Driver State Estimation Device

Abstract

To detect as early as possible a sign that a driver driving a mobile body falls into a driving disabled state.SOLUTION: A driver state estimating device is equipped with a head portion behavior detecting portion that detects a behavior of a head portion of a driver by using a sensor, and a detecting portion that detects an abnormality sign of the driver. The detecting portion computes a periodic feature quantity with respect to time-sequence data indicating the head behavior of the driver, and computes a time-sequence fluctuation pattern with respect to the periodic feature quantity obtained by the computing. The time-sequence fluctuation pattern obtained by the computing is compared with a specified pattern computed in advance, thereby detecting the presence / absence of the abnormality sign of the driver. The specified pattern is the time-sequence fluctuation pattern computed from the head portion behavior of the driver in a specified period including a time when the driver is in an abnormality sign state.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The technology disclosed herein belongs to the technical field related to a driver state estimation device that estimates the state of a driver who drives a mobile object. [Background technology]

[0002] Recently, the development of automated driving systems has been promoted nationwide. The applicant of this application believes that, at present, there are two main directions for automated driving systems.

[0003] The first direction is a system in which the car takes the initiative and transports passengers to their destination without the need for driver operation, known as fully automated driving. On the other hand, the second direction is an automated driving system that assumes that a human will still be driving the car, for example, for the enjoyment of driving.

[0004] In the second direction of automated driving systems, it is assumed that the vehicle will automatically take over from the driver and continue driving automatically when, for example, the driver develops an illness or other condition that makes normal driving difficult. For this reason, from the perspective of improving the driver's survival rate and ensuring the safety of those around the vehicle, it is extremely important to be able to detect driver abnormalities, particularly functional disorders or illnesses, as early and accurately as possible.

[0005] Patent Document 1 discloses a state detection device that detects a driver's inability to drive based on the amount of shaking of the driver's head, or detects a driver's inability to drive based on the degree to which the driver's eyes are white. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent No. 6361312 [Non-patent literature]

[0007] [Non-Patent Document 1] T. Nakamura, et al., “Multiscale Analysis of Intensive Longitudinal Biomedical Signals and its Clinical Applications”, Proceedings of the IEEE, Institute of Electrical and Electronics Engineers, 2016, vol.104, pp.242-261 [Non-Patent Document 2] Mizuta et al., "Fractal Analysis of Center of Gravity Sway," Equilibrium Research, Japan Society of Equilibrium Medicine, 2016, Vol. 75(3), pp. 154-161 Summary of the Invention [Problem to be solved by the invention]

[0008] As shown in Patent Documents 1 and 2, a technique for determining whether a driver is unable to drive or has an abnormality based on the movement of the driver's head and the state of the driver's eyes is already known. However, Patent Document 1 can detect a decrease in concentration and physical fatigue, but cannot predict in advance the illness that the driver is suffering from. Patent Document 2 detects a state in which the driver is unable to drive after the illness has appeared. When an abnormality occurs in the driver, in order to perform an emergency stop or the like more safely, it is preferable to quickly detect the signs before the driver becomes unable to drive.

[0009] The technology disclosed herein has been made in consideration of the above points, and its purpose is to detect, as early as possible, a sign that a driver operating a mobile object is becoming unable to drive. [Means for solving the problem]

[0010] In order to solve the above problems, the technology disclosed herein is directed to a driver state estimation device that estimates the state of a driver driving a moving object, and includes a head behavior detection unit that uses a sensor to detect the behavior of the driver's head, and a detection unit that detects signs of abnormality in the driver from the head behavior detected by the head behavior detection unit, and the detection unit is configured to calculate a periodic feature amount for time series data indicating the driver's head behavior, calculate a time series variation pattern for the periodic feature amount obtained by the calculation, and compare the time series variation pattern obtained by the calculation with a specific pattern calculated in advance to detect the presence or absence of signs of abnormality in the driver, wherein the specific pattern is a time series variation pattern calculated from the head behavior of the driver in a specific period including a time when the driver is in an abnormality sign state.

