JP2013027514A - Driver condition determining apparatus, and driver condition determination method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a driver condition determining apparatus capable of determining the fact that a driver yawns appropriately.SOLUTION: The driver condition determining apparatus includes a respiratory signal output means 10 that detects the respiratory motion of the driver and outputs a respiratory signal corresponding to the breath of the driver, and a determination means 20 that determines whether the driver yawns based on the respiratory signal.

Description

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

  2. Description of the Related Art Conventionally, a technique for determining whether a target person has yawned based on image data of a portion around the mouth of the target person is known (for example, Patent Document 1).

JP-A-8-257017

  However, in the prior art, since it is determined whether or not the target person yawns based on the image data around the mouth of the target person, when the target person yawns, When covered or withstood to open the mouth, it may not be possible to appropriately determine whether or not the target person has yawned.

  The problem to be solved by the present invention is to provide a driver state determination device capable of appropriately determining whether or not a driver yawns.

  The present invention solves the above problem by detecting the driver's respiratory motion and determining whether the driver yawns based on the detected driver's respiratory motion.

  According to the present invention, since it is possible to determine whether or not the driver yawns based on the actual breathing motion of the driver, it is possible to more appropriately determine whether or not the driver yawns. be able to.

It is a block diagram which shows the structure of the driver | operator state determination apparatus which concerns on 1st Embodiment. It is a side view of vehicles showing the state where a driver sat down in the driver's seat of vehicles to which a driver state judging device is applied. FIG. 3 is a view as seen from an arrow A in FIG. 2. FIG. 4A is a graph showing an example of a respiratory signal output in accordance with the driver's respiratory motion, and FIG. 4B is detected based on the respiratory signal shown in FIG. It is a graph which shows a driver | operator's breathing depth. It is a figure for demonstrating the method to detect the depth of a driver | operator's respiration, and the length of a driver | operator's respiration. It is a flowchart which shows the driver | operator state determination process which concerns on 1st Embodiment. It is a block diagram which shows the structure of the driver | operator state determination apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the driver | operator state determination process which concerns on 2nd Embodiment. It is a block diagram which shows the structure of the driver | operator state determination apparatus which concerns on 3rd Embodiment. It is a flowchart which shows the driver | operator state determination process which concerns on 3rd Embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, a driver state determination device mounted on a vehicle will be described as an example.

<< First Embodiment >>
FIG. 1 is a configuration diagram illustrating a configuration of a driver state determination device 100 according to the first embodiment. As shown in FIG. 1, the driver state determination device 100 according to the first embodiment includes a pressure sensor 10 and a processing device 20.

  The pressure sensor 10 is a sensor using a piezoelectric element such as a polyvinylidene fluoride (PVDF) film, for example, detects a pressure change generated in the pressure sensor 10 due to a driver's breathing motion, and detects the detected pressure change as an electric signal ( (Respiration signal) and output to the processing device 20. Below, with reference to FIG. 2 and FIG. 3, the detection method of the respiration signal according to a driver | operator's respiration motion is demonstrated. 2 is a side view of the vehicle showing a state in which the driver is seated on the driver's seat of the vehicle on which the driver state determination device 100 is mounted, and FIG. 3 is a view as seen from the arrow A in FIG.

  As shown in FIG. 2, the seat 1 includes a seat back 3 that supports the back surface of the driver (occupant) 2 and a seat cushion 4 that supports the lower limbs of the driver 2. Further, as shown in FIG. 3, a seat belt buckle 7 into which a tongue 6 a of the seat belt 6 is inserted is supported on the seat back 3 on the seat side portion (seat side portion) 5 on the inner side in the vehicle width direction of the seat cushion 4. Stay 8 is attached. The stay 8 is attached to the seat side part 5 via a stay attaching part 9. The stay attaching portion 9 fixes the stay 8 by bolting. However, since a washer and a spring washer (not shown) are inserted between the stay 8 and the seat side portion 5, the stay 8 swings in the vehicle width direction. It is possible to move. The stay attaching portion 9 is fixed to a bracket (not shown) located inside the seat cushion 4.

