Occupant authentication device, occupant authentication method, and program

Abstract

The present invention makes it possible to suppress facial authentication failure under conditions in which a light environment may change, when authenticating an occupant of a vehicle using facial authentication. An authentication unit (11) authenticates an occupant of a vehicle using facial authentication. A determining unit (12) changes criteria for determining success and failure of the facial authentication in accordance with a traveling state of the vehicle.

Description

Occupant authentication device, occupant authentication method, and computer-readable medium

[0001] The present disclosure relates to an occupant authentication device, an occupant authentication method, and a computer-readable medium.

[0002] As a related technique, Patent Document 1 discloses a vehicle authentication device using biometric authentication. The authentication device estimates the risk of fraudulent use depending on the situation in which the vehicle is located. The risk of fraudulent use indicates the degree of possibility that the vehicle will be fraudulently used. In Patent Document 1, the risk of fraudulent use is estimated using factors that affect the likelihood of fraudulent use, such as the time of day and the region. The authentication device changes the authentication level depending on the estimated risk of fraudulent use.

[0003] Japanese Patent Application Laid-Open No. 2007-145200

[0004] However, Patent Document 1 does not take into consideration that face recognition is performed under circumstances where the lighting environment may change. For example, if an image is captured in a dark place, backlit, or in an environment where highlights are blown out, the degree of match or matching score in face recognition may be significantly reduced even for the same person, which may result in authentication failure.

[0005] In view of the above circumstances, the present disclosure aims to provide an occupant authentication device, an occupant authentication method, and a computer-readable medium that can reduce the failure of facial authentication when authenticating vehicle occupants using facial authentication in situations where the lighting environment may change.

[0006] To achieve the above object, the present disclosure provides an occupant authentication device that includes an authentication unit that authenticates a vehicle occupant through facial recognition, and a determination unit that changes criteria for determining whether authentication is successful or unsuccessful in the facial recognition in accordance with the running state of the vehicle.

[0007] The present disclosure also provides an occupant authentication method, which includes authenticating a vehicle occupant through facial recognition and changing criteria for determining whether authentication is successful or unsuccessful in the facial recognition in accordance with a running state of the vehicle.

[0008] The present disclosure provides a program that causes a processor to execute a process including authenticating a vehicle occupant through facial recognition and changing criteria for determining whether authentication is successful or unsuccessful in the facial recognition depending on the running state of the vehicle.

[0009] The occupant authentication device, occupant authentication method, and computer-readable medium according to the present disclosure can reduce failures in facial authentication when authenticating vehicle occupants using facial authentication in situations where the lighting environment may change.

[0010] A block diagram showing a schematic configuration of an occupant authentication device according to the present disclosure. A block diagram showing an occupant authentication device according to a first embodiment of the present disclosure. A schematic diagram showing face authentication in a certain aspect. A flowchart showing an operation procedure of the occupant authentication device. A block diagram showing a system including an occupant authentication device according to a second embodiment of the present disclosure. A block diagram showing a hardware configuration of the occupant authentication device.

[0011] Prior to describing embodiments of the present disclosure, an overview of the present disclosure will be described. Fig. 1 shows a schematic configuration of an occupant authentication device according to the present disclosure. The occupant authentication device 10 includes an authentication unit 11 and a determination unit 12. The authentication unit 11 authenticates vehicle occupants through facial recognition. The determination unit 12 changes criteria for determining whether authentication is successful or unsuccessful in facial recognition depending on the running state of the vehicle.

[0012] The occupant authentication device 10 according to the present disclosure changes the criteria for determining whether authentication is successful or unsuccessful depending on the vehicle's driving state when facial recognition is performed. When the vehicle is moving, for example, the lighting environment around the occupant may change, and an image suitable for facial recognition may not be obtained when facial recognition is performed. Assuming that the same criteria are used when the vehicle is moving and when it is stopped, facial recognition of the same person may be successful when the vehicle is stopped, but may fail when the vehicle is moving. In the present disclosure, the criteria for determination are changed depending on the driving state, and therefore the criteria for determination can be appropriately changed depending on changes in the surrounding lighting environment. This allows the occupant authentication device to reduce facial recognition failures in situations where the lighting environment may change.

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Note that the following description and drawings have been omitted and simplified as appropriate for clarity of explanation. In addition, in the following drawings, the same or similar elements are designated by the same reference numerals, and duplicate explanations are omitted as necessary.

[0014] 2 shows an occupant authentication device according to the first embodiment of the present disclosure. The occupant authentication device 100 includes a face authentication unit 101, a determination unit 102, a situation information acquisition unit 103, and a warning unit 104. The occupant authentication device 100 is configured as a device including, for example, one or more processors and one or more memories. At least some of the functions of each unit in the occupant authentication device 100 can be realized by the processor executing processing in accordance with a program read from the memory. The occupant authentication device 100 corresponds to the occupant authentication device 10 shown in FIG. 1.

[0015] In this embodiment, the occupant authentication device 100 is used to determine whether an occupant of a vehicle such as an automobile, van, or truck is a pre-registered legitimate user. The occupant authentication device 100 is mounted on, for example, a vehicle. The occupant authentication device 100 repeatedly authenticates the occupant by facial recognition, for example, from the time the occupant gets into the vehicle until the occupant gets out of the vehicle. In addition to the above determination, the occupant authentication device 100 may also be used for interior entry in a vehicle such as an automobile. The occupant authentication device 100 is not limited to interior entry and can be applied to authentication in various systems.

[0016] The occupant authentication device 100 acquires an image of the subject, i.e., the occupant, from the camera 130 and performs face authentication using the acquired image. The camera 130 captures an image of the vehicle occupant who is the subject of authentication. In this embodiment, the camera 130 captures an image of the interior of the vehicle. The camera 130 is installed, for example, between the driver's seat and the passenger seat, in a position that allows a view of the entire interior of the vehicle. Multiple cameras 130 may be installed inside the vehicle. In this case, the occupant authentication device 100 may acquire images of multiple occupants from the multiple cameras 130.

[0017] The face authentication unit 101 acquires images captured by the camera 130, i.e., image data of the interior of the vehicle. The face authentication unit 101 sequentially acquires the latest image data captured by the camera 130. The face authentication unit 101 detects a face area from the acquired image data. The face authentication unit 101 cuts out an image of the face area from the acquired image data. The face authentication unit 101 cuts out, for example, a facial image of the vehicle driver from the image data. The face authentication unit 101 performs face authentication of the person to be authenticated, i.e., the vehicle occupant, using the cut-out facial image. The face authentication unit 101 performs face authentication, for example, when a specific condition is met. The face authentication unit 101 performs face authentication, for example, every time a predetermined time has elapsed since the previous face authentication.

[0018] The face authentication unit 101 registers face images of one or more users to be authenticated, i.e., one or more registrants. In the following description, the face images of registrants are also referred to as registered images. For example, registered images of people who hold driver's licenses and are able to drive vehicles are registered in the face authentication unit 101. In addition to or instead of the registered images, feature amounts extracted from the registered images may also be registered in the face authentication unit 101.

[0019] The face authentication unit 101 compares the face image of the occupant with a registered image. For example, the face authentication unit 101 extracts facial features from the face image of the occupant and compares the extracted features with features extracted from the registered image. The face authentication unit 101 calculates a matching score indicating the degree of match or similarity between the face image of the occupant and the registered image. In the following description, it is assumed that the higher the degree of match or similarity, the higher the matching score.

[0020] The face authentication unit 101 determines whether face authentication has been successful or not based on the matching score. The face authentication unit 101 compares the matching score with an authentication threshold. The authentication threshold corresponds to a criterion for determining whether face authentication has been successful or not. The face authentication unit 101 determines whether face authentication has been successful or not based on the comparison result between the matching score and the authentication threshold. For example, if the matching score is equal to or greater than the authentication threshold, the face authentication unit 101 determines that face authentication has been successful. If the matching score is less than the authentication threshold, the face authentication unit 101 determines that face authentication has failed. The face authentication unit 101 corresponds to the authentication unit 11 shown in FIG. 1.

[0021] The situation information acquisition unit 103 acquires information about the vehicle's running state. The information about the vehicle's running state may include, for example, the vehicle's speed, the vehicle's position, and the gear position. The situation information acquisition unit 103 may acquire information about the vehicle's running state from a device such as a vehicle control ECU (Electronic Control Unit) that controls the vehicle, via an in-vehicle communication network such as a CAN (Controller Area Network). The situation information acquisition unit 103 may also acquire vehicle position information measured using a GNSS (Global Navigation Satellite System) as information about the vehicle's running state.

[0022] The situation information acquisition unit 103 may acquire surrounding environment information in addition to the above information. The surrounding environment information includes, for example, information on the lighting environment that affects the facial image captured using the camera 130. The surrounding environment information includes at least one of whether or not overexposure occurs, whether or not the image is backlit, and whether or not the brightness of the facial image is insufficient. The surrounding environment information can be acquired, for example, by analyzing the brightness and histogram of each pixel of the in-vehicle image captured using the camera 130.

[0023] The determination unit 102 changes the authentication threshold in the face authentication unit 101 according to the information acquired by the situation information acquisition unit 103. For example, the determination unit 102 changes the authentication threshold according to whether the vehicle is moving or not, or whether the vehicle is stopped or not. For example, the determination unit 102 lowers the authentication threshold when the vehicle is moving compared to when the vehicle is stopped. The face authentication unit 101 determines whether face authentication is successful or unsuccessful using the authentication threshold determined or set by the determination unit 102. The determination unit 102 corresponds to the determination unit 12 shown in FIG. 1 .

[0024] 3 schematically illustrates face authentication in a certain situation. When the vehicle is stopped, the determination unit 102 sets the authentication threshold to a high value, for example, 0.7. On the other hand, when the vehicle is moving, the determination unit 102 sets the authentication threshold to a low value, for example, 0.6. Assume that the matching score calculated by the face authentication unit 101 is 0.65. In this case, when the authentication threshold is 0.7, the face authentication unit 101 determines that authentication has failed. On the other hand, when the authentication threshold is 0.6, the face authentication unit 101 determines that authentication has succeeded.

[0025] When a vehicle is moving, the lighting environment can change in a short period of time as the vehicle moves. The determination unit 102 sets the authentication threshold to a low value when the vehicle is moving. In this case, the face authentication unit 101 determines that face authentication is successful even if the matching score, i.e., the similarity between the registered image and the occupant's face image, is somewhat low. Therefore, the possibility of face authentication failing while the vehicle is moving is reduced. On the other hand, the determination unit 102 sets the authentication threshold to a high value when the vehicle is stopped. In this case, the face authentication unit 101 determines that face authentication has failed unless the matching score is relatively high. Therefore, the face authentication unit 101 can perform face authentication under stricter conditions while the vehicle is stopped, and can check for driver changes while the vehicle is stopped under stricter conditions.

[0026] When the vehicle is stopped, the determination unit 102 may change the authentication threshold depending on whether the vehicle is parked, or whether the vehicle is temporarily stopped. The state in which the vehicle is temporarily stopped includes, for example, when the vehicle is stopped at a traffic light or when the vehicle is stopped on a congested road. The determination unit 102 may determine that the vehicle is parked, for example, when the speed is 0 and the shift position is P (Parking), and may determine that the vehicle is temporarily stopped, for example, when the speed is 0 and the shift position is other than P. Alternatively, the determination unit 102 may determine whether the vehicle is parked or temporarily stopped based on the elapsed time since the vehicle stopped. For example, the determination unit 102 may determine that the vehicle is parked, for example, when the speed becomes 0 and the speed remains 0 for a predetermined time or more.

[0027] The determination unit 102 may determine whether the vehicle is parked or temporarily stopped based on an image from a camera that captures an image of an area outside the vehicle. For example, the determination unit 102 may determine that the vehicle is parked when the vehicle is parked close to the edge of the road. Alternatively, the determination unit 102 may determine that the vehicle is parked when the vehicle is parked in a parking space such as a parking lot. The determination unit 102 may compare the vehicle's location information with map information to determine whether the vehicle is located in a parking lot. The determination unit 102 may determine that the vehicle is parked when the vehicle is located in a parking lot.

[0028] The determination unit 102 may change the authentication threshold based on surrounding environment information in addition to information about the driving state. For example, the determination unit 102 may temporarily lower the authentication threshold when there is blown-out highlights in the image, when the image is backlit, or when the brightness of the facial image is insufficient. In this case, it is possible to reduce the possibility of facial authentication failing due to the inability to obtain an image suitable for facial authentication.

[0029] The warning unit 104 issues an alert when the face authentication unit 101 fails to authenticate the face. The warning unit 104 may use, for example, at least one of sound and light to notify the vehicle occupant that face authentication has failed, i.e., that the occupant is not a person registered in advance. The warning unit 104 may issue an alert when the face authentication unit 101 fails to authenticate the face a predetermined number of times in succession. Furthermore, for example, if the operation of the vehicle is managed by a corporation, the warning unit 104 may notify the vehicle operations manager of the corporation of the alert. In this case, the warning unit 104 may notify, for example, that the occupant is not a person registered in advance, using a communication means such as e-mail.

[0030] Next, the operation procedure will be explained. Fig. 4 shows the operation procedure of the occupant authentication device 100. The operation procedure of the occupant authentication device 100 corresponds to the occupant authentication method. The face authentication unit 101 acquires an image of the interior of the vehicle from the camera 130 (step S1). The face authentication unit 101 detects the face area of ​​the occupant from the image acquired from the camera 130 (step S2).

[0031] The situation information acquisition unit 103 acquires information about the vehicle's traveling state (step S3). In step S3, the situation information acquisition unit 103 may acquire information about the vehicle's surrounding environment in addition to the information about the vehicle's traveling state. The determination unit 102 determines an authentication threshold value according to the information acquired in step S3 (step S4). The determination unit 102 sets the authentication threshold value determined in step S4 in the face authentication unit 101. Steps S1 and S2 and steps S3 and S4 may be performed in any order, or may be performed in parallel.

[0032] The face authentication unit 101 performs face authentication on the image of the face area of ​​the occupant detected in step S2, i.e., the face image (step S5). In face authentication, the face authentication unit 101 compares the matching score with the authentication threshold determined in step S4. If the matching score is equal to or greater than the authentication threshold, the face authentication unit 101 determines that face authentication has been successful. If the matching score is less than the authentication threshold, the face authentication unit 101 determines that face authentication has failed.

[0033] The warning unit 104 determines whether or not the face authentication unit 101 has succeeded in face authentication (step S6). If the face authentication unit 101 has failed in face authentication, the warning unit 104 generates an alert (step S7). In step S7, the warning unit 104 uses, for example, sound and light to warn the driver inside the vehicle that a person other than a registered person is driving.

[0034] In this embodiment, the determination unit 102 changes the authentication threshold value in the face authentication unit 101 depending on the traveling state of the vehicle. By appropriately setting the authentication threshold value depending on the traveling state of the vehicle when face authentication is performed, even if an image suitable for face authentication cannot be acquired, it is possible to prevent face authentication from failing due to this.

[0035] For example, while the vehicle is traveling, the determination unit 102 sets the authentication threshold to a low value because there is a possibility that an image suitable for authentication may not be acquired due to changes in the lighting environment. When the face authentication unit 101 performs face authentication using a low authentication threshold, the possibility of face authentication failure due to changes in the lighting environment while the vehicle is traveling can be reduced. Since frequent notifications of face authentication failures are suppressed, vehicle occupants can board the vehicle without feeling annoyed. On the other hand, the determination unit 102 sets the authentication threshold to a higher value when the lighting environment does not change, such as when the vehicle is stopped. In this case, the face authentication unit 101 can perform face authentication under stricter conditions, and can check for driver changes while the vehicle is stopped under stricter conditions.

[0036] Next, a second embodiment of the present disclosure will be described. FIG. 5 shows a system including an occupant authentication device according to the second embodiment of the present disclosure. In this embodiment, the configuration of the occupant authentication device 100 may be the same as the configuration of the occupant authentication device 100 described in the first embodiment shown in FIG. 2. In this embodiment, if the face authentication unit 101 fails to perform face authentication, the occupant authentication device 100 notifies the vehicle control device 150 that face authentication has failed. If the face authentication unit 101 fails to perform face authentication a predetermined number of times consecutively, the occupant authentication device 100 may notify the vehicle control device 150 that face authentication has failed. Note that in this embodiment, the occupant authentication device 100 does not need to include the warning unit 104.

[0037] The vehicle control device 150 includes a vehicle control ECU that performs vehicle driving control and other functions. The vehicle control ECU has a processor, memory, I / O (Input / Output), and a bus connecting these. The vehicle control ECU acquires sensor information from vehicle sensors and performs vehicle driving control and other functions. The vehicle sensors are sensors for detecting various states of a moving object. The vehicle sensors include, for example, a vehicle speed sensor that detects vehicle speed, a steering sensor that detects steering angle, an accelerator pedal position sensor that detects accelerator pedal position, and a brake pedal force sensor that detects brake pedal depression. Based on the sensor information output by the vehicle sensors, the vehicle control ECU performs various controls, such as control of fuel injection amount, engine ignition timing, and power steering assist amount.

[0038] The vehicle control device 150 may include an autonomous driving ECU that controls autonomous driving of the vehicle. The autonomous driving ECU has a processor, memory, I / O, and a bus connecting these. The autonomous driving ECU acquires sensor information from perimeter monitoring sensors and vehicle sensors, and controls the autonomous driving of the vehicle based on the acquired sensor information. The perimeter monitoring sensors are sensors that monitor the surrounding conditions of the moving object. The perimeter monitoring sensors include, for example, cameras, radar, and LiDAR (Light Detection and Ranging). The perimeter monitoring sensors may include, for example, multiple cameras that capture images of the front, rear, right side, and left side of the vehicle.

