Driver monitoring system, driver monitoring method, and program

Abstract

A driver monitoring system according to the present disclosure comprises: a biological information acquisition unit that acquires biological information of a driver who drives a vehicle; an identification information acquisition unit that acquires identification information of the driver by performing biometric authentication of the driver on the basis of the biological information; a vital information acquisition unit that acquires vital information of the driver who drives the vehicle; a determination criterion setting unit that, on the basis of the identification information of the driver, sets a determination criterion for the vital information to be used for determining an abnormal state of the driver; and an abnormal state determination unit that, on the basis of the determination criterion corresponding to the driver and the acquired vital information of the driver, determines an abnormal state of the driver who drives the vehicle.

Description

Driver monitoring system, driver monitoring method and program

[0001] The present disclosure relates to a driver monitoring system, a driver monitoring method, and a program.

[0002] Patent Document 1 discloses a technique for determining the consciousness state of a vehicle driver. The consciousness state detection apparatus according to Patent Document 1 detects biological information and the like of a vehicle driver and determines the driver's consciousness state.

[0003] Japanese Unexamined Patent Application Publication No. 2019-084271

[0004] In Patent Document 1, by acquiring biological information and the like of a target driver, a determination criterion for the driver is created, and the driver's consciousness state is determined using the determination criterion. Therefore, in Patent Document 1, if the driver to be determined is different from the driver for whom the determination criterion was created, there is a risk that the consciousness state cannot be correctly determined.

[0005] The present disclosure has been made to solve such problems, and an object of the present disclosure is to provide a driver monitoring system, a driver monitoring method, and a program that can more correctly determine an abnormal state according to a driver to be monitored.

[0006] The driver monitoring system according to the present disclosure comprises: a biological information acquisition unit that acquires biological information of a driver driving a vehicle; an identification information acquisition unit that acquires identification information of the driver by performing biometric authentication of the driver based on the biological information; a vital information acquisition unit that acquires vital information of the driver driving the vehicle; a determination criterion determination unit that determines a determination criterion for the vital information used for determining an abnormal state of the driver based on the identification information of the driver; and an abnormal state determination unit that determines the abnormal state of the driver driving the vehicle based on the determination criterion corresponding to the driver and the vital information acquired for the driver.

[0007] The driver monitoring method relating to this disclosure includes a computer that performs a biometric information acquisition process to acquire biometric information of a driver operating a vehicle; an identification information acquisition process to acquire identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition process to acquire vital information of the driver operating the vehicle; a judgment criterion determination process to determine judgment criteria for the vital information used to determine the abnormal state of the driver based on the driver's identification information; and an abnormal state determination process to determine the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver.

[0008] The program relating to this disclosure causes a computer to execute the following steps: a biometric information acquisition step for acquiring biometric information of a driver operating a vehicle; an identification information acquisition step for acquiring identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition step for acquiring vital information of the driver operating the vehicle; a judgment criterion determination step for determining judgment criteria for the vital information used to determine the abnormal state of the driver based on the driver's identification information; and an abnormal state determination step for determining the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver.

[0009] This disclosure provides a driver monitoring system, driver monitoring method, and program that can identify drivers to be monitored and more accurately determine abnormal conditions corresponding to the identified drivers.

[0010] Figure 1 is a block diagram showing the configuration of the driver monitoring system according to this disclosure. Figure 2 is a flowchart showing an example of the flow of the driver monitoring method by the driver monitoring system. Figure 3 is a block diagram showing the configuration of the driver monitoring system according to this disclosure. Figure 4 is a flowchart showing an example of the flow up to determining the judgment criteria corresponding to the driver operating the vehicle. Figure 5 is a flowchart showing an example of the flow of operations when dangerous driving occurs. Figure 6 is a flowchart showing an example of the flow of operations when changing the judgment criteria based on the location information of the vehicle being driven. Figure 7 is a flowchart showing an example of the flow of operations when determining an abnormal state of the driver. Figure 8 is a diagram showing an example of the hardware configuration of the driver monitoring system.

[0011] (Embodiment 1) Hereinafter, an example of the configuration of the driver monitoring system 1 will be described with reference to Figure 1. Figure 1 is a block diagram showing the configuration of the driver monitoring system 1 according to the present disclosure. The driver monitoring system 1 is typically one or more computer devices that operate by a processor executing a program stored in memory. In other words, the driver monitoring system 1 may be composed of one computer device or two or more computer devices.

[0012] Driver monitoring system 1 is a system that monitors the driver operating a vehicle. Here, "vehicle" typically refers to automobiles such as four-wheeled vehicles and two-wheeled vehicles, but may also refer to light vehicles such as bicycles, railway vehicles, and streetcars. Furthermore, "driver" typically refers to a person who manually operates the vehicle. That is, "driver" refers to a person who can move the vehicle by operating the steering wheel, accelerator, brakes, etc., provided on the vehicle. Here, the state of operation by the driver includes the state in which the vehicle is temporarily stopped during the process of movement.

[0013] Furthermore, the term "driver" does not necessarily refer to the person actually moving the vehicle by operating the steering wheel or other controls. In other words, if the vehicle being driven is capable of autonomous driving, the term "driver" may refer to the person who will be driving the vehicle when the autonomous driving mode is switched to manual driving. Also, while the term "driver" typically refers to the person riding in the vehicle being driven, the "driver" does not necessarily have to be riding in the vehicle being driven. In other words, the term "driver" may refer to the person who can move the vehicle being driven by remotely controlling it.

[0014] The driver monitoring system 1 may or may not be installed in the vehicle driven by the driver being monitored. If the driver monitoring system 1 is installed in the vehicle driven by the driver, the driver monitoring system 1 may consist of one or more on-board computer devices. If the driver monitoring system 1 is not installed in the target vehicle, the vehicle and the driver monitoring system 1 are connected in a data communication manner. Data communication may be performed via an internet line or using short-range wireless communication technology. The type of communication protocol used for data communication is not limited.

[0015] The driver monitoring system 1 comprises a biometric information acquisition unit 11, an identification information acquisition unit 12, a vital information acquisition unit 13, a judgment criterion determination unit 14, and an abnormal state determination unit 15. The biometric information acquisition unit 11, the identification information acquisition unit 12, the vital information acquisition unit 13, the judgment criterion determination unit 14, and the abnormal state determination unit 15 are typically software or modules whose processing is performed by a processor executing a program stored in memory. These components of the driver monitoring system 1 may also be hardware such as circuits or chips. That is, the components of the driver monitoring system 1 may be composed of the same computer device, or each may be composed of different computer devices.

