JP6521490B2 - Driver status determination device - Google Patents

Description

  The present invention relates to a driver state determination device, and more particularly to a driver state determination device that determines an abnormal state of a driver driving a vehicle.

  2. Description of the Related Art In the related art, there is known a driver state determination device which is mounted on a vehicle and monitors the state of a driver in order to prevent occurrence of a vehicle accident caused by a nap or the like. For example, when the driver's face determination apparatus of Patent Document 1 compares the face image of the driver captured by the far-infrared camera with the face image of the normal state and the temperature distribution is different, it determines that the driver is in a nap state Sounding an alarm.

  On the other hand, there is also known a driver state determination device that determines whether or not the driver is in a nap state by detecting a change in the steering operation of the driver (for example, Patent Document 2).

JP, 2016-57944, A JP-A-11-227489

However, when the driver's condition is determined from the face image, the driver may be awakened depending on the driver's face characteristics (eg, thin eyes, etc.) and temporary symptoms (eg, increase in the number of blinks due to eye dryness). However, there is a problem that it is erroneously determined to be a doze state despite it. In the driver state determination device of Patent Document 1, in order to reduce the influence of disturbance light, the state of the driver is determined based on the face image captured by the far-infrared camera. However, the driver's face characteristics and temporary Affected by symptoms, it is difficult to determine the driver's condition correctly.
On the other hand, since the driver state determination device of Patent Document 2 determines the state of the driver based on the variation of the steering operation, the driver's state is not affected by the above-described features of the driver's face or temporary symptoms. The state can be determined. However, when the driver's steering skill is low, there is a problem that the driver is erroneously determined to be asleep while in the awake state.

  Therefore, the present invention provides a driver state determination device capable of accurately determining an abnormal state of a driver without being influenced by the driver's facial features, temporary symptoms, and driver's steering skill. The purpose is that.

  In order to solve the problems described above, a driver state determination device of the present invention is a driver state determination device that determines an abnormal state of a driver driving a vehicle, and an out-of-vehicle camera that captures the front of the vehicle; Based on a vehicle speed sensor that detects the vehicle speed of the vehicle, a data analysis unit that calculates an offset distance of the vehicle in the lateral direction with respect to a reference position on the traveling road based on an image captured by a camera outside the vehicle The driver state determination unit determines an abnormal state of the driver, and the driver state determination unit multiplies the integral value of the variation amount of the vehicle speed and the integral value of the variation amount of the offset distance within a predetermined time. It is characterized in that it is configured to execute a driver state determination process of determining an abnormal state of the driver based on the determined determination value.

  In the present invention configured as described above, the driver state determination unit determines the driver based on the determination value obtained by multiplying the integral value of the variation amount of the vehicle speed and the integral value of the variation amount of the offset distance within a predetermined time. Therefore, the abnormal condition of the driver can be accurately determined without being influenced by the facial features and temporary symptoms of the driver and the steering skill of the driver.

  In the present invention, preferably, the driver state determination unit is configured to execute the driver state determination process when the offset distance is equal to or more than a predetermined threshold. In the present invention configured as described above, the abnormal state of the driver can be determined by excluding in advance the case where the driver is in the normal state in advance. Therefore, the number of times of execution of the driver state determination process can be reduced, and power consumption of the device can be suppressed.

  Further, in the present invention, preferably, after the driver state determination processing determines that the driver is in an abnormal state, a traffic congestion determination unit that determines whether the travel path of the vehicle is congested or not is included; If the determination unit determines that there is a congestion, the driver condition determination unit further determines the driver's abnormal condition based on the result of comparing the cycle of the vehicle speed fluctuation of the preceding vehicle with the cycle of the vehicle speed fluctuation of the vehicle. Are configured to determine. When the traveling path is congested, it is difficult to determine the driver's abnormal condition because the variation amount of the vehicle speed and the offset distance used in the driver's condition determination process is small. However, according to the present invention configured as described above, it is possible to accurately determine the driver's abnormal state even when the road is congested.

  In the present invention, preferably, the traffic congestion determination unit determines whether the traveling road is congested or not based on the vehicle speed of the vehicle and the integral value of the fluctuation amount of the vehicle speed of the preceding vehicle in a predetermined time to determine the driver's condition The unit is configured to determine that the driver is in the normal state when the cycle of the vehicle speed fluctuation of the preceding vehicle and the cycle of the vehicle speed fluctuation of the vehicle are substantially the same. In the present invention configured as described above, the driver's abnormal state can be determined with high accuracy even when the road is congested.

  In the present invention, preferably, an inter-vehicle distance measuring unit for measuring an inter-vehicle distance between a vehicle and a preceding vehicle is provided, and driving is performed after the driver state is determined to be abnormal by the driver state determination process. The human state determination unit is further configured to determine the abnormal state of the driver based on the integral value of the variation amount of the inter-vehicle distance in a predetermined time. In the present invention configured as described above, since the driver's abnormal condition is determined using the inter-vehicle distance, the driver's abnormal condition can be determined more accurately.

