KR20200128285A - Method for opening vehicle door and strating vehicle based on facial recognition and apparatus for the same - Google Patents

Abstract

Disclosed is a face portion recognition-based vehicle opening and starting method. The face portion recognition-based vehicle opening and starting method according to the present invention comprises the steps of: activating at least one external camera when a push on a vehicle door opening and closing button is recognized; performing face portion authentication for opening a door for an actor who pressed the vehicle door opening and closing button based on an analysis of external image information acquired through the external camera; opening the vehicle door when the face portion of the actor who pressed the vehicle door opening and closing button is authenticated as a face portion of a registered user through the face portion authentication for opening the door; activating at least one internal camera when a push on a start button is recognized; performing face portion authentication for starting for an actor who pressed the start button based on an analysis of internal image information acquired through the internal camera; and starting the vehicle when the face portion of the actor who pressed the start button is authenticated as the face portion of the registered user through the face portion authentication for starting.

Description

Facial recognition-based vehicle opening and starting method and device {METHOD FOR OPENING VEHICLE DOOR AND STRATING VEHICLE BASED ON FACIAL RECOGNITION AND APPARATUS FOR THE SAME}

The present invention relates to a method and apparatus for starting a vehicle door opening, and more particularly, to a method and apparatus for enabling a vehicle door opening and starting by recognizing a face of a registered user without a vehicle key such as a smart key.

Various advanced technologies are being applied to automobiles to improve the safety of automobiles and to promote driver's convenience with the development of various sensors and automotive electronic technology. In particular, technologies for preventing drowsy driving and lane departure using cameras and face recognition are receiving much attention.

In particular, a technology that enables authentication for authorization for driving a vehicle based on the recognized facial part and biometric signals (including information) beyond simple facial recognition and biometric recognition is also attracting much attention.

In relation to the situation where the spread of smart keys is expanding, driver convenience by allowing vehicle owners (including legal drivers) to use their own vehicles even if they do not bring the smart keys due to mistakes or use the smart keys due to battery discharge. Need to increase. At this time, it is necessary to prevent someone other than the vehicle owner from using the vehicle by opening the vehicle door and starting the vehicle.

An object of the present invention for meeting the above needs is to enable vehicle owners who temporarily cannot use a smart key to open a vehicle and start a vehicle by using a camera installed inside and outside the vehicle, and determining whether the face has been forged or not, and authentication technology. To provide a method and apparatus.

The opening and starting method based on facial recognition according to an embodiment of the present invention for achieving the above object includes the steps of activating at least one external camera when a push on a button for opening and closing a vehicle door is recognized, and an external image acquired through the external camera. Performing a facial part authentication for the person who pressed the car door open/close button based on the analysis of the information, and if the facial part of the person who pressed the car door open/close button through the authentication of the car door open/close button is authenticated as a registered user facial part, the car door The opening step, the step of starting at least one internal camera when the press of the start button is recognized, and authentication of the start-up face part for the actor who pressed the start button based on the analysis of the internal image information acquired through the internal camera And performing vehicle start when the face of the actor who pressed the start button is authenticated as the registered user face through the authentication of the starting face part.

In addition, the step of performing the authentication of the face part for the door opening may include determining whether the face part of the person who pressed the car door open/close button is recognized based on the analysis of the external image information, and the face part of the person who pressed the door open button When it is recognized, determining whether the face of the actor who pressed the recognized door open button is forged or altered, and if it is determined that the face of the actor who pressed the recognized door opening button has not been forged, the actor who pressed the recognized door opening button And performing authentication of the facial part for opening the door to certify that the facial part of the is the same as the facial part for the normal user.

In addition, in the analysis of the external image information, it is analyzed whether the face part of the person who pressed the door open/close button is recognized in consideration of the external illumination environment.

In addition, the face part of the actor who pressed the car door open/close button is recognized by a deep learning CNN-based 3D input image face authentication technique.

In addition, the performing of the start-up facial part authentication includes determining whether the face part of the actor who pressed the start button is recognized based on the analysis of the internal image information, and when the face part of the actor who pressed the start button is recognized The step of determining whether the face of the actor who pressed the recognized start button is forged or altered, and if it is determined that the face of the actor who pressed the recognized start button has not been forged, the face of the actor who pressed the recognized start button is normal And performing authentication of the face part for starting to certify that it is the same as the face part for the.

