Entry system and authentication method

Abstract

To properly authenticate a user who tries to enter a moving body even in a dark place while suppressing power consumption.SOLUTION: An entry system includes a detection unit that detects a target person approaching a moving body, and an authentication unit that authenticates that the target person is a registered user based on a face image of the target person, in which the detection unit measures illuminance around the moving body when detecting an object entering a range of predetermined distance from the moving body, and selects a sensor to be used for determining whether or not the object is the target person according to the illuminance.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an entry system and an authentication method. [Background technology]

[0002] In recent years, efforts to provide access to sustainable transport systems that take into consideration vulnerable transport participants such as the elderly, people with disabilities, and children have been gaining momentum. To achieve this, we are focusing on research and development to further improve transport safety and convenience through development of vehicle ingress and egress.

[0003] Patent Document 1 discloses a vehicle control device that performs object and human detection after determining the illuminance of the surrounding environment. In this vehicle control device, if a power-saving camera or illuminance sensor determines that the vehicle environment is dark, and if a human sensor detects an object, it activates an LED and a high-precision camera to detect whether the object is a human. This makes it possible to reduce the power consumption of the on-board camera and accurately identify people present around the vehicle, even in dark environments. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2022-133769 Summary of the Invention [Problem to be solved by the invention]

[0005] Incidentally, when it comes to getting on and off a vehicle, it is an issue to properly authenticate a user who is trying to get on even in a dark place.

[0006] The above-mentioned conventional technology requires that energy-saving cameras, illuminance sensors, etc. be operated at all times to determine illuminance, and human detection is performed using high-precision cameras that consume a lot of power regardless of whether the place is dark or not, so there is room for further improvement in terms of power consumption.

[0007] The present application aims to solve the above-mentioned problems by appropriately authenticating users attempting to enter a moving object even in dark places while reducing power consumption, thereby contributing to the development of sustainable transportation systems. [Means for solving the problem]

[0008] One aspect of the present invention is an entry system that includes a detection unit that detects a target person approaching a moving body, and an authentication unit that authenticates that the target person is a registered user based on a facial image of the target person, wherein the detection unit measures the illuminance around the moving body when it detects an object that has entered within a predetermined distance from the moving body, and selects a sensor to use to determine whether the object is the target person based on the illuminance. Another aspect of the present invention is an authentication method performed by a computer of an entry system that authenticates a subject approaching a moving body, the authentication method comprising a detection step of detecting a subject approaching a moving body, and an authentication step of authenticating that the subject is a registered user based on a facial image of the subject, wherein the detection step measures the illuminance around the moving body when an object is detected that has entered within a predetermined distance from the moving body, and selects a sensor to be used to determine whether the object is the subject depending on the illuminance. [Effects of the Invention]

[0009] According to the present invention, it is possible to appropriately authenticate a user attempting to enter a moving body even in a dark place while suppressing power consumption. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a moving body equipped with an entry system according to one embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing the configuration of the entry system. [Figure 3]FIG. 3 is an explanatory diagram for explaining the operation of the entry system in a dark place. [Figure 4] FIG. 4 is an explanatory diagram for explaining the operation of the entry system in a bright place. [Figure 5] FIG. 5 is a flowchart showing the procedure of the operation in the entry system. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0012] [1. Vehicle configuration] FIG. 1 is a diagram showing the configuration of a mobile body 2 equipped with an entry system 1 of this embodiment. The mobile body 2 is equipped with an entry control device 3 that constitutes the entry system 1. The entry system 1 is installed in the mobile body 2 and authenticates a subject P, who is any person attempting to enter the mobile body 2, and allows the subject P to use the mobile body 2 if it is authenticated that the subject P has legitimate access to the mobile body 2. Here, "entering" the mobile body 2 refers to at least boarding (or getting on) the mobile body 2 from outside the mobile body 2, and may also include starting to use the system of the mobile body 2 by logging in to the system after boarding.

[0013] In this embodiment, the moving body 2 is, for example, a passenger car, and may be a shared car that can accommodate multiple people. However, the moving body 2 is not limited to a passenger car, and may be any moving body. Such moving bodies may be land moving bodies such as passenger cars, buses, taxis, and trains, marine moving bodies such as ships and submarines, and air moving bodies such as aircraft including eVTOL (Electric Vertical Take-Off and Landing aircraft), and airborne moving bodies such as airships.

[0014] The right side of the moving body 2 is equipped with a right ranging sensor 4a that detects objects present on the right side of the moving body 2, a first right camera 5a and a second right camera 6a that photograph the right side of the moving body 2, and a right illuminator 7a that illuminates the right side of the moving body 2.

[0015] The left side of the moving body 2 is equipped with a left ranging sensor 4b that detects objects present on the left side of the moving body 2, a first left camera 5b and a second left camera 6b that photograph the left side of the moving body 2, and a left illuminator 7b that illuminates the left side of the moving body 2.

