JP2024094708A - Driver Monitoring System - Google Patents

Abstract

A driver monitoring system is provided that can improve the accuracy of determining whether or not a driver is in an abnormal state.
[Solution] A driver monitoring system 1 includes a driver state determination unit 10 that determines the state of the driver based on a monitoring image I acquired by a camera 2. The driver state determination unit 10 performs processing to determine whether or not the driver has performed a preparatory movement based on a change in the direction of the driver's face in the monitoring image I. The driver state determination unit 10 also performs processing to determine whether or not the driver is in a state that should be notified based on an amount of change in the position of the driver's face in the monitoring image I. The driver state determination unit 10 then performs processing to determine whether or not the driver is in an abnormal state based on the determination result of whether or not the driver has performed a preparatory movement and the determination result of whether or not the driver is in a state that should be notified.
[Selected Figure] Figure 1

Description

The present invention relates to a driver monitoring system.

As a conventional driver monitoring system, for example, Patent Document 1 discloses a vehicle warning system that judges the driver's condition and the vehicle's driving situation, and issues a warning to the driver if it is judged to be at a dangerous level.

The "Basic Design Document for Driver Abnormality Automatic Detection System" presented by the Ministry of Land, Infrastructure, Transport and Tourism states that the driver's state will be judged based on changes in the position of the driver's face, with the normal state of the driver being used as the standard. With this type of technology, if it is determined that the driver has changed state, such as "slumping sideways" or "leaning to the side," it is determined that an abnormality has occurred with the driver (for example, the driver has suddenly fallen ill).

JP 2021-2182 A

However, in the conventional driver monitoring system described above, even if the driver is not suddenly ill and in a normal state, for example if the driver looks at luggage placed on the passenger seat, the driver monitoring system may determine that something is wrong with the driver and issue a warning or caution to the driver, so there is room for improvement in terms of the accuracy of determining driver abnormalities.

The present invention has been made to address the above-mentioned issues, and aims to provide a driver monitoring system that can improve the accuracy of determining whether or not a driver is in an abnormal state.

In order to achieve the above object, the driver monitoring system according to the present invention comprises a driver state determination unit that determines the state of the driver based on a monitoring image including an image of the face of the vehicle driver, and a notification unit that notifies the driver according to the determination result by the driver state determination unit, and the driver state determination unit is capable of executing a process of determining whether the driver has performed a preparatory movement before performing a predetermined movement based on a change in the direction of the driver's face in the monitoring image, a process of determining whether the driver is in a state that is different from a normal state and that is subject to notification based on the amount of change in the position of the driver's face in the monitoring image, and a process of determining whether the driver is in an abnormal state based on the determination result of whether the driver has performed the preparatory movement and the determination result of whether the driver is in the state that is subject to notification.

The driver monitoring system according to the present invention has the effect of improving the accuracy of determining whether the driver is in an abnormal state.

FIG. 1 is a block diagram showing a schematic configuration of a driver monitoring system according to an embodiment of the present invention. FIG. 2 is a flow chart illustrating an example of control in the driver monitoring system according to the embodiment. FIG. 3 is a flow chart showing an example of the preparatory movement state determination in step S1 of FIG. FIG. 4 is a flow chart showing an example of the notification target state determination in step S2 of FIG. FIG. 5 is a flow chart showing an example of the abnormal state determination in step S3 of FIG. FIG. 6 is a schematic diagram showing an example of a change in the state of the driver in the embodiment.

The following describes in detail the embodiments of the present invention with reference to the drawings. Note that the present invention is not limited to the following embodiments. In other words, the components in the following embodiments include those that a person skilled in the art would easily imagine or that are substantially the same, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention.

[Embodiment]
A driver monitoring system 1 according to this embodiment will be described with reference to Fig. 1. The driver monitoring system 1 is, for example, an in-vehicle system mounted on a vehicle (not shown). Here, the vehicle is, for example, a so-called right-hand drive vehicle, with the driver's seat provided on the right side in the vehicle width direction. The driver monitoring system 1 is a structural module that monitors the situation of the driver (not shown) of the vehicle and performs processing according to the situation. The driver monitoring system 1 includes a camera 2, an output device 3, and a control unit 4.

