User detection device, user detection system, user detection method, and user detection program

Abstract

A user detection device (1) according to the present disclosure comprises: an image processing unit (11) that, on the basis of image in which the area near a vehicle is captured, detects a user candidate and a prescribed mark indicating a vehicle boarding location; and a determination unit (12) that determines whether the user candidate is a user of the vehicle, on the basis of information on the user candidate and on the prescribed mark detected by the image processing unit (11).

Description

Technical Field

[0001] The present disclosure relates to a user detection device, a user detection system, a user detection method, and a non-transitory computer-readable medium.

Background Art

[0002] As a related art, Patent Document 1 discloses an out-of-vehicle information providing device that provides information to a driver about the presence of a person outside the vehicle who wants to convey a message to the driver. The out-of-vehicle information providing device described in Patent Document 1, for example, assists a bus driver in detecting bus passengers.

[0003] When assisting in detecting users of buses, taxis, etc., not only information on user candidates but also position information of predetermined landmarks such as bus stops and taxi stands is used together, which improves the accuracy of user detection.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] For obtaining the position information of a predetermined landmark, for example, a position information acquisition system using artificial satellites or the like is used. However, the position information provided by the position information acquisition system may have an error that hinders user detection, which has been a cause of a decrease in the accuracy of user detection.

[0006] The present disclosure has been made to solve such problems, and an object thereof is to provide a user detection device, a user detection system, a user detection method, and a non-transitory computer-readable medium that improve the accuracy of user detection.

Means for Solving the Problems

[0007] The present disclosure includes an image processing unit that detects a predetermined landmark indicating a user candidate and a boarding location based on an image captured near a vehicle, and a determination unit that determines whether the user candidate is a user of the vehicle based on information on the user candidate and the predetermined landmark detected by the image processing unit. A user detection device is provided.

[0008] The present disclosure includes an in-vehicle device and a server device, wherein the in-vehicle device captures an image near the vehicle, and the server device determines whether the user candidate is a user of the vehicle based on a predetermined landmark indicating a user candidate and a boarding location detected by image processing of the image. A user detection system is provided.

[0009] The present disclosure recognizes a predetermined landmark indicating a user candidate and a boarding location based on an image near the vehicle, and determines whether the user candidate is a user of the vehicle based on information on the recognized user candidate and the predetermined landmark. A user detection method is provided.

[0010] The present disclosure includes an operation of recognizing a predetermined landmark indicating a user candidate and a boarding location based on an image near the vehicle, and an operation of determining whether the user candidate is a user of the vehicle based on information on the recognized user candidate and the predetermined landmark, and a non-transitory computer-readable medium having recorded thereon a user detection program that causes a computer to execute the operations. A non-transitory computer-readable medium is provided.

Advantages of the Invention

[0011] According to the present disclosure, a user detection device, a user detection system, a user detection method, and a non-transitory computer-readable medium that improve the accuracy of user discovery can be provided.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Modes for Carrying Out the Invention

[0013] (First Embodiment) <Configuration of the User Detection Device> With reference to the drawings, the configuration of the user detection device according to the first embodiment will be described. FIG. 1 is a block diagram showing the configuration of the user detection device according to the first embodiment.

[0014] The user detection device 1 according to this embodiment includes an image processing unit 11 and a determination unit 12. The image processing unit 11 detects user candidates and a predetermined landmark based on an image of the vicinity of the vehicle. Further, the determination unit 12 determines whether the user candidate is a user of the vehicle based on the information of the user candidate detected by the image processing unit 11 and a predetermined landmark indicating the boarding location.

[0015] <Operation of the user detection device> With reference to the drawings, the operation of the user detection device according to the first embodiment will be described. FIG. 2 is a flowchart showing the operation of the user detection device according to the first embodiment.

[0016] First, the image processing unit 11 detects user candidates and a predetermined landmark based on an image of the vicinity of the vehicle (step ST101). Next, the determination unit 12 determines whether the user candidate is a user of the vehicle (step ST102).

