Vehicle theft detection device

Abstract

To achieve both convenience and crime prevention in authentication of a user of a vehicle.SOLUTION: A vehicle theft determination device 1 includes a biological information acquisition part 10 for acquiring biological information of a user of a vehicle, a determination part 30 for determining that the user is the principal, when first biological information similarity between the acquired first biological information of the user and previously registered biological information is equal to or more than a first threshold, and a driving feature acquisition part 20 for acquiring the driving feature of the user driving the vehicle, wherein when the first biological information similarity is less than the first threshold, driving feature similarity between the driving feature acquired by the driving feature acquisition part and the previously registered driving feature is equal to or more than a predetermined value, the biological information acquisition part acquires second biological information of the user, and the determination part determines that the user is the principal, when second biological information similarity between the second biological information and the previously registered biological information is equal to or more than a second threshold smaller than the first threshold.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a vehicle theft detection device. [Background technology]

[0002] Patent Document 1 describes a vehicle personal authentication system configured to include a face image capturing camera, a face authentication control unit, and a car navigation control unit. The face authentication control unit has a threshold setting unit that sets the magnitude of the threshold used in face authentication, and the car navigation control unit has a time information acquisition unit, a vehicle position information acquisition unit, and a threshold setting condition determination unit. The threshold setting condition determination unit compares the time information and vehicle position information acquired by the time information acquisition unit and the vehicle position information acquisition unit with threshold setting conditions and determines whether the conditions for changing the threshold are met. Furthermore, the threshold setting unit changes the threshold from its default value based on the determination result of the threshold setting condition determination unit. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-306191 Summary of the Invention [Problem to be solved by the invention]

[0004] Although facial recognition can improve crime prevention, setting a high threshold value for facial recognition judgment reduces convenience. For this reason, Patent Document 1 describes lowering the threshold value for facial recognition judgment when the vehicle's location information indicates a predetermined location (such as the driver's home).

[0005] On the other hand, there is a possibility that sample information obtained during facial recognition may be passed onto a third party through photographs, images, etc. If a vehicle is stolen from the specified location, the threshold used for facial recognition judgment will be relatively low, which may reduce security.

[0006] In view of the above circumstances, an object of the present invention is to achieve both convenience and security in authenticating a vehicle user. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, the vehicle theft detection device of the present invention comprises a biometric information acquisition unit that acquires biometric information of a vehicle user, a determination unit that determines that the user is the user if the first biometric information similarity between the acquired first biometric information of the user and pre-registered biometric information is equal to or greater than a first threshold, and a driving characteristic acquisition unit that acquires driving characteristics of the user who drives the vehicle.When the first biometric information similarity is less than the first threshold, if the driving characteristic similarity between the driving characteristics acquired by the driving characteristic acquisition unit and the pre-registered driving characteristics is equal to or greater than a predetermined value, the biometric information acquisition unit acquires second biometric information of the user, and the determination unit determines that the user is the user if the second biometric information similarity between the second biometric information and the pre-registered biometric information is equal to or greater than a second threshold that is smaller than the first threshold. [Effects of the Invention]

[0008] According to the present invention, it is possible to achieve both convenience and security in authentication of a vehicle user. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of an in-vehicle system. [Figure 2] 4 is a flowchart showing a process performed by the vehicle theft determination device. [Figure 3] FIG. 2 is a block diagram showing an example of the configuration of computer hardware of the vehicle theft determination device. DETAILED DESCRIPTION OF THE INVENTION

[0010] The present invention will be described below based on the illustrated embodiments, but the present invention is not limited to the embodiments described below.

[0011] As shown in Fig. 1, the in-vehicle system S includes a vehicle theft detection device 1, and a front camera 2 and a driver monitor camera 3 connected to the vehicle theft detection device 1. The vehicle theft detection device 1 includes a biometric information acquisition unit 10, a driving characteristic acquisition unit 20, a determination unit 30, and a control unit 40. The processing performed by each unit will be described later.