[0011] The inventors of the present application have focused on the homeostatic function of humans and have estimated the driver's abnormal sign from the periodic behavior of the head when transitioning from a normal state to an abnormal state. In particular, the inventors of the present application have found that even in the case of a disease such as epilepsy, in which consciousness is suddenly lost, periodic behavior of the head occurs as an abnormal sign. Therefore, in the technology according to the present disclosure, the driver's head behavior is acquired by a sensor.

[0012] Furthermore, the inventors of the present application have found through extensive research that in the case of a disease that causes sudden loss of consciousness, a characteristic pattern occurs in the time-series fluctuation pattern of the periodic feature of head behavior. Therefore, in the technology disclosed herein, the periodic feature of the head behavior acquired by a sensor is calculated, a time-series fluctuation pattern is calculated for the periodic feature, and the time-series fluctuation pattern is compared with a specific pattern.

[0013] This makes it possible to detect abnormal signs even for diseases that cause sudden loss of consciousness, and as a result, it is possible to detect signs that a driver of a moving object may become unable to drive as early as possible.

[0014] In the driver state estimation device, the specific pattern may be two-dimensional data obtained by performing dimensionality reduction using a nonlinear dimensionality compression method on the time series data of the periodic feature for the specific period obtained by calculation, and the detection unit may perform dimensionality reduction using a nonlinear dimensionality compression method on the time series data of the current periodic feature obtained by calculation to obtain two-dimensional data as the time-series fluctuation pattern, and detect the presence or absence of a sign of abnormality in the driver based on whether or not the two-dimensional data of the current time-series fluctuation pattern has a pattern similar to the two-dimensional data of the specific pattern.

[0015] With this configuration, it is possible to more easily determine whether or not there is a sign of an abnormality in the driver from the time-series data of the periodic feature amount of the head behavior.

[0016] In the driver state estimation device, the detection unit may be configured to accumulate the time-series fluctuation patterns including times when the driver is in an abnormality precursor state, and to modify data regarding the specific pattern based on the accumulated time-series fluctuation patterns.

[0017] According to this configuration, a specific pattern can be set in accordance with the driver, and a sign of abnormality in the driver can be determined accurately and early. Effect of the Invention

[0018] As described above, according to the technology disclosed herein, it is possible to detect as early as possible a sign that the driver is becoming unable to drive. [Brief description of the drawings]

[0019] [Figure 1] FIG. 1 is a graph illustrating the fluctuations in driving ability levels as a driver develops a disease state. [Diagram 2] FIG. 2 shows the relationship between head behavior homeostasis and disease, where (a) shows the normal state, (b) shows the critical deceleration state, and (c) shows the disease state. [Diagram 3]FIG. 3 is a diagram showing the drive simulator used in the experiment. [Figure 4] FIG. 4 is a diagram showing head behavior obtained by an experiment. [Diagram 5] FIG. 5 is a diagram showing head behavior, periodic feature amounts of head behavior, and time-series fluctuation patterns of the periodic feature amounts. [Figure 6] FIG. 6 is a diagram showing two-dimensional data of a time-series fluctuation pattern. [Figure 7] FIG. 7 is a configuration diagram of an in-vehicle system including a driver state estimating device. [Figure 8] FIG. 8 is a flowchart showing a process for estimating a driver's state based on a head behavior. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Exemplary embodiments will now be described in detail with reference to the drawings.

[0021] FIG. 1 is a conceptual diagram showing the positioning of the technology disclosed herein. The changes in a driver's condition that cause them to become unable to drive are summarized into three patterns. Case A is a pattern in which some of the functions of perception, judgment, and movement decline, Case B is a pattern in which the overall functions decline gradually, and Case C is a pattern in which consciousness is suddenly lost. Of these, in the case of Case C, as shown in FIG. 1, the driving ability declines suddenly after the disease develops. Therefore, it is particularly important to detect the signs of the driver's inability to drive before the disease occurs. If the signs of inability to drive can be detected, then it becomes possible to take emergency measures such as, for example, confirming the driver's intention and pulling the vehicle to the shoulder by automatic driving control.

[0022] The technology according to the present disclosure focuses on the human homeostasis maintenance function and detects a sign of inability to drive (hereinafter referred to as an abnormality sign) from the behavior of the driver's head.

[0023] Figure 2 shows the relationship between homeostasis of head behavior and disease (see Non-Patent Documents 1 and 2). Each graph in Figure 2 shows head movement as seen from above. (a) in Figure 2 shows the normal state in which homeostasis is maintained, (b) in Figure 2 shows the state of critical deceleration between normal and disease, and (c) in Figure 2 shows the diseased state. The graphs in Figures 2(a) and (c) are taken from Non-Patent Document 1.

[0024] Humans have a function called homeostasis, which tries to keep a constant state against disturbances. Head behavior homeostasis refers to the tendency to maintain the head posture while driving. As shown in Fig. 2(a), in a normal state, the head moves irregularly to maintain homeostasis. On the other hand, as shown in Fig. 2(c), in an ill state, the head movement becomes smaller and the behavior becomes stable. And, as shown in Fig. 2(b), in the critical deceleration state during the transition from a normal state to an ill state, the head is thought to move with periodicity (autocorrelation) (see Non-Patent Document 2).

[0025] The inventors of the present application have focused on the above-mentioned findings and have considered that if the state transition to the critical deceleration state can be captured from the driver's head behavior, it is possible to detect signs of abnormality. They have also considered that the periodic feature amount of the head behavior can be used to detect signs of abnormality in the driver.

[0026] <Head movement in case C> In order to obtain head behavior when symptoms of case C occur, the inventors of the present application conducted an experiment in which a subject with an actual disease of case C (here, an epilepsy patient) was made to drive a vehicle using a driving simulator 80 as shown in Fig. 3. In the experiment, the pitch angle (angle in the forward / backward direction) and roll angle (angle in the left / right direction) of the head were obtained by a sensor as data indicating the subject's head behavior. Also, in the experiment, the subject's brain waves were obtained to determine whether or not epilepsy actually occurred.

[0027] Figure 4 shows the results of actually acquiring head behavior. The normal zone, premonition zone, and seizure zone shown in Figure 4 were determined from the results of EEG analysis. The lower panel of Figure 4 shows an enlarged portion of the upper panel of Figure 4.

[0028] The inventors of the present application conducted an experiment, and found that, as shown in FIG. 4, in a normal state, the head moves randomly and slightly, in a premonition state, a minute vibration occurs, and in a seizure state, the head moves randomly and significantly. Furthermore, as shown in the lower diagram of FIG. 4, in a premonition state, although there are occasional large movements, the vibration is basically quite small and continues. Therefore, in order to detect this periodic change, the inventors of the present application obtained an autocorrelation index (scaling exponent α) for the time series data of the head pitch angle and roll angle by DFA (Detrended Fluctuation Analysis). DFA is a method for investigating scaling by removing components that change very slowly, that is, so-called trends. The autocorrelation index (scaling exponent α) is an example of a feature that indicates the periodicity of data.

[0029] The top graph in Figure 5 is an example of time series data for the pitch and roll angles of the head. The center graph in Figure 5 is a graph showing the autocorrelation index of the head pitch and roll angles. A smaller autocorrelation index value indicates stronger autocorrelation, and a larger autocorrelation index value indicates weaker autocorrelation. The top graph in Figure 5 is a cut-out of a portion of the results in Figure 4.

[0030] As shown in Figure 5, in the warning period, the autocorrelation index tends to decrease and changes regularly. This experimental result is consistent with the above-mentioned finding that in a normal state, the head moves irregularly, and in a critical deceleration state, the head moves periodically. However, as shown in Figure 5, even in a normal period, the autocorrelation index may be at the same level as in the warning period. For this reason, estimating abnormal warnings based only on the absolute value of the autocorrelation index may lead to erroneous judgment.

[0031] Therefore, the inventors of the present application focused on the time-series fluctuation patterns of the autocorrelation index. The inventors of the present application extracted the time-series data of the autocorrelation index in chronological order, and performed pattern classification using this as a time-series fluctuation pattern. Here, the nonlinear dimensionality reduction method (UMAP: Uniform Manifold Approximation and Projection) was used as the pattern classification method.

[0032] The lower diagram of Figure 5 shows the classification results of the time series fluctuation pattern of the autocorrelation index. The lower diagram of Figure 5 shows the pattern index obtained by reducing the dimension of the time series fluctuation pattern using UMAP. As shown in the lower diagram of Figure 5, it can be seen that the pattern index fluctuates greatly in the warning period.

[0033] FIG. 6 is a two-dimensional map of the patterns shown in FIG. 5. The vertical and horizontal axes are both pattern indices. As shown by the arrows in FIG. 6, when an abnormality sign occurs, a portion where the pattern index calculated from the autocorrelation index decreases significantly occurs. Therefore, the inventors of the present application have defined that when such a decrease in the pattern index is detected, the driver is presumed to be in an abnormality sign state. That is, the two-dimensional map of the time-series fluctuation pattern calculated from the head behavior of the driver in a specific period including the time when the driver is in an abnormality sign state as shown in FIG. 6 is set as a specific pattern, and the presence or absence of an abnormality sign of the driver is detected based on whether or not the two-dimensional data of the driver's current time-series fluctuation pattern has a sudden decrease pattern similar to that of the two-dimensional data of the specific pattern. Driver This makes it possible to detect an abnormality sign of the driver as early as possible.

[0034] The presence or absence of this decrease pattern may be defined, for example, based on the amount of decrease in the pattern index, or a specific region including plots when the pattern index decreases is set in the two-dimensional data of the specific pattern, and it may be defined based on whether or not a plot belonging to the specific region has appeared in the two-dimensional data of the driver's current time-series fluctuation pattern.

[0035] From the above, it is considered that the presence or absence of a pre-existing abnormality in the driver can be detected by calculating a periodic feature for time series data representing the behavior of the driver's head, calculating a time series variation pattern for the periodic feature obtained by the calculation, and comparing the current time series variation pattern obtained by the calculation with a specific pattern, which is a time series variation pattern calculated from the behavior of the driver's head during a specific period including a time when the driver is in a pre-existing abnormality state.

[0036] <Configuration of the Driver State Estimation Device> Next, a driver state estimating device 100 for executing the above-mentioned estimation method will be described.

[0037] Fig. 7 is a block diagram showing an example of the configuration of an in-vehicle system including a driver state estimation device according to this embodiment. In the in-vehicle system of Fig. 7, a camera 10, a speaker 11, an information presentation unit 12, a switch 13, and a microphone 14 are mounted inside the vehicle. The information processing device 20 is composed of, for example, a single IC chip having a processor and a memory, or multiple IC chips having a processor and a memory. A vehicle stop control unit 40 receives an instruction from the information processing device 20 and performs control to automatically move the vehicle to the shoulder of the road and stop it.

[0038] The camera 10 is installed, for example, on the inside of the windshield, and captures the situation inside the vehicle including the driver. The image captured by the camera 10 is transmitted to the information processing device 20, for example, via an in-vehicle network. The camera 10 is a high-performance camera capable of measuring minute head movements of the driver. Instead of the camera 10, the head behavior may be measured by a sensor worn by the driver.

[0039] In the information processing device 20, the head behavior detection unit 21 detects the behavior of the driver's head from the image captured by the camera 10. For example, the head of the driver is recognized from the image, and the tilt angle of the head, for example, the pitch angle and roll angle, is obtained. The processing in the head behavior detection unit 21 can be realized by existing image processing technology. The processing by the head behavior detection unit 21 makes it possible to obtain time-series data of the head behavior as shown in FIG. 4. The time-series data of the head behavior is sent to a detection unit 30 that detects signs of abnormality in the driver.

[0040] The detection unit 30 includes a periodic feature amount calculation unit 31, a time series variation pattern calculation unit 32, an abnormality determination unit 33, and an abnormality determination database 34. The periodic feature amount calculation unit 31 calculates a periodic feature amount from the time series data of head behavior obtained by the head behavior detection unit 21. Specifically, for example, an autocorrelation index (scaling exponent α) is found as the periodic feature amount by DFA (Detrended Fluctuation Analysis). The periodic feature amount calculation unit 31 can obtain time series data of the periodic feature amount as shown in the middle diagram in FIG. 5.

[0041] The time-series fluctuation pattern calculation unit 32 cuts out the time-series data of the periodic feature obtained by the periodic feature calculation unit 31 in chronological order, calculates a time-series fluctuation pattern from the cut-out time-series data, and classifies the patterns. Specifically, for example, the time-series data of the periodic feature is subjected to dimensionality reduction using UMAP, which is one of the nonlinear dimensionality reduction methods, and converted into two-dimensional data.

[0042] The abnormality determination unit 33 compares the data obtained by the time-series variation pattern calculation unit 32 with a specific pattern stored in the abnormality determination database 34 to determine whether or not an abnormality sign has occurred in the driver. As described above, the specific pattern is a time-series variation pattern calculated from the head behavior of the driver in a specific period including the time when the driver is in an abnormality sign state. The abnormality determination unit 33 determines whether or not an abnormality sign has occurred in the driver, for example, based on whether or not a two-dimensional map of the current time-series variation pattern has a sudden drop in the pattern index as seen in the specific pattern.

[0043] The detection unit 30 accumulates time-series variation patterns including times when the driver is in an abnormality precursor state, and corrects data relating to specific patterns stored in the abnormality determination database 34 based on the accumulated time-series variation patterns.

[0044] When the abnormality determination unit 33 of the detection unit 30 determines that an abnormality sign has occurred, the detection unit 30 outputs to the interrogation unit 22 a request to interrogate the driver.

[0045] The interrogation unit 22 interrogates the driver when receiving a request to interrogate the driver from the detection unit 30. This interrogation is for confirming the driver's intention as to whether or not it is acceptable to make the vehicle automatically drive to an emergency evacuation. The interrogation is performed, for example, by voice through the speaker 11 or by display through the information presentation unit 12 such as a monitor.

[0046] The response detection unit 23 detects the driver's response to the question posed by the questioning unit 22. The driver responds, for example, by operating the switch 13 or by speaking via the microphone 14. When the driver's intention is confirmed or when there is no response from the driver, the information processing device 20 instructs the vehicle stop control unit 40 to automatically move the vehicle to the shoulder of the road and stop it.

[0047] The driver state estimating device according to the present embodiment includes at least a head behavior detecting unit 21 and a detecting unit 30 in an information processing device 20. The driver state estimating device according to the present disclosure may also include a camera 10.

[0048] FIG. 8 is a flowchart showing the processing operation for detecting a sign of abnormality in case C based on head behavior.

[0049] First, in step S1, head behavior detection unit 21 recognizes the driver's head from the image captured by camera 10, and calculates the inclination angles, here the pitch angle and roll angle, of the recognized head. This calculation is performed, for example, every 100 ms.

[0050] Next, in step S2, the detection unit 30 determines whether or not a prescribed number of pieces of head tilt angle data have been accumulated. If the result is YES, that is, the detection unit 30 has accumulated the prescribed number of pieces of head tilt angle data, the detection unit 30 proceeds to step S3. On the other hand, if the result is NO, that is, the detection unit 30 has not accumulated the prescribed number of pieces of head tilt angle data, the detection unit 30 returns to step S1.