  A pressure sensor 10 is interposed between the seat side surface (stay side surface) 11 of the stay 8 and the seat side portion 5. The pressure sensor 10 is fixed to the stay side surface 11, detects a change in the distance between the seat side portion 5 and the stay side surface 11 as a pressure change, converts it into an electrical signal (a breathing signal), and outputs it.

  When the seat belt 6 expands and contracts according to the breathing motion of the driver 2, the force generated thereby is transmitted to the seat belt buckle 7 via the seat belt 6. The seat belt buckle 7 and the stay 8 swing in the vehicle width direction (in the direction of the arrow in FIG. 3) about the stay mounting portion 9, and the distance between the stay side surface 11 and the seat side portion 5 changes. To do. The pressure sensor 10 can detect the breathing state of the driver 2 by detecting such a change in the distance between the seat side portion 5 and the stay side surface 11 as a pressure change. In particular, in this embodiment, since the pressure sensor 10 is sandwiched between the stay 8 and the seat side portion 5, when the stay 8 swings in the vehicle width direction due to the breathing of the driver 2, the seat belt buckle 7 is applied to the power point. The lever principle is developed with the stay mounting portion 9 of the stay 8 as a fulcrum and the contact portion between the pressure sensor 10 and the seat side portion 5 as an action point, so that the voltage value of the respiratory signal detected by the pressure sensor 10 can be reduced. The amplitude can be greatly changed, and the pressure change can be detected with higher sensitivity.

  Here, FIG. 4 (A) is a graph showing an example of the respiratory signal output by the pressure sensor 10, and FIG. 4 (B) is detected based on the respiratory signal shown in FIG. 4 (A). It is a graph which shows the depth of breathing of a driver. 4A, the horizontal axis indicates time, and the vertical axis indicates voltage. In the graph of FIG. 4B, the horizontal axis indicates time, and the vertical axis indicates the breathing depth of the driver. Show.

  When the stay 8 swings in the vehicle width direction in accordance with the driver's breathing motion, a waveform breathing signal is output by the pressure sensor 10 as shown in FIG. For example, in one breathing exercise of the driver, the seat belt 6 expands and contracts once, and the stay 8 reciprocates once in the vehicle width direction, thereby breathing for one cycle of the breathing signal shown in FIG. A signal is output. Then, by repeating the driver's respiratory motion, a waveform respiratory signal is output in accordance with the driver's respiratory motion, as shown in FIG. Thus, the breathing signal corresponds to the driver's actual breathing motion. Specifically, as shown in FIG. 5, the amplitude of the respiration signal corresponds to the respiration depth Bt, and the respiration signal period corresponds to the respiration length Lt. Therefore, in this embodiment, the depth of breathing of the driver can be detected based on this breathing signal. FIG. 5 is a diagram for explaining a method of detecting the depth of breathing of the driver and the length of breathing of the driver based on the breathing signal. Similarly to FIG. 4A, the horizontal axis Represents time, and the vertical axis represents voltage.

  Returning to FIG. 1, the processing device 20 will be described. The processing device 20 includes a ROM (Read Only Memory) that stores a program for determining whether the driver yawns, a CPU (Central Processing Unit) that executes the program stored in the ROM, and an access It is composed of a RAM (Random Access Memory) that functions as a possible storage device.

  Then, the processing device 20 executes a program stored in the ROM by the CPU, so that the breathing depth detection function for detecting the breathing depth of the driver and the yawn that determines whether or not the driver yawns. A determination function and an arousal state determination function for determining a driver's arousal state are realized. Below, each function with which the processing apparatus 20 is provided is demonstrated.

  The respiration depth detection function of the processing device 20 acquires the respiration signal output from the pressure sensor 10, and detects the respiration depth Bt of the driver based on the acquired respiration signal. Specifically, as shown in FIG. 5, the breathing depth detection function detects the amplitude of the breathing signal for one cycle obtained by one breathing motion of the driver as the breathing depth Bt of the driver. To do. Accordingly, the processing device 20 can periodically detect the breathing depth Bt of the driver as shown in FIG. 4B based on the respiratory signal shown in FIG. 4A, for example. .

  The yawning determination function of the processing device 20 determines whether or not the driver yawns. Specifically, the yawning determination function stores the driver's breathing depth Bt detected by the breathing depth detection function in the RAM of the processing device 20, and the stored driver's breathing depth Bt. As shown in FIG. 4B, the average value is calculated as the driver's normal breathing depth B0. The yawning determination function compares the driver's breathing depth Bt detected by the breathing depth detection function with the driver's normal breathing depth B0 to determine whether the driver yawned. Determine whether or not. A method for determining whether or not the driver yawns will be described later.

  The awake state determination function of the processing device 20 determines the driver's awake state based on the determination result of the yawn determination function. Specifically, the arousal state determination function is configured such that when the yawn determination function determines that the driver yawns, the driver's arousal level is equal to or less than a predetermined value at which the driver may fall asleep. Yes, it is determined that the driver's arousal state is low. On the other hand, the awakening state determination function determines that the driver's awakening state is not in a low state when the yawning determination function does not determine that the driver yawns.

  Next, with reference to FIG. 6, the driver state determination process according to the first embodiment will be described. Here, FIG. 6 is a flowchart showing a driver state determination process according to the first embodiment. Note that the processing described below is performed by the processing device 20.

  First, in step S101, the respiration depth Bt of the driver is detected by the respiration depth detection function. Here, in the present embodiment, the pressure sensor 10 outputs a respiration signal corresponding to the respiration motion of the driver to the processing device 20 as shown in FIG. The respiration depth detection function acquires the respiration signal output from the pressure sensor 10, and detects the amplitude of the acquired respiration signal for each cycle as the respiration depth Bt of the driver as shown in FIG. . In step S101, the breathing depth detection function detects the breathing depth Bt of the driver according to the breathing motion of the driver for each cycle of the breathing signal. Therefore, in this embodiment, the process after step S101 is also performed for every period of a respiration signal.

  In step S102, it is determined whether or not the driver's normal breathing depth B0 is detected by the yawning determination function. If the driver's normal breathing depth B0 is detected, the process proceeds to step S104. If the driver's normal breathing depth B0 is not detected, the process proceeds to step S103. .

  In step S103, since the driver's normal breathing depth B0 is not detected, the yawning determination function detects the driver's normal breathing depth B0. Specifically, the yawning determination function stores the driver's breathing depth Bt detected in step S101 in the RAM of the processing device 20, and stores the stored driver's breathing depth Bt. The average value is calculated as the driver's normal breathing depth B0.

  In step S104, the respiration depth ratio Xt is calculated by the yawning determination function. Specifically, the yawning determination function calculates the ratio of the driver's normal breathing depth B0 detected in step S103 and the driver's breathing depth Bt detected in step S101 to the breathing depth ratio. Calculated as Xt (Xt = Bt / B0).

  In step S105, the yawn determination function determines whether the respiration depth ratio Xt calculated in step S104 is greater than a predetermined reference value X1. Here, the predetermined reference value X1 is a reference value for determining whether or not the driver yawns based on the breathing depth of the driver, and is a value larger than 1, for example, 1 It can be set to a value of 2 or more. When the breathing depth ratio Xt is larger than the reference value X1, the process proceeds to step S106, and the driver is determined to have yawned by the yawn determination function. On the other hand, if the breathing depth ratio Xt is equal to or less than the reference value X1, the process proceeds to step S107, and it is determined by the yawn determination function that the driver is not yawning. As described above, in the first embodiment, when the driver's breathing depth Bt is larger than the value based on the driver's normal breathing depth B0 (for example, when X1 is set to 1.2). Is determined that the driver yawns when the driver's breathing depth Bt is greater than 1.2 times the driver's normal breathing depth B0).