[0012] FIG. 2 shows the flow of processing performed by the vehicle theft detection device 1. First, in step S11, the biometric information acquisition unit 10 acquires first facial image data of the vehicle user captured by the driver monitor camera 3. The determination unit 30 calculates the similarity between the first facial image data and facial image data of a pre-registered individual (a person who has the right to legitimately use the vehicle, such as the owner of the vehicle), and determines whether this similarity is equal to or greater than a first threshold. This first threshold is greater than the second and third thresholds described below. If the calculated similarity is equal to or greater than the first threshold, step S12 is performed; otherwise, step S21 is performed.

[0013] In step S12, the determination unit 30 determines that the user is the person in question, followed by step S13.

[0014] In step S13, the driving characteristics acquisition unit 20 acquires the driving characteristics (driving habits) of the user who has been determined to be the user himself / herself.

[0015] Acquiring driving characteristics includes the following processes. 1. Identifying high-frequency routes Of the routes traveled by the vehicle driven by the user who has been determined to be the user, the system stores, for example, the top 30% of routes in descending order of frequency of travel. The number "top 30%" is an example and can be changed depending on the specifications of the navigation system installed in the vehicle. 2. Loading road features of high frequency routes Examples of road features that may be read are: Speed ​​limit Traffic congestion situation Road gradient · Presence of crosswalks, traffic lights, and intersections - Whether there is a stop sign or a tunnel -Time of day, country in which the road is located, number of lanes, type of road, geographic location 3. Reading information from the front camera Examples of information obtained from the front camera 2 are as follows: Distance to the vehicle ahead - Road signal status - Operation frequency of each system ·Setting characteristics of each system Other information recognized by the front camera 2 4. Acquiring driving characteristics Machine learning is performed using road features of high-frequency routes, forward camera information, and vehicle information (vehicle speed, yaw rate, vehicle acceleration, braking, accelerator opening change rate, etc.). Examples of driving features acquired by the trained model are as follows. However, these are merely examples, and when using DNN (deep neural network) technology, etc., feature calculations are also performed by the machine, so driving features are not limited to these examples. - Accelerator opening change rate and vehicle speed before and after crosswalks Yaw rate or yaw rate change rate when turning right or left at an intersection - Rate of change in throttle opening before and after a slope -Average speed in a specific section - Vehicle acceleration before and after the intersection -Distribution of distance to stop signs, vehicle acceleration, vehicle speed and stopping position - Vehicle speed setting after the ACC (Adaptive Cruise Control) main switch is turned on, speed until the accelerator is released, etc.

[0016] In addition, when driving on a route that is not frequently driven, there is a possibility that many disturbances may be included in the original driving characteristics, so it is possible to prevent the driving characteristics from being acquired. Furthermore, the acquired driving characteristics are registered in the in-vehicle system, but it is possible to prevent the registered driving characteristics from being disclosed to the driver himself.

[0017] When step S13 is completed, the process ends.

[0018] As described above, if the similarity calculated in step S11 is less than the first threshold, step S21 is subsequently performed. In step S21, the determination unit 30 determines that the user is a guest user. A guest user is a user whose available vehicle functions are more limited than those of the user himself / herself. Then, step S22 is performed.

[0019] Step S22 is a step that assumes that step S13 has been executed at least once in advance. In step S22, the driving information acquisition unit 20 acquires driving characteristics of the user determined to be a guest user. Then, the determination unit 30 calculates a similarity between the driving characteristics of the user determined to be a guest user acquired by the driving information acquisition unit 20 and the driving characteristics of the user determined to be the actual user acquired in step S13. If the calculated similarity is equal to or greater than a predetermined value, it is determined that the user is likely the actual user, and step S23 is subsequently performed; otherwise, step S31 is subsequently performed.