In addition, in the driver monitoring system 1 shown in FIG. 1, the connection method between each component for transmitting and receiving power supply, control signals, various information, etc. may be either a wired connection or a wireless connection unless otherwise specified. A wired connection is, for example, a connection via wiring materials such as electric wires and optical fibers. A wireless connection is, for example, a connection by wireless communication, contactless power supply, etc. In addition, the vehicle to which the driver monitoring system 1 is applied may be any vehicle that uses a motor or an engine as a drive source, such as an electric vehicle (EV (Electric Vehicle)), a hybrid vehicle (HEV (Hybrid Electric Vehicle)), a plug-in hybrid vehicle (PHEV (Plug-in Hybrid Electric Vehicle)), a gasoline vehicle, or a diesel vehicle. In addition, the vehicle may be driven manually by the driver, semi-automatically, fully automatically, etc. The vehicle in question may be a privately owned car, a rental car, a shared car, a bus, a taxi, or a ride-sharing car.

Camera 2 continuously captures surveillance images I (see also FIG. 6) including an image of the face of the driver who is the subject of surveillance in the vehicle cabin. Camera 2 is installed, for example, on an instrument panel (not shown), dashboard, steering column, etc., provided in the vehicle cabin. Camera 2 is positioned with its camera lens (not shown) facing the driver's face. Camera 2 captures an image of the driver's face by receiving reflected light from light irradiated onto the driver's face by, for example, an LED unit (not shown). Camera 2 is activated when the vehicle's ACC (accessory) power supply or IG (ignition) power supply is turned on, and captures an image of the driver's face until these power supplies are turned off. Camera 2 is connected to control unit 4, and outputs captured surveillance images I to control unit 4 at any time.

The output device 3 outputs various information to the interior of the vehicle. For example, the output device 3 outputs audio, and is a speaker provided in the vehicle. The output device 3 outputs audio in response to an audio signal from the control unit 4. The output device 3 may be dedicated to the driver monitoring system 1, or may be pre-installed in the vehicle.

The control unit 4 is a part that performs overall control of each part of the driver monitoring system 1. The control unit 4 executes various calculation processes related to monitoring the state of the driver who is the monitoring target and various support. The control unit 4 is composed of electronic circuits mainly composed of a well-known microcomputer including a central processing unit such as a CPU (Central Processing Unit), MPU (Micro Processing Unit), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), ROM (Read Only Memory), RAM (Random Access Memory) and an interface. The control unit 4 is electrically connected to the camera 2 and the output device 3. The control unit 4 can exchange various electrical signals with each part, such as image signals corresponding to the captured image and drive signals for driving each part.

Specifically, the control unit 4 is functionally configured to include a driver state determination unit 10 and a notification unit 20. The driver state determination unit 10 and the notification unit 20 can exchange various information with various devices electrically connected thereto. The driver state determination unit 10 and the notification unit 20 execute various programs stored in a storage unit (not shown) based on various input signals, etc., and output output signals to each unit by the operation of the programs to execute various processes for realizing various functions. Here, the storage unit is a storage device such as a memory. The storage unit stores conditions and information necessary for various processes in the control unit 4, various programs to be executed by the control unit 4, etc. The storage unit also stores auditory information such as voice to be output by the output device 3. The storage unit can also temporarily store various information including information regarding images captured by the camera 2 and vehicle information acquired via an external connection unit (not shown). The storage unit reads out such information as necessary by the driver state determination unit 10, the notification unit 20, etc.

The driver state determination unit 10 is a part capable of executing the driver state determination process shown in FIG. 2. More specifically, the driver state determination unit 10 is functionally conceptually configured to include a preparatory movement state determination unit 11, a notification target state determination unit 12, and an abnormal state determination unit 13.

The preparatory movement state determination unit 11 is a part capable of executing the preparatory movement determination process shown in FIG. 3. In the preparatory movement determination process, the preparatory movement state determination unit 11 determines whether or not the driver has performed a preparatory movement before performing a predetermined movement based on multiple monitoring images I acquired by the camera 2. The multiple monitoring images I are continuous over time. The preparatory movement state determination unit 11 determines whether or not the driver has performed a preparatory movement before performing a predetermined movement based on a change in the driver's facial direction in the multiple monitoring images I. For example, the preparatory movement state determination unit 11 detects the driver's facial direction and line of sight as a change in the driver's facial direction in the multiple monitoring images I, and determines whether or not the driver has performed a preparatory movement that is likely to be performed before performing a predetermined movement based on the detected facial direction and line of sight.

