection result to the second face recognition network;
The second face recognition network is used for judging whether the second face detection result is matched with the pre-stored face information or not.
4. A face recognition-based car control system for implementing the face recognition-based car control method according to any one of claims 1 to 3, comprising:
the first face detection and recognition module is arranged on the outer side of the automobile and is used for acquiring a first face detection result through a first face detection and recognition network, and performing comparison operation on the first face detection result and pre-stored face information to acquire a first face recognition result;
the unlocking module is used for determining an unlocking mode of the automobile according to the first face recognition result and successfully unlocking the automobile through the unlocking mode of the automobile;
the second face detection and recognition module is arranged in a cab of the automobile and is used for acquiring a second face detection result through a second face detection and recognition network, performing comparison operation on the second face detection result and the pre-stored face information and performing comparison operation on the second face detection result and the pre-stored face information to determine the identity of an automobile driver;
and the driving part control module is used for extracting driving part adjusting information corresponding to the pre-stored face information matched with the user after determining the identity of the automobile driver as the user, and adjusting the driving part of the automobile according to the driving part adjusting information.
5. An apparatus comprising a memory and a processor, wherein the memory has a program stored therein, which when executed by the processor, implements the face recognition-based vehicle control method of any one of claims 1 to 3.
6. A storage medium having a program stored therein, which when executed by a processor, implements the face recognition-based automobile control method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210258115.5A CN114619993B (en) | 2022-03-16 | 2022-03-16 | Automobile control method based on face recognition, system, equipment and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210258115.5A CN114619993B (en) | 2022-03-16 | 2022-03-16 | Automobile control method based on face recognition, system, equipment and storage medium thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114619993A CN114619993A (en) | 2022-06-14 |
| CN114619993B true CN114619993B (en) | 2023-06-16 |
Family
ID=81901212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210258115.5A Active CN114619993B (en) | 2022-03-16 | 2022-03-16 | Automobile control method based on face recognition, system, equipment and storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114619993B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105235615A (en) * | 2015-10-27 | 2016-01-13 | 浙江吉利控股集团有限公司 | Vehicle control system based on face recognition |
| CN106004735A (en) * | 2016-06-27 | 2016-10-12 | 京东方科技集团股份有限公司 | Vehicle-mounted system and adjusting method for vehicle facilities |
| CN106740596A (en) * | 2016-11-30 | 2017-05-31 | 北京汽车集团有限公司 | Steering position method of adjustment, device and vehicle |
| CN108263250A (en) * | 2017-12-28 | 2018-07-10 | 江西爱驰亿维实业有限公司 | Vehicle-mounted memory seat method of adjustment, system and terminal based on recognition of face |
| CN110765936A (en) * | 2019-10-22 | 2020-02-07 | 上海商汤智能科技有限公司 | Vehicle door control method, vehicle door control device, vehicle door control system, vehicle, electronic equipment and storage medium |
| KR102079351B1 (en) * | 2018-08-31 | 2020-02-19 | 니덱모빌리티코리아 주식회사 | Apparatus and method for automatically adjusting driver's comfort of a vehicle through driver authentication |
| DE102019104675A1 (en) * | 2019-02-25 | 2020-08-27 | STC Corporation Co., Ltd. | System and method for starting a vehicle using facial recognition data |
| CN111645633A (en) * | 2020-06-10 | 2020-09-11 | 中国第一汽车股份有限公司 | Vehicle control method and device, vehicle and storage medium |
| CN112037380A (en) * | 2020-09-03 | 2020-12-04 | 上海商汤临港智能科技有限公司 | Vehicle control method and device, electronic equipment, storage medium and vehicle |
| CN112215187A (en) * | 2020-10-21 | 2021-01-12 | 广州市晶华精密光学股份有限公司 | Intelligent automobile door opening method and device, intelligent automobile and storage medium |
| CN112381073A (en) * | 2021-01-12 | 2021-02-19 | 上海齐感电子信息科技有限公司 | IQ (in-phase/quadrature) adjustment method and adjustment module based on AI (Artificial Intelligence) face detection |
| CN113822145A (en) * | 2021-07-30 | 2021-12-21 | 的卢技术有限公司 | Face recognition operation method based on deep learning |