[0016] The components of the driver monitoring system 1 are connected to each other so that data can be communicated as needed. Data communication between components may be performed by wired connection or by wireless connection. Data communication may be performed within the same computer device, via an internet connection, or via short-range wireless communication technology. The type of communication protocol used for data communication is not limited.

[0017] The biometric information acquisition unit 11 is configured to acquire the driver's biometric information. The driver's biometric information refers to information present within the driver that allows the driver to be identified from other people. The driver's biometric information may be any of the following: facial information, palm print information, iris information, voiceprint information, or vein information, or a combination thereof. However, the driver's biometric information is not limited to the above. The biometric information acquisition unit 11 acquires necessary biometric information from various sensors (not shown). The biometric information acquisition unit 11 may receive biometric information directly from various sensors, or it may receive biometric information via other terminals or communication devices (not shown).

[0018] The identification information acquisition unit 12 performs biometric authentication of the driver based on the driver's biometric information acquired by the biometric information acquisition unit 11. That is, the identification information acquisition unit 12 receives the driver's biometric information from the biometric information acquisition unit 11. The identification information acquisition unit 12 then verifies the driver's biometric information by referring to a driver database (DB) (not shown) that stores, for example, the biometric information of one or more users. As a result, the identification information acquisition unit 12 can authenticate the driver whose biometric information was acquired by the biometric information acquisition unit 11. The identification information acquisition unit 12 can then acquire the identification information of the driver.

[0019] The vital information acquisition unit 13 acquires vital information of the driver operating the vehicle. Vital information refers to information indicating the driver's life activities and health status. Vital information includes, for example, the driver's heart rate, respiratory rate, blood pressure, body temperature, and blood oxygen saturation. It also includes information on the driver's body movements, the degree of eyelid opening, and the degree of eye movement. Body movement information includes the movement of the body and the movement of the head and face. The vital information acquisition unit 13 acquires necessary vital information from various sensors (not shown). The vital information acquisition unit 13 may receive vital information directly from the various sensors, or it may receive vital information via other terminals or communication devices (not shown).

[0020] The judgment criteria determination unit 14 determines the judgment criteria for vital information used to determine the abnormal state of the driver, based on the driver identification information acquired by the identification information acquisition unit 12. In other words, the judgment criteria determination unit 14 is configured to determine judgment criteria according to the driver operating the vehicle. That is, the judgment criteria determination unit 14 can uniquely determine the judgment criteria used for a driver based on the driver's identification information. For example, the judgment criteria determination unit 14 can determine the judgment criteria by referring to a driver database that stores the driver's identification information and the judgment criteria used for that driver in association.

[0021] The abnormal state determination unit 15 determines the abnormal state of the driver operating the vehicle based on the determination criteria corresponding to the driver determined by the determination criteria determination unit 14 and the vital information acquisition unit 13 acquired for the driver. An "abnormal state of the driver" refers to a state in which it is presumed that the driver may not be able to perform normal perception, judgment, or operation. Examples of "abnormal states" include drowsiness, distraction, loss of consciousness, and sudden illness. Based on the determination criteria corresponding to the driver, the abnormal state determination unit 15 can output a determination result of whether the driver is abnormal or not from the acquired vital information of the driver.

[0022] Next, the flow of the driver monitoring method by the driver monitoring system 1 will be explained. Figure 2 is a flowchart showing an example of the flow of the driver monitoring method by the driver monitoring system 1. First, the biometric information acquisition unit 11 acquires the biometric information of the driver operating the vehicle (S101). Next, the identification information acquisition unit 12 acquires the identification information of the driver by performing biometric authentication of the driver based on the biometric information acquired by the biometric information acquisition unit 11 (S102). After that, the vital information acquisition unit 13 acquires the vital information of the driver operating the vehicle (S103). Steps S102 and S103 may be performed simultaneously. After that, the judgment criterion determination unit 14 determines the judgment criteria for the vital information used to determine the abnormal state of the driver based on the driver's identification information acquired by the identification information acquisition unit 12 (S104). After that, the abnormal state determination unit 15 determines the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver determined by the judgment criterion determination unit 14 and the vital information of the driver acquired by the vital information acquisition unit 13 (S105).

[0023] Thus, in this embodiment, the driver monitoring system 1 can identify the driver to be monitored. Specifically, the driver monitoring system 1 obtains the driver's identification information by performing biometric authentication using the driver's biometric information. The driver monitoring system 1 can then more accurately determine abnormal conditions corresponding to the identified driver. In other words, the driver monitoring system 1 can correctly determine the driver's abnormal condition even when different drivers are operating the vehicle.

[0024] (Embodiment 2) This second embodiment is a specific example of the first embodiment described above. Figure 3 is a block diagram showing the configuration of the driver monitoring system 2 according to this disclosure. The driver monitoring system 2 includes a driver DB 21, a dangerous driving location DB 22, a biometric information acquisition unit 23, an identification information acquisition unit 24, a vital information acquisition unit 25, a location information acquisition unit 26, a surrounding information acquisition unit 27, a dangerous driving judgment unit 28, a judgment criterion determination unit 29, an abnormal state judgment unit 30, a warning output unit 31, and a driving control unit 32. The driver monitoring system 2 is a system that monitors the driver of an automobile. That is, in this second embodiment, "vehicle" refers to an automobile. The driver monitoring system 2 may also be applied to light vehicles, railway vehicles, trams, and other vehicles. Furthermore, it is assumed that the driver is riding in the vehicle being driven. The driver monitoring system 2 is also called a "driver monitoring system".

[0025] The components of the driver monitoring system 2 are connected to each other so that data can be communicated as needed. Data communication between components may be performed by wired connection or by wireless connection. Data communication may be performed within the same computer device, via an internet line, or using short-range wireless communication technology. The type of communication protocol used for data communication is not limited. Hereafter, for the sake of clarity, explanations that overlap with Embodiment 1 will be omitted as appropriate.

[0026] The driver database 21 is composed of a storage device such as a hard disk or flash memory. The driver database 21 stores information about the driver operating the vehicle in an associated manner. Specifically, the driver database 21 stores identification information 211, registered biometric information 212, vital history 213, and judgment criteria 214 in an associated manner. Identification information 211 is the driver's identification information. Identification information 211 is a driver-specific ID (Identification) given to drivers registered in the driver database 21. Identification information 211 may include the driver's name. Registered biometric information 212 is the driver's biometric information used when biometric authentication is performed on the driver. Registered biometric information 212 may be any of the driver's facial information, palm print information, iris information, voiceprint information, vein information, a combination thereof, or other biometric information. Registered biometric information 212 is data acquired using a visible light camera, infrared sensor, microphone, etc. (none of which are shown). When a driver registers information in the driver database 21, they also register their biometric information. The registered biometric information 212 may be the biometric information itself, features extracted from the biometric information, or both.