The actions performed by the driver include, for example, actions such as picking up a bag placed on the passenger seat to the left of the driver's seat or on the back seat in the vehicle cabin. In this case, the preparatory action is the driver's facial direction or the driver's gaze "turning downward to the left". The preparatory action state determination unit 11 stores in advance the reference facial direction and gaze direction. For example, as shown in FIG. 6, the preparatory action state determination unit 11 stores the driver's face 32 as the reference facial direction and gaze direction. Then, based on multiple monitoring images I acquired by the camera 2, the preparatory action state determination unit 11 detects changes over time in the driver's facial direction and gaze direction relative to the reference facial direction and gaze direction, thereby determining whether the driver has performed a preparatory action.

If the action performed by the driver is, for example, an action to pick up an object placed on the center console in the vehicle cabin, the preparatory action is the direction of the driver's face 33 in the multiple monitoring images I or the driver's gaze "turning downward to the left" as shown in FIG. 6. Furthermore, if the action performed by the driver is, for example, an action to pick up an object that has fallen on the floor in the vehicle cabin, the preparatory action is the direction of the driver's face or the driver's gaze "turning downward". Furthermore, if the action performed by the driver is, for example, an action to look at the rearview mirror to turn the vehicle right or left, the preparatory action is the direction of the driver's face or the driver's gaze "turning upward to the left". Furthermore, if the action performed by the driver is, for example, an action to look at a navigation image displayed on the center display, the preparatory action is the direction of the driver's face or the driver's gaze "turning left" or "turning downward to the left". Furthermore, if the action performed by the driver is, for example, an action of looking between the right door of the vehicle and the driver's seat, the preparatory action is the driver's face direction or the driver's gaze "looking down" or "looking down to the right". Also, if the action performed by the driver is, for example, an action of operating a sun visor, the preparatory action is the driver's face direction or the driver's gaze "looking up". Also, if the action performed by the driver is, for example, an action of searching for the driver's belongings inside the vehicle, the preparatory action is the driver's face direction or the driver's gaze "looking down to the left and down to the right alternately".

The notification target state determination unit 12 is a part capable of executing the notification target state determination process shown in FIG. 4. The notification target state determination process is a process in which the notification target state determination unit 12 determines whether or not the driver is in a notification target state different from a normal state based on the amount of change in the driver's face position in multiple monitoring images I acquired by the camera 2. The notification target state determination unit 12 determines whether or not the driver is in a notification target state different from a normal state based on the amount of change in the driver's face position in multiple monitoring images I. The notification target state determination unit 12 detects, for example, the inclination and position of the driver's face in each monitoring image I, and determines whether or not the driver is in a notification target state based on the amount of change in the driver's face inclination and face position detected from the multiple monitoring images.

The normal state of the driver is, for example, as shown in FIG. 6, the inclination and position of the driver's face 32 as a reference. On the other hand, the notification target state corresponds to, for example, the driver's face 34 as shown in FIG. 6, which is inclined to one side. The notification target state determination unit 12 determines whether the driver has transitioned from a normal state to a notification target state by detecting changes over time in the inclination and position of the driver's face relative to the inclination and position of the reference face based on multiple monitoring images I acquired by the camera 2.

The notification target state includes the above-mentioned actions performed by the driver in addition to the case where the driver is in an abnormal state. For example, in the frame 31 shown in FIG. 6, the preparatory movement state determination unit 11 determines "turning to the left" as a preparatory movement, the driver temporarily returns to a normal state, and then the notification target state determination unit 12 determines "falling to the left" as a notification target state. This series of actions is the driver visually confirming a package placed on the passenger seat and then picking up the package. In a conventional driver monitoring system, for example, the driver's action of picking up a package on the passenger seat is also determined as a notification target state as "falling to the left," and as a result, the driver is determined to be in an abnormal state even though he or she is not in an abnormal state.

The abnormal state determination unit 13 is a part capable of executing the abnormal state determination process shown in FIG. 5. The abnormal state determination process is a process in which the abnormal state determination unit 13 determines whether the driver is in an abnormal state based on the determination result of whether the driver has performed the preparatory movement described above and the determination result of whether the driver is in a state that is subject to notification described above. The abnormal state determination unit 13 determines whether the driver is in an abnormal state based on the determination result by the preparatory movement state determination unit 11 and the determination result by the notification subject state determination unit 12.