In addition, in the analysis of the internal image information, it is analyzed whether the facial part of the person who pressed the start button is recognized in consideration of the internal illumination environment.

In addition, the face part of the actor who pressed the start button is recognized by a deep learning CNN-based 2D input image face authentication technique.

In addition, the external camera is a TOF type 3D image camera, and the internal camera is an IR type 2D camera.

In addition, the external camera is installed on the B pillar.

In addition, the internal camera is installed in at least one of an instrument panel in a vehicle steering wheel, a dashboard in a driver's seat, a rear-view mirror, and near a ceiling above the driver's seat.

In the face recognition-based opening start system according to an embodiment of the present invention, at least one external camera module that acquires external image information including an actor who presses a vehicle door open/close button, and internal image information including an actor who presses the start button At least one internal camera module that performs facial recognition of at least one of an actor pressing the door open/close button and an actor pressing the start button based on image analysis of at least one of the external image information and the internal image information And an analysis module, a forgery determination authentication module that determines and authenticates whether or not the recognized face is forged or altered, and an ECU that controls the external camera module, an internal camera module, an image analysis module, and the forgery determination authentication module.

In addition, the ECU requests at least one of the vehicle door opening and closing and starting from the MCU that controls the opening and closing of the vehicle door based on the authentication result of the forgery and alteration determination authentication module.

In addition, the MCU opens the vehicle door through the vehicle door opening and closing unit when a request for opening the door is received from the ECU, and starts the vehicle through the starting unit upon receiving a request to start starting.

In addition, the external camera module is a TOF type 3D image camera installed on the B-pillar.

In addition, the internal camera module is an IR type 2D camera installed in at least one of an instrument panel in a vehicle steering wheel, a dashboard in a driver's seat, a rear-view mirror, and near a ceiling above the driver's seat.

According to the present invention, the vehicle owner can accurately recognize the vehicle owner even when the smart key is temporarily unavailable by using a camera installed inside and outside the vehicle and a detection and authentication technology to determine whether or not the face is forged or altered to enable the vehicle to be opened and started.

1 is a conceptual diagram illustrating a vehicle door opening system based on facial recognition according to an embodiment of the present invention.
2 is a flowchart illustrating a method of opening and starting a vehicle based on facial recognition according to an embodiment of the present invention.
3 is a flow chart illustrating a method of performing authentication of a facial part for an open door according to an embodiment of the present invention.
4 is a flowchart illustrating a method of performing authentication of a face part for starting according to an embodiment of the present invention.

In the present invention, various modifications may be made and various embodiments may be provided, and some embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to a specific embodiment, and the scope of the present invention should be understood as including all changes, modifications, equivalents or substitutes belonging to the technical idea of the present invention conceived from the embodiments. do.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be. It should be understood that there is no other component in the middle only when it is stated that a component is "directly connected" or "directly connected" to another component.

The terms used in the present application are only used to describe the examples presented, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof, does not preclude in advance.

All terms used in this specification, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention belongs, and are ideal or excessively reduced formal It should not be interpreted as a meaning, and when defining the meaning of a term in this specification, the term should be interpreted as defined.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate an overall understanding, the same reference numerals are used for the same elements in the drawings, and duplicate descriptions for the same elements are omitted.

1 is a conceptual diagram illustrating a vehicle door opening system based on facial recognition according to an embodiment of the present invention.

Referring to FIG. 1, a vehicle door opening system 100 based on facial recognition according to an embodiment of the present invention includes a face part of an actor attempting door opening and starting from an image acquired through a camera installed inside and outside the vehicle. Recognizes, and if the face is not forged and is authenticated as a face for a normal user, a request for opening and starting is requested to the MCU 160 that controls the opening and closing of the car door (normal user is the owner of the vehicle or has legal driving rights. Means ruler).

The vehicle opening start system 100 based on face recognition according to an embodiment of the present invention includes at least one external camera module 120 for acquiring external image information including an actor who presses a vehicle door opening/closing button. The external camera module 120 according to an embodiment of the present invention may be implemented as a 3D time-of-flight (TOF) camera.