[0027] The vital signs history 213 contains the driver's past vital signs information. Furthermore, the vital signs history 213 associates the driver's past vital signs with the date and time the information was acquired. Additionally, each vital sign in the vital signs history 213 is flagged to indicate whether it represents vital signs during normal driving or during dangerous driving. For example, vital signs during normal driving are flagged with "0," while vital signs during dangerous driving are flagged with "1." In other words, for each vital sign in the vital signs history 213, vital signs recorded during normal driving are flagged with "0," and vital signs recorded during dangerous driving are flagged with "1." The vital signs history 213 may contain all of the driver's past vital signs, or it may be limited by period, number of data points, etc. For example, the vital signs history 213 may contain vital signs for the past five years, or it may contain vital signs for the past 1000 records.

[0028] Here, dangerous driving refers to driving in the event of an accident occurring or an event that poses a risk of an accident occurring. "Accident" typically refers to a collision. In other words, dangerous driving includes driving in the event of a collision involving a person or property, or driving in the event that poses a risk of a collision occurring. "Event that poses a risk of an accident" refers to an event in which an accident has not actually occurred, but which has a high probability of occurring.

[0029] Criterion 214 is a set of criteria for vital information used to determine the driver's abnormal condition. Criterion 214 is, for example, a standard value for each vital information. In other words, Criterion 214 is, for example, a threshold value for each vital information. For example, Criterion 214 is the standard value for the driver's heart rate, respiratory rate, blood pressure, body temperature, and blood oxygen saturation. For eyelid opening and eye movement, Criterion 214 is the standard value for the distance between the driver's eyelids and the standard value for the frequency of eye movement. For body movement information, Criterion 214 is the standard value for the time interval between the movement of a specified body part and the next movement.

[0030] The judgment criterion 214 is calculated, for example, from the vital history 213 for each driver. For example, the judgment criterion 214 may be the average value of each of the driver's past vital information. Here, the judgment criterion 214 may be the average value of the vital information that has been flagged as normal driving from the driver's past vital information. Alternatively, the judgment criterion 214 may be a value that takes into account the vital information that has been flagged as dangerous driving. For example, the judgment criterion 214 may be set based on vital information at a time prior to the occurrence of dangerous driving. Specifically, the judgment criterion 214 may be the average value of vital information at a time predetermined before the occurrence of dangerous driving, or the worst value at that time. Or, the judgment criterion 214 may be the average value of vital information that has been flagged as dangerous driving.

[0031] Furthermore, the judgment criterion 214 may include an allowable time for vital information to be judged as abnormal. That is, the judgment criterion 214 may include an allowable time for which the driver's condition is not judged as abnormal unless the driver's vital information temporarily exceeds or falls below a standard value, and the deviation from the standard value continues for a predetermined period of time.

[0032] The judgment criteria 214 may include an acceptable deviation from the standard value for each vital information. The acceptable deviation may be a predetermined deviation from the standard value that can be recognized as vital information during normal driving, for example, from the standard deviation or variance of vital information during the driver's past normal driving.

[0033] Multiple criteria for judgment 214 can be defined for the same driver. For example, different criteria for judgment 214 may be defined depending on the location of the vehicle being driven by the driver. For example, judgment 214 can be defined in two ways: whether the location of the vehicle being driven by the driver is in a dangerous position or in a non-dangerous position. A dangerous position is, for example, a highway or a narrow road. That is, judgment criterion 214 may have two types of criteria for the same driver: one for when the vehicle being driven by the driver is located on a highway or a narrow road, and another for when it is located on a general road, etc. Furthermore, a dangerous position may be a location where dangerous driving has occurred in the past. In this case, the dangerous driving may or may not be by a specific driver. For example, if two types of criteria are defined for driver A's judgment criterion 214—one for a location where dangerous driving has occurred in the past, and one for a location where dangerous driving has not occurred in the past—then the party involved in the dangerous driving may be driver A, or it may be dangerous driving by another driver. Furthermore, if a dangerous location is a location where dangerous driving has occurred in the past, the non-dangerous location may be referred to as a "non-dangerous driving location."

[0034] The criteria 214 for determining an abnormal condition in a dangerous location may be stricter than the criteria 214 for determining an abnormal condition in a non-dangerous location. For example, if the criteria 214 has criteria for multiple vital signs, the criteria 214 for dangerous locations may be defined as criteria that are uniformly stricter by a predetermined percentage compared to the criteria 214 for non-dangerous locations.

[0035] Furthermore, the judgment criteria 214 may have different criteria depending on the time of day the driver is operating the vehicle. For example, the judgment criteria 214 may have different criteria for the same driver during the daytime and at night. In other words, the judgment criteria 214 may have different criteria for the time of day when the driver's visibility is good and the time of day when their visibility is poor.

[0036] Furthermore, the judgment criterion 214 may be a pre-trained model defined for each driver. That is, the judgment criterion 214 may be a pre-trained model that outputs the driver's abnormal state when the vital information of the target driver is input. The pre-trained model may be generated using a machine learning algorithm based on a neural network (NN), such as a CNN (Convolutional Neural Network).

[0037] The Dangerous Driving Location DB 22 is composed of a storage device such as a hard disk or flash memory. The Dangerous Driving Location DB 22 stores location information 221, driver identification information 222, and date and time information 223 in association with each other. Location information 221 is the location information where the dangerous driving occurred. Location information 221 may be information about the location of a specific point based on coordinate information, or it may be information about a specific area. For example, location information 221 may be location information about the location where a collision occurred, or it may be location information about an area where collisions frequently occur. Driver identification information 222 is the identification information of the driver who committed the dangerous driving at the dangerous driving location. Driver identification information 222 is the driver's ID or driver's name, similar to identification information 211. One driver identification information 222 may be associated with one location information 221 of a dangerous driving location, or multiple driver identification information 222 may be associated. Date and time information 223 is information about the date and time when the dangerous driving occurred at the dangerous driving location. The date and time information 223 may include information down to the hour and minute, or it may include information up to the day. One date and time information 223 may be associated with one location information 221, or multiple date and time information 223 may be associated with one location information 221.

[0038] The biometric information acquisition unit 23 is configured to acquire the driver's biometric information. In other words, the biometric information acquisition unit 23 corresponds to the biometric information acquisition unit 11 in the driver monitoring system 1. The biometric information acquisition unit 23 acquires the driver's biometric information from a sensor (not shown) installed at a predetermined position in the driver's seat of the vehicle. The sensor may be a visible light camera, an infrared sensor, a microphone, etc. The biometric information acquisition unit 23 acquires from the driver the same type of biometric information as the driver's registered biometric information 212 stored in the driver DB 21. Typically, the biometric information acquisition unit 23 acquires biometric information when the driver gets into the vehicle. In other words, the biometric information acquisition unit 23 acquires biometric information at the time the driver starts driving the vehicle. However, the biometric information acquisition unit 23 may acquire the driver's biometric information at any time while the driver is driving the vehicle.