[0051] In step S3, the detection unit 30 calculates a periodic feature amount for the time series data of the head tilt angle. The detection unit 30 obtains an autocorrelation index (scaling exponent α) as the periodic feature amount by, for example, DFA. The calculation of the periodic feature amount is performed, for example, every 100 ms, using, for example, 256 pieces of tilt angle data while shifting the time range of the target tilt angle data.

[0052] Next, in step S4, the detection unit 30 judges whether or not the data of the periodicity feature amount has been accumulated to a prescribed number or more. If the result is YES, that is, that the data has been accumulated to a prescribed number or more, the detection unit 30 proceeds to step S5. On the other hand, if the result is NO, that is, that the data has not been accumulated to a prescribed number or more, the detection unit 30 returns to step S1.

[0053] In step S5, the detection unit 30 calculates a time series variation pattern for the periodic feature. The detection unit 30 reduces the dimension of the time series variation data of the periodic feature by, for example, using UMAP, which is one of the nonlinear dimensionality reduction techniques, and converts it into two-dimensional data. The calculation of the time series variation pattern is performed by shifting the time range of the data of the target periodic feature every 100 ms, for example, using data of 256 periodic features.

[0054] Next, in step S6, the detection unit 30 acquires the specific pattern stored in the abnormality determination database 34. The specific pattern is a time-series variation pattern calculated from the head behavior of the driver during a specific period including the time when the driver is in an abnormality prediction state. Here, the specific pattern acquired from the abnormality determination database 34 is two-dimensional data in which the time-series variation pattern is converted into a two-dimensional map.

[0055] Then, in step S7, the detection unit 30 compares the two-dimensional data of the current time-series variation pattern obtained in step S5 with the specific pattern acquired in step S6 to determine whether the current time-series variation pattern has a pattern equivalent to the specific pattern. If the current time-series variation pattern has a pattern equivalent to the specific pattern (YES), the detection unit 30 determines that the driver has a sign of abnormality and proceeds to step S8. On the other hand, if the current time-series variation pattern does not have a pattern equivalent to the specific pattern (NO), the detection unit 30 determines that the driver does not have a sign of abnormality and returns to step S1.

[0056] In step S8, the detection unit 30 outputs a request to inquire of the driver to the inquiry unit 22. After step S8, the process ends.

[0057] Therefore, according to the present embodiment, the head behavior detection unit 21 detects the behavior of the driver's head using the camera 10, and the detection unit 30 detects the driver's abnormal sign from the head behavior detected by the head behavior detection unit 21. The detection unit 30 is configured to calculate a periodic feature amount for time-series data showing the driver's head behavior, calculate a time-series variation pattern for the periodic feature amount obtained by the calculation, and compare the time-series variation pattern obtained by the calculation with a specific pattern calculated in advance to detect the presence or absence of the driver's abnormal sign, where the specific pattern is a time-series variation pattern calculated from the head behavior of the driver in a specific period including the time when the driver is in an abnormal sign state. This makes it possible to detect an abnormal sign based on the periodic head behavior before the disease, even for diseases that cause sudden loss of consciousness. As a result, it is possible to detect a sign that the driver who drives a moving object will fall into an incapacity state as early as possible.

[0058] In this embodiment, the specific pattern is a two-dimensional map obtained by performing dimension reduction using a nonlinear dimension compression method on the time series data of the periodic feature amount for a specific period obtained by calculation, and the detection unit 30 performs dimension reduction using a nonlinear dimension compression method on the time series data of the current periodic feature amount obtained by calculation to obtain a two-dimensional map as a time series fluctuation pattern, and detects the presence or absence of a driver's abnormality sign based on whether or not the two-dimensional map of the current time series fluctuation pattern has a pattern similar to the two-dimensional map of the specific pattern. This makes it easier to determine the presence or absence of a driver's abnormality sign from the time series data of the periodic feature amount of the head behavior.

[0059] In this embodiment, the detection unit 30 accumulates time-series variation patterns including the time when the driver is in an abnormality prediction state, and corrects the data related to the specific pattern based on the accumulated time-series variation patterns. This makes it possible to set a specific pattern according to the driver, and to accurately and quickly determine the driver's abnormality prediction.

[0060] (Other embodiments) The technology disclosed herein is not limited to the above-described embodiment, and may be substituted without departing from the spirit and scope of the claims.

[0061] For example, in the above embodiment, the autocorrelation index (scaling exponent α) is calculated as the periodic feature amount by DFA for the time-series data of head behavior, but the periodic feature amount may be calculated by a method other than DFA.

[0062] Furthermore, in the above-described embodiment, an automobile is exemplified as a moving body, but the driver state estimating device 100 described above may be adopted in moving bodies other than an automobile, such as a train.

[0063] The above-described embodiments are merely illustrative and should not be construed as limiting the scope of the present disclosure. The scope of the present disclosure is defined by the claims, and all modifications and variations within the scope of the claims are within the scope of the present disclosure. [Industrial Applicability]

[0064] The technology disclosed herein is useful as a driver state estimation device that estimates the state of a driver who drives a mobile object. [Explanation of symbols]

[0065] 10 Camera (sensor) 21 Head behavior detection unit 30 Detection unit 100 Driver state estimation device

Claims

1. A driver state estimation device that estimates a state of a driver who drives a moving object, comprising: a head behavior detection unit that detects a behavior of the driver's head using a sensor; a detection unit that detects a sign of an abnormality in the driver from the head behavior detected by the head behavior detection unit, The detection unit is Calculating a periodic feature amount for time series data indicating a driver's head behavior; A time series fluctuation pattern is calculated for the periodic feature obtained by the calculation; comparing the time-series variation pattern obtained by the calculation with a specific pattern calculated in advance to detect the presence or absence of an abnormality sign of the driver; It is configured as follows: the specific pattern is a time-series variation pattern calculated from a head behavior of the driver during a specific period including a time when the driver is in an abnormality prediction state, the specific pattern is two-dimensional data obtained by performing dimensionality reduction using a nonlinear dimensionality reduction method on the time series data of the periodicity feature amount for the specific period obtained by the calculation, The detection unit is A nonlinear dimension reduction method is used to reduce the dimension of the time series data of the current periodic feature obtained by the calculation, to obtain two-dimensional data as the time series fluctuation pattern; A driver state estimation device, comprising: a driver state estimation unit that detects the presence or absence of an abnormality sign of the driver based on whether or not the current two-dimensional data of the time-series variation pattern has a pattern similar to the two-dimensional data of the specific pattern.

2. 2. The driver state estimating device according to claim 1, The detection unit accumulates the time-series variation patterns including times when the driver is in an abnormality precursor state, and corrects data regarding the specific pattern based on the accumulated time-series variation patterns.

3. A driver state estimation device that estimates a state of a driver who drives a moving object, comprising: a head behavior detection unit that detects a behavior of the driver's head using a sensor; a detection unit that detects a sign of an abnormality in the driver from the head behavior detected by the head behavior detection unit, The detection unit is Calculating a periodic feature amount for time series data indicating a driver's head behavior; A time series fluctuation pattern is calculated for the periodic feature obtained by the calculation; comparing the time-series variation pattern obtained by the calculation with a specific pattern calculated in advance to detect the presence or absence of an abnormality sign of the driver; It is configured as follows: the specific pattern is a time-series variation pattern calculated from a head behavior of the driver during a specific period including a time when the driver is in an abnormality prediction state, The detection unit accumulates the time-series variation patterns including times when the driver is in an abnormality precursor state, and corrects data regarding the specific pattern based on the accumulated time-series variation patterns.

Images