[0017] With such a configuration, the user detection device 1 according to this embodiment can accurately obtain the positional relationship between the user candidate and the predetermined landmark by detecting not only the user candidate but also the predetermined landmark in the image. As a result, the user detection device 1 improves the accuracy of user discovery.

[0018] (Second Embodiment) <Configuration of the user detection device> With reference to the drawings, the configuration of the user detection device according to the second embodiment will be described in detail. FIG. 3 is a block diagram showing the configuration of the user detection device according to the second embodiment.

[0019] The user detection device 1 according to this embodiment is a device attached to a vehicle that needs to discover users, such as a bus or a taxi. The user detection device 1 includes an image processing unit 11, a determination unit 12, a photographing unit 13, and a determination result output unit 14.

[0020] Note that in this embodiment, the user detection device 1 does not necessarily have to be configured as a single physical device. For example, the image processing unit 11, the determination unit 12, the imaging unit 13, and the determination result output unit 14 may be distributed and arranged in a plurality of physical devices. Further, the image processing unit 11, the determination unit 12, the imaging unit 13, and the determination result output unit 14 may each be configured as an individual device.

[0021] The imaging unit 13 captures an image of the vicinity of the vehicle and outputs it to the image processing unit 11. The vicinity of the vehicle here may include, for example, an area on the sidewalk existing in the traveling direction of the vehicle. That is, when the vehicle is traveling on the left side, it is preferable to include the left front of the vehicle in the imaging range, and when the vehicle is traveling on the right side, it is preferable to include the right front of the vehicle in the imaging range.

[0022] When the vehicle discovers a user, it needs to stop near the user. Therefore, at the stage when the vehicle acquires the user information detected by the user detection device 1, a distance sufficient for the vehicle to perform a safe stop operation is required between the vehicle and the user. Thus, the area captured by the imaging unit 13 may include an area farther from the vehicle than the distance required for the vehicle to perform a safe stop operation.

[0023] The imaging unit 13 may be a single camera provided in the vehicle or a plurality of cameras. For example, the imaging unit 13 may be a plurality of cameras installed at two or more of the four directions of the front, left and right sides, and rear of the vehicle.

[0024] The image processing unit 11 acquires an image of the vicinity of the vehicle captured by the imaging unit 13. The image processing unit 11 performs image processing on the acquired image and detects user candidates and predetermined landmarks. The image processing unit 11 may detect the state of the user candidate in the image processing. Further, the image processing unit 11 may detect the distance between the detected user candidate and the predetermined landmark. The image processing unit 11 outputs the information of the detected user candidate and the predetermined landmark to the determination unit 12.

[0025] For example, the image processing unit 11 searches for a person's area in the acquired image and detects user candidates. When the acquired image contains a plurality of persons, the image processing unit 11 detects those plurality of persons as user candidates. Further, the state of the user candidate refers to information such as the position and movement of the user candidate, for example.

[0026] In addition, the image processing unit 11 detects, as a predetermined landmark, a landmark for indicating a boarding location in image processing, for example. When the vehicle is a bus, for example, the image processing unit 11 detects a bus stop as a predetermined landmark.

[0027] Also, when the vehicle is a taxi, for example, the image processing unit 11 may detect a display board indicating a taxi stand as a predetermined landmark. Alternatively, when the user designates a feature such as a structure or a signboard as a feature near the meeting place, the image processing unit 11 may detect the designated feature as a predetermined landmark.

[0028] Further, the image processing unit 11 may include an AI (artificial intelligence) engine. The AI engine is learned, for example, to detect a person and the state of that person from an image. The image processing unit 11 inputs the acquired image into the AI engine and obtains a detection result of user candidates from the AI engine.

[0029] The determination unit 12 obtains information regarding the state of the user candidate and the distance between the user candidate and the predetermined landmark from the image processing unit 11. Then, the determination unit 12 determines whether the user candidate is a user of the vehicle based on the state of the user candidate and the distance between the user candidate and the predetermined landmark.