[0039] The identification information acquisition unit 24 performs biometric authentication of the driver based on the driver's biometric information acquired by the biometric information acquisition unit 23. The identification information acquisition unit 24 then acquires the driver's identification information 211. In other words, the identification information acquisition unit 24 corresponds to the identification information acquisition unit 12 in the driver monitoring system 1. The identification information acquisition unit 24 extracts feature quantities from the driver's biometric information acquired by the biometric information acquisition unit 23. The identification information acquisition unit 24 then compares these feature quantities with the registered biometric information 212 stored in the driver DB 21 and calculates a comparison score between each registered biometric information 212. Drivers whose comparison score is above a predetermined threshold are then authenticated as drivers operating the vehicle. The identification information acquisition unit 24 acquires the driver's identification information 211 by extracting the identification information 211 associated with the registered biometric information 212. Typically, the identification information acquisition unit 24 acquires the driver's identification information when the driver gets into the vehicle, but it may also acquire the driver's identification information each time the biometric information acquisition unit 23 acquires the driver's biometric information.

[0040] The vital information acquisition unit 25 acquires vital information of the driver operating the vehicle. In other words, the vital information acquisition unit 25 corresponds to the vital information acquisition unit 13 in the driver monitoring system 1. The vital information acquisition unit 25 acquires the driver's vital information from sensors (not shown) installed at predetermined locations in the driver's seat of the vehicle. For example, the vital information acquisition unit 25 can acquire predetermined vital information using images captured by a visible light camera or infrared camera of the driver's face, predetermined body parts, and pulse. The vital information acquisition unit 25 can also acquire predetermined vital information using vibration sensors installed in the driver's seat. Furthermore, the vital information acquisition unit 25 can acquire predetermined vital information by attaching predetermined sensors to the driver's arm or earlobe.

[0041] When acquiring vital information based on images captured by a visible light camera, infrared camera, etc., the vital information acquisition unit 25 can acquire vital information by inputting the captured images into a predetermined trained model. For example, if it is desired to acquire the degree of eyelid opening as vital information, the vital information acquisition unit 25 inputs the captured images into the trained model. The vital information acquisition unit 25 can then output vital information from the trained model, such as the distance between the driver's eyelids. The trained model may be generated for each piece of vital information based on the captured images. The trained model may be generated using, for example, an NN-based machine learning algorithm such as CNN.

[0042] The vital information acquisition unit 25 may acquire vital information using the same sensor as the biological information acquisition unit 23, or it may acquire vital information using a different sensor. For example, suppose the biological information acquisition unit 23 acquires a facial image of the driver using the driver's visible light camera, and the vital information acquisition unit 25 acquires the degree of eyelid opening of the driver as vital information from the driver's facial image. In this case, the vital information acquisition unit 25 may acquire various vital information by acquiring the driver's facial image using the same visible light camera as the biological information acquisition unit 23.

[0043] The vital information acquisition unit 25 can acquire vital information of a driver who is driving a vehicle at any time. For example, the vital information acquisition unit 25 may acquire vital information once per second, 10 times per second, 30 times per second, or 60 times per second. The vital information acquisition unit 25 stores the acquired vital information in the vital history 213 of the driver DB 21. Here, the vital information acquisition unit 25 may store all the acquired vital information in the vital history 213, or may store part of the vital information.

[0044] The position information acquisition unit 26 can acquire position information of the vehicle. Typically, the position information acquisition unit 26 acquires position information of the current position of the vehicle. The position information acquisition unit 26 can measure the current position, for example, by communicating with a GPS (Global Positioning System) satellite. In addition, the position information acquisition unit 26 may measure the position of the vehicle using short-range wireless communication technology using Wi-fi (registered trademark) or Bluetooth (registered trademark). For example, the position information acquisition unit 26 can acquire position information of the vehicle by communicating with access points or beacons arranged near the road on which the vehicle travels.

[0045] The surrounding information acquisition unit 27 can acquire surrounding information of the vehicle. The surrounding information of the vehicle is mainly information about obstacles existing around the vehicle. Here, the term "obstacle" includes static obstacles and dynamic obstacles. Static obstacles refer to, for example, guardrails, utility poles, median strips, fallen trees, parked vehicles, and the like. Dynamic obstacles refer to vehicles located in the front, rear or side directions, moving in the same direction, oncoming vehicles, pedestrians, animals, and the like. The surrounding information acquisition unit 27 acquires surrounding information of the vehicle using a plurality of sensors (not shown) provided on the vehicle. The sensors provided on the vehicle are, for example, ultrasonic sensors, LiDAR (Light Detection and Ranging), millimeter-wave radar, and cameras.

[0046] The surrounding information acquisition unit 27 can acquire the degree of approach between a vehicle and an obstacle present around the vehicle. The "degree of approach" may be, for example, the distance between the vehicle and an obstacle around the vehicle, or may be information indicating whether or not the vehicle is in contact with the obstacle. That is, the surrounding information acquisition unit 27 can measure the distance between the vehicle and the obstacle.

[0047] The dangerous driving determination unit 28 is configured to determine driving by a driver as dangerous driving. The dangerous driving determination unit 28 determines dangerous driving based on, for example, the driver's driving operation of the vehicle. The "driving operation of the vehicle" refers to operations of components provided in the vehicle such as the steering wheel, accelerator, and brake. The dangerous driving determination unit 28 detects dangerous behavior by the driver using, for example, an acceleration sensor or a gravity sensor provided in the vehicle (neither is shown). The "dangerous behavior" refers to sudden steering, sudden braking, sudden acceleration, sudden stopping, and the like. When dangerous behavior is detected based on various sensors, the dangerous driving determination unit 28 can determine that the driving is dangerous driving. Further, the dangerous driving determination unit 28 can acquire the degree of approach between the vehicle and an obstacle present around the vehicle from the surrounding information acquisition unit 27. Accordingly, for example, when the distance between the vehicle and the obstacle becomes equal to or less than a predetermined threshold, or when the vehicle comes into contact with a surrounding obstacle, the dangerous driving determination unit 28 can determine that the driving that led to the situation is dangerous driving. The dangerous driving determination unit 28 may determine dangerous driving using both the dangerous behavior by the driver and the degree of approach to surrounding obstacles.