| US11254270B1 (en) * | 2018-05-02 | 2022-02-22 | State Farm Mutual Automobile Insurance Company | Technologies for using image analysis to facilitate adjustments of vehicle components |
-
2022
- 2022-03-16 CN CN202210258115.5A patent/CN114619993B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105235615A (en) * | 2015-10-27 | 2016-01-13 | 浙江吉利控股集团有限公司 | Vehicle control system based on face recognition |
| CN106004735A (en) * | 2016-06-27 | 2016-10-12 | 京东方科技集团股份有限公司 | Vehicle-mounted system and adjusting method for vehicle facilities |
| CN106740596A (en) * | 2016-11-30 | 2017-05-31 | 北京汽车集团有限公司 | Steering position method of adjustment, device and vehicle |
| CN108263250A (en) * | 2017-12-28 | 2018-07-10 | 江西爱驰亿维实业有限公司 | Vehicle-mounted memory seat method of adjustment, system and terminal based on recognition of face |
| US11254270B1 (en) * | 2018-05-02 | 2022-02-22 | State Farm Mutual Automobile Insurance Company | Technologies for using image analysis to facilitate adjustments of vehicle components |
| KR102079351B1 (en) * | 2018-08-31 | 2020-02-19 | 니덱모빌리티코리아 주식회사 | Apparatus and method for automatically adjusting driver's comfort of a vehicle through driver authentication |
| DE102019104675A1 (en) * | 2019-02-25 | 2020-08-27 | STC Corporation Co., Ltd. | System and method for starting a vehicle using facial recognition data |
| CN110765936A (en) * | 2019-10-22 | 2020-02-07 | 上海商汤智能科技有限公司 | Vehicle door control method, vehicle door control device, vehicle door control system, vehicle, electronic equipment and storage medium |
| CN111645633A (en) * | 2020-06-10 | 2020-09-11 | 中国第一汽车股份有限公司 | Vehicle control method and device, vehicle and storage medium |
| CN112037380A (en) * | 2020-09-03 | 2020-12-04 | 上海商汤临港智能科技有限公司 | Vehicle control method and device, electronic equipment, storage medium and vehicle |
| CN112215187A (en) * | 2020-10-21 | 2021-01-12 | 广州市晶华精密光学股份有限公司 | Intelligent automobile door opening method and device, intelligent automobile and storage medium |
| CN112381073A (en) * | 2021-01-12 | 2021-02-19 | 上海齐感电子信息科技有限公司 | IQ (in-phase/quadrature) adjustment method and adjustment module based on AI (Artificial Intelligence) face detection |
| CN113822145A (en) * | 2021-07-30 | 2021-12-21 | 的卢技术有限公司 | Face recognition operation method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114619993A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104816694B (en) | One kind is driven condition intelligent adjusting apparatus and method | |
| WO2018000999A1 (en) | On-board system and control method for vehicle facility | |
| EP2915707B1 (en) | Methods and sytems for preventing unauthorized vehicle operation using face recogntion | |
| US20200001892A1 (en) | Passenger assisting apparatus, method, and program | |
| CN108725357A (en) | Parameter control method, system based on recognition of face and cloud server | |
| CN105035025A (en) | Driver identification management method and system | |
| CN207015293U (en) | System for the personal settings of pilot instrument | |
| CN110901632A (en) | Automatic parking control method and device | |
| CN105909116B (en) | Control method, the apparatus and system of car door | |
| CN106627490A (en) | Automobile trunk opening-closing control system and method based on identity recognition and speech recognition | |
| CN111055731B (en) | Safe riding control method, device and equipment | |
| CN110789477B (en) | Control method and device for test driving vehicle, cloud platform and vehicle-mounted intelligent equipment | |
| CN112734985B (en) | Vehicle door control method, device, equipment, terminal and readable storage medium | |
| CN112124232A (en) | Method for automatically adjusting vehicle seat | |
| CN107764986A (en) | Driver's drunk driving detection method and system, data processing method and server | |
| CN110816448A (en) | Adjusting control system and method for seat and rearview mirror | |
| CN114619993B (en) | Automobile control method based on face recognition, system, equipment and storage medium thereof | |
| CN116001716A (en) | Intelligent remote management system for mechanical equipment | |
| US10977505B2 (en) | Occupant monitoring device for vehicle | |
| CN210836483U (en) | Vehicle-mounted ETC intelligent terminal equipment with driver state detection function | |
| KR20120012666A (en) | System and method for protecting drunk driving using face recognition technology | |
| CN115162865B (en) | Vehicle door control method, device, equipment and storage medium | |
| CN114194122B (en) | Safety prompt system and automobile | |
| US10592758B2 (en) | Occupant monitoring device for vehicle | |
| CN113507593A (en) | Monitoring method, device, system and terminal for vehicle cabin |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |