JP2020194228A - Driver state determination device, driver state determination method, and program - Google Patents

Abstract

To obtain relation between a vehicle travel direction and a face direction of a driver even on a curved road.SOLUTION: A driver state determination device (10) successively acquires a direction of a driver in a predetermined period, successively acquires a vehicle travel direction, repetitively calculates a correlation coefficient indicating a degree of correlation between the direction of the driver and the vehicle travel direction, repetitively calculates a difference between the direction of the driver and the vehicle travel direction as a correction value in the predetermined period, and determines whether a difference is to be calculated according to the correlation coefficient.SELECTED DRAWING: Figure 1

Description

The present invention relates to a driver state determination device, a driver state determination method, and a program.

The DMS (Driver Monitoring System) is a system that monitors the driver's attention, consciousness, health condition, etc. by using a camera or other sensor installed in the vehicle. In DMS, for example, it is necessary to capture the driver's face orientation in order to detect the driver's inattentiveness. However, there are individual differences in the face orientation of the vehicle driver. Further, even when the vehicle is traveling on a straight road, the driver does not always look directly in front of the vehicle. Therefore, in order to improve the accuracy of the inattentive judgment, the DMS needs to learn the relationship between the traveling direction of the vehicle and the face orientation of the driver in order to perform the inattentive judgment using the face orientation with respect to the front of each driver. There is.

JP-A-2010-257293

In the learning method assuming straight driving, if there are not many straight roads between the start and the start of automatic driving (for example, between the departure from the parking area and the confluence of the main line), sufficient learning opportunities cannot be obtained. There is a problem. As such, in a state where learning is insufficient, it is necessary to limit driving by a system such as automatic driving.

Note that Patent Document 1 discloses a driver condition monitoring device that prevents a driver monitor camera from erroneously determining that the driver is looking aside and giving an alarm even when the driver looks ahead of a curved road to confirm safety. There is. However, the technique of Patent Document 1 does not solve the above problem.

One aspect of the present invention is to grasp the relationship between the traveling direction of the vehicle and the face orientation of the driver even on a curved road.

In order to solve the above problems, the driver state determination device according to one aspect of the present invention includes a driver information acquisition unit that sequentially acquires the direction of the driver in a predetermined period, and the driver in the predetermined period. A correlation coefficient that repeatedly calculates a correlation coefficient indicating the degree of correlation between the direction of the driver and the traveling direction of the vehicle in the predetermined period with the vehicle information acquisition unit that sequentially acquires the traveling direction of the vehicle driven by the vehicle. The calculation unit includes a calculation unit and a correction value calculation unit that repeatedly calculates the difference between the direction of the driver and the traveling direction of the vehicle as a correction value in the predetermined period, and the correction value calculation unit includes the correlation coefficient. Whether or not to calculate the difference is determined accordingly.

According to the above configuration, the direction of the driver and the traveling direction of the vehicle are sequentially acquired without assuming straight-line driving, and the difference between them is repeatedly calculated. Therefore, even on a curved road, the traveling direction of the vehicle , It is possible to grasp the relationship with the direction of the driver. Further, since it is determined whether or not to calculate the difference according to the correlation coefficient, an effective correction value can be obtained. The direction of the driver is the direction of the driver's face or the direction of the driver's line of sight.

In the driver state determination device according to one aspect of the present invention, in the first aspect, the correction value calculation unit changes the direction of the driver and the traveling direction of the vehicle according to the correlation coefficient. You may calculate the difference with.

In the driver state determination device according to one aspect of the present invention, the correction value calculation unit may calculate the difference when the correlation coefficient is equal to or greater than a predetermined value.

According to the above configuration, since the difference is calculated when the correlation coefficient is equal to or more than a predetermined value, the difference is not calculated when the degree of correlation between the direction of the driver and the traveling direction of the vehicle is weak, so that an effective correction is made. You can get the value.

The driver state determination device according to one aspect of the present invention further includes a driver state determination unit that determines the state of the driver using the direction of the driver and the traveling direction of the vehicle, and the correction value. The calculation unit may not accumulate the correction value when the driver state determination unit determines that the driver is performing an operation of looking around.

The orientation of the driver looking around is not appropriate to define the front of the driver while driving. According to the above configuration, it is possible to prevent the accumulation of correction values using such a driver's orientation. The operation of the driver looking at the surroundings includes an operation of checking the surroundings, an operation of looking aside, and the like.

In the driver state determination device according to one aspect of the present invention, the vehicle information acquisition unit may acquire the traveling direction of the vehicle estimated by using the speed and steering information of the vehicle.

In the driver state determination device according to one aspect of the present invention, the vehicle information acquisition unit may acquire the traveling direction of the vehicle estimated using the speed and yaw rate of the vehicle.

In the driver state determination device according to one aspect of the present invention, the vehicle information acquisition unit may acquire the traveling direction of the vehicle estimated by using the rotation speed of each wheel of the vehicle.

The driver state determination device according to one aspect of the present invention is used when the correction value defines the front surface of the driver after the elapse of the predetermined period and corrects the face orientation output by the face recognition algorithm. It may be that.

According to the above configuration, the face orientation of the driver can be appropriately corrected by using the relationship between the traveling direction of the vehicle and the orientation of the driver.

The driver state determination method according to one aspect of the present invention is a driver state determination method executed by a driver state determination device that determines the state of the driver of a vehicle, and sequentially directs the driver in a predetermined period. The driver information acquisition step to be acquired, the vehicle information acquisition step for sequentially acquiring the traveling direction of the vehicle driven by the driver in the predetermined period, and the direction of the driver and the traveling direction of the vehicle in the predetermined period. The correlation coefficient calculation step for repeatedly calculating the correlation coefficient indicating the degree of correlation with the driver and the correction value calculation for repeatedly calculating the difference between the direction of the driver and the traveling direction of the vehicle as a correction value in the predetermined period. In the correction value calculation step, it is determined whether or not to calculate the difference according to the correlation coefficient.

According to the above configuration, since the traveling direction of the vehicle is sequentially acquired without assuming straight driving, it is possible to grasp the relationship between the traveling direction of the vehicle and the direction of the driver even on a curved road. it can. Further, since it is determined whether or not to calculate the difference according to the correlation coefficient, an effective correction value can be obtained.

The program according to one aspect of the present invention is a program for operating a computer as the driver state determination device, and is a driver information acquisition unit, a vehicle information acquisition unit, a correlation coefficient calculation unit, and a program. This is a program for operating a computer as the correction value calculation unit.

According to one aspect of the present invention, it is possible to grasp the relationship between the traveling direction of the vehicle and the face orientation of the driver even on a curved road.

It is a block diagram which shows an example of the structure of the driver state determination apparatus which concerns on embodiment of this invention. It is a block diagram which shows an example of the whole structure of the driver state determination system which concerns on embodiment of this invention. It is a flowchart which shows the whole processing of the driver state determination apparatus which concerns on embodiment of this invention. It is a flowchart which shows the accumulation process of the acquisition information of the driver state determination apparatus which concerns on embodiment of this invention. It is a flowchart which shows the calculation process of the statistical value of the driver state determination apparatus which concerns on embodiment of this invention. It is a figure which shows the example of the method of measuring the traveling direction of the vehicle which concerns on embodiment of this invention.

[Embodiment]
Hereinafter, embodiments of the present invention will be described in detail.

(Configuration of driver condition determination device 10)
FIG. 1 is a block diagram showing an example of the configuration of the driver state determination device 10 according to the present embodiment. FIG. 1 is a block diagram centered on a feature portion of the present invention. As shown in FIG. 1, the driver state determination device 10 includes a monitoring data acquisition unit (driver information acquisition unit) 11, a vehicle information acquisition unit 12, and an acquisition information processing unit (correlation coefficient calculation unit, correction value calculation). Section 13), a statistical calculation section 14, a driver state determination section 15, a face orientation correction section 16, and a statistical storage section 17.

The monitoring data acquisition unit 11 acquires driver information from a driver monitoring sensor 21 that detects the behavior of the driver and is installed at a predetermined position in the vehicle for the driver. For example, the driver monitoring sensor 21 is installed at a place where the driver's face can be imaged, and is arranged on the dashboard, the center of the steering wheel, the side of the speedometer, the front pillar, or the like, and the upper body including the driver's face is placed. It is a camera that captures images. This camera may be a still camera that captures a plurality of still images of the driver per second, or may be a video camera that captures a moving image of the driver. The monitoring data acquisition unit 11 digitizes the image signal from the camera and captures it as driver information including the driver's image. The monitoring data acquisition unit 11 passes the captured driver information to the acquisition information processing unit 13.

The vehicle information acquisition unit 12 acquires vehicle information indicating the state of the vehicle from the vehicle state sensors 22 arranged at each predetermined position of the vehicle. The vehicle condition sensor 22 is a sensor that detects the speed of the vehicle, steering information, yaw rate, rotational speed of each wheel, and the like. The vehicle information acquisition unit 12 digitizes the detection information detected by the vehicle state sensor 22 and captures it as vehicle information indicating the state of the vehicle. The vehicle information acquisition unit 12 passes the captured vehicle information to the acquisition information processing unit 13.

The acquisition information processing unit 13 acquires driver information from the monitoring data acquisition unit 11, acquires vehicle information from the vehicle information acquisition unit 12, refers to the acquired driver information and vehicle information, and outputs a face recognition algorithm. Calculate the correction value used to correct the face orientation. Further, the acquisition information processing unit 13 has, as storage media, a non-volatile memory such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) that can be written and read at any time, and a volatile memory such as a RAM. The acquisition information processing unit 13 stores the calculated correction value in the storage medium.

The statistical calculation unit 14 sets the average value and deviation amount of the holding direction (correction value), which is the direction in which the driver holds the face or the line of sight as the front, with respect to the traveling direction of the vehicle within the predetermined time every predetermined time. Calculate the statistical information of. The statistical information calculated at each predetermined time is updated and stored in the statistical storage unit 17 as will be described later. That is, statistical information is learned. The predetermined time is, for example, several seconds (X seconds).

The driver state determination unit 15 determines the degree of deviation from the reference direction of the driver's face, or the degree of deviation from the reference direction of the driver's face determined by the statistical calculation unit 14, and the acquisition information processing unit 13. Based on the vehicle information stored in the recording medium of the above, the driver's state, for example, the state during the lane confirmation operation, the inattentive state, and the like are determined.

The face orientation correction unit 16 corrects the driver's face orientation with reference to the statistical values stored in the statistical storage unit 17.

(Configuration of driver status judgment system)
FIG. 2 is a block diagram showing an example of the overall configuration of the driver state determination system including the driver state determination device 10 according to the present embodiment.

The driver state determination system includes a driver state determination device 10 according to the present embodiment, various sensors 41 to 46, and a determination result output device 50.

In the present embodiment, as the sensors, for example, a driver camera 41 which is a driver monitoring sensor and a vehicle speed sensor 42, a steering sensor 43, a winker sensor 44, a gear selector sensor 45 and a parking brake sensor 46 which are vehicle condition sensors are used. Including. Of course, this is just an example and may include other sensors.

The driver camera 41 is installed at a place where the driver's face can be imaged. For example, the driver camera 41 is arranged on the dashboard, the center of the steering wheel, the side of the speedometer, the front pillar, etc., and is a camera that images the upper body including the driver's face. is there. The driver camera 41 may be a still camera that captures a plurality of still images per second, or may be a video camera that captures a moving image.

The vehicle speed sensor 42 detects the moving speed of the vehicle. The steering sensor 43 detects the steering angle of the steering. The steering sensor 43 may be a sensor that detects the steering operation itself by the driver, or may be a sensor that detects the steering angle of the wheel whose direction can be changed by the steering operation. The winker sensor 44 detects the operation of the winker. The winker sensor 44 may be a sensor that detects the operation of the winker lever by the driver itself, or may be a sensor that detects a blinking control signal of the winker that blinks in response to the winker lever operation.

Further, the gear selector sensor 45 detects the parking position of the gear selector in the automatic gear vehicle. The gear selector sensor 45 may be a sensor that detects the gear selector selection operation itself by the driver, or may be a sensor that detects a lighting control signal of an indicator that displays the selected position. The parking brake sensor 46 detects the state of the parking brake. The parking brake sensor 46 may be a sensor that detects the operation of the parking brake lever itself by the driver, or may be a sensor that detects a drive control signal that drives the parking brake. Both the gear selector sensor 45 and the parking brake sensor 46 do not necessarily have to be provided. For example, in a vehicle equipped with an automatic gear, the parking brake sensor 46 may not be provided and only the gear selector sensor 45 may be provided. In a vehicle equipped with a manual gear, only the parking brake sensor 46 may be used.

The driver state determination device 10 includes a control unit 32 and an input / output interface unit 31.
And a storage unit 33.

The input / output interface unit 31 receives the image signal output from the driver camera 41, converts it into digital data, and inputs it to the control unit 32. The input / output interface unit 31 also receives sensing data of each of the vehicle speed sensor 42, the steering sensor 43, the winker sensor 44, the gear selector sensor 45, and the parking brake sensor 46, and inputs them to the control unit 32. The input / output interface unit 31 further converts the driver state determination result information output from the control unit 32 into an output control signal and outputs the information to the determination result output device 50.

The storage unit 33 uses, for example, a non-volatile memory such as an SSD or an HDD that can be written and read at any time and a volatile memory such as a RAM as a storage medium. The storage unit 33 includes a monitoring data storage unit 331 that stores the driver's monitoring data, a vehicle information storage unit 332 that stores the state of the vehicle, and statistical information as a storage area used for carrying out the present embodiment. It includes a learning data storage unit 333 that stores a learning result including the number of times of learning as learning data.

(Processing of driver state determination device 10)
FIG. 3 is a flowchart showing the overall processing of the driver state determination device 10 according to the present embodiment.

(Step S301: Driver information acquisition step)
In the driver state determination device 10, the monitoring data acquisition unit (driver information acquisition unit) 11 sequentially acquires the driver's face orientation from the driver monitoring sensor 21 in a predetermined period, and acquires the face orientation. Information processing unit Hand over to 13. The predetermined period is the period from the start of the vehicle to the start of automatic driving (for example, from the time when the vehicle departs from the parking area until it joins the main line of the expressway).

(Step S302: Vehicle information acquisition step)
In parallel with the process of step S301, the vehicle information acquisition unit 12 sequentially acquires vehicle information (traveling direction of the vehicle driven by the driver) from the vehicle state sensor 22 in a predetermined period, and acquires and processes the vehicle information. Hand over to department 13.

(Step S303)
The acquisition information processing unit 13 accumulates correction values calculated from the driver's face direction and the traveling direction of the vehicle in a predetermined period. Details will be described with reference to FIG.

(Step S304)
The statistical calculation unit 14 refers to the correction value accumulated in the acquisition information processing unit 13, calculates a statistical value for individual difference correction, and stores the calculated statistical value in the statistical storage unit 17. Details will be described with reference to FIG.

(Step S305)
The face orientation correction unit 16 defines the front surface of the driver using the statistical values stored in the statistical storage unit 17, and corrects the face orientation output by the face recognition algorithm. The corrected face orientation is separately used in the determination of inattentiveness.

FIG. 4 is a flowchart showing a process of accumulating the acquired information of the driver state determination device 10 according to the present embodiment. This process is a refinement of the process of step S303 of FIG. This process is performed for each combination of the face information acquired in step S301 and the vehicle information acquired in step S302.

When the acquisition information processing unit 13 detects the driver's face from the face information acquired from the monitoring data acquisition unit 11, the acquisition information processing unit 13 validates the driver's face orientation among the face information.

Further, when the acquisition information processing unit 13 has already calculated the traveling direction of the vehicle and there is data in which the yaw direction of the face is valid, the yaw direction of the face and the traveling of the vehicle in the last 8.0 seconds. Calculate the correlation coefficient with the direction. Note that 8.0 seconds is an example and may be another number of seconds.

(Step S401)
In the driver state determination device 10, the acquisition information processing unit 13 determines whether or not the speed of the vehicle is 20 km / h or more with reference to the vehicle information. When the speed of the vehicle is 20 km / h or more (YES in step S401), the acquisition information processing unit 13 executes the determination in step S402. When the speed of the vehicle is not 20 km / h or more (less than 20 km / h) (NO in step S401), the acquisition information processing unit 13 ends the process. That is, the correction values based on the driver's face orientation and the traveling direction of the vehicle are not accumulated (hereinafter, the same applies). This is because the driver's face orientation during slow-moving changes greatly and is treated as a face orientation that should not be learned. Note that 20 km / h is an example and may be another speed.

(Step S402)
The acquisition information processing unit 13 determines whether or not the driver is in the lane confirmation operation.

Specifically, the acquisition information processing unit 13 outputs face information and vehicle information to the driver state determination unit 15, and acquires a determination result from the driver state determination unit 15. The driver state determination unit 15 acquires face information and vehicle information from the acquisition information processing unit 13, determines the driver's state using the driver's face orientation and the traveling direction of the vehicle, and determines the determination result. Is output to the acquisition information processing unit 13.

When the driver is in the lane confirmation operation (it is determined that the driver is performing the operation of looking around) (YES in step S402), the acquisition information processing unit 13 ends the process (that is, the correction value). Does not accumulate). When the driver is not in the lane confirmation operation (NO in step S402), the acquisition information processing unit 13 executes the determination in step S403.

(Step S403: Correlation coefficient calculation step)
The acquisition information processing unit 13 refers to the face information and the vehicle information, and determines whether or not there is a strong correlation between the yaw direction of the face and the traveling direction of the vehicle. The acquisition information processing unit (correlation coefficient calculation unit) 13 repeatedly calculates the correlation coefficient indicating the degree of correlation between the driver's face direction and the traveling direction of the vehicle in a predetermined period. Then, the acquisition information processing unit 13 determines that the correlation is strong, for example, if the correlation coefficient is 0.6 or more. Note that 0.6 is an example and may be another threshold value.

When the correlation is strong (the correlation coefficient is equal to or greater than a predetermined value) (YES in step S403), the acquisition information processing unit 13 executes the process of step S404. If the correlation is not strong (NO in step S403), the acquisition information processing unit 13 executes the determination in step S405. That is, the acquisition information processing unit 13 determines whether or not to calculate the difference according to the correlation coefficient.

(Step S404)
The acquisition information processing unit (correction value calculation unit) 13 repeatedly calculates the difference between the yaw direction of the face and the traveling direction of the vehicle as a correction value. That is, "correction value (degree) = yaw direction of face (degree) -vehicle traveling direction (degree)". The acquisition information processing unit 13 may calculate the difference between the driver's face orientation and the direction in which the traveling direction of the vehicle is changed according to the correlation coefficient. For example, the acquisition information processing unit 13 calculates "corrected face orientation (degrees) = face orientation (degrees) -correlation coefficient x traveling direction (degrees)".