[0048] When it is determined that driving by a driver is dangerous driving, the dangerous driving determination unit 28 associates date and time information 223 when the dangerous driving occurred, position information 221 where the dangerous driving occurred, and driver identification information 222 with each other, and stores the associated information in the dangerous driving occurrence position DB 22. Here, the dangerous driving determination unit 28 acquires the position information where the dangerous driving occurred from the position information acquisition unit 26. Further, the dangerous driving determination unit 28 adds a dangerous driving flag to the vital information of the driver at the occurrence timing of the dangerous driving in the vital history 213 stored in the driver DB 21.

[0049] The judgment criterion determination unit 29 is configured to determine judgment criteria 214 for vital information used to determine the abnormal state of the driver, based on the driver's identification information 211. In other words, the judgment criterion determination unit 29 corresponds to the judgment criterion determination unit 14 in the driver monitoring system 1. The judgment criterion determination unit 29 searches for judgment criteria 214 associated with the driver's identification information 211 acquired by the identification information acquisition unit 24. If there is only one judgment criterion 214 associated with the driver's identification information 211, the judgment criterion determination unit 29 determines that judgment criterion 214 as the judgment criterion for the driver. Here, the judgment criterion 214 is, for example, the average value of vital information from the driver's past vital information that has been flagged as normal driving. Alternatively, the judgment criterion 214 may be, for example, a trained model associated with the driver's identification information 211.

[0050] If multiple judgment criteria 214 are defined associated with the driver identification information 211, the judgment criterion determination unit 29 selects a judgment criterion 214 according to the driver's driving situation. For example, if the vehicle's current location is a dangerous location, such as on a highway or a narrow road, based on the vehicle's location information acquired by the location information acquisition unit 26, the judgment criterion determination unit 29 can determine a judgment criterion 214 for when the vehicle is in a dangerous location. Furthermore, based on the vehicle's location information acquired by the location information acquisition unit 26 and the location information 221 of dangerous driving occurrence locations stored in the dangerous driving occurrence location DB 22, it is assumed that the vehicle's current location is a location where dangerous driving has occurred in the past. In this case, the judgment criterion determination unit 29 can determine a judgment criterion 214 for a dangerous location. In other words, the judgment criterion determination unit 29 can determine a different criterion 214 for a location where dangerous driving has not occurred, i.e., a non-dangerous driving occurrence location. Here, the determination criterion unit 29 may determine the determination criterion for the dangerous location as the determination criterion 214 only if the driver identification information 222 of a driver who has previously committed dangerous driving at the vehicle's current location is the same as the identification information 211 of the driver currently operating the vehicle. In other words, the determination criterion unit 29 can determine a different criterion as the determination criterion 214 when the vehicle's current location is a location where the driver operating the vehicle has previously committed dangerous driving, compared to when the location is a location where the driver of the vehicle has committed non-dangerous driving.

[0051] Furthermore, the determination criterion unit 29 may select the determination criterion 214 based on the current time information. For example, if the determination criterion 214 differs between daytime and nighttime, the determination criterion unit 29 can determine the daytime determination criterion as the determination criterion 214 when the current time is daytime.

[0052] The abnormal state determination unit 30 determines the abnormal state of the driver operating the vehicle. In other words, the abnormal state determination unit 30 corresponds to the abnormal state determination unit 15 in the driver monitoring system 1. The abnormal state determination unit 30 uses the determination criteria 214 determined by the determination criteria determination unit 29 to determine whether the current state of the driver is abnormal or not. The abnormal state determination unit 30 determines the abnormal state by comparing the vital information acquired by the vital information acquisition unit 25 with the determination criteria 214. For example, if the determination criteria 214 is a threshold for each vital information, the abnormal state determination unit 30 determines that the driver's state is abnormal if each vital information acquired by the vital information acquisition unit 25 deviates from the threshold for vital information in the corresponding determination criteria 214. Furthermore, if an allowable deviation amount is set for the determination criteria 214, the abnormal state determination unit 30 determines that the driver's state is abnormal if the vital information acquired by the vital information acquisition unit 25 further deviates from the allowable deviation amount in the corresponding determination criteria 214.

[0053] Here, the abnormal state determination unit 30 can determine an abnormal state based on the driver's vital information at the time of a past dangerous driving incident. This applies, for example, when the determination criterion 214 determined by the determination criterion determination unit 29 takes into account vital information to which a dangerous driving flag has been assigned. For example, the abnormal state determination unit 30 can use the determination criterion 214 set based on vital information at a time prior to the occurrence of a past dangerous driving incident. As a result, the abnormal state determination unit 30 can determine an abnormal state based on the driver's vital information at the time of a past dangerous driving incident.

[0054] The abnormal state determination unit 30 may determine the driver's condition as abnormal if one of the multiple vital signs exceeds a threshold, or if multiple vital signs exceed a threshold. The abnormal state determination unit 30 can also assign a priority to the vital signs used for abnormality determination. For example, the abnormal state determination unit 30 may determine that the driver's condition is abnormal if the heart rate exceeds a threshold, but not if only the degree of eyelid opening exceeds a threshold. In this case, the determination criterion determination unit 29 may determine that the driver's condition is abnormal if, in addition to the degree of eyelid opening, the degree of eye movement also exceeds a threshold. Furthermore, if the determination criterion 214 includes an allowable time for vital signs, the abnormal state determination unit 30 will determine the driver's condition as abnormal if the vital signs acquired by the vital signs acquisition unit 25 continuously exceed the corresponding threshold for a period longer than the allowable time.

[0055] Furthermore, if the judgment criterion 214 is a trained model, the abnormal state determination unit 30 inputs the vital information acquired by the vital information acquisition unit 25 into the trained model. The abnormal state determination unit 30 inputs, for example, all acquired vital information into the same trained model. Then, the abnormal state determination unit 30 outputs a judgment result from the trained model. That is, the abnormal state determination unit 30 outputs a judgment result from the trained model indicating whether or not the driver is in an abnormal state.

[0056] The warning output unit 31 can output a predetermined warning to the driver and other occupants when the abnormal condition determination unit 30 determines that the driver is in an abnormal condition. The warning is a notification that the driver's condition is abnormal. The warning output unit 31 can output a warning sound to the occupants, for example, via a speaker (not shown). The warning sound may be, for example, a buzzer sound, or a message indicating that the driver's condition is abnormal. The warning output unit 31 can also display a warning to the occupants via a display device (not shown). The display device may be installed on the instrument panel of the vehicle, or it may be a display device used in a car navigation system. The display content may be the illumination or flashing of a warning light on the instrument panel, or a message indicating that the driver's condition is abnormal.