[0016] The rear of the moving body 2 is equipped with a rear ranging sensor 4c that detects objects present behind the moving body 2, a first rear camera 5c and a second rear camera 6c that photograph the area behind the moving body 2, and a rear illuminator 7c that illuminates the area behind the moving body 2.

[0017] In the following, when there is no distinction between the right distance measuring sensor 4a, the left distance measuring sensor 4b, and the rear distance measuring sensor 4c, they will be referred to as distance measuring sensors 4. When there is no distinction between the first right camera 5a, the first left camera 5b, and the first rear camera 5c, they will be referred to as first cameras 5. When there is no distinction between the second right camera 6a, the second left camera 6b, and the second rear camera 6c, they will be referred to as second cameras 6. When there is no distinction between the right illuminator 7a, the left illuminator 7b, and the rear illuminator 7c, they will be referred to as illuminators 7.

[0018] The second camera 6 has a higher resolution and consumes more power than the first camera 5. The first camera 5 and the second camera 6 are, for example, CCD cameras with different pixel counts. The distance measurement sensor 4 is, for example, any sensor that can detect surrounding objects and measure the distance to the objects. In this embodiment, the distance measurement sensor 4 is a radar, and more specifically, a millimeter-wave radar. In addition to radar, the distance measurement sensor 4 may also be, for example, a lidar, a sonar, or the like. The illuminator 7 illuminates the imaging range of the second camera 6. The illuminator 7 may be configured using, for example, any light emitter or light emitting element. In this embodiment, the illuminator 7 is, for example, an LED floodlight.

[0019] The mobile body 2 also includes a door opener 9 provided at each of the doors 8 of the mobile body 2 for locking and unlocking the door 8 and opening and closing the door 8. The door opener 9 may include an actuator for locking and unlocking the corresponding door 8 and an actuator for opening and closing the door 8.

[0020] In this embodiment, the moving body 2 is equipped with, as the doors 8 and door opening / closing devices 9, a right front door opening / closing device 9a provided on a driver's door 8a on the right front side of the moving body 2, and a right rear door opening / closing device 9b provided on a right rear door 8b on the right rear side of the moving body 2. The moving body 2 also is equipped with a left front door opening / closing device 9c provided on a passenger's door 8c on the left front side of the moving body 2, and a left rear door opening / closing device 9d provided on a left rear door 8d on the left rear side of the moving body 2. The moving body 2 further is equipped with a back door opening / closing device 9e provided on a back door (tailgate door) 8e of the moving body 2.

[0021] The mobile object 2 also includes a communication device 10. The communication device 10 includes a transceiver for communicating with an electronic key 11 used to use the mobile object 2. The electronic key 11 may be, for example, a smart key such as a FOB key, or a mobile terminal such as a smartphone that stores key information used to use the mobile object 2.

[0022] [2. Entry system configuration] The configuration of the entry system 1 will be described. 2 is a diagram showing the configuration of the entry system 1. The entry system 1 includes at least an entry control device 3. The entry control device 3 authenticates a subject P, who is any person attempting to enter the mobile object 2, and allows the subject P to use the mobile object 2 if authentication is successful. The authentication is performed based on a facial image acquired of the subject P.

[0023] In the following, "target person" refers to a person who is the subject of authentication by the entry system 1. Furthermore, "user" refers to a registered user who has been pre-registered as a person with legitimate authority to use the mobile object 2, and who actually uses the mobile object 2. Target person P becomes a user when he or she is authenticated by the entry control device 3 and becomes able to use the mobile object 2.

[0024] Some of the functional elements of the entry control device 3 described below may be provided in other devices. For example, a control unit 28 (described later) provided in the entry control device 3 may be realized as a functional element of an electronic control device (ECU, Electronic Control Unit) that controls the operation of the mobile object 2. In this case, the entry system 1 includes the entry control device 3 and the electronic control device, and the entry control device 3 can communicate with the electronic control device and cause the electronic control device to execute the functions of the control unit 28. The entry system 1 may also include other devices such as a distance measuring sensor 4, a first camera 5, a second camera 6, etc., which are used by the entry control device 3.

[0025] The entry control device 3 includes a processor 20 and a memory 21. The memory 21 is configured, for example, with a volatile and / or non-volatile semiconductor memory and / or a hard disk drive, etc. The memory 21 stores authentication data 23 for each of one or more registered users who have been registered in advance as persons having legitimate authority to use the mobile object 2.

[0026] The processor 20 is, for example, a computer including a CPU, etc. The processor 20 may have a configuration including a ROM in which a program is written, a RAM for temporarily storing data, etc. The processor 20 includes, as functional elements or functional units, a detection unit 24, an acquisition unit 25, a determination unit 26, an authentication unit 27, and a control unit 28.

[0027] These functional elements of the processor 20 are realized, for example, by the processor 20, which is a computer, executing a program 22 stored in a memory 21. The program 22 can be stored in any computer-readable storage medium. Alternatively, all or part of the functional elements of the processor 20 can be configured by hardware including one or more electronic circuit components.