The yaw direction of the face and the traveling direction of the vehicle are represented by angles with respect to the reference direction. The correction value is the difference between the two angles. The correction value is used to define the front of the driver after a lapse of a predetermined period and to correct the face orientation output by the face recognition algorithm.

(Step S405)
The acquisition information processing unit 13 determines whether or not the yaw direction of the face, the correction value calculated in step S404, and the pitch direction of the face are within a specified value (for example, between ± 20 degrees). .. When the yaw direction or correction value of the face and the pitch direction of the face are within the specified values (YES in step S405), the acquisition information processing unit 13 executes the process of step S406. When the yaw direction or correction value of the face and the pitch direction of the face are not within the specified values (NO in step S405), the acquisition information processing unit 13 ends the process. In addition to the yaw direction or correction value of the face and the pitch direction of the face, the acquisition information processing unit 13 may further determine whether or not the roll direction of the face is within the specified value.

(Step S406)
The acquisition information processing unit 13 stores the yaw direction of the face, the correction value calculated in step S404, and the pitch direction of the face in the storage medium for learning. In addition to the yaw direction or correction value of the face and the pitch direction of the face, the acquisition information processing unit 13 may further store the roll direction of the face in the recording medium.

FIG. 5 is a flowchart showing a calculation process of statistical values of the driver state determination device 10 according to the present embodiment. This process is a refinement of the process of step S304 in FIG.

(Step S501)
The statistical calculation unit 14 determines whether or not the correction value has been accumulated in the acquisition information processing unit 13 for a predetermined time or longer. When the correction value is accumulated for a predetermined time or more (YES in step S501), the statistical calculation unit 14 executes the process of step S502. When the correction value is not accumulated for a predetermined time or more (NO in step S501), the statistical calculation unit 14 ends the process.

(Step S502)
The statistical calculation unit 14 calculates an average value of correction values for learning, and stores the average value as a statistical value in the statistical storage unit 17. The statistical calculation unit 14 may calculate a statistical value such as a standard deviation of the corrected value instead of the average value of the corrected value, and store the calculated statistical value in the statistical storage unit 17.

(Example of measuring method of vehicle traveling direction)
FIG. 6 is a diagram showing an example of a method of measuring the traveling direction of the vehicle according to the present embodiment.

In the driver state determination device 10, the acquisition information processing unit 13 obtains the driver's gaze direction. The driver's gaze direction can be obtained by using the following equation 1.

図６に示すように、車両が位置ｘ_１から位置ｘ_２に移動した場合、例えば、車両のヨーがφだけ変化したときに、運転者の注視方向は、θ（＝１／２φ）になる。この運転者の注視方向は、車両の進行方向に用いることができる。

As shown in FIG. 6, when the vehicle moves from the position x ₁ to the position x ₂ , for example, when the yaw of the vehicle changes by φ, the gaze direction of the driver becomes θ (= 1 / 2φ). .. This driver's gaze direction can be used in the traveling direction of the vehicle.

The vehicle information acquisition unit 12 may acquire the traveling direction of the vehicle estimated by using the speed and steering information of the vehicle. The vehicle information acquisition unit 12 may acquire the traveling direction of the vehicle estimated using the speed and yaw rate of the vehicle. The vehicle information acquisition unit 12 may acquire the traveling direction of the vehicle estimated by using the rotation speed of each wheel of the vehicle. In these cases, the acquisition information processing unit 13 acquires the traveling direction of the vehicle from the vehicle information acquisition unit 12.

Further, in the present embodiment, the case of acquiring and processing the driver's face orientation has been described, but the present embodiment also describes the case of acquiring and processing the driver's line-of-sight direction instead of the driver's face orientation. The form is applicable.

[Example of realization by software]
The control block of the driver state determination device 10 may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be realized by software.