[0030] Specifically, the determination unit 12 determines whether the distance between the user candidate and the predetermined landmark is equal to or less than a predetermined value. When a plurality of user candidates are detected, the determination unit 12 determines for each of the plurality of user candidates whether the distance is equal to or less than the predetermined value.

[0031] Next, for the user candidates determined by the determination unit 12 to be at a distance of a predetermined value or less from a predetermined landmark, the determination unit 12 determines whether the state of the user candidates satisfies a predetermined condition. Then, the determination unit 12 determines that the user candidates satisfying the predetermined condition are users. When the determination unit 12 determines that at least one or more user candidates are users, the determination unit 12 outputs the user information to the determination result output unit 14.

[0032] The predetermined condition of the state of the user candidate here may be, for example, that the user candidate stays in the same place. That is, the user candidate may be detected in a state of waiting near a predetermined landmark and determined to be a user. Note that staying in the same place does not mean that the user candidate completely and precisely stops at one point, and movement within a range that does not deviate from the gist is allowed.

[0033] Also, the predetermined condition of the state of the user candidate may be that a plurality of user candidates are gathered. That is, the determination unit 12 counts the number of user candidates determined to be at a distance of a predetermined value or less from a predetermined landmark, and when the number of the user candidates is equal to or more than a predetermined number, the determination unit 12 may determine that all of the user candidates are users.

[0034] Also, the predetermined condition of the state of the user candidate may be that the user candidates are lined up. That is, when the user candidates are lined up in a straight line with one of the user candidates determined to be at a distance of a predetermined value or less from a predetermined landmark as the head, the determination unit 12 may determine that all of the user candidates lined up in a straight line are users.

[0035] In addition, when a part of the user candidates lined up in a straight line is a user candidate determined to be at a distance greater than a predetermined value from a predetermined landmark, the determination unit 12 may also determine that the user candidate is a user. Also, being lined up in a straight line does not necessarily mean a strict straight line, and includes cases where they are lined up in a distorted manner within a range that does not deviate from the gist.

[0036] Also, the predetermined condition of the state of the user candidate may be that the user candidate is performing a predetermined action. The predetermined action here may be, for example, an action of raising a hand or an action of visually tracking a vehicle. That is, any action that can be detected by the image processing unit 11 may be used.

[0037] Also, the predetermined condition of the state of the user candidate is not limited to one, and a plurality of conditions may be set. Then, when any one or a plurality of conditions are detected, the determination unit 12 may determine the user candidate as a user.

[0038] The image processing unit 11 and the determination unit 12 may be realized, for example, by an arithmetic unit P such as a CPU (Central Processing Unit) as shown in FIG. 4, and a storage unit M such as a RAM (Random Access Memory) or a ROM (Read Only Memory) in which programs, data, etc. for controlling the arithmetic unit are stored. Alternatively, the image processing unit 11 and the determination unit 12 may be realized as a single device or component. That is, the image processing unit 11 and the determination unit 12 may be realized as software or as hardware.

[0039] Note that when the program is loaded into a computer, it includes a set of instructions (or software code) for causing 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, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD), or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc, or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0040] The determination result output unit 14 notifies the user information acquired from the determination unit 12. The target for which the determination result output unit 14 notifies the user information is, for example, the driver of the vehicle or the automatic driving control system mounted on the vehicle.

[0041] When the target for which the user information is notified is the driver of the vehicle, the determination result output unit 14 may notify the user information by voice, for example, or may notify the user information by turning on or flashing a light source such as a lamp. In this case, the determination result output unit 14 may only notify the driver of the presence of the user, or may notify the information such as the position and number of users together.

[0042] Also, when the target for which the user information is notified is the automatic driving control system mounted on the vehicle, the determination result output unit 14 may output the position information of the user to the automatic driving control system.