[0028] The detection unit 24 uses the distance measurement sensor 4 and the first camera 5 to detect a target person P approaching the moving body 2. In this embodiment, particularly, when the detection unit 24 detects an object that has entered a predetermined distance range from the moving body 2, it measures the illuminance around the moving body 2. Then, the detection unit 24 selects a sensor to use for determining whether the object is the target person or not, depending on the illuminance.

[0029] The detection unit 24 operates, for example, as shown in Figures 3 and 4. Figure 3 is an explanatory diagram for explaining operation in a dark place, and Figure 4 is an explanatory diagram for explaining operation in a bright place. The detection unit 24 first determines whether or not an actual object (or substance) has entered within a predetermined distance D1 from the moving body 2 using the distance measurement sensor 4. The actual object may be any object, including living and non-living objects. When an actual object has entered within the predetermined distance D1, the detection unit 24 activates the first camera 5 closest to the distance measurement sensor 4 that detected the actual object. The detection unit 24 measures the illuminance around the moving body 2 using the activated first camera 5.

[0030] When the illuminance around the moving body 2 is less than a predetermined first predetermined value (see FIG. 3), the detection unit 24 selects the distance measurement sensor 4 as the sensor to be used to determine whether or not the object detected by the distance measurement sensor 4 is the target person P. The detection unit 24 repeatedly acquires the distance from the moving body 2 to the object at predetermined time intervals using the distance measurement sensor 4. Then, based on the acquired distance at predetermined time intervals, the detection unit 24 determines that the object is the target person P if the moving speed of the object is within a predetermined range and the distance between the object and the moving body 2 is decreasing over time.

[0031] On the other hand, when the illuminance around the moving object 2 is equal to or greater than a first predetermined value (see FIG. 4), the detection unit 24 selects the first camera 5 as the sensor to use for determining whether or not the object is the subject P. At that time, when the illuminance around the moving object 2 is equal to or greater than a predetermined second predetermined value, the detection unit 24 may change (or adjust) the exposure setting of the first camera 5 so that the image acquired from the first camera 5 does not have blown-out highlights.

[0032] The detection unit 24 repeatedly acquires images of an object at a predetermined time interval using the first camera 5. The detection unit 24 performs image recognition processing on each of the acquired images at the predetermined time interval, determines whether the object is a human, and identifies the direction of movement of the human. The detection unit 24 then determines that the object is a target person P when it is able to recognize the object as a human with a predetermined frequency and determines that the object recognized as a human is moving in a direction approaching the moving body 2.

[0033] In both the examples shown in Figures 3 and 4, the detection unit 24 determines that the actual object detected by the ranging sensor 4 at a position at distance D1 is a subject P approaching the moving body 2 as the object moves to a position at distance D2, and when the subject P reaches a position at distance D2, notifies the judgment unit 26 and the authentication unit 27 that the subject P has been detected. In this case, when the illuminance is equal to or greater than a first predetermined value and the detection unit 24 detects the approach of the subject P using the first camera 5, the detection unit 24 may notify the judgment unit 26 of the number of times that the detected object was not recognized as a human in the image recognition process for multiple images acquired from the first camera 5 at predetermined time intervals.

[0034] In response to receiving an image acquisition instruction from the determination unit 26 and / or the authentication unit 27, which will be described later, the acquisition unit 25 acquires a high-definition image of the subject P using the second camera 6. As described above, the second camera 6 has a higher resolution and consumes more power than the first camera 5. Specifically, the acquisition unit 25 activates the second camera 6 close to the first camera 5 used to detect the subject P, and acquires second images of the subject P at predetermined time intervals using the activated second camera 6. At this time, when the illuminance around the moving object 2 is less than the first predetermined value, the acquisition unit 25 may turn on the illuminator 7 close to the activated second camera 6. The acquisition unit 25 uses the activated second camera 6 to continuously capture high-resolution second images of the subject P at predetermined time intervals.

[0035] Every time the acquisition unit 25 captures a second image of the subject P, it extracts a facial image of the subject P from the second image and acquires a plurality of facial images of the subject P captured at predetermined time intervals. Every time the acquisition unit 25 captures a second image of the subject P, it sends the captured image of the subject P and the extracted facial image to the determination unit 26 and authentication unit 27, which are the senders of the image acquisition instruction, respectively.

[0036] The determination unit 26 determines whether or not the subject person P intends to board the moving object 2. When the illuminance around the moving object 2 measured by the detection unit 24 is equal to or greater than the first predetermined value (see FIG. 4), upon receiving a notification from the detection unit 24 that the subject P has been detected, the determination unit 26 sends an image acquisition instruction to the acquisition unit 25 to cause the acquisition unit 25 to acquire a second image of the subject P. As described above, the acquisition unit 25 repeatedly acquires the second image of the subject P by the second camera 6 at predetermined time intervals.