[0020] In step S23, the biometric information acquisition unit 10 acquires second facial image data of the user captured by the driver monitor camera 3 at a timing after step S11. The determination unit 30 calculates the similarity between the second facial image data and pre-registered facial image data of the user, and determines whether this similarity is equal to or greater than a second threshold. This second threshold is a threshold smaller than the first threshold used in step S11. If the calculated similarity is equal to or greater than the second threshold, step S12 is performed; otherwise, step S32 is performed.

[0021] In this way, if the driving characteristics of a user who is determined to be not the user in steps S11 and S21 are determined to be similar to the user's driving characteristics to a certain extent in step S22, and the user passes face authentication in step S23, which is more lenient than in step S11, the user is determined to be the user in step S12.

[0022] The facial recognition in step S23 can be performed using only a partial area of ​​the face, such as image information around the user's eyes, rather than the entire face. For example, the facial recognition in step S23 has a lower threshold and is more lenient than the facial recognition in step S11, so that the user can pass even if they are wearing a mask.

[0023] After step S22 (determination based on driving characteristics), face authentication is performed in step S23 separately from step S11 to prepare for the possibility that the driving characteristics of the thief may be determined to be similar to that of the thief by chance.

[0024] As described above, if the similarity calculated in step S22 is less than the predetermined value, step S31 is subsequently performed. In step S31, the biometric information acquisition unit 10 acquires third facial image data of the user captured by the driver monitor camera 3 at a timing after step S11. The determination unit 30 calculates the similarity between the third facial image data and pre-registered facial image data of the user, and determines whether this similarity is equal to or greater than a third threshold. The third threshold is a threshold that is smaller than the first threshold in step S11 and larger than the second threshold in step S23. If the calculated similarity is equal to or greater than the third threshold, step S32 is subsequently performed; otherwise, step S41 is subsequently performed.

[0025] In this way, even if it is determined that the driving characteristics acquired in step S22 are different from those of the person in question, face authentication separate from step S11 is performed in step S31. This is because it is technically quite difficult to distinguish between a case where the person is driving unusually due to internal factors (impatience) or the like and a case where the person is driving a car that is being stolen.

[0026] In step S32, the determination unit 30 again determines that the user is a guest user, followed by step S33.

[0027] In step S33, the control unit 40 requests the user to update the registration information by displaying a message on the in-vehicle monitor, etc. Then, the process ends.

[0028] As described above, if the similarity calculated in step S31 is less than the third threshold, step S41 is subsequently performed. In step S41, the control unit 40 requests the user to update the registration information by displaying a message on the in-vehicle monitor, etc. Then, step S42 is performed.

[0029] In step S42, the determination unit 30 indicates to the user that the vehicle may have been stolen. This indication can be made by displaying a message on the in-vehicle monitor, etc. Then, step S43 is performed.

[0030] In step S43, the determination unit 30 determines whether a certain time has elapsed since the suggestion in step S42. If it is determined that the certain time has elapsed, step S44 is subsequently performed; otherwise, step S22 is performed again. Note that if step S42 is performed multiple times in the same ignition cycle, it is determined in step S43 whether a certain time has elapsed since the first execution of step S42.

[0031] In step S44, the determination unit 30 determines that the vehicle is in a stolen state, followed by step S45.

[0032] In step S45, the control unit 40 sends commands to the electric steering, braking mechanism, etc. of the vehicle to forcibly stop the vehicle. Then, step S46 is carried out.

[0033] In step S46, control unit 40 notifies the owner of the vehicle that the vehicle has been stolen and that the vehicle has been forcibly stopped. This notification can be sent by email to the owner's email address, and the process then ends.

[0034] In this way, if the user is not determined to be the same person in both step S22 (determination based on driving characteristics) and step S31 (face authentication using the third threshold), step S41 (request to update registration information) is performed. This step S41 can prompt the user to take action such as removing the mask they were wearing or calming down. After a certain time has passed since step S42 (indication of theft), step S44 (determining the theft) is performed, and step S45 (forcibly stopping the vehicle) is performed.