[0043] With such a configuration, the user detection device 1 according to the present embodiment detects a predetermined landmark by image processing, so the accuracy of the position information of the predetermined landmark is improved. Furthermore, based on the acquired position information of the predetermined landmark, the user is determined from the user candidates, so the accuracy of user discovery can be improved.

[0044] <Operation of User Detection Device> With reference to the drawings, the operation of the user detection device according to the second embodiment, that is, the user detection method will be described in detail. FIG. 5 is a flowchart showing the operation of the user detection device according to the second embodiment.

[0045] First, the imaging unit 13 captures an image in the vicinity of the vehicle (step ST201). Next, the image processing unit 11 detects user candidates and a predetermined landmark based on the captured image (step ST202), and detects the state of the user candidates and the distance between the user candidates and the predetermined landmark (step ST203).

[0046] Next, the determination unit 12 determines whether the distance between the user candidate and the predetermined landmark is less than or equal to a predetermined value (step ST204). If the distance between the user candidate and the predetermined landmark is greater than the predetermined value, that is, if the determination in step ST204 is No, the determination unit 12 determines that the user candidate is not a user and ends the series of operations.

[0047] If the distance between the user candidate and the predetermined landmark is less than or equal to the predetermined value, that is, if the determination in step ST204 is Yes, the determination unit 12 determines whether the state of the user candidate satisfies a predetermined condition (step ST205). If the state of the user candidate does not satisfy the predetermined condition, that is, if the determination in step ST205 is No, the determination unit 12 determines that the user candidate is not a user and ends the series of operations.

[0048] When the state of the user candidate satisfies a predetermined condition, that is, when the determination in step ST205 is Yes, the determination result output unit 14 notifies the user's information (step ST206) and ends the series of operations. The series of operations described above are repeatedly executed while the user detection device 1 is operating.

[0049] Note that the number of user candidates determined by the series of operations described above varies depending on the predetermined conditions in step ST205. For example, when the predetermined conditions are that the user candidate stays in the same place or the user candidate performs a predetermined operation, the series of operations are executed for each user candidate.

[0050] On the other hand, when the predetermined conditions are, for example, that the number of user candidates is equal to or more than a predetermined number or the user candidates are aligned, the series of operations are executed for a plurality of user candidates.

[0051] With the configuration as described above, the user detection device 1 according to the present embodiment can improve the accuracy of user detection and notify the detected user information to the driver or the automatic driving control system.

[0052] (Third Embodiment) <Configuration of User Detection System> With reference to the drawings, the configuration of the user detection device according to the third embodiment will be described in detail. In the following embodiments, descriptions overlapping with those of the first or second embodiment will be omitted as appropriate. FIG. 6 is a block diagram showing the configuration of the user detection system according to the third embodiment.

[0053] The user detection system 1001 according to this embodiment includes an in-vehicle device 2 and a server device 3. The in-vehicle device 2 and the server device 3 can communicate via a network including a wireless communication network. The user detection system 1001 according to this embodiment causes a server device 3 not mounted on the vehicle to perform part of the functions of the user detection device 1 according to the first or second embodiment. Specifically, the server device 3 according to this embodiment executes functions corresponding to the image processing unit 11 and the determination unit 12 according to the first or second embodiment.

[0054] In the above, an example in which the server device executes functions corresponding to the image processing unit and the determination unit has been described, but this embodiment is not limited to this. For example, the in-vehicle device 2 may execute the function corresponding to the image processing unit 11 according to the first or second embodiment, and the server device 3 may execute only the function corresponding to the determination unit 12 according to the first or second embodiment.

[0055] That is, the in-vehicle device 2 only needs to have at least a function of capturing an image in the vicinity of the vehicle, and the server device 3 only needs to have a function of determining whether or not the user candidate is a user of the vehicle based on at least the user candidate detected by image processing and a predetermined landmark.