  In step S108, the driver's arousal state is determined based on the determination result in step S106 or step S107 by the arousal state determination function. Specifically, when it is determined in step S106 that the driver yawns in the awakening state determination function, the driver's arousal level is equal to or less than a predetermined value that may cause the driver to fall asleep. The driver's arousal state is determined to be low. Conversely, if it is determined in step S107 that the driver is not yawning, the awakening state determination function determines that the driver's awakening state is not in a low state. The determination result by the arousal state determination function can be used, for example, for awakening state guidance processing for guiding the driver's awakening state to an appropriate state.

  As described above, in the first embodiment, the driver's respiration depth Bt is detected based on the respiration signal corresponding to the driver's actual respiration motion, and the respiration depth Bt of the driver When the value is greater than the value based on the normal breathing depth B0 of the driver (for example, when the driver's breathing depth Bt is greater than 1.2 times the driver's normal breathing depth B0) ), It is determined that the driver is yawning. Thus, in the present embodiment, it is possible to appropriately determine whether or not the driver yawns based on the driver's actual breathing motion. On the other hand, in the conventional configuration in which it is determined whether or not the driver yawns based on the image data of the driver's mouth peripheral part, the driver covers the mouth peripheral part with his / her hand, When a driver yawns without opening his mouth, there is a problem that it is impossible to detect that the driver yawns. On the other hand, in this embodiment, since it can be determined whether or not the driver yawns based on the driver's actual breathing motion, when the driver covers the mouth peripheral portion by hand Even when the driver yawns without opening his / her mouth, it is possible to appropriately detect that the driver yawns.

<< Second Embodiment >>
Next, the driver state determination device 100a according to the second embodiment will be described with reference to FIG. FIG. 7 is a configuration diagram illustrating the configuration of the driver state determination device 100a according to the second embodiment. The driver state determination device 100a according to the second embodiment has the same configuration as the driver state determination device 100 according to the first embodiment except for the points described below, and the driver according to the first embodiment. The same operation as the state determination device 100 is performed.

  Specifically, the processing device 20a according to the second embodiment adds to the functions of the processing device 20 according to the first embodiment, or as a breathing depth detection function of the processing device 20 according to the first embodiment. Instead, a breathing length detection function for detecting the breathing length of the driver is provided.

  The respiration length detection function acquires the respiration signal output from the pressure sensor 10, and detects the period of the acquired respiration signal as the respiration length Lt of the driver as shown in FIG. The driver's breathing length Lt detected by the breathing length detection function is used to determine whether or not the driver yawns by the yawning determination function.

  Specifically, the yawning determination function stores the driver's breathing length Lt detected by the breathing length detection function in the RAM of the processing device 20, and the stored driver's breathing length Lt. Is calculated as the driver's normal breathing length L0. The yawning determination function compares the driver's breathing length Lt detected by the breathing length detection function with the driver's normal breathing length L0 to determine whether the driver yawned. Determine whether or not. A method for determining whether or not the driver yawns will be described later.

  Then, with reference to FIG. 8, the driver state determination process which concerns on 2nd Embodiment is demonstrated. Here, FIG. 8 is a flowchart showing a driver state determination process according to the second embodiment. The processing described below is also performed by the processing device 20.

  First, in step S201, the respiration length Lt of the driver is detected by the respiration length detection function. Here, in the present embodiment, the pressure sensor 10 outputs a respiration signal corresponding to the respiration motion of the driver to the processing device 20 as shown in FIG. The respiration length detection function acquires the respiration signal output from the pressure sensor 10, and detects the period of the acquired respiration signal as the respiration length Lt of the driver as shown in FIG. In step S201, the breathing length detection function detects the breathing length Lt of the driver corresponding to the breathing motion of the driver for each cycle of the breathing signal. Therefore, in this embodiment, the process after step S201 is also performed for every period of a respiration signal.

  In step S202, it is determined whether or not the driver's normal breathing length L0 is detected by the yawning determination function. If the driver's normal breathing length L0 has been detected, the process proceeds to step S204. If the driver's normal breathing length L0 has not been detected, the process proceeds to step S203. .

  In step S203, since the driver's normal breath length L0 is not detected, the yawn determination function detects the driver's normal breath length L0. Specifically, the yawning determination function stores the driver's breathing length Lt detected in step S201 in the RAM of the processing device 20, and stores the stored driver's breathing length Lt. The average value is calculated as the driver's normal breathing length L0.