[0035] In the process of Figure 2, the user is ultimately determined to be the person in question in the following cases. If you are identified as the person in step S11 (face recognition) If the person was not identified in step S11 (face recognition), but was identified in step S22 (determination based on driving characteristics) and step S23 (face recognition),

[0036] In the process of FIG. 2, the user is ultimately determined to be a guest user in the following cases. If the person is not authenticated in step S11 (face authentication), is authenticated in step S22 (determination based on driving characteristics), and is not authenticated in step S23 (face authentication) If the person is not authenticated as the person in both step S11 (face authentication) and step S22 (determination based on driving characteristics), but is authenticated as the person in step S31 (face authentication)

[0037] In the process of FIG. 2, the following cases are considered to be cases where a vehicle is possibly stolen. If the person is determined to be not the person in any of the three steps: step S11 (face recognition), step S22 (determination based on driving characteristics), and step S31 (face recognition).

[0038] If it is determined that there is a possibility of theft, the user is prompted to update the registration information in step S41 (registration information update request). This registration information update requires identity verification using a password, rather than facial authentication.

[0039] In addition, registration information must be updated based on the location information on the map under the following conditions.

[0040] If the road being traveled is a highway or a toll road, the registration information must be updated before the vehicle reaches within 32 km of the vehicle's position at the time the request in step S41 is made, or before the vehicle reaches the next PA (parking area) or SA (service area). If an update is not performed under these conditions, the vehicle will enter forced automatic driving mode until it reaches the nearest IC (interchange), PA, or SA, and after entering one of the ramps, it will stop or park at a location where it is possible to stop or park. At this time, the information display device inside the vehicle will also display a message indicating that the vehicle has entered forced automatic driving mode. Alternatively, the vehicle's current location and the fact that it has switched to forced autonomous driving mode may be notified to a device such as a smartphone that the user has registered in advance.

[0041] If the road being traveled is a motorway that is neither an expressway nor a toll road, the registration information must be updated by the time the vehicle reaches the next interchange from its current position at the time the request in step S41 is made. If an update is not performed under these conditions, the system will switch to forced automatic driving mode and proceed onto the nearest IC ramp. Automatic driving control will continue while on the ramp, and then the system will switch to the theft confirmation process for ordinary roads (described below) in order to receive information about ordinary roads from the map information. At this time, the information display device inside the vehicle will also display a message indicating that the vehicle has entered forced automatic driving mode. Alternatively, the vehicle's current location and the fact that it has switched to forced autonomous driving mode may be notified to a device such as a smartphone that the user has registered in advance.

[0042] If the road being traveled is not a highway for exclusive use by the vehicle but an ordinary road, after receiving the road type information for the ordinary road, the registration information needs to be updated by the time the vehicle reaches the nearest convenience store or a store such as a gas station that is open during business hours. It may be specified that the registration information needs to be updated by the time the vehicle travels the total distance of the distance to the store and a predetermined distance (a predetermined distance that can be set in advance by the user). If the vehicle is parked off-road and the shift position is changed to park while the vehicle is on its way to the store or while the vehicle is traveling the total distance, the shift lever can be locked until the registration information is updated. The user's registered device may also be notified that the shift lever has been locked. If the update is not performed under these conditions, the vehicle will automatically control the vehicle to the nearest convenience store or gas station that is open and will implement parking control at a location where parking is possible. However, if the distance to the above facilities is more than 15 km, the vehicle will make an emergency stop as soon as a parking space on the road is detected by the front camera installed in the vehicle. At this time, the information display device inside the vehicle will also notify the driver that the vehicle has switched to automatic driving mode. Alternatively, the vehicle's current location and the transition to autonomous driving mode can be notified to a device such as a smartphone that the user has registered in advance.

[0043] The distance until theft is confirmed may be set to multiple values, such as "long distance," "medium distance," and "short distance," so that the user can select one in advance.