[0056] The in-vehicle device 2 includes a photographing unit 21, a determination result output unit 22, and a communication device 23. The photographing unit 21 corresponds to the photographing unit 13 according to the second embodiment and has the same configuration and function.Similarly, the determination result output unit 22 corresponds to the determination result output unit 14 according to the second embodiment and has the same configuration and function. The communication device 23 transmits the image captured by the photographing unit 21 to the server device 3. Also, it receives user information from the server device 3 and outputs it to the determination result output unit 22.

[0057] The server device 3 includes an image processing unit 31, a determination unit 32, and a communication unit 33. The image processing unit 31 corresponds to the image processing unit 11 according to the first or second embodiment and has the same configuration and functions. The determination unit 32 corresponds to the determination unit 12 according to the first or second embodiment and has the same configuration and functions. The communication unit 33 receives an image from the in-vehicle device 2 and outputs it to the image processing unit 31. Further, the information of the user output by the determination unit 32 is transmitted to the in-vehicle device 2.

[0058] In this way, when a part of the functions of the user detection device 1 according to the first or second embodiment is executed by the server device 3, the equipment installed in the vehicle is simplified, so the cost can be reduced.

[0059] (Fourth Embodiment) <Configuration of User Detection System> The fourth embodiment is a first application example of the user detection system 1001 according to the third embodiment. The configuration of the user detection system according to the fourth embodiment will be described in detail with reference to the drawings. FIG. 7 is a block diagram showing the configuration of the user detection system according to the fourth embodiment.

[0060] The user detection system 1002 according to the present embodiment is obtained by adding a position information providing system 4 and a control unit 34, which will be described later, to the user detection system 1001 according to the third embodiment. Note that the position information providing system 4 and the control unit 34 are elements applicable to the user detection device 1 according to the first or second embodiment.

[0061] The position information providing system 4 is, for example, a position information providing system using artificial satellites such as GNSS (Global Navigation Satellite System), and outputs the current location information of the vehicle and the position information of a predetermined landmark to the control unit 34. Specifically, the position information providing system 4 includes a position measurement unit mounted on a vehicle (not shown) and a transmission unit that transmits the position information of the vehicle acquired by the position measurement unit to the control unit 34.

[0062] The control unit 34 acquires the current location information of the vehicle from the location information providing system 4. Then, based on the current location information of the vehicle and the location information of a predetermined landmark that the control unit 34 has stored in advance, the image processing unit 31 and the determination unit 32 are controlled.

[0063] Specifically, the control unit 34 estimates the distance between the vehicle and the predetermined landmark, and determines whether the estimated distance is less than or equal to a predetermined distance. When the estimated distance is less than or equal to the predetermined distance, the image processing unit 31 and the determination unit 32 are operated. When the estimated distance is greater than the predetermined distance, the image processing unit 31 and the determination unit 32 are not operated.

[0064] With such a configuration, the range for detecting the user can be appropriately limited, and false detection of the user can be suppressed.

[0065] (The Fifth Embodiment) <Configuration of the User Detection System> The fifth embodiment is a second application example of the user detection system according to the third embodiment. With reference to the drawings, the configuration of the user detection system according to the fifth embodiment will be described in detail. FIG. 8 is a block diagram showing the configuration of the user detection system according to the fifth embodiment.

[0066] The user detection system 1003 according to the fifth embodiment is obtained by applying the user detection system according to the fourth embodiment to a vehicle equipped with the automatic driving control system 5.

[0067] The automatic driving control system 5 receives the position of a predetermined landmark from the control unit 34, and based on the position information provided by the position information providing system 4, drives the vehicle to move toward the position of the predetermined landmark. Then, the automatic driving control system 5 acquires the position information of the user from the determination result output unit 22, and drives the vehicle to stop near the user.

[0068] Thus, the user detection system according to the present disclosure can also be applied to the detection of users of vehicles equipped with an automatic driving control system.