  In step S204, the respiration length ratio Yt is calculated by the yawning determination function. Specifically, the yawning determination function calculates the ratio of the driver's normal breathing length L0 detected in step S203 and the driver's breathing length Lt detected in step S201 to the breathing length ratio. Calculated as Yt (Yt = Lt / L0).

  In step S205, the yawn determination function determines whether the respiratory length ratio Yt calculated in step S204 is greater than a predetermined reference value Y1. Here, the predetermined reference value Y1 is a reference value for determining whether or not the driver yawns based on the breathing length of the driver, and is a value larger than 1, for example, 1 It can be set to a value of 2 or more. When the breathing length ratio Yt is larger than the reference value Y1, the process proceeds to step S206, and it is determined by the yawning determination function that the driver has yawned. On the other hand, when the breathing length ratio Yt is equal to or less than the reference value Y1, the process proceeds to step S207, and the driver is determined not to yawn by the yawn determination function. Thus, in the second embodiment, when the driver's breathing length Lt is larger than the value based on the driver's normal breathing length L0 (for example, when Y1 is set to 1.2) In this case, it is determined that the driver yawns when the driver's breathing length Lt is longer than 1.2 times the driver's normal breathing length L0).

  In step S208, as in step S108 of the first embodiment, the driver's arousal state is determined based on the determination result in step S206 or step S207 by the arousal state determination function.

  As described above, in the second embodiment, the driver's breathing length Lt is detected based on the respiratory signal corresponding to the driver's breathing motion, and the driver's breathing length Lt is determined by the driver's breathing length Lt. When the value is longer than the value based on the normal breathing length L0 (for example, when the driver's breathing length Lt is longer than 1.2 times the driver's normal breathing length L0). It is determined that the driver yawns. Thus, in the second embodiment, since it is possible to determine whether or not the driver yawns based on the actual breathing length of the driver, the driver covers the mouth peripheral portion with his hand. Even when yawning or when the driver yawns without opening his / her mouth, it is possible to appropriately detect that the driver yawns.

«Third embodiment»
Next, the driver state determination device 100b according to the third embodiment will be described with reference to FIG. FIG. 9 is a configuration diagram showing the configuration of the driver state determination device 100b according to the third embodiment. The driver state determination device 100b according to the third embodiment has the same configuration as the driver state determination device 100 according to the first embodiment, except for the points described below, and the driver according to the first embodiment. The same operation as the state determination device 100 is performed.

  As illustrated in FIG. 9, the driver state determination device 100 b according to the third embodiment includes a pressure sensor 10, a processing device 20 b, and a face image capturing camera 30.

  The face image capturing camera 30 is installed, for example, in an instrument panel in front of the driver, and images a portion around the driver's mouth at predetermined time intervals. Image data captured by the face image capturing camera 30 is transmitted to the processing device 20.

  The processing device 20b, in addition to the functions provided in the processing device 20 according to the first embodiment, an image processing function for determining whether or not the driver yawns based on the image data of the portion around the driver's mouth. Is provided.

  In the image processing function, the yawning of the driver is detected based on the image data of the portion around the mouth of the driver acquired from the face image capturing camera 30. For example, in this embodiment, the image processing function detects the size and opening time of the driver's opening based on the image data of the driver's mouth peripheral portion, and the detected opening size and opening time are a predetermined value or more. In such a case, the driver's yawn is detected as the driver yawning.

  Then, with reference to FIG. 10, the driver state determination process which concerns on 3rd Embodiment is demonstrated. Here, FIG. 10 is a flowchart showing a driver state determination process according to the third embodiment. The processing described below is also performed by the processing device 20.

  First, in steps S301 to S307, as in steps S101 to S107 of the first embodiment, the driver's breathing depth Bt is detected and detected based on the breathing signal corresponding to the driver's breathing motion. Based on the breathing depth Bt of the driver, it is determined whether or not the driver yawns.