[0037] The determination unit 26 determines whether or not the subject P intends to board the moving object 2, based on the movement of the subject P recognized from the plurality of second images captured by the acquisition unit 25 at predetermined time intervals. For example, the determination unit 26 may determine that the subject P intends to board the moving object 2 when the subject P approaches further to any of the doors 8 of the moving object 2, when the subject P stops in front of any of the doors 8 of the moving object 2, when the subject P reaches for the door handle of any of the doors 8, etc. In the example shown in FIG. 4 , the determination unit 26 determines whether or not the subject P intends to board the moving object 2, for example, at a position at a distance D32 from the moving object 2.

[0038] On the other hand, when the illuminance around the moving body 2 measured by the detection unit 24 is less than the first predetermined value (see Figure 3), when the judgment unit 26 receives a notification from the detection unit 24 that the subject P has been detected, it judges whether the subject P intends to board the moving body 2 based on the sensor data from the ranging sensor 4 without sending an image acquisition instruction to the acquisition unit 25.

[0039] Specifically, the determination unit 26 determines whether or not the subject P intends to board the moving body 2 based on the change over time in the distance from the moving body 2 to the subject P acquired from the distance measurement sensor 4, depending on whether or not the subject P has stopped within a predetermined distance from the door of the moving body 2. For example, the determination unit 26 determines that the subject P intends to board the moving body 2 when the subject P has stopped within a predetermined distance from the door of the moving body 2. In the example shown in FIG. 3, the determination unit 26 determines whether or not the subject P intends to board the moving body 2, for example, at a position at a distance D31 that is shorter than the distance D32 shown in FIG. 4.

[0040] Note that even if the illuminance around the moving object 2 measured by the detection unit 24 is equal to or greater than the first predetermined value, if the number of times that the detection unit 24 does not recognize that a detected object is a human exceeds a predetermined number in the image recognition process performed on multiple images acquired at predetermined time intervals from the first camera 5, the determination unit 26 may determine whether or not the subject P intends to board based on the sensor data from the distance measurement sensor 4. For example, the determination unit 26 determines whether or not the subject P intends to board based on whether or not the subject P has stopped within a predetermined distance range from the door of the moving object 2 (for example, within the above-mentioned distance D31) based on a change over time in the distance from the moving object 2 detected by the distance measurement sensor 4.

[0041] The determination unit 26 notifies the authentication unit 27 of the determination result as to whether or not the subject person P intends to board.

[0042] The authentication unit 27 authenticates that the subject P is a registered user based on the face image of the subject P extracted from the second image by the acquisition unit 25. Specifically, when the illuminance around the moving object 2 is equal to or greater than a first predetermined value (see FIG. 4), upon receiving a notification from the detection unit 24 that the target person P has been detected, the authentication unit 27 sends an image acquisition instruction to the acquisition unit 25, and acquires facial images of the target person P, which are repeatedly captured by the acquisition unit 25 at predetermined time intervals. Then, the target person P is authenticated using the acquired facial images of the target person P.

[0043] When the illuminance around the moving object 2 is equal to or greater than the first predetermined value, the authentication unit 27 transmits the image acquisition instruction to the acquisition unit 25 when it receives a notification from the detection unit 24 that the target person P has been detected, similar to the transmission of the image acquisition instruction from the determination unit 26 to the acquisition unit 25. Therefore, when the illuminance around the moving object 2 is equal to or greater than the first predetermined value, the authentication unit 27 can authenticate the target person P simultaneously with the determination unit 26 determining whether the target person P intends to board. For example, in the example of FIG. 4 , the authentication unit 27 can operate to complete the authentication of the target person P at a distance D32 at which the determination unit 26 completes the determination as to whether the target person P intends to board.

[0044] On the other hand, when the illuminance around the moving object 2 is less than the first predetermined value (see FIG. 3), upon receiving a notification from the determination unit 26 that the subject P intends to board, the authentication unit 27 transmits an image acquisition instruction to the acquisition unit 25, and the acquisition unit 25 acquires facial images of the subject P, which are captured repeatedly at predetermined time intervals. For example, in the example of FIG. 3, the authentication unit 27 starts and ends authentication of the subject P when the subject P is standing still at a distance D31 at which the determination unit 26 completes the determination as to whether the subject P intends to board.

[0045] Authentication of the subject P based on a face image in the authentication unit 27 can be performed, for example, as follows. The authentication unit 27 calculates the features of the facial image acquired by the acquisition unit 25, and calculates a matching score for each registered user indicating the degree of match between the calculated features (hereinafter referred to as target features) and the features of the facial image stored in the authentication data 23 of each registered user stored in the memory 21 (hereinafter referred to as authentication features).

[0046] Then, based on the calculated matching scores, the authentication unit 27 determines whether the subject P is one of the registered users. Specifically, for example, when there is a matching score that is equal to or greater than a first predetermined value among the calculated matching scores, the authentication unit 27 authenticates the subject P as being the registered user corresponding to the matching score that shows the highest value among the matching scores that are equal to or greater than the first predetermined value. As a result, the authentication of the subject P is successful.