[0069] The present invention has been described above with reference to the embodiments. However, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

[0070] For example, some or all of the above embodiments can be described as follows in the appended claims, but are not limited thereto. (Appended Claim 1) An image processing unit that detects a predetermined mark indicating a user candidate and a boarding location based on an image captured near the vehicle; A determination unit that determines whether the user candidate is a user of the vehicle based on information on the user candidate and the predetermined mark detected by the image processing unit. User detection device. (Appended Claim 2) The image processing unit detects the state of the user candidate and the distance between the user candidate and the predetermined mark; The determination unit determines whether the user candidate is a user of the vehicle based on the state of the user candidate and the distance between the user candidate and the predetermined mark. The user detection device according to Appended Claim 1. (Appended Claim 3) The determination unit, when the distance between the user candidate and the predetermined mark is equal to or less than a predetermined value, and when the state of the user candidate is staying in the same place, determines that the user candidate is the user. The user detection device according to Appended Claim 2. (Appended Claim 4) The determination unit, when the distance between the user candidate and the predetermined mark is equal to or less than a predetermined value, and when the state of the user candidate is a predetermined number or more, determines that the user candidate is the user. The user detection device according to Appended Claim 2 or 3. (Appended Claim 5) The determination unit, The distance between the user candidate and the predetermined landmark is equal to or less than a predetermined value, and when the user candidate is aligned as the state of the user candidate, it is determined that the user candidate is the user. The user detection device according to any one of appendices 2 to 4. (Appendix 6) The determination unit, the distance between the user candidate and the predetermined landmark is equal to or less than a predetermined value, and when the user candidate is performing a predetermined operation as the state of the user candidate, it is determined that the user candidate is the user. The user detection device according to any one of appendices 2 to 5. (Appendix 7) The vehicle is a bus, and the image processing unit detects a bus stop as the predetermined landmark. The user detection device according to any one of appendices 1 to 6. (Appendix 8) further includes a determination result output unit, the vehicle is a vehicle driven under the control of a driver, when the determination unit determines that the user candidate is the user, the determination result output unit notifies the driver of the presence of the user. The user detection device according to any one of appendices 1 to 7. (Appendix 9) Notify the driver of the number of users. The user detection device according to appendix 8. (Appendix 10) further includes a determination result output unit, the vehicle is a vehicle driven under the control of an automatic driving control system, when the determination unit determines that the user candidate is the user, the determination result output unit outputs the position information of the user to the automatic driving control system. The user detection device according to any one of Supplementary Notes 1 to 7. (Supplementary Note 11) Based on the position information of the vehicle, estimate the distance between the vehicle and the predetermined landmark, When the estimated distance is less than or equal to a predetermined distance, operate the image processing unit and the determination unit, The user detection device according to any one of Supplementary Notes 1 to 10. (Supplementary Note 12) The image processing unit includes an AI (artificial intelligence) engine, The AI engine Learns an image of the predetermined landmark or an image of an object similar to the predetermined landmark, Assists in detecting the predetermined landmark, The user detection device according to any one of Supplementary Notes 1 to 11. (Supplementary Note 13) Comprises an in-vehicle device and a server device, The in-vehicle device Takes an image of the vicinity of the vehicle, The server device Based on the user candidate and the predetermined landmark indicating the boarding location detected by the image processing of the image, determines whether the user candidate is a user of the vehicle, User detection system. (Supplementary Note 14) The in-vehicle device includes a plurality of cameras respectively installed in the front, left and right side surfaces, and rear of the vehicle, The user detection system according to Supplementary Note 12. (Supplementary Note 15) Based on an image of the vicinity of the vehicle, recognize a predetermined landmark indicating a user candidate and a boarding location, Based on the information of the recognized user candidate and the predetermined landmark, determine whether the user candidate is a user of the vehicle, User detection method. (Supplementary Note 16) An operation of recognizing a predetermined landmark indicating a user candidate and a boarding location based on an image of the vicinity of the vehicle, A user detection program that causes a computer to execute an operation of determining whether the candidate user is a user of the vehicle based on the information of the recognized candidate user and the predetermined mark is recorded on a non-transitory computer-readable medium.