[0044] The following provides additional information regarding control in the event of theft. [How to determine mileage] PAs on expressways are generally located at 15km intervals, so the total distance between two of these intervals (30km) plus a safety margin (2km) makes up the total driving distance, or 32km. In addition, the reason why the vehicle is not permitted to travel to the nearest PA, SA, or IC is that, for example, if the point where the registration information update status is reached is 100 meters before the entrance (ramp) of a PA and the vehicle is traveling in the right lane, it may be difficult or dangerous to enter the PA. Therefore, the vehicle is permitted to travel to the next PA or SA. The driving range may be the sum of the distance to the nearest convenience store or gas station and a safety margin (2 km).

[0045] [Reason for dividing by road type] The reason for dividing the roads by type is to make it possible to determine whether it is okay to stop the vehicle on the shoulder of the road when theft is confirmed and the system is forced to switch to stopping control. In an emergency, it is considered acceptable to stop the vehicle even on a highway. However, for example, if theft is confirmed due to an erroneous judgment and the system switches to stopping control, it is unlikely that this is an emergency situation. For this reason, the road type is acquired and the range within which the user can stop the vehicle comfortably and safely is determined according to the road type.

[0046] The process shown in FIG. 2 can be performed periodically (for example, every 5 minutes).

[0047] According to the above embodiment, the following effects can be obtained. By periodically performing the process shown in Figure 2, reliability can be increased. In contrast, if facial recognition is performed only when the ignition is turned on, there is a possibility that it could be circumvented by using a photograph of the face. Furthermore, by periodically performing the process shown in Figure 2, even if authentication fails the first time, the user's identity can be confirmed while driving. However, if this is strictly enforced, the user will always have to drive with the same facial expression as when they registered, and if they are not in the same state as when they registered, they will not be able to enjoy the benefits of identity authentication. Even if your facial condition is different from when you registered it, as long as you drive normally, your driving characteristics will be recognized and you will be able to continue using the vehicle. There is also no need to re-register your facial information. If facial recognition is used solely with a relatively low threshold, the probability of falsely identifying a person who is not the person in question (false acceptance rate) increases, making it unreliable for theft prevention. According to the above embodiment, the decrease in reliability caused by facial recognition using a low threshold is addressed by also using a map or a front camera to determine driving characteristics. - On unfamiliar roads, it is often difficult to drive as usual, so by excluding this from the calculation of the driver's driving characteristics, more accurate feature extraction is possible. Driving characteristics are more abstract than facial characteristics, making them more effective as keys that are difficult for others to steal.

[0048] As described above, according to the above embodiment, it is possible to achieve both convenience and security in authenticating the vehicle user.

[0049] [Other forms] For example, a flow that references past data within the same ignition cycle may be added. If the rate of being identified as the person within the same ignition cycle is high and step S23 (face authentication) is passed, the annoyance of incorrect determination can be reduced by adding a process to lower the determination threshold when driving a new route or for a long period of time. The calculation of driving characteristics is not limited to routes with high usage rates, and may be calculated for routes declared by the driver himself / herself. Even if step S11 (face recognition) is passed, if the degree of similarity with the user's driving characteristics is relatively low, a system can be implemented that suggests the user take a break. The acquired driving characteristics can also be compared with driving characteristics considered to be safe driving to calculate a driving score. It is also possible to finely divide the strictness of facial recognition judgments and perform authentication in stages.

[0050] It is not limited to facial recognition, and other biometric authentication methods such as fingerprint recognition, iris recognition, and voiceprint recognition may also be used.Facial recognition does not require additional components if the vehicle is equipped with a driver monitoring camera (fingerprint recognition requires dedicated components), it is easy to obtain information (iris recognition also obtains information from a camera, but there are strict restrictions on installation location), and it is highly accurate (generally considered to be more accurate than voiceprint recognition).For these reasons, facial recognition has advantages over other biometric authentication methods.

[0051] If a user is determined to be a guest user, the basic functions of a car, such as driving, turning, and stopping, are available. If a user is determined to be the principal, services other than vehicle driving (for example, various payment services, changing various vehicle settings (including registering personal information in the above embodiment), automatic driving functions, transitioning to a chargeable state, internet access, ETC card locking, and use of accessories such as car navigation and smartphone charging) are also available.