More specifically, if the preparatory movement state determination unit 11 determines that the driver is not in a state in which a preparatory movement has been performed, and the notification target state determination unit 12 determines that the driver is in a state in which a notification target has been performed, the abnormal state determination unit 13 determines that the driver is in an abnormal state. For example, the actions and monitoring image I for which the abnormal state determination unit 13 determines that the driver is in an abnormal state are a series of actions exemplified by the frame 30 shown in FIG. 6. On the other hand, if the preparatory movement state determination unit 11 determines that the driver is in a state in which a preparatory movement has been performed, and the notification target state determination unit 12 determines that the driver is in a state in which a notification target has been performed, the abnormal state determination unit 13 determines that the driver is in a movement state different from the abnormal state. For example, the actions and monitoring image I for which the abnormal state determination unit 13 determines that the driver is in a movement state different from the abnormal state are a series of actions exemplified by the frame 31 shown in FIG. 6.

The notification unit 20 notifies the driver according to the judgment result by the driver state judgment unit 10. The notification unit 20 is connected to an output device 3 outside the control unit 4, and causes the output device 3 to output audio. When the driver state judgment unit 10 judges that the driver is in an abnormal state, the notification unit 20 checks the state of the driver as a notification. For example, this check of the state is performed by the notification unit 20 controlling the output device 3 to output a voice message saying "Are you OK?" On the other hand, when the driver state judgment unit 10 judges that the driver is in an operating state other than the abnormal state, the notification unit 20 issues a notice or warning to the driver as a notification. For example, this notice or warning is performed by the notification unit 20 controlling the output device 3 to output a voice message saying "Please face forward."

Next, an example of control in the driver monitoring system 1 will be described with reference to Figures 2 to 5.

In step S1, the preparatory movement state determination unit 11 of the control unit 4 executes the preparatory movement state determination process described above.

In step S2, the notification target state determination unit 12 of the control unit 4 executes the notification target state determination process described above.

In step S3, the abnormal state determination unit 13 of the control unit 4 executes the abnormal state determination process described above and ends this process. Note that this process repeats steps S1 to S3.

Next, the details of the preparatory movement state determination process in step S1 of FIG. 2 will be described with reference to FIG. 3.

In step S11, the preparatory movement state determination unit 11 determines whether or not the change in the driver's facial direction corresponds to a preparatory movement based on the monitoring image I. If the change in the driver's facial direction corresponds to a preparatory movement before the driver performs a predetermined movement, the preparatory movement state determination unit 11 proceeds to step S12, and if it does not correspond to a preparatory movement, the preparatory movement state determination unit 11 proceeds to step S13. For example, if the change in the driver's facial direction is a movement to "turn down and to the left", the preparatory movement state determination unit 11 proceeds to step S12, and if the driver's facial direction is "turn to the right", the preparatory movement state determination unit 11 proceeds to step S13.

In step S12, the preparatory movement state determination unit 11 changes the preparatory movement flag to "1" and returns.

In step S13, the preparatory movement state determination unit 11 determines whether the preparatory movement flag is "1" or not, and if the preparatory movement flag is "1", proceeds to step S14, and if the preparatory movement flag is "0", returns.

In step S14, the preparatory movement state determination unit 11 determines whether the elapsed time after the preparatory movement has been performed has exceeded a first threshold (e.g., 3 seconds), and if the elapsed time has exceeded the first threshold, the process proceeds to step S15, and if the elapsed time has not exceeded the first threshold, the process returns. By making the determination in step S14, if the driver does not perform a predetermined movement after the preparatory movement determination, the preparatory movement state determination unit 11 determines that the detected movement is not a preparatory movement but an independent movement. This enables the driver monitoring system 1 to accurately determine the preparatory movement state. Note that the first threshold is set to 3 seconds, but is not limited to this value.

In step S15, the preparatory movement state determination unit 11 changes the preparatory movement flag to "0" and returns.

Next, the details of the notification target state determination process in step S2 of FIG. 2 will be described with reference to FIG. 4.

In step S21, the notification target state determination unit 12 determines whether the change in the driver's face position is equal to or greater than the second threshold based on the monitoring image I. The change in the face position means, for example, the change in the inclination or position of the driver's face, as shown in FIG. 6. If the change in the driver's face position is equal to or greater than the second threshold, the notification target state determination unit 12 proceeds to step S22, and if the change in the driver's face position is less than the second threshold, the notification target state determination unit 12 returns. For example, if the change in the inclination (e.g., angle) of the driver's face is equal to or greater than the angle as the second threshold, the notification target state determination unit 12 proceeds to step S22, and if the change in the driver's face position is less than the angle as the second threshold, the notification target state determination unit 12 returns. Alternatively, if the change in the position of the driver's face (e.g., coordinates in the monitoring image I) is equal to or greater than the distance as the second threshold, the notification target state determination unit 12 proceeds to step S22, and if the change in the position of the driver's face is less than the distance as the second threshold, the notification target state determination unit 12 returns. In this embodiment, the notification target state determination unit 12 makes a determination using two parameters, the amount of change in the driver's face tilt and the amount of change in the face position, but it may use only one of these parameters or both.