[0039] For example, when the vehicle control device 150 receives a notification from the occupant authentication device 100 indicating that face authentication has failed, the vehicle control device 150 stops the vehicle on the shoulder of the road. For example, the vehicle control device 150 instructs the automatic driving ECU to stop the vehicle, and the automatic driving ECU automatically stops the vehicle on the shoulder of the road. When the vehicle is traveling in automatic driving mode, the vehicle control device 150 may terminate automatic driving and switch the vehicle's driving mode from automatic driving to manual driving. When the vehicle control device 150 receives a notification from the occupant authentication device 100 indicating that face authentication has succeeded after stopping the vehicle on the shoulder of the road or switching to manual driving, the vehicle control device 150 may switch the vehicle to automatic driving and continue to drive the vehicle in automatic driving mode.

[0040] In this embodiment, if the occupant authentication device 100 fails to authenticate the face, the vehicle control device 150 stops the vehicle on the side of the road. Alternatively, if the vehicle was traveling in autonomous driving mode, the vehicle control device 150 terminates autonomous driving. This prevents unauthorized use of the vehicle by people other than registered individuals, i.e., legitimate users. Other effects are the same as those in the first embodiment.

[0041] In the above embodiment, an example has been described in which the occupant authentication device 100 is mounted on a vehicle. However, the present disclosure is not limited to this. In the present disclosure, the occupant authentication device 100 does not necessarily have to be mounted on a vehicle. The occupant authentication device 100 may be a device installed outside the vehicle. In this case, the occupant authentication device 100 may acquire images captured by the camera 130 via a wireless communication network.

[0042] In the present disclosure, the occupant authentication device 100 does not necessarily have to be a single device. The occupant authentication device 100 may be configured using multiple physically separated devices. Furthermore, all functions of the occupant authentication device 100 do not necessarily have to be mounted on the vehicle or located outside the vehicle. For example, some of the functions of the occupant authentication device 100 may be located outside the vehicle, and the remaining functions may be mounted on the vehicle.

[0043] Next, the hardware configuration of the occupant authentication device 100 will be described. Fig. 6 shows the hardware configuration of the occupant authentication device 100. The occupant authentication device 100 has a processor (CPU: Central Processing Unit) 501, a ROM (read only memory) 502, and a RAM (random access memory) 503. In the occupant authentication device 100, the processor 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. Although not shown, the occupant authentication device 100 may include other circuits such as peripheral circuits, communication circuits, and interface circuits.

[0044] The ROM 502 is a non-volatile storage device. For example, a semiconductor storage device with a relatively small capacity, such as a flash memory, is used as the ROM 502. The ROM 502 stores the programs executed by the processor 501.

[0045] The program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include RAM, ROM, flash memory, solid-state drive (SSD) or other memory technologies, compact discs (CDs), digital versatile discs (DVDs), Blu-ray discs or other optical disc storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. The program may also be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0046] The RAM 503 is a volatile storage device. Various semiconductor memory devices such as a dynamic random access memory (DRAM) or a static random access memory (SRAM) are used for the RAM 503. The RAM 503 can be used as an internal buffer for temporarily storing data and the like.

[0047] The processor 501 loads a program stored in the ROM 502 into the RAM 503 and executes the program. When the CPU 501 executes the program, the functions of each unit in the occupant authentication device 100 can be realized.

[0048] The above describes the embodiments of the present disclosure in detail, but the present disclosure is not limited to the above-described embodiments, and changes and modifications to the above-described embodiments that do not deviate from the spirit of the present disclosure are also included in the present disclosure.

[0049] For example, some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0050] [Supplementary Note 1] An occupant authentication device comprising: an authentication unit that authenticates a vehicle occupant by facial recognition; and a determination unit that changes a criterion for determining whether authentication is successful or unsuccessful in the facial recognition according to a running state of the vehicle.

[0051] [Supplementary Note 2] The occupant authentication device according to Supplementary Note 1, wherein the determination unit changes the criteria for the determination depending on whether the vehicle is moving or stopped.

[0052] [Supplementary Note 3] The occupant authentication device according to Supplementary Note 1 or 2, wherein the decision unit lowers the standard of the determination when the vehicle is moving compared to when the vehicle is stopped.