[0057] The warning output unit 31 may output specific countermeasures as warnings in response to abnormal conditions of the driver. For example, the warning output unit 31 may output a warning urging the driver to take a break. The warning output unit 31 may also output route information to the driver to park the vehicle in a designated location.

[0058] The driving control unit 32 is configured to control the driving operations of the vehicle being driven by the driver. Specifically, the driving control unit 32 can control the vehicle to stop automatically. That is, the driving control unit 32 can control the brakes of the vehicle. The driving control unit 32 may also be able to control the steering wheel of the vehicle. That is, the driving control unit 32 may be able to stop the vehicle automatically at a predetermined location by controlling the steering wheel of the vehicle.

[0059] The driving control unit 32 can switch the control method from manual operation by the driver to automatic operation by the driving control unit 32 if the driver's condition is abnormal. The driving control unit 32 can then stop the vehicle by controlling the vehicle's operation. Here, regardless of whether the driver is in an abnormal state, if the vehicle has an automatic driving function that can be switched between manual and automatic driving, and the vehicle is already in automatic driving mode when the driver becomes abnormal, the driving control unit 32 will continue the automatic driving mode and stop the vehicle. Note that the driver monitoring system 2 does not necessarily have to include the configuration of the driving control unit 32.

[0060] Next, the flow of the driver monitoring method by the driver monitoring system 2 will be explained. Figure 4 is a flowchart showing an example of the flow until the judgment criteria corresponding to the driver operating the vehicle are determined. Figure 4 is an example of the flow at the time the driver gets into the vehicle. First, the biometric information acquisition unit 23 acquires the biometric information of the driver operating the vehicle (S201). Next, the identification information acquisition unit 24 extracts feature quantities from the biometric information acquired by the biometric information acquisition unit 23 (S202). After that, the identification information acquisition unit 24 compares the extracted feature quantities with the registered biometric information 212 stored in the driver DB 21 (S203). After that, the identification information acquisition unit 24 acquires driver identification information 211 that has feature quantities that match the feature quantities of the biometric information acquired by the biometric information acquisition unit 23 (S204). After that, the judgment criteria determination unit 29 determines the judgment criteria corresponding to the driver based on the driver identification information 211 (S205).

[0061] Figure 5 is a flowchart showing an example of the flow of operations when dangerous driving occurs. In Figure 5, the identification information acquisition unit 24 acquires the driver's identification information at the time the driver starts driving. First, the vital information acquisition unit 25 acquires the vital information of the driver operating the vehicle (S205). Next, the location information acquisition unit 26 acquires the location information of the vehicle (S206). After that, the surrounding information acquisition unit 27 acquires information about the surroundings of the vehicle (S207). Here, steps S205 to S207 may be performed simultaneously, or S206 and S207 may be performed before S205. After that, the dangerous driving determination unit 28 determines whether or not dangerous driving has occurred (S208). The dangerous driving determination unit 28 determines whether or not the driver's driving is dangerous based on the driver's driving operations and the degree of proximity between the vehicle and obstacles present around the vehicle, which is acquired from the surrounding information acquisition unit 27. If NO is determined in step S208, the process returns to S205. If the result in step S208 is determined to be YES, the dangerous driving determination unit 28 associates the date and time information 223 in which the dangerous driving occurred, the location information 221 in which the dangerous driving occurred, and the driver identification information 222 and stores them in the dangerous driving location DB 22 (S209).

[0062] Figure 6 is a flowchart showing an example of the operation flow in which the judgment criteria are changed based on the location information of a vehicle in motion. First, the judgment criterion determination unit 29 determines the judgment criterion corresponding to the driver based on the driver's identification information 211 (S210). Step S210 is the same as step S205 in Figure 4. That is, step S210 is a step in which the judgment criteria are determined at the time the driver gets into the vehicle. After that, the driver starts driving the vehicle. Next, the location information acquisition unit 26 acquires the location information of the vehicle (S211). After that, the judgment criterion determination unit 29 determines whether the current position of the vehicle is a dangerous position or not (S212). If it is determined to be NO in step S212, the process returns to S211. If it is determined to be YES in step S212, the judgment criterion determination unit 29 determines the judgment criterion for when the current position of the vehicle is a dangerous position as judgment criterion 214 (S213). That is, the judgment criterion determination unit 29 changes from the initial judgment criterion to the judgment criterion for when the vehicle is in a dangerous position.

[0063] Figure 7 is a flowchart showing an example of the operation flow when determining an abnormal state of the driver. First, the determination criterion unit 29 determines a determination criterion 214 corresponding to the driver based on the driver's identification information 211 (S214). Step S214 is the same as S205 in Figure 4 and S210 or S213 in Figure 6. That is, step S214 may be the operation of the determination criterion unit 29 when the driver gets into the vehicle, or it may be the operation of the determination criterion unit 29 when the driver is driving the vehicle. Next, the vital information acquisition unit 25 acquires the driver's vital information (S215). After that, the abnormal state determination unit 30 determines whether the driver's condition is abnormal or not based on the determination criterion 214 corresponding to the driver and the acquired vital information (S216). If NO is determined in step S216, the process returns to S215. If YES is determined in step S216, the warning output unit 31 outputs a predetermined warning to the occupant (S217). Subsequently, the driving control unit 32 stops the vehicle at a predetermined location (S218). Steps S217 and S218 may be performed simultaneously.

[0064] In this way, the driver monitoring system 2 can concretely implement the driver monitoring system 1. Specifically, the driver monitoring system 2 obtains the driver's identification information by performing biometric authentication on the driver who is in the vehicle and driving. Then, the driver monitoring system 2 can determine judgment criteria corresponding to the driver based on the identification information, and can determine the driver's abnormal condition based on the judgment criteria and the driver's vital information. As a result, the driver monitoring system 2 can correctly determine the driver's abnormal condition even when different drivers are operating the vehicle.

[0065] In driver monitoring systems that monitor drivers operating vehicles, the judgment criteria may be fixed. Using such a driver monitoring system may lead to an inability to correctly determine the driver's abnormal condition. For example, a driver monitoring system may misidentify a driver with relatively narrow eyes as being drowsy. With driver monitoring system 2, the judgment criteria can be changed depending on the driver, thereby reducing misjudgments based on vital information. In other words, driver monitoring system 2 can improve the accuracy of driver monitoring.

[0066] Furthermore, the driver monitoring system 2 can determine whether an abnormal condition exists based on the driver's vital signs at the time of past dangerous driving incidents. This allows the driver monitoring system 2 to infer whether the driver's vital signs are signs that precede dangerous driving. As a result, the driver monitoring system 2 can make more accurate abnormal condition determinations.