In step S22, the notification target state determination unit 12 determines whether the elapsed time after the amount of change in the driver's face position became equal to or greater than the second threshold has exceeded a third threshold (e.g., 2 seconds) that is different from the second threshold. If the elapsed time exceeds the third threshold, the process proceeds to step S23. If the elapsed time does not exceed the third threshold, the process returns. By making the determination in step S22, the notification target state determination unit 12 determines whether the inclination and position of the driver's face are continuously changing. This enables the driver monitoring system 1 to accurately determine the notification target state. Note that the third threshold is set to 2 seconds, but is not limited to this value.

In step S23, the notification target state determination unit 12 changes the abnormality flag to "1" and proceeds to step S24.

In step S24, the notification target state determination unit 12 determines whether the preparatory movement flag is "1" or not, and if the preparatory movement flag is "1", the process proceeds to step S25, and if the preparatory movement flag is "0", the process returns.

In step S25, the notification target state determination unit 12 determines whether or not the "driver has fallen to the left side" based on the monitoring image I. If it determines that the driver has fallen to the left side, it proceeds to step S26, and if it determines that the driver has not fallen to the left side, it returns. By making the determination in step S25, the notification target state determination unit 12 determines whether or not the driver has fallen to the left side to pick up luggage on the passenger seat. This enables the driver monitoring system 1 to accurately determine the notification target state.

In step S26, the notification target state determination unit 12 changes the abnormality flag to "0" and returns.

Next, the abnormal state determination process in step S2 of FIG. 2 will be described in detail with reference to FIG. 5.

In step S31, the abnormal state determination unit 13 determines whether the driver is in a state that should be notified by determining whether the abnormal flag is "1". That is, if the abnormal state flag is "1", the abnormal state determination unit 13 determines that the driver is in a state that should be notified and proceeds to step S32, and if the abnormality flag is not "1", the abnormal state determination unit 13 determines that the driver is not in a state that should be notified and proceeds to step S33.

In step S32, the abnormal state determination unit 13 determines whether the driver has performed a preparatory movement by determining whether the preparatory movement flag is "1". That is, if the preparatory movement flag is "1", the abnormal state determination unit 13 determines that the driver has performed a preparatory movement and proceeds to step S33, whereas if the preparatory movement flag is not "1", the abnormal state determination unit 13 determines that the driver has not performed a preparatory movement and proceeds to step S35. In this way, by executing steps S31 and S32, the abnormal state determination unit 13 determines whether the driver is in an abnormal state based on the determination result of whether the driver has performed a preparatory movement and the determination result of whether the driver is in a state to be notified.

In step S33, the abnormal state determination unit 13 determines that the driver is in a normal state and proceeds to step S34.

In step S34, since the driver state determination unit 10 has determined that the driver is in an operating state other than an abnormal state, the notification unit 20 issues a notice to the driver, such as a caution or warning, and then returns.

In step S35, the abnormal state determination unit 13 determines that the driver is in an abnormal state and proceeds to step S36.

In step S35, since the driver state determination unit 10 has determined that the driver is in an abnormal state, the notification unit 20 notifies the driver by checking the driver's state and then returns.

The driver monitoring system 1 described above includes a driver state determination unit 10 that determines the state of the driver based on the monitoring image I acquired by the camera 2. The driver state determination unit 10 performs a process of determining whether or not the driver has performed a preparatory movement based on a change in the direction of the driver's face in the monitoring image I. The driver state determination unit 10 also performs a process of determining whether or not the driver is in a state that should be notified based on the amount of change in the position of the driver's face in the monitoring image I. The driver state determination unit 10 then performs a process of determining whether or not the driver is in an abnormal state based on the determination result of whether or not the driver has performed a preparatory movement and the determination result of whether or not the driver is in a state that should be notified.

With the above configuration, the driver monitoring system 1 of this embodiment performs a process of determining whether the driver is in a state that should be notified, as well as a process of determining whether the driver has performed a preparatory action before performing a predetermined action. This makes it possible for the driver monitoring system 1 to take into consideration, for example, whether the driver has performed an action such as picking up luggage on the passenger seat, even if it determines that the driver is in a state that should be notified that is different from a normal state. As a result, the driver monitoring system 1 can improve the accuracy of determining whether the driver is in an abnormal state.