  In step S308, the image processing function acquires the image data of the driver's mouth peripheral portion. In the subsequent step S309, the image processing function acquires the driver's mouth peripheral portion image data. Driver yawning is detected.

  In step S310, the yawn determination function determines whether or not the driver's yawn has been detected based on the detection result in step S309. If the driver's yawn is detected, the process proceeds to step S311, and it is determined by the yawn determination function that the driver yawns. On the other hand, if the driver's yawn is not detected, the process proceeds to step S312, and it is determined by the yawn determination function that the driver is not yawning.

  Next, in step S313, the yawning determination function allows the driver to yawn both the determination result based on the respiratory signal in steps S306 and S307 and the determination result based on the image data of the driver's mouth periphery in steps S311 and S312. A determination is made as to whether or not the determination has been made. If both the determination result based on the respiration signal and the determination result based on the image data indicate that the driver yawns, the process proceeds to step S317, and the yawn determination function determines that the driver yawns. Is done. On the other hand, if both the determination result based on the respiration signal and the determination result based on the image data are not determinations that the driver yawns, the process proceeds to step S314.

  In step S314, the yawn determination function causes the driver to yawn both the determination result based on the respiratory signal in steps S306 and S307 and the determination result based on the image data of the driver's mouth periphery in steps S311 and S312. A determination is made as to whether or not there is no determination. If both the determination result based on the respiration signal and the determination result based on the image data indicate that the driver is not yawning, the process proceeds to step S318, and the yawn determination function causes the driver to yawn. It is determined that it is not. On the other hand, if both the determination result based on the respiration signal and the determination result based on the image data are not determinations that the driver is not yawning, the process proceeds to step S315.

  That is, the scene that proceeds to step S315 means that, on one of the determination result based on the respiratory signal and the determination result based on the image data, it is determined that the driver yawns, and on the other hand, the driver yawns. It is a scene that has been determined not to have. Therefore, in step S315, in order to increase the determination accuracy of whether or not the driver yawns, the yawn determination function evaluates the reliability of the determination result that the driver yawns.

  For example, the yawning determination function determines whether the driver is yawning as a result of the determination based on the respiration signal (step S306), and determines whether the vehicle is vibrating. In severe cases, the reliability of the determination result based on the respiratory signal is evaluated to be less than a predetermined value with low reliability. As a result, in step S316, the yawning determination function determines that the reliability of the determination result that the driver yawns is less than a predetermined value (step S316 = No), and proceeds to step S318, where the yawning determination function It is determined that the driver is not yawning.

  Further, the yawning determination function determines that the driver yawns as a result of the determination based on the image data around the driver's mouth (step S311). If it is a dark place, it is evaluated that the reliability of the determination result based on the image data of the driver's mouth periphery is not more than a predetermined value with low reliability. As a result, it is determined in step S316 that the reliability of the determination result that the driver yawns is less than a predetermined value (step S316 = No), and in step S318, the driver does not yawn. Determined.

  On the other hand, as a result of the evaluation in step S315, if it is determined in step S316 that the reliability of the determination result that the driver yawns is greater than or equal to a predetermined value, the process proceeds to step S317, and the yawn determination function It is determined that the driver has yawned.

  In step S319, as in step S108 of the first embodiment, the driver's arousal state is determined based on the determination result in step S317 or step S318 by the arousal state determination function.

  As described above, in the third embodiment, it is determined whether or not the driver yawns based on the depth of breathing of the driver, and based on the image data of the driver's mouth peripheral portion, By determining whether or not the driver yawns, in addition to the effect of the first embodiment, it is possible to determine whether or not the driver yawns with high accuracy. In particular, in the third embodiment, when the determination result based on the driver's breathing signal and the determination result based on the image data of the driver's mouth periphery do not match, it is determined that the driver yawns. By evaluating the reliability of the determination result, it is possible to determine whether or not the driver yawns with higher accuracy.