[0047] On the other hand, if there is no matching score that is equal to or greater than the first predetermined value among the calculated matching scores, the authentication unit 27 determines that the subject P is not a registered user. As a result, the authentication of the subject P is unsuccessful.

[0048] Here, the authentication unit 27 may calculate the matching score for each of a plurality of facial images of the subject P extracted from a plurality of images acquired by the acquisition unit 25 at a predetermined time interval, and determine whether or not there is a registered user corresponding to the subject P based on the calculated matching score. In this case, the authentication unit 27 may determine that the subject P is the one registered user when the registered user corresponding to the subject P determined for each of the plurality of facial images is the same one registered user in the plurality of facial images with a probability equal to or greater than a predetermined value. When the authentication unit 27 cannot identify the one registered user, it can determine that the subject P is not a registered user.

[0049] When the illuminance around the moving object 2 is equal to or greater than a first predetermined value, the authentication unit 27 may perform a so-called liveness determination to determine whether or not the facial image acquired for the subject P is an image of the actual face of the subject P when authenticating the subject P. If the authentication unit 27 determines in the liveness determination that the acquired facial image is not an image of the actual face of the subject P, such as an image of the head of a third party wearing a mask with a facial photograph printed on it, the authentication unit 27 may determine that the authentication using the facial image is unsuccessful.

[0050] Specifically, authentication unit 27 can authenticate whether subject P is a registered user based on the facial images, on the condition that the hue of each of the facial images extracted from each of the plurality of images captured continuously at a predetermined time interval by detection unit 24 from second camera 6 and / or the change in the time-series brightness distribution of the facial images satisfy a predetermined criterion. Here, the criterion can be, for example, that the hue of the facial image is not a hue specific to printed matter, and / or that the illumination of subject P's face as understood from the plurality of time-series facial images changes continuously and without contradiction.

[0051] This effectively prevents, for example, a target person P from fraudulently attempting to enter the moving object 2 by wearing a mask on which the face image of a registered user who is another person is printed.

[0052] The control unit 28 controls the operation of the moving body 2 . When the authentication unit 27 has successfully authenticated the target person P, the control unit 28 instructs the door opener 9 of the mobile object 2 to automatically unlock the door 8. At this time, the control unit 28 may instruct the door opener 9 to unlock the door 8, and then instruct the door opener 9 to automatically open the door 8. The control unit 28 may, for example, execute the automatic unlocking and automatic opening operations on the door 8 that is closest to the target person P. The door 8 that is closest to the target person P may be identified by the acquisition unit 25 from the second image most recently acquired, and notified to the control unit 28.

[0053] [3. Entry System Operation] Next, the operation procedure of the entry system 1 will be described. 5 is a flowchart showing the procedure of the entry control method executed by the computer of the entry system 1. In this embodiment, the computer of the entry system 1 is the processor 20 of the entry control device 3, for example.

[0054] The process shown in FIG. 5 starts when the power of each device shown in FIG. 2, including the entry control device 3, is turned on, and is repeatedly executed. When the process starts, first, the detection unit 24 determines whether or not an object has been detected within a predetermined distance from the moving body 2 by the distance measurement sensor 4 (S100). If no object is detected (S100, NO), the detection unit 24 returns to step S100 and repeats the process, waiting for an object to be detected.

[0055] On the other hand, when an object is detected within a predetermined distance from the moving object 2 (S100, YES), the detection unit 24 measures the illuminance around the moving object 2 using the first camera 5 (S102). Hereinafter, the detected object will be referred to as the detected object.

[0056] The detection unit 24 determines whether the measured illuminance around the moving object 2 is less than a first predetermined value (S104). Then, when the illuminance around the moving object 2 is less than the first predetermined value (S104, YES), the detection unit 24 selects the distance measurement sensor 4 as the sensor to use for determining whether the detected object is the target person P. That is, the detection unit 24 uses the distance measurement sensor 4 to determine whether the detected object is the target person P (S106). When the detection unit 24 determines that the detected object is the target person P, it transmits a notification to the determination unit 26 and the authentication unit 27 that the target person P has been detected.

[0057] As a result of the determination in step S106, when the target person P has not been detected (S108, NO), the detection unit 24 returns to step S100 and repeats the process. On the other hand, when the target person P is detected (S108, YES), the determination unit 26 acquires the distance from the moving body 2 to the target person P from the distance measurement sensor 4 (S110). Then, as described above, the determination unit 26 determines whether or not the target person P intends to board the moving body 2 based on the time transition of the distance from the moving body 2 to the target person P acquired from the distance measurement sensor 4 (S112). The determination result on whether or not the target person P intends to board is sent from the determination unit 26 to the authentication unit 27.