In addition, the driver monitoring system 1 described above determines that the driver is in an abnormal state when the driver state determination unit 10 determines that the driver is not performing a preparatory movement and determines that the driver is in a state that requires notification. Then, when the driver state determination unit 10 determines that the driver is in an abnormal state, the notification unit 20 performs a state check with the driver as a notification. This allows the driver monitoring system 1 to further improve the accuracy of determining whether the driver is in an abnormal state or not. In addition, by performing a state check with the driver, the driver monitoring system 1 is able to take appropriate action against a driver who is no longer able to maintain a normal state while driving. As a result, the driver monitoring system 1 can provide a higher level of safety to the driver.

In addition, the driver monitoring system 1 described above determines that the driver is in an operating state other than the abnormal state when the driver state determination unit 10 determines that the driver has performed a preparatory movement and that the driver is in a state to be notified. Then, when the driver state determination unit 10 determines that the driver is in an operating state other than the abnormal state, the notification unit 20 issues a notice to the driver, such as a warning or caution. This allows the driver monitoring system 1 to further improve the accuracy of determining whether the driver is in an abnormal state. In addition, by issuing a notice or warning to the driver, the driver monitoring system 1 can issue an appropriate warning or caution to a driver who performs an action that interferes with normal driving (for example, an action of picking up luggage from the passenger seat). As a result, the driver monitoring system 1 can provide a higher level of safety to the driver.

In the above embodiment, the preparatory movement state determination unit 11 may detect, for example, a preparatory movement when the driver "turns alternately to the lower left and right" to check for safety after temporarily stopping the vehicle in front of an intersection. As a modification of the above embodiment, the control unit 4 may be configured to acquire vehicle speed information, brake operation information, and the like from an ECU in the vehicle. In this case, even if a preparatory movement is detected in response to the driver's "turning alternately to the lower left and right" movement, the preparatory movement state determination unit 11 changes the "preparatory movement flag = 1" to the "preparatory movement flag = 0" if the vehicle speed information is "vehicle speed = 0 km/h". This enables the driver monitoring system 1 to more accurately perform the preparatory movement determination of the driver by the preparatory movement state determination unit 11.

In the above embodiment, in step S25 of FIG. 4, the notification target state determination unit 12 determines whether or not the "driver has fallen sideways to the left" based on the monitoring image I, but this is not limited to this. For example, if the driver is trying to remove an object from a door pocket, the preparatory movement is the driver's face direction or the driver's line of sight "looking down" or "looking down and to the right", and the determination criterion for step S25 is "the driver has fallen sideways to the right".

In the above embodiment, the output device 3 is described as a speaker that outputs sound and is provided in the vehicle, but is not limited to this. For example, the output device 3 is a visual information display device that outputs visual information (graphical information, textual information), and may be configured, for example, with a thin liquid crystal display, plasma display, organic EL display, etc., or may have both sound output and image output.

REFERENCE SIGNS LIST 1 Driver monitoring system 2 Camera 3 Output device 4 Control unit 10 Driver state determination unit 11 Preparatory movement state determination unit 12 Notification target state determination unit 13 Abnormal state determination unit 20 Notification unit

Claims (3)

a driver state determination unit that determines a state of a driver of a vehicle based on a monitor image including an image of the face of the driver;
A notification unit that notifies the driver in response to a determination result by the driver state determination unit,
The driver state determination unit is
A process of determining whether or not the driver is performing a preparatory movement before performing a predetermined movement based on a change in a facial direction of the driver in the monitoring image;
A process of determining whether the driver is in a notification target state different from a normal state based on an amount of change in a face position of the driver in the monitoring image; and
a driver monitoring system capable of executing a process for determining whether or not the driver is in an abnormal state based on a determination result of whether or not the driver is in a state to be notified, and a determination result of whether or not the driver is in the state to be notified. The driver state determination unit is
When it is determined that the driver is not in the state of performing the preparatory movement and the driver is in the state to be notified, it is determined that the driver is in an abnormal state;
The notification unit is
The driver monitoring system according to claim 1 , wherein, when the driver state determination unit determines that the driver is in an abnormal state, the notification is made by confirming the state of the driver. The driver state determination unit is
When it is determined that the driver is in the state of having performed the preparatory movement and that the driver is in the state to be notified, it is determined that the driver is in an operating state other than an abnormal state;
The notification unit is
The driver monitoring system according to claim 1 , wherein, when the driver state determination unit determines that the driver is in an operating state other than an abnormal state, the notification is to issue a caution or a warning to the driver.

Images