Since the exterior environment of the vehicle can be various indoor and outdoor environments, it is necessary to recognize the actor attempting to open the vehicle in such various environments (bright or cloudy daytime, nighttime, snowy and rainy environments, etc.). A 3D TOF camera capable of acquiring even 3D depth information at high speed can be used (but is not limited thereto, and a 2D camera that can be linked with any kind of 3D camera and proximity sensor can be applied). It can also be driven together with an auxiliary camera with a wide-angle function to improve recognition performance.

The external camera module 120 of the vehicle opening start system 100 based on facial recognition according to an embodiment of the present invention may be installed in the B pillar portion in the driver's seat direction of the vehicle (not necessarily limited thereto, but different according to the vehicle design). It can be installed at the same time as a filler or in another direction (passenger seat)).

The vehicle door opening system 100 based on facial recognition according to an embodiment of the present invention includes at least one internal camera module 130 that acquires internal image information including an actor who presses a start button. The internal camera module 130 may be installed in a position where it is easy to recognize the person who presses the start button (for example, the dashboard of the steering wheel of the vehicle, the dashboard of the driver's seat, rear-view mirror, near the ceiling of the top of the driver's seat, etc. Can be installed and multiple cameras can be installed for accuracy of recognition).

The internal camera module may be implemented as an IR-based 2D camera, but is not limited thereto, and may be implemented as a 3D camera or a general 2D camera, and may be implemented in combination by using various cameras.

The vehicle door opening system 100 based on facial recognition according to an embodiment of the present invention performs an image analysis of the external image information on the face of the person who presses the door opening/closing button and performs an image of the internal image information. Based on the analysis, it includes an image analysis module 140 that performs facial recognition of an actor who presses the start button.

The image analysis module 140 includes external image information acquired and transmitted by an external camera (which may include information on an external photographed image, a photographing time, and a photographing location) and internal image information obtained and transmitted by the internal camera (internal image information). The video is analyzed and the actor who pressed the opening button (especially the actor's face) and/or the actor who pressed the start button (especially the actor's face) after analyzing the photographed image, recording time, recording location, etc. Is included in (i.e., whether the actor's face is recognizable) is analyzed.

At this time, the image analysis module 140 also considers factors that influence the identification of the facial part in the image information, such as the illuminance environment in the corresponding image information, and checks whether the facial part of the person pressing the open door button and the person pressing the start button can be recognized.

The vehicle opening start system 100 based on facial recognition according to an embodiment of the present invention includes a forgery determination authentication module 150 that determines whether or not the recognized face is forged or altered and authenticates.

The forgery and alteration determination authentication module 150 determines whether or not the recognized face is forged or altered when the face of the actor who pressed the open door button and the actor who pressed the start button are recognized in the image analysis module 140.

That is, because someone other than the normal user of the vehicle may attempt to open and start the vehicle using a photo or video including a normal user's face, a mask or marks, etc., according to an embodiment of the present invention The forgery and alteration determination authentication module 150 accordingly determines whether the face part of the actor in the image information acquired and recognized from the internal camera and the external camera has been forged or altered in the above manner.

In addition, if the forgery determination authentication module 150 according to an embodiment of the present invention determines that the face of the actor has not been forged, authenticates whether the face of the actor in the image information corresponds to the face of a normal user. . That is, by applying a deep learning CNN-based 3D input image face authentication technique to the recognized facial part of the actor who pressed the open door button in the external image information, it is determined whether the user is a normal user (determining whether the face is the same as the normal user's face) If it is determined that it is the face of a normal user, it is authenticated that the actor who pressed the open door button is a normal user.

In addition, by applying a deep learning CNN-based input image face authentication technique to the recognized facial part of the actor who pressed the start button in the internal image information, it is determined whether the user is a normal user (determining whether the face is the same as the normal user's face), If it is determined that it is the face of a normal user, it is authenticated that the actor who pressed the start button is a normal user.

On the other hand, the forgery determination authentication module 150 according to an embodiment of the present invention may be implemented separately as a forgery determination authentication module for an actor who pressed the open button and a forgery determination authentication module for an actor who pressed the start button.

The facial recognition-based vehicle door opening system 100 according to an embodiment of the present invention controls the external camera module 120, the internal camera module 130, the image analysis module 140, and the forgery determination authentication module 150 It includes an electronic control unit (ECU) 110.