In the latter case, the driver state determination device 10 includes a computer that executes a program instruction, which is software that realizes each function. The computer includes, for example, one or more processors and a computer-readable recording medium that stores the program. Then, in the computer, the processor reads the program from the recording medium and executes it, thereby achieving the object of the present invention. As the processor, for example, a CPU (Central Processing Unit) can be used. As the recording medium, in addition to a "non-temporary tangible medium" such as a ROM (Read Only Memory), a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. Further, a RAM (Random Access Memory) for expanding the above program may be further provided. Further, the program may be supplied to the computer via an arbitrary transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. One aspect of the present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission.

[Additional notes]
The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims, and the embodiments obtained by appropriately combining the technical means disclosed in the different embodiments. Is also included in the technical scope of the present invention.

10 Driver status determination device 11 Monitoring data acquisition unit (driver information acquisition unit)
12 Vehicle information acquisition unit 13 Acquisition information processing unit (correlation coefficient calculation unit, correction value calculation unit)
15 Driver status judgment unit

Claims (10)

The driver information acquisition unit that sequentially acquires the direction of the driver in a predetermined period,
A vehicle information acquisition unit that sequentially acquires the traveling direction of the vehicle driven by the driver in the predetermined period,
A correlation coefficient calculation unit that repeatedly calculates a correlation coefficient indicating the degree of correlation between the direction of the driver and the direction of travel of the vehicle during the predetermined period.
A correction value calculation unit that repeatedly calculates the difference between the direction of the driver and the traveling direction of the vehicle as a correction value in the predetermined period.
With
The driver state determination device is characterized in that the correction value calculation unit determines whether or not to calculate the difference according to the correlation coefficient. The driver according to claim 1, wherein the correction value calculation unit calculates a difference between the direction of the driver and the direction in which the traveling direction of the vehicle is changed according to the correlation coefficient. Status judgment device. The driver state determination device according to claim 2, wherein the correction value calculation unit calculates the difference when the correlation coefficient is equal to or greater than a predetermined value. Further provided with a driver state determination unit that determines the state of the driver using the direction of the driver and the traveling direction of the vehicle.
The correction value calculation unit is characterized in that, when the driver state determination unit determines that the driver is performing an operation of looking at the surroundings, the correction value calculation unit does not accumulate the correction value. The driver condition determination device according to any one item. The driver state according to any one of claims 1 to 4, wherein the vehicle information acquisition unit acquires the traveling direction of the vehicle estimated by using the speed and steering information of the vehicle. Judgment device. The driver state determination according to any one of claims 1 to 4, wherein the vehicle information acquisition unit acquires the traveling direction of the vehicle estimated using the speed and yaw rate of the vehicle. apparatus. The driver according to any one of claims 1 to 4, wherein the vehicle information acquisition unit acquires the traveling direction of the vehicle estimated by using the rotation speed of each wheel of the vehicle. Status judgment device. Any one of claims 1 to 7, wherein the correction value is used when the front surface of the driver is defined after the elapse of the predetermined period and the face orientation output by the face recognition algorithm is corrected. The driver condition determination device according to the section. It is a driver state determination method executed by a driver state determination device that determines the state of the driver of a vehicle.
A driver information acquisition step for sequentially acquiring the driver's orientation in a predetermined period,
A vehicle information acquisition step for sequentially acquiring the traveling direction of a vehicle driven by the driver in the predetermined period,
A correlation coefficient calculation step of repeatedly calculating a correlation coefficient indicating the degree of correlation between the direction of the driver and the traveling direction of the vehicle in the predetermined period.
A correction value calculation step of repeatedly calculating the difference between the direction of the driver and the traveling direction of the vehicle as a correction value in the predetermined period.
Includes
A driver state determination method, characterized in that, in the correction value calculation step, it is determined whether or not to calculate the difference according to the correlation coefficient. The program for operating a computer as the driver state determination device according to claim 1, wherein the driver information acquisition unit, the vehicle information acquisition unit, the correlation coefficient calculation unit, and the correction value calculation unit. A program to make your computer work as.

Images