[0067] The driver monitoring system 2 can determine whether a driver's driving is dangerous based on the degree of proximity between the vehicle and obstacles around the vehicle. Furthermore, the driver monitoring system 2 can determine dangerous driving based on the driver's vehicle operation. As a result, the driver monitoring system 2 can determine with high accuracy whether a driver's driving is dangerous or not.

[0068] Furthermore, the driver monitoring system 2 can determine judgment criteria corresponding to the driver based on the vehicle's location information. This allows the driver monitoring system 2 to change the judgment criteria according to the vehicle's current location. Therefore, the driver monitoring system 2 can determine the driver's abnormal condition using appropriate judgment criteria according to the vehicle's current location.

[0069] Furthermore, the driver monitoring system 2 can determine different criteria for determining whether a vehicle's current location is a location where dangerous driving has occurred in the past, compared to when the location is a location where non-dangerous driving has occurred. This allows the driver monitoring system 2 to determine the criteria based on past driving behavior at that location, enabling it to make a more accurate determination of abnormal conditions. In particular, if the past dangerous driving at that location was caused by the driver operating the vehicle, the driver monitoring system 2 can make an even more accurate determination.

[0070] (Example Hardware Configuration) Figure 8 shows an example hardware configuration of the driver monitoring system 50. In Figure 8, the driver monitoring system 50 includes a processor 51 and a memory 52. ​​The processor 51 may be, for example, a microprocessor, an MPU (Micro Processing Unit), or a CPU (Central Processing Unit). The processor 51 may include multiple processors. The memory 52 is composed of a combination of volatile memory and non-volatile memory. The memory 52 may include storage located away from the processor 51. In this case, the processor 51 may access the memory 52 via an I / O (Input / Output) interface, which is not shown.

[0071] In the embodiments described above, the disclosure was explained as a hardware configuration, but the disclosure is not limited thereto. The disclosure can also be implemented by having the CPU execute a computer program to perform any processing.

[0072] Programs can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (random access memory)). Programs may also be supplied to a computer using various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0073] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0074] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments, rather than being associated with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps described in any of the drawings may be changed as appropriate.

[0075] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) A driver monitoring system comprising: a biometric information acquisition unit that acquires biometric information of a driver operating a vehicle; an identification information acquisition unit that acquires identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition unit that acquires vital information of the driver operating the vehicle; a judgment criterion determination unit that determines judgment criteria for the vital information used to determine an abnormal state of the driver based on the driver's identification information; and an abnormal state determination unit that determines the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver. (Note 2) The driver monitoring system according to Note 1, further comprising a dangerous driving determination unit that determines that driving by the driver is dangerous driving, wherein the abnormal state determination unit determines the abnormal state based on the driver's vital information at the time of the occurrence of dangerous driving that the driver has previously committed. (Note 3) The driver monitoring system according to Note 1 or 2, further comprising a location information acquisition unit that acquires location information of the vehicle, wherein the judgment criterion determination unit determines the judgment criterion based on the location information of the vehicle. (Note 4) The driver monitoring system according to Note 2, further comprising a surrounding information acquisition unit that acquires surrounding information of the vehicle, wherein the dangerous driving judgment unit determines the dangerous driving based on the degree of proximity between the vehicle and obstacles around the vehicle, based on the surrounding information. (Note 5) The driver monitoring system according to Note 3, wherein the judgment criterion determination unit determines a different criterion as the judgment criterion when the current location of the vehicle based on the location information is a location where dangerous driving has occurred in the past, compared to when the location is a location where non-dangerous driving has occurred. (Note 6) The driver monitoring system according to Note 5, wherein the judgment criterion determination unit determines a different criterion as the judgment criterion when the current location of the vehicle is a location where the driver operating the vehicle has committed dangerous driving in the past, compared to when the location is a location where non-dangerous driving has occurred by the driver.(Note 7) The driver monitoring system according to any one of Notes 2 to 6, wherein the dangerous driving determination unit determines the dangerous driving based on the driver's driving operations of the vehicle. (Note 8) A driver monitoring method, wherein a computer performs: a biometric information acquisition process to acquire biometric information of a driver operating a vehicle; an identification information acquisition process to acquire identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition process to acquire vital information of the driver operating the vehicle; a judgment criterion determination process to determine judgment criteria for the vital information used to determine the driver's abnormal state based on the driver's identification information; and an abnormal state determination process to determine the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver. (Note 9) The driver monitoring method according to Note 8, further comprising: (Note 10) The driver monitoring method according to Note 8 or 9, further comprising: (Note 11) The driver monitoring method according to Note (Note 12) In the judgment criterion determination process, if the current position of the vehicle based on the position information is a position where dangerous driving has occurred in the past, a different criterion is determined as the judgment criterion than when the position is a position where non-dangerous driving has occurred. The driver monitoring method described in Note 10.(Note 13) In the judgment criterion determination process, if the current position of the vehicle is the same as a position where the driver operating the vehicle has previously committed dangerous driving, a different criterion is determined as the judgment criterion compared to when the position is the same as when the driver has committed non-dangerous driving, as described in Note 12. (Note 14) In the dangerous driving judgment process, dangerous driving is determined based on the driver's driving operations of the vehicle, as described in any one of Notes 9 to 13. (Note 15) A program that causes a computer to execute the following steps: a biometric information acquisition step of acquiring biometric information of a driver operating a vehicle; an identification information acquisition step of acquiring identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition step of acquiring vital information of the driver operating the vehicle; a judgment criterion determination step of determining judgment criteria for the vital information used to determine the abnormal state of the driver based on the driver's identification information; and an abnormal state determination step of determining the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver. (Note 16) The program according to Note 15, further comprising a dangerous driving determination step of determining that the driving by the driver is dangerous driving, wherein in the abnormal state determination step, the abnormal state is determined based on the vital information of the driver at the time of the occurrence of the dangerous driving that the driver has previously committed. (Appendix 17) The program according to Appendix 15 or 16, further comprising a location information acquisition step for acquiring location information of the vehicle, wherein in the judgment criterion determination step, the judgment criterion is determined based on the location information of the vehicle. (Appendix 18) The program according to Appendix 16, further comprising a surrounding information acquisition step for acquiring surrounding information of the vehicle, wherein in the dangerous driving judgment step, the dangerous driving is determined based on the degree of proximity between the vehicle and obstacles around the vehicle, based on the surrounding information.(Note 19) The program according to Note 17, wherein in the judgment criterion determination step, if the current position of the vehicle based on the position information is a position where dangerous driving has occurred in the past, a different criterion is determined as the judgment criterion than when the position is a position where non-dangerous driving has occurred. (Note 20) The program according to Note 19, wherein in the judgment criterion determination step, if the current position of the vehicle is a position where the driver operating the vehicle has committed dangerous driving in the past, a different criterion is determined as the judgment criterion than when the position is a position where non-dangerous driving has occurred by the driver. (Note 21) The program according to any one of Notes 16 to 20, wherein in the dangerous driving determination step, dangerous driving is determined based on the driver's driving operations of the vehicle.