For example, when the door opening/closing unit 170 to be described later recognizes the push of the vehicle door opening/closing button, information about this is transmitted through the MCU 160 to the ECU of the face recognition-based vehicle door opening system 100 according to an embodiment of the present invention. 110), and at this time, the ECU 110 may cause the external camera module 120 to start an operation to obtain external image information.

The ECU 110 of the vehicle door opening system 100 based on facial recognition according to an embodiment of the present invention may request the MCU 160 to open the car door when it is authenticated that the actor who pressed the door opening button is a normal user. In this case, the MCU 160 causes the vehicle door opening and closing unit 170 to open the vehicle (the door opened at this time may be based on opening the driver's seat door, and may be implemented to open the door of the assistant seat and the rear seat as necessary). have).

In addition, when the starter 180, which will be described later, recognizes that the start button is pressed, information about this is transmitted to the ECU 110 of the vehicle door opening system 100 based on facial recognition according to an embodiment of the present invention through the MCU 160. ), and at this time, the ECU 110 may cause the internal camera module 130 to start an operation to obtain internal image information.

The ECU 110 of the vehicle door opening system 100 based on facial recognition according to an embodiment of the present invention requests the MCU 160 to start the vehicle when it is authenticated that the person who pressed the start button is a normal user. I can. In this case, the MCU 160 causes the starter 180 to start the vehicle (including triggering, triggering, triggering, etc.).

On the other hand, the device for recognizing the push of the car door button and the device for recognizing the push of the start button may be implemented outside the vehicle door opening start system 100 based on facial recognition according to an embodiment of the present invention, or the door opening and closing unit 170 And the starter 180 may also be implemented inside the vehicle door opening start system 100 based on facial recognition according to an embodiment of the present invention.

In addition, the face recognition-based vehicle door opening system 100 according to an embodiment of the present invention may be implemented with various biometric recognition technologies such as fingerprint recognition and iris recognition to further increase the accuracy of normal user authentication.

Next, a method of opening and starting a vehicle using the vehicle opening start system 100 based on facial recognition according to an embodiment of the present invention will be described.

2 is a flowchart illustrating a method of starting a vehicle door opening based on facial recognition according to an embodiment of the present invention.

A method of opening and starting a vehicle based on face recognition according to an embodiment of the present invention of FIG. 2 relates to a method of opening and starting a vehicle using a vehicle opening and starting system based on facial recognition according to the embodiment of the present invention of FIG. 1. First, while a vehicle key such as a smart key is not recognized around the vehicle, it is recognized that the vehicle door opening/closing button is pressed by a certain force (S210).

In general, the door opening and closing button may be installed on each part of the handle outside the vehicle, but the vehicle door opening and closing button recognized in the vehicle opening start method based on facial recognition according to embodiments of the present invention is described based on the vehicle door opening and closing button on the driver's seat side (this is For convenience of explanation, the present invention is not limited thereto, and may be applied to opening and closing of a vehicle door at another location according to the need in vehicle design)

In this way, when the push of the door opening/closing button is recognized, the external camera is activated (S220) to generate image information (external image information) on the exterior of the vehicle. As described above, the external image information may include an image photographed outside the vehicle and information about a time and location at which the image was photographed. The externally photographed image may include an image (especially an image of the face of the door opener) of an actor who pressed the door opening and closing button (hereinafter referred to as an open door actor).

When the external image information is generated, authentication of the face part for opening the door is performed based on this (S230). That is, when the open door actor is authenticated as a normal user by determining whether the open door actor is authenticated as a normal user (S240), the car door is opened (S250).

At this time, the opened car door may be implemented so that only a car door with a pushed car door open/close button may be opened, or a car door in a different direction may also be opened. If the door opening agent is not authenticated as a normal user (No in S240), the vehicle door is not opened and waits until the vehicle door opening/closing button is pressed again.

On the other hand, a specific method of performing the authentication of the facial part for opening the door according to an embodiment of the present invention follows the procedure shown in the flowchart shown in FIG. 3. That is, when the execution of the facial part authentication for opening is started by the operation of the external camera by the recognition of the push of the car door opening/closing button (S210) (S310), it is determined whether the facial part of the door opening agent is recognized from the external image information generated by the external camera. Do (S320).

In addition, in the authentication of the facial part for an open door according to an embodiment of the present invention, when recognizing the face part of the open door agent, factors that affect the identification of the facial part of the external image information, such as the illumination environment in the corresponding external image information, are also considered. You can check if the facial part of the is recognizable.