[0053] [Supplementary Note 4] The occupant authentication device according to any one of Supplementary Notes 1 to 3, wherein the determination unit changes the criteria for the determination further depending on ambient environment information of the vehicle.

[0054] [Supplementary Note 5] The occupant authentication device according to any one of Supplementary Notes 1 to 4, wherein the authentication unit repeatedly performs the face authentication from the time the occupant gets into the vehicle until the occupant gets out of the vehicle.

[0055] [Supplementary Note 6] The occupant authentication device according to any one of Supplementary Notes 1 to 5, wherein the determination unit changes the criteria for the determination when the vehicle is stopped depending on whether the vehicle is parked or temporarily stopped.

[0056] [Supplementary Note 7] The occupant authentication device according to any one of Supplementary Notes 1 to 6, further comprising a warning unit that issues an alert when the authentication unit fails to perform the face authentication.

[0057] [Appendix 8] The occupant authentication device described in any one of Appendices 1 to 7, wherein the authentication unit compares the facial image of the occupant or features extracted from the facial image with a registered image of a registered person or features extracted from the registered image, calculates a matching score indicating the degree of match between the occupant and the registered person, compares the calculated matching score with the judgment criterion, and judges whether the facial authentication was successful or not based on the result of the comparison.

[0058] [Supplementary Note 9] The occupant authentication device according to Supplementary Note 8, wherein the determination unit determines a threshold value for the matching score as the criterion for the judgment, and the authentication unit determines whether the face authentication has been successful or not depending on whether the matching score is equal to or greater than the threshold value.

[0059] [Supplementary Note 10] An occupant authentication method comprising: authenticating a vehicle occupant by facial authentication; and changing a criterion for determining whether authentication is successful or unsuccessful in the facial authentication according to a running state of the vehicle.

[0060] [Supplementary Note 11] A program for causing a processor to execute a process including authenticating a vehicle occupant through facial recognition, and changing criteria for determining whether authentication is successful or unsuccessful in the facial recognition depending on the running state of the vehicle.

[0061] This application claims priority based on Japanese Patent Application No. 2022-138697, filed on August 31, 2022, the disclosure of which is incorporated herein in its entirety by reference.

[0062] 10: Occupant authentication device 11: Authentication unit 12: Determination unit 100: Occupant authentication device 101: Face authentication unit 102: Determination unit 103: Situation information acquisition unit 104: Warning unit 130: Camera 150: Vehicle control device

Claims

1. an authentication unit that authenticates vehicle occupants by facial recognition; A determination unit that changes a criterion for determining whether authentication is successful or unsuccessful in the face authentication depending on the running state of the vehicle.

2. The occupant authentication device according to claim 1 , wherein the determination unit changes the criterion for the determination depending on whether the vehicle is moving or stopped.

3. The occupant authentication device according to claim 1 , wherein the decision unit lowers the standard for the determination when the vehicle is moving compared to when the vehicle is stopped.

4. The occupant authentication device according to claim 1 , wherein the determination unit changes the criterion for the determination further depending on surrounding environment information of the vehicle.

5. The occupant authentication device according to claim 1 , wherein the authentication unit repeatedly performs the face authentication from when the occupant gets into the vehicle until when the occupant gets out of the vehicle.

6. The occupant authentication device according to claim 1 or 2, wherein when the vehicle is stopped, the decision unit changes the criterion for the determination depending on whether the vehicle is parked or temporarily stopped.

7. The occupant authentication device according to claim 1 , further comprising a warning unit that issues an alert when the authentication unit fails to authenticate the face.

8. the authentication unit compares a facial image of the occupant or a feature amount extracted from the facial image with a registered image of a registered person or a feature amount extracted from the registered image, calculates a matching score indicating a degree of match between the occupant and the registered person, compares the calculated matching score with the determination criterion, and determines whether or not the face authentication has been successful based on a result of the comparison; The determination unit determines a threshold value for the matching score as a criterion for the determination, The occupant authentication device according to claim 1 , wherein the authentication unit determines whether the face authentication has been successful or not depending on whether the matching score is equal to or greater than the threshold value.

9. Vehicle occupants are identified by face recognition. An occupant authentication method comprising changing a criterion for determining whether authentication is successful or unsuccessful in the face authentication in accordance with a traveling state of the vehicle.

10. Vehicle occupants are identified by face recognition. A program for causing a processor to execute a process including changing criteria for determining whether authentication is successful or not in the face authentication in accordance with the traveling state of the vehicle.