[0076] Some or all of the elements described in any appendix may apply to various hardware, software, recording means, systems, and methods for recording software.

[0077] 1 Driver monitoring system 2 Driver monitoring system 11 Biometric information acquisition unit 12 Identification information acquisition unit 13 Vital information acquisition unit 14 Judgment criterion determination unit 15 Abnormal state determination unit 21 Driver database 22 Dangerous driving location database 23 Biometric information acquisition unit 24 Identification information acquisition unit 25 Vital information acquisition unit 26 Location information acquisition unit 27 Surrounding information acquisition unit 28 Dangerous driving determination unit 29 Judgment criterion determination unit 30 Abnormal state determination unit 31 Warning output unit 32 Driving control unit 50 Driver monitoring system 51 Processor 52 Memory 211 Identification information 212 Registered biometric information 213 Vital history 214 Judgment criteria 221 Location information 222 Driver identification information 223 Date and time information

Claims

1. A driver monitoring system comprising: a biometric information acquisition unit that acquires biometric information of a driver operating a vehicle; an identification information acquisition unit that acquires identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition unit that acquires vital information of the driver operating the vehicle; a judgment criterion determination unit that determines judgment criteria for the vital information used to determine the abnormal state of the driver based on the driver's identification information; and an abnormal state determination unit that determines the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver.

2. The driver monitoring system according to claim 1, further comprising a dangerous driving determination unit that determines that the driver's driving is dangerous driving, wherein the abnormal state determination unit determines the abnormal state based on the driver's vital information at the time of the occurrence of the dangerous driving that the driver has previously committed.

3. A driver monitoring system according to claim 1 or 2, further comprising: a location information acquisition unit that acquires location information of the vehicle, wherein the determination criterion unit determines the determination criterion based on the location information of the vehicle.

4. The driver monitoring system according to claim 2, further comprising a surrounding information acquisition unit that acquires surrounding information of the vehicle, wherein the dangerous driving determination unit determines the dangerous driving based on the degree of proximity between the vehicle and obstacles around the vehicle, based on the surrounding information.

5. The driver monitoring system according to claim 3, wherein the judgment criterion determination unit determines a different criterion as the judgment criterion when the current position of the vehicle based on the position information is a position where dangerous driving has occurred in the past, compared to when the position is a position where non-dangerous driving has occurred.

6. The driver monitoring system according to claim 5, wherein the judgment criterion determination unit determines a different criterion as the judgment criterion when the current position of the vehicle is a position where the driver operating the vehicle has previously committed dangerous driving, compared to when the position is a position where the driver has committed non-dangerous driving.

7. The driver monitoring system according to claim 2, wherein the dangerous driving determination unit determines the dangerous driving based on the driver's driving operations of the vehicle.

8. Driver monitoring method, wherein a computer performs: a biometric information acquisition process to acquire biometric information of a driver operating a vehicle; an identification information acquisition process to acquire identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition process to acquire vital information of the driver operating the vehicle; a judgment criterion determination process to determine judgment criteria for the vital information used to determine an abnormal state of the driver based on the driver's identification information; and an abnormal state determination process to determine the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver.

9. The driver monitoring method according to claim 8, further comprising: a dangerous driving determination process that determines that the driving by the driver is dangerous driving; and in the abnormal state determination process, the abnormal state is determined based on the driver's vital information at the time of the occurrence of the dangerous driving that the driver has previously committed.

10. A driver monitoring method according to claim 8 or 9, further comprising: a location information acquisition process for acquiring location information of the vehicle, wherein in the determination criterion process, the determination criterion is determined based on the location information of the vehicle.

11. The driver monitoring method according to claim 9, further comprising: an ambient information acquisition process for acquiring ambient information of the vehicle; and in the dangerous driving determination process, the dangerous driving is determined based on the degree of proximity between the vehicle and obstacles in the vicinity of the vehicle, based on the ambient information.

12. The driver monitoring method according to claim 10, wherein in the judgment criterion determination process, if the current position of the vehicle based on the position information is a position where dangerous driving has occurred in the past, a different criterion is determined as the judgment criterion than when the position is a position where non-dangerous driving has occurred.

13. The driver monitoring method according to claim 12, wherein in the judgment criterion determination process, if the current position of the vehicle is a position where the driver operating the vehicle has previously committed dangerous driving, a different criterion is determined as the judgment criterion than when the position is a position where the driver has committed non-dangerous driving.

14. The driver monitoring method according to claim 9, wherein the dangerous driving determination process determines the dangerous driving based on the driver's driving operations of the vehicle.

15. A program that causes a computer to execute the following steps: a biometric information acquisition step for acquiring biometric information of a driver operating a vehicle; an identification information acquisition step for acquiring identification information of the driver by performing biometric authentication of the driver based on the biometric information; a vital information acquisition step for acquiring vital information of the driver operating the vehicle; a judgment criterion determination step for determining judgment criteria for the vital information used to determine an abnormal state of the driver based on the driver's identification information; and an abnormal state determination step for determining the abnormal state of the driver operating the vehicle based on the judgment criteria corresponding to the driver and the vital information acquired for the driver.

16. The program according to claim 15, further comprising a dangerous driving determination step of determining that the driving by the driver is dangerous driving, wherein in the abnormal state determination step, the abnormal state is determined based on the driver's vital information at the time of the occurrence of the dangerous driving that the driver has previously committed.

17. The program according to claim 15 or 16, further comprising: a location information acquisition step of acquiring location information of the vehicle, wherein in the determination criterion step, the determination criterion is determined based on the location information of the vehicle.

18. The program according to claim 16, further comprising the steps of acquiring surrounding information for the vehicle, wherein in the dangerous driving determination step, dangerous driving is determined based on the degree of proximity between the vehicle and obstacles around the vehicle, based on the surrounding information.

19. The program according to claim 17, wherein in the step of determining the judgment criteria, if the current position of the vehicle based on the position information is a position where dangerous driving has occurred in the past, a different criterion is determined as the judgment criterion than when the position is a position where non-dangerous driving has occurred.

20. The program according to claim 19, wherein in the step of determining the judgment criteria, if the current position of the vehicle is a position where the driver operating the vehicle has previously committed dangerous driving, a different criterion is determined as the judgment criterion than when the position is a position where the driver has committed non-dangerous driving.

Images