[0058] Then, when the subject person P does not have the intention to board the moving object 2 (S112, NO), the determination unit 26 ends this process. On the other hand, if the subject P intends to board the moving object 2 (S112, YES), the authentication unit 27 transmits an image acquisition instruction to the acquisition unit 25. In response to this, the acquisition unit 25 turns on the illuminator 7 close to the subject P (S114), and then acquires a high-resolution facial image of the subject P using the second camera 6 and transmits it to the authentication unit 27 (S116). The authentication unit 27 authenticates the subject P based on the facial image of the subject P received from the acquisition unit 25, and transmits the authentication result to the control unit 28.

[0059] Next, the control unit 28 determines whether or not the authentication unit 27 has successfully authenticated the target person P (S118). If the authentication of the target person P has succeeded (YES in S118), the control unit 28 instructs the door opener 9 to automatically unlock the door 8 (S120), and ends this process. On the other hand, if the authentication of the target person P is not successful in step S118 (S118, NO), the control unit 28 ends this process without unlocking the door 8.

[0060] On the other hand, if the illuminance around the moving object 2 is equal to or greater than the first predetermined value in step 104 (S104, NO), the detection unit 24 selects the first camera 5 as the sensor to use for determining whether or not the detected object is the target person P. That is, the detection unit 24 determines whether or not the detected object is the target person P from the image from the first camera 5 (S106). When the detection unit 24 determines that the detected object is the target person P, it transmits a notification to the determination unit 26 and the authentication unit 27 that the target person P has been detected.

[0061] As a result of the determination in step S122, when the target person P has not been detected (S124, NO), the detection unit 24 returns to step S100 and repeats the process. On the other hand, when the subject P is detected (S122, YES), the judgment unit 26 judges whether the number of times the detected object was not recognized as a human (hereinafter referred to as the number of unsuccessful subject recognition attempts) in the image recognition process performed by the detection unit 24 on multiple images acquired from the first camera 5 at a predetermined time interval is less than a predetermined number of times (S126).

[0062] Then, when the number of unsuccessful attempts at target person recognition is less than the predetermined number of times (S126, YES), the determination unit 26 sends an image acquisition instruction to the acquisition unit 25 to repeatedly acquire high-resolution images of the target person P at predetermined time intervals (S128). Based on the acquired high-resolution images of the target person P, the determination unit 26 determines whether or not the target person P intends to board the moving object 2 (S130). The determination unit 26 transmits a notification of the determination result to the authentication unit 27.

[0063] Then, when the object person P has no intention to board (S130, NO), the determination unit 26 ends this process. On the other hand, if the subject person P has an intention to board (S130, YES), the authentication unit 27 transmits an image acquisition instruction to the acquisition unit 25, and the process proceeds to step S116.

[0064] On the other hand, if the number of unsuccessful attempts at target person recognition in step S126 is equal to or greater than the predetermined number (S126, NO), the determination unit 26 acquires the distance from the moving body 2 to the target person P from the distance measurement sensor 4 (S132), similar to when the illuminance around the moving body 2 is less than the first predetermined value. Then, the determination unit 26 determines whether or not the target person P intends to board the moving body 2, based on the change over time in the distance from the moving body 2 to the target person P acquired from the distance measurement sensor 4 (S134). The determination result on whether or not the target person P intends to board is sent from the determination unit 26 to the authentication unit 27.

[0065] Then, when the object person P has no intention to board (S134, NO), the determination unit 26 ends this process. On the other hand, if the subject person P has an intention to board (S134, YES), the authentication unit 27 transmits an image acquisition instruction to the acquisition unit 25, and the process proceeds to step S116.

[0066] After this process is completed, the processor 20 of the entry control device 3 repeats the process from step S100.

[0067] 5, the processes from steps S100 to S108 and the processes of steps S122 and S124 correspond to the detection step in the present disclosure, and the processes of steps S116 and S118 correspond to the authentication step in the present disclosure.

[0068] The present invention is not limited to the configurations of the above-described embodiments, and can be implemented in various forms without departing from the spirit of the present invention.

[0069] 5. Configurations supported by the above embodiments The above-described embodiment supports the following configurations.

[0070] (Configuration 1) An entry system comprising a detection unit that detects a target person approaching a moving body, and an authentication unit that authenticates that the target person is a registered user based on a facial image of the target person, wherein the detection unit measures the illuminance around the moving body when it detects an object that has entered within a predetermined distance from the moving body, and selects a sensor to use to determine whether the object is the target person depending on the illuminance. The entry system of configuration 1 selects and uses a sensor that can perform appropriate detection operation according to the brightness around the moving object, so power is not wasted unnecessarily by sensors that are unsuitable for dark places. Therefore, the entry system of configuration 1 can appropriately authenticate users while suppressing power consumption even in dark places.

[0071] (Configuration 2) The moving body is equipped with a ranging sensor and a first camera, and the detection unit detects an object that enters a predetermined distance range from the moving body using the ranging sensor and measures the illuminance around the moving body using the first camera, in an entry system described in Configuration 1. According to the entry system of configuration 2, an object toward the moving body is detected using a ranging sensor that can operate with appropriate sensitivity even in dark places, and the surrounding illuminance is measured using a camera that can also be used to acquire visual information.Therefore, without installing an additional sensor for illuminance measurement, it is possible to appropriately detect the approach of a target even in dark places and easily measure the illuminance that serves as the basis for selecting the appropriate sensor.