  The embodiment described above is described for facilitating the understanding of the present invention, and is not described for limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

  For example, in the above-described embodiment, as shown in FIG. 3, by interposing the pressure sensor 10 between the seat side surface (stay side surface) 11 and the seat side portion 5 of the stay 8, However, the present invention is not limited to this configuration. For example, by providing the pressure sensor 10 in the belt portion of the seat belt 6 or the buckle portion of the seat belt, the operation is performed. It may be configured to directly detect a pressure change due to a person's breathing motion and output a breathing signal. Or it is good also as a structure which converts and outputs the expansion / contraction of the seatbelt 6 by a driver | operator's breathing movement into a respiration signal, or directly detects driver | operator's respiration, such as a driver | operator's expiration, and breathes according to a driver | operator's respiration. It is good also as a structure which outputs a signal.

  In the above-described embodiment, the average value of the driver's breathing depth Bt is detected as the driver's normal breathing depth B0. In this case, the driver's normal breathing depth Bt is detected. The depth B0 is detected when the driver drives the vehicle for the first time and is stored in the RAM of the processing device 20. Thereafter, when the driver drives, the normal time of the driver detected first is detected. The breathing depth B0 may be read from the RAM of the processing device 20, or the driver's normal breathing depth B0 may be detected every time the driver drives the vehicle. Good. The same configuration can be applied to the normal breathing length L0 of the driver.

  Furthermore, in the above-described embodiment, in order to determine whether or not the driver yawns, the configuration of detecting the depth of breathing of the driver or the length of breathing of the driver is exemplified. For example, the driver's breathing depth and the driver's breathing length are detected, and based on the judgment result based on the driver's breathing depth and the judgment result based on the driver's breathing length, driving It may be configured to determine whether the person yawns. Also in this case, it can be determined with high accuracy whether or not the driver yawns.

  Note that the pressure sensor 10 of the above-described embodiment is used as a respiratory signal output unit of the present invention, and the processing device 20 is used as a determination unit, a first threshold setting unit, a second threshold setting unit, and a wakefulness determination unit of the present invention. The face image capturing camera 30 corresponds to the image capturing unit of the present invention.

DESCRIPTION OF SYMBOLS 100 ... Driver state determination apparatus 10 ... Pressure sensor 20, 20a, 20b ... Processing apparatus 30 ... Face image pick-up camera

Claims (7)

A breathing signal output means for detecting the breathing motion of the driver and outputting a breathing signal corresponding to the breathing of the driver;
And a determination unit that determines whether or not the driver yawns based on the breathing signal. The driver state determination device according to claim 1,
Based on the breathing signal detected by the driver's normal breathing, the driver's normal breathing depth is estimated, and based on the estimated driver's normal breathing depth, driving A first threshold value setting means for setting a first threshold value for determining whether or not the person yawns;
The determination means detects the breathing depth of the driver based on the breathing signal detected by the breathing motion of the driver, and the detected breathing depth of the driver is not less than the first threshold value. In this case, the driver state determining device determines that the driver yawns. The driver state determination device according to claim 1 or 2,
Based on the breathing signal detected by the driver's normal breathing, the driver's normal breathing length is estimated, and based on the estimated driver's normal breathing length, driving A second threshold value setting means for setting a second threshold value for determining whether or not the person yawns;
The determination means detects the breathing length of the driver based on the breathing signal detected by the breathing motion of the driver, and the detected breathing length of the driver is equal to or more than the second threshold value. In this case, the driver state determining device determines that the driver yawns. The driver state determination device according to any one of claims 1 to 3,
It further comprises imaging means for imaging the periphery of the driver's mouth
The determination means determines whether or not the driver yawns based on the respiratory signal output by the respiratory signal output means and image data of a portion around the driver's mouth imaged by the imaging means. A driver state determination device characterized in that The driver state determination device according to claim 4,
The determination means evaluates the reliability of the breathing signal and the image data based on the traveling state of the host vehicle, and determines whether or not the driver yawns in consideration of the reliability. A characteristic driver state determination device. The driver state determination device according to claim 5,
A driver state determination device, further comprising: an awakening state determination unit that determines that the driver's arousal level is a predetermined value or less when the determination unit determines that the driver yawns.   A driver state determination method characterized by detecting a driver's breathing motion and determining whether or not the driver yawns based on the detection result.

Images