[0052] In anticipation of use by the vehicle owner's family, those who have been registered in advance by the owner can be authorized to use the service. In addition, when the vehicle is temporarily rented out (to a hotel staff member, etc.), a mode can be set in which theft detection is not performed after a certain distance (approximately 2 km). When the vehicle is rented out for a long period of time (to a dealer, etc.), a deactivation key can be set via USB, which can disable theft detection and allow the vehicle to be used as a guest user.

[0053] When a user is determined to be the user, multiple locations may be set, and the similarity of driving characteristics may be determined to be greater than or equal to a predetermined value by passing through each of the set locations in a predetermined order.

[0054] The predetermined distance to the forced stop may not only be determined automatically based on road information, but may also be set by the user. The predetermined location for the forced stop is not on the road, but on a highway, it could be an IC, PA, or SA, or on a general road, it could be a convenience store, gas station, etc. These locations are determined by cameras and map information. When the vehicle stops at a predetermined location, the vehicle's location information may be transmitted to the user's terminal.

[0055] 3 shows an example of the computer hardware configuration of the vehicle theft detection device 1. This device includes a CPU 351, an interface device 352, a display device 353, an input device 354, a drive device 355, an auxiliary storage device 356, and a memory device 357, which are interconnected by a bus 358.

[0056] A program that realizes the functions of this device is provided by a recording medium 359 such as a CD-ROM. When recording medium 359 on which the program is recorded is set in drive device 355, the program is installed from recording medium 359 to auxiliary storage device 356 via drive device 355. Alternatively, the program does not necessarily have to be installed from recording medium 359, but can also be installed via a network. Auxiliary storage device 356 stores the installed program as well as necessary files, data, etc.

[0057] The memory device 357 reads and stores the program from the auxiliary storage device 356 when an instruction to start the program is received. The CPU 351 realizes the functions of the vehicle theft determination device in accordance with the program stored in the memory device 357. The interface device 352 is used as an interface for connecting to other computers via a network. The display device 353 displays a GUI (Graphical User Interface) or the like according to the program. The input device 354 is a keyboard, a mouse, a touch panel, or the like.

[0058] The following notes are provided regarding the embodiments described above. [Appendix 1] a biometric information acquisition unit that acquires biometric information of a vehicle user; a determination unit that determines that the user is the user when a first biometric information similarity between the acquired first biometric information of the user and pre-registered biometric information is equal to or greater than a first threshold; a driving characteristic acquisition unit that acquires driving characteristics of the user who drives the vehicle; Equipped with When the first biometric information similarity is less than the first threshold, if the driving feature similarity between the driving feature acquired by the driving feature acquisition unit and the pre-registered driving feature is equal to or greater than a predetermined value, the biometric information acquisition unit acquires second biometric information of the user; the determination unit determines that the user is the user himself / herself when a second biometric information similarity between the second biometric information and the pre-registered biometric information is equal to or greater than a second threshold that is smaller than the first threshold. Vehicle theft detection device. [Effect 1] Driving information is more abstract than biometric information and is less likely to be easily obtained. Therefore, even if authentication using biometric information based on the first threshold fails, if the degree of match with the driving information is above a predetermined value, re-authentication of the person can be performed using the second threshold, thereby increasing the chances of being authenticated as the person in question and improving convenience, and by performing authentication in two stages using biometric information and driving information, a decrease in security can be prevented. [Appendix 2] The vehicle theft detection device described in Appendix 1, wherein the determination unit determines that the user is a guest user whose available vehicle functions are more limited than those of the user himself / herself when the second biometric information similarity is less than the second threshold. [Effect 2] If the degree of coincidence of the driving information is equal to or greater than a predetermined value, convenience can be maintained by authenticating the user as a guest user even if subsequent re-authentication of the user fails. [Appendix 3] When the driving feature similarity is less than the predetermined value, the biometric information acquisition unit acquires third biometric information of the user; the determination unit determines that the user is a guest user whose available functions of the vehicle are more limited than those of the user himself / herself when a third biometric information similarity between the third biometric information and the pre-registered biometric information is equal to or greater than a third threshold that is smaller than the first threshold and larger than the second threshold. 3. A vehicle theft detection device according to claim 1 or 2. [Effect 3] Even if the degree of coincidence of the driving information is less than a predetermined value, if the subsequent re-authentication of the user is successful, convenience can be maintained by authenticating the user as a guest user. [Appendix 4] 4. The vehicle theft determination device according to claim 3, wherein the determination unit determines that the vehicle may have been stolen if the third biometric information similarity is less than the third threshold value. [Effect 4] By determining the possibility of theft when authentication of both biometric information and driving information fails, the possibility of theft can be determined with high accuracy, thereby improving crime prevention. [Appendix 5] 3. The vehicle theft determination device according to claim 1, wherein the second threshold value is set to a smaller value as the driving characteristic similarity increases. [Effect 5] With the above configuration, if the degree of match of the driving information is high, re-authentication of the person becomes easier, thereby improving convenience. [Appendix 6] The pre-registered driving characteristics relate to a specific route traveled by the vehicle driven by the person determined to be the principal, The driving characteristic similarity is a similarity between a route traveled by the vehicle driven by the user and the specific route. 3. A vehicle theft detection device according to claim 1 or 2. [Effect 6] By using route information as driving information, authentication can be performed in a way that makes it difficult for a third party to steal a sample, thereby improving crime prevention. Furthermore, users can be authenticated simply by driving, eliminating the need for special authentication procedures, enhancing convenience.