[0072] (Configuration 3) The detection unit, when the illuminance around the moving body is less than a predetermined first predetermined value, selects the ranging sensor as the sensor to be used to determine whether the object is the target person, acquires the distance from the moving body to the object using the ranging sensor at predetermined time intervals, and determines that the object is the target person when the moving speed of the object is within a predetermined range and the distance between the object and the moving body is decreasing over time, is an entry system described in Configuration 2. According to the entry system of configuration 3, when the surroundings of the moving body are dark, a distance measuring sensor suitable for operation in dark places is used not only to detect an object but also to determine whether the object is a target person approaching the moving body. Therefore, the entry system of configuration 3 does not use a camera to determine whether a target person is approaching in dark places, so there is no need to use lighting or the like to ensure illuminance, and it can appropriately detect targets while suppressing power consumption even in dark places.

[0073] (Configuration 4) The detection unit, when the illuminance around the moving body is equal to or greater than the first predetermined value, selects the first camera as the sensor to use to determine whether the object is the target person, and determines that the object is the target person when it can recognize the object as a human based on images of the object acquired from the first camera at predetermined time intervals and it is determined that the human is moving in a direction approaching the moving body, is an entry system described in Configuration 3. According to the entry system of configuration 4, when the area around the moving body is bright, a target person approaching the moving body is detected based on visual information obtained from the camera, so that the approach of the target person can be detected quickly.

[0074] (Configuration 5) The moving body is equipped with a second camera having a higher resolution than the first camera, and further comprises an acquisition unit that acquires an image of the target person using the second camera at predetermined time intervals when the target person is detected, and a judgment unit that determines whether the target person intends to board the moving body, wherein when the illuminance measured by the detection unit is equal to or greater than the first predetermined value, the judgment unit determines whether the target person intends to board based on the image of the target person acquired from the second camera, and when the illuminance measured by the detection unit is less than the first predetermined value, determines whether the target person intends to board based on the change in the distance from the moving body to the target person acquired from the ranging sensor over time, and by determining whether the target person has stopped within a predetermined distance from the door of the moving body, an entry system described in configuration 3 or 4. According to the entry system of configuration 5, when the surroundings of the moving body are bright, the intention of the subject to board can be accurately determined using a higher resolution image than the image used to detect the subject. On the other hand, when the surroundings of the moving body are dark, the intention of the subject to board can be determined using a distance measuring sensor without using a high-resolution camera that is not suitable for dark places and consuming unnecessary power, so the intention of the subject to board can be appropriately determined while suppressing power consumption even in dark places.

[0075] (Configuration 6) The moving body is equipped with an illuminator that illuminates the imaging range of the second camera, the acquisition unit turns on the illuminator when the illuminance detected by the detection unit is less than a predetermined value, and the authentication unit authenticates that the subject is a registered user based on a facial image of the subject acquired from the second camera, in the entry system described in Configuration 5. According to the entry system of configuration 6, the illuminator is turned on when it is time to authenticate a subject who approaches a moving object in a dark place. This limits the operating period of the illuminator, thereby reducing power consumption and enabling proper authentication of the subject even in a dark place.

[0076] (Configuration 7) An entry system according to any one of configurations 2 to 6, wherein the detection unit changes the exposure setting of the first camera when the measured illuminance is equal to or greater than a second threshold value. According to the entry system of configuration 7, the exposure sensitivity of the first camera is set according to the ambient brightness, thereby preventing overexposure in the image acquired by the first camera and enabling proper determination of subjects approaching the moving body.

[0077] (Configuration 8) The entry system according to any one of configurations 2 to 7, wherein the distance measurement sensor is a radar. According to the entry system of configuration 8, a radar whose detection accuracy does not decrease even in dark places is used as a distance measuring sensor, and an object approaching a moving body can be accurately detected.

[0078] (Configuration 9) An entry system described in any one of configurations 5 to 8, wherein when the illuminance is equal to or greater than a first threshold, and when the number of times the detection unit does not recognize the object as a human in multiple images acquired from the first camera at predetermined time intervals exceeds a predetermined number, the judgment unit determines whether or not the subject intends to board based on the change over time in the distance from the moving body to the subject acquired from the ranging sensor, and by determining whether or not the subject has stopped within a predetermined distance from the door of the moving body. According to the entry system of configuration 9, even if the surroundings of the moving body are brighter than a predetermined level, if the results of the image recognition processing for multiple images from the camera vary, the target person's intention to board can be detected using a ranging sensor.