Explanation of Signs

[0071] 1 User detection device 2 In-vehicle device 3 Server device 4 Position information providing system 5 Autonomous driving control system 11, 31 Image processing unit 12, 32 Determination unit 13, 21 Photographing unit 14, 22 Determination result output unit 23 Communication device 33 Communication unit 34 Control unit 1001, 1002, 1003 User detection system

Claims

1. An image processing unit that detects a predetermined mark indicating a user candidate and a boarding location based on an image captured near the vehicle, A determination unit that counts the number of user candidates based on the information of the user candidates and the predetermined mark detected by the image processing unit, and determines that the user candidates are users of the vehicle when the number of user candidates is equal to or more than a predetermined number. User detection device.

2. The image processing unit detects the distance between the user candidate and the predetermined mark, The determination unit counts the number of user candidates whose distance between the user candidate and the predetermined mark is equal to or less than a predetermined value, and determines that all the user candidates are users of the vehicle when the number of user candidates whose distance between the user candidate and the predetermined mark is equal to or less than a predetermined value is at least a plurality of people. The user detection device according to claim 1.

3. An image processing unit that detects a user candidate, a predetermined mark indicating a boarding location, and the distance between the user candidate and the predetermined mark based on an image captured near the vehicle, A determination unit that determines that the user candidate is a user of the vehicle when it is determined that the distance is greater than a predetermined value based on the distance between the user candidate and the predetermined mark detected by the image processing unit. User detection device.

4. An image processing unit that detects a user candidate, a predetermined mark indicating a boarding location, the state of the user candidate, and the distance between the user candidate and the predetermined mark based on an image captured near the vehicle, A determination unit that determines whether the user candidate is a user of the vehicle based on the state of the user candidate and the distance between the user candidate and the predetermined mark. The determination unit is When one of the user candidates determined to have a distance between the user candidate and the predetermined mark equal to or less than a predetermined value is the first, and the other user candidates are arranged in a straight line, all of the other user candidates arranged in a straight line are determined to be users. User detection device.

5. The image processing unit detects the state of the user candidate, The determination unit is The distance between the user candidate and the predetermined mark is equal to or less than a predetermined value, And when the state of the user candidate is staying in the same place, more than a predetermined number When the above conditions are met, when the candidate users are aligned, or when at least two of the cases where a predetermined operation is being performed are satisfied, it is determined that the candidate user is the user. The user detection device according to any one of claims 1 to 4.

6. further comprising a determination result output unit, wherein the vehicle is a vehicle driven by a driver's control, when the determination unit determines that the candidate user is the user, the determination result output unit notifies the driver of the presence of the user. The user detection device according to any one of claims 1 to 5.

7. the image processing unit includes an AI (artificial intelligence) engine, the AI engine learns an image of the predetermined landmark or an image of an object similar to the predetermined landmark, and assists in detecting the predetermined landmark. The user detection device according to any one of claims 1 to 6.

8. comprising an in-vehicle device and a server device, the in-vehicle device captures an image of the vicinity of the vehicle, the server device counts the number of candidate users based on the candidate users and a predetermined landmark indicating the boarding location detected by image processing of the image, and when the number of candidate users is equal to or more than a predetermined number, determines that the candidate user is a user of the vehicle. User detection system.

9. A computer detects a predetermined landmark indicating a candidate user and a boarding location based on an image captured of the vicinity of the vehicle, counts the number of candidate users based on the detected candidate users and information on the predetermined landmark, and when the number of candidate users is equal to or more than a predetermined number, determines that the candidate user is a user of the vehicle. User detection method.

10. an operation of detecting a predetermined landmark indicating a candidate user and a boarding location based on an image of the vicinity of the vehicle, and a user detection program that causes a computer to count the number of candidate users based on the detected candidate users and information on the predetermined landmark, and when the number of candidate users is equal to or more than a predetermined number, determines that the candidate user is a user of the vehicle.

Images