[0059] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and various modifications and changes can be made based on the technical concept of the present invention. [Explanation of symbols]

[0060] S In-vehicle system 1. Vehicle theft detection device 2. Front camera 3 Driver monitor camera 10 Biometric information acquisition unit 20 Driving characteristics acquisition unit 30 Judgment section 40 Control Unit

Claims

1. a biometric information acquisition unit that acquires biometric information of a vehicle user; a determination unit that determines that the user is the user when a first biometric information similarity between the acquired first biometric information of the user and pre-registered biometric information is equal to or greater than a first threshold; a driving characteristic acquisition unit that acquires driving characteristics of the user who drives the vehicle; Equipped with When the first biometric information similarity is less than the first threshold, if the driving feature similarity between the driving feature acquired by the driving feature acquisition unit and a pre-registered driving feature is equal to or greater than a predetermined value, the biometric information acquisition unit acquires second biometric information of the user, the determination unit determines that the user is the user himself / herself when a second biometric information similarity between the second biometric information and the pre-registered biometric information is equal to or greater than a second threshold that is smaller than the first threshold. Vehicle theft detection device.

2. 2. The vehicle theft detection device according to claim 1, wherein the determination unit determines that the user is a guest user whose available vehicle functions are more limited than those of the user himself / herself when the second biometric information similarity is less than the second threshold.

3. When the driving feature similarity is less than the predetermined value, the biometric information acquisition unit acquires third biometric information of the user; the determination unit determines that the user is a guest user whose available functions of the vehicle are more limited than those of the user himself / herself when a third biometric information similarity between the third biometric information and the pre-registered biometric information is equal to or greater than a third threshold that is smaller than the first threshold and larger than the second threshold.

3. The vehicle theft detection device according to claim 1 or 2.

4. The vehicle theft determination device according to claim 3 , wherein the determination unit determines that there is a possibility that the vehicle has been stolen when the third biometric information similarity is less than the third threshold value.

5. The vehicle theft detection device according to claim 1 or 2, wherein the second threshold value is set to a smaller value as the driving characteristics similarity increases.

6. the pre-registered driving characteristics relate to a specific route traveled by the vehicle driven by the person determined to be the principal; The driving characteristic similarity is a similarity between a route traveled by the vehicle driven by the user and the specific route.

3. The vehicle theft detection device according to claim 1 or 2.

Images