[0079] (Configuration 10) An authentication method performed by a computer of an entry system that authenticates a subject approaching a moving body, the authentication method comprising a detection step of detecting a subject approaching a moving body, and an authentication step of authenticating that the subject is a registered user based on a facial image of the subject, wherein in the detection step, when an object is detected that has entered within a predetermined distance from the moving body, the illuminance around the moving body is measured, and a sensor to be used to determine whether the object is the subject is selected according to the illuminance. According to the authentication method of configuration 10, even when the surroundings of the moving object are dark, it is possible to appropriately authenticate the user while suppressing power consumption. [Explanation of symbols]

[0080] 1...Entry system, 2...Mobile object, 3...Entry control device, 4...Distance measurement sensor, 4a...Right distance measurement sensor, 4b...Left distance measurement sensor, 4c...Rear distance measurement sensor, 5...First camera, 5a...First right camera, 5b...First left camera, 5c...First rear camera, 6...Second camera, 6a...Second right camera, 6b...Second left camera, 6c...Second rear camera, 7...Illuminator, 7a...Right illuminator, 7b...Left illuminator, 7c...Rear illuminator, 8...Door, 8a...Driver Passenger door, 8b...right rear passenger door, 8c...passenger door, 8d...left rear passenger door, 8e...tail door, 9...door opener, 9a...right front door opener, 9b...right rear door opener, 9c...left front door opener, 9d...left rear door opener, 9e...tail door opener, 10...communication device, 20...processor, 21...memory, 22...program, 23...authentication data, 24...detection unit, 25...acquisition unit, 26...judgment unit, 27...authentication unit, 28...control unit.

Claims

1. a detection unit that detects a target person approaching a moving object; an authentication unit that authenticates that the subject is a registered user based on a facial image of the subject; Equipped with The detection unit When an object is detected that has entered within a predetermined distance from the moving body, the illuminance around the moving body is measured; selecting a sensor to be used for determining whether the object is the target person according to the illuminance; Entry system.

2. the moving body includes a distance measurement sensor and a first camera; The detection unit The distance measuring sensor detects an object that has entered a predetermined distance range from the moving body, measuring the illuminance around the moving object using the first camera; The entry system of claim 1 .

3. When the illuminance around the moving object is less than a first predetermined value, the detection unit: selecting the distance measurement sensor as a sensor to be used for determining whether the object is the target person; The distance from the moving body to the object is acquired at predetermined time intervals by the distance measuring sensor, and when the moving speed of the object is within a predetermined range and the distance between the object and the moving body is decreasing over time, the object is determined to be the target person. The entry system according to claim 2 .

4. When the illuminance around the moving object is equal to or greater than the first predetermined value, selecting the first camera as a sensor to be used to determine whether the object is the target person; When the object can be recognized as a human based on images of the object acquired from the first camera at predetermined time intervals and it is determined that the human is moving in a direction approaching the moving body, the object is determined to be the target person.

4. The entry system according to claim 3.

5. the moving body is provided with a second camera having a higher resolution than the first camera; an acquisition unit that acquires an image of the target person at predetermined time intervals using the second camera when the target person is detected; a determination unit that determines whether or not the subject person intends to board the moving object; Further provided with The determination unit When the illuminance measured by the detection unit is equal to or greater than the first predetermined value, it is determined whether or not the subject has an intention to board the vehicle based on an image of the subject acquired from the second camera; When the illuminance measured by the detection unit is less than the first predetermined value, the presence or absence of the target person's intention to board is determined based on a change over time in the distance from the moving body to the target person acquired from the distance measurement sensor, depending on whether or not the target person has stopped within a predetermined distance from a door of the moving body.

4. The entry system according to claim 3.

6. the moving body includes an illuminator that illuminates an imaging range of the second camera, the acquisition unit turns on the illuminator when the illuminance detected by the detection unit is less than a predetermined value; the authentication unit authenticates that the subject is a registered user based on a facial image of the subject acquired from the second camera.

6. The entry system according to claim 5.

7. the detection unit changes an exposure setting of the first camera when the measured illuminance is equal to or greater than a second threshold value; The entry system according to claim 2 .

8. the distance measurement sensor is a radar; 8. An entry system according to any one of claims 2 to 7.

9. The determination unit When the illuminance is equal to or greater than a first threshold, if the number of times the detection unit does not recognize the object as a human in a plurality of images acquired at predetermined time intervals from the first camera exceeds a predetermined number, the detection unit determines whether or not the subject intends to board the vehicle based on a change over time in the distance from the vehicle to the subject acquired from the distance measurement sensor, depending on whether or not the subject has stopped within a predetermined distance from the door of the vehicle.

9. An entry system according to any one of claims 5 to 8.

10. An authentication method performed by a computer in an entry system that authenticates a subject approaching a mobile object, comprising: a detection step of detecting a target person approaching the moving body; an authentication step of authenticating that the subject is a registered user based on a facial image of the subject; and In the detecting step, When an object is detected that has entered within a predetermined distance from the moving body, the illuminance around the moving body is measured; selecting a sensor to be used for determining whether the object is the target person according to the illuminance; Authentication method.

Images