At this time, if the face part of the open door agent is recognized (example of S320), it is determined whether the face part of the recognized door open agent is forged or altered (S330). On the other hand, if the face of the door opening actor is not recognized (No in S320), it waits until the vehicle door opening/closing button is pressed again. If it is determined that the face of the recognized open door actor is not forged or altered (No in S330), the facial part authentication is performed on the face part of the open door actor in the corresponding external image information (S340).

In other words, as described above, a deep learning CNN-based 3D input image face authentication technique is applied to the recognized facial part of an actor in external image information to determine whether the user is a normal user (determining whether the face is the same as a normal user), and If it is determined that it is the user's face, it is authenticated that the open door actor is a normal user. On the other hand, if it is determined that the face of the recognized door opener is forged or altered (YES in S330), it waits until it is recognized that the door opening/closing button is pressed again.

When the car door is opened through the above procedure, the door opener may attempt to start the vehicle by pressing the ignition button after sitting in the driver's seat of the vehicle (as described above, in this case, the smart key for starting the vehicle is discharged or smiled, etc.) It is unavailable for reasons). When it is recognized that the start button is pressed (S260), the internal camera installed inside the vehicle is activated (S270) to generate image information (internal image information) about the vehicle interior.

As described above, the internal image information may include an image captured inside the vehicle and information about a time and location at which the image was captured. The internally photographed image may include an image (in particular, an image of the face part of the ignition actor) of an actor who pressed the ignition button (hereinafter referred to as ignition actor).

When the internal image information is generated, authentication of the face part for start-up is performed based on this (S280). That is, when the starting actor is authenticated as a normal user by determining whether the starting actor is authenticated as a normal user by authentication of the starting face part (S290), and the starting actor is authenticated as a normal user (YES in S290), the vehicle is started (S295). If the start-up actor is not authenticated as a normal user (No in S290), start-up is not started and waits until the start-up button is pressed again.

On the other hand, a specific method of performing authentication of the face part for start-up according to an embodiment of the present invention follows the procedure shown in the flowchart shown in FIG. 4. That is, when the start button is recognized (S260), and the internal camera is activated to start the authentication of the starting face (S410), it is determined whether the face of the starting actor is recognized from the internal image information generated by the internal camera. It is determined (S420).

In addition, in the face part authentication for start-up according to an embodiment of the present invention, when the face part of the start-up agent is recognized, factors that affect the face part confirmation of the internal image information, such as the illumination environment in the corresponding internal image information, are also taken into account. You can check if the facial part of the is recognizable.

At this time, if the face of the starting actor is recognized (YES in S420), it is determined whether the face of the recognized starting actor is forged or altered (S430). On the other hand, if the face of the ignition actor is not recognized (No in S420), it waits until the ignition of the ignition button is recognized again. If it is determined that the recognized face of the starting actor is not forged or altered (No in S430), the face portion of the face of the starting actor in the corresponding internal image information is authenticated (S440).

That is, as described above, a deep learning CNN-based input image face authentication technique is applied to the recognized facial part of the starting actor in the internal image information to determine whether the user is a normal user (determining whether the face is the same as the normal user), and the normal user If it is determined that it is the face part of, it is authenticated that the starting actor is a normal user. On the other hand, if it is determined that the face of the recognized door-to-door actor is forged or altered (example in S430), it waits until the start button is pressed again.

Meanwhile, each of the above-described configurations has been described as a separate device, but this is only an exemplary description for convenience of description and enhancement of understanding, and may be implemented in various forms within the scope of the technical idea of the present invention. Of course. For example, the forgery and alteration determination authentication module 150 may be implemented by being integrated into one device, or may be implemented by dividing into two or more devices.

The methods according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the computer-readable medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in computer software.

Examples of computer-readable media include hardware devices specially configured to store and execute program instructions, such as rom, ram, flash memory, and the like. Examples of program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The above-described hardware device may be configured to operate as at least one software module to perform the operation of the present invention, and vice versa.

In the above, the configuration of the present invention has been described in detail through a preferred embodiment of the present invention. However, the above-described embodiments are for illustrative purposes only, and do not limit the scope of the present invention. Those of ordinary skill in the art of the present invention will be able to make various modifications and changes within the scope of the technical idea of the present invention from the teachings and suggestions of the present specification. Accordingly, the scope of protection of the present invention should be determined by the description of the following claims.

Claims (15)

Activating at least one external camera when it is recognized that the vehicle door opening and closing button is pressed;
Performing a face part authentication for opening a door for an actor who pressed the car door open/close button based on analysis of the external image information acquired through the external camera;
Opening the car door when the face part of the actor who pressed the car door opening/closing button through the face part authentication for the door is authenticated as the registered user face part;
Activating at least one internal camera when it is recognized that the start button is pressed;
Performing a start-up facial part authentication for an actor who pressed the start button based on analysis of the internal image information acquired through the internal camera; And
A face recognition-based vehicle door opening start method comprising the step of starting a vehicle when the face portion of the actor who pressed the start button is authenticated as the registered user face portion through the face portion authentication for start-up; The method of claim 1,
The step of performing the facial authentication for the opening of the door,
Determining whether a face part of an actor who pressed the door opening/closing button is recognized based on the analysis of the external image information;
Determining whether or not the face of the actor who pressed the door opening/closing button is recognized, whether or not the face of the actor who pressed the recognized vehicle door opening/closing button is forged or altered; And
If it is determined that the face part of the actor who pressed the recognized car door open/close button has not been forged, performing a face part authentication for opening door to certify that the face part of the actor who pressed the recognized car door open button is identical to the face part for a normal user Facial recognition-based vehicle opening start method comprising a; The method of claim 2,
In the analysis of the external image information, a vehicle door opening start method based on facial recognition is performed to analyze whether a face part of an actor who pressed the door opening button is recognized in consideration of an external illumination environment. The method of claim 3,
A face recognition method based on facial recognition, in which the face portion of the actor pressing the door opening button is recognized by a deep learning CNN-based 3D input image face authentication technique. The method of claim 1,
The step of performing the start-up facial part authentication,
Determining whether the face of the actor who pressed the start button is recognized based on the analysis of the internal image information;
Determining whether the facial part of the actor who pressed the recognized start button is forged or altered when the face of the actor who pressed the start button is recognized; And
If it is determined that the face part of the actor who pressed the recognized start button has not been forged, performing a face part authentication for start-up certifying that the face part of the actor who pressed the recognized start button is the same as the face part for a normal user. Face recognition-based vehicle opening start method; The method of claim 5,
In the analysis of the internal image information, the facial recognition-based vehicle opening start method analyzes whether or not the face part of the person who pressed the start button is recognized in consideration of the internal illumination environment. The method of claim 6,
A facial recognition method based on facial recognition, in which the face of the actor pressing the start button is recognized by a deep learning CNN-based 2D input image face authentication technique. The method of claim 1,
The external camera is a TOF type 3D image camera, and the inner camera is an IR type 2D camera, facial recognition-based vehicle opening start method. The method of claim 1,
The external camera is installed on the B pillar, facial recognition-based vehicle door opening method. The method of claim 1,
The internal camera is installed in at least one of a vehicle steering wheel dashboard, a driver's dashboard, a rear-view mirror, and an upper ceiling of a driver's seat. At least one external camera module for acquiring external image information including an actor pressing a vehicle door opening/closing button;
At least one internal camera module for acquiring internal image information including an actor pressing the start button;
An image analysis module for performing facial recognition on at least one of an actor pressing the door open/close button and an actor pressing a start button based on image analysis of at least one of the external image information and the internal image information;
A forgery determination authentication module that determines and authenticates whether or not the recognized facial part is forged or altered; And
Facial recognition-based door opening system comprising an ECU that controls the external camera module, the internal camera module, the image analysis module, and the forgery and alteration determination authentication module. The method of claim 11,
The ECU requests at least one of the vehicle door opening and closing and starting from the MCU that controls the opening and closing of the vehicle door based on the authentication result of the forgery and alteration determination authentication module. The method of claim 12,
The MCU opens the car door through a car door opening and closing part when a door opening is requested from the ECU, and starts starting the vehicle through a starter when a start-up is requested. The method of claim 11,
The external camera module is a TOF type 3D video camera installed on the B-pillar, facial recognition-based opening start system. The method of claim 11,
The internal camera module is an IR type 2D camera installed in at least one of a vehicle steering wheel dashboard, a driver's dashboard, a rear-view mirror, and an upper ceiling of a driver's seat.

Images