  In the present invention, preferably, the driver state determination unit further includes a brake sensor for detecting a brake operation of a driver of the vehicle, and after the driver state determination processing determines that the driver is in an abnormal state, The abnormal condition of the driver is determined based on the brake reaction time from detection of lighting of the brake lamp of the preceding vehicle by the camera outside the vehicle to detection of the brake operation by the brake sensor. In the present invention configured as described above, the abnormal state of the driver can be determined using the brake reaction time, so that the abnormal state of the driver can be determined more accurately.

  In the present invention, preferably, the in-vehicle camera further includes an in-vehicle camera having an in-vehicle camera for capturing an image of the driver and determining that the driver is in an abnormal state by the driver state determination process. It is comprised so that a driver | operator's abnormal condition may be determined based on the image of the driver imaged by this. In the present invention configured as described above, the abnormal condition of the driver can be determined using the determination result of the image by the in-vehicle camera, so that the abnormal condition of the driver can be determined more accurately.

  In the present invention, preferably, the vehicle includes a danger avoiding means for executing notification processing for causing the driver to drive normally and / or automatic driving support processing for the vehicle, and the driver state determination unit is in an abnormal state. When it is determined that the risk avoidance means performs the notification processing or / and the automatic driving support processing. In the present invention configured as described above, the notification processing and / or the automatic driving support processing can be executed with high accuracy to make the driver drive normally or drive support can be performed automatically.

  The driver state determination device of the present invention can accurately determine the abnormal state of the driver without being influenced by the facial features and temporary symptoms of the driver and the steering skill of the driver.

It is a basic composition figure of a driver state judging device by an embodiment of the present invention. It is a time-series graph of the awakening degree at the time of a test subject (driver) driving continuously for about 60 minutes, an offset distance, a vehicle speed, and a multiplication value. It is a flow of the driver state determination processing of the driver state determination device according to the first embodiment of the present invention. It is a calculation image figure in driver | operator condition determination by 1st Embodiment of this invention. It is the whole flow of the driver condition determination processing of the driver condition determination device according to the second embodiment of the present invention. It is a flow of the 2nd driver state judging processing of the driver state judging device by a 2nd embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.
First, with reference to FIG. 1, a basic configuration of a driver state determination device according to an embodiment of the present invention will be described. FIG. 1 is a basic configuration diagram of a driver state determination device.

  As shown in FIG. 1, the driver state determination device 1 is mounted on a vehicle, and includes an out-of-vehicle camera 3, a vehicle speed sensor 5, a radar 7, a traveling environment information acquisition unit 9, a brake sensor 11, an in-vehicle camera 13 and an ECU ( An electronic control unit) 15, a notification device 17, and an automatic driving support device 18 are provided.

  The camera 3 outside the vehicle is mounted at the front center outside the vehicle or at the front center inside the vehicle (the back of the front mirror), and captures an image of the front periphery of the vehicle. The out-of-vehicle camera 3 transmits the signal of the captured image to the ECU 15. As the camera 3 outside the vehicle, a stereo camera, a CCD camera, a monocular camera, etc. are used.

  The vehicle speed sensor 5 detects a vehicle speed (absolute speed of the vehicle), and transmits a signal of the vehicle speed to the ECU 15.

  The radar 7 is mounted in front of the vehicle and measures the relative position and relative velocity of an object (for example, a preceding vehicle, a parked vehicle, a pedestrian, an obstacle, etc.). Specifically, the radar 7 transmits a radio wave (transmission wave) toward the front, and receives a reflection wave generated by the transmission wave being reflected by the object. The radar 7 transmits to the ECU 15 signals of the relative position and relative velocity of the measured object. As the radar 7, a millimeter wave radar, a laser radar, an ultrasonic sensor or the like is used.

  The traveling environment information acquisition unit 9 receives a signal from a plurality of GPS satellites, receives the signal from the reception unit for detecting the current position of the vehicle, and stores the map information (the position of the expressway, the position of the city area, etc.) And an information processing unit that specifies a traveling environment (highway, city area, etc.) in which the vehicle is currently traveling based on current location of the vehicle and map information. The traveling environment information acquisition unit 9 transmits to the ECU 15 a signal of traveling environment information indicating whether the vehicle is traveling in a city area or is traveling outside the city area (highway, mountain road, etc.). The traveling environment information acquisition unit 9 uses a car navigation system or the like.

  The brake sensor 11 is provided near the brake pedal, and detects an on / off state of the driver's brake operation. The brake sensor 11 transmits an on / off signal of the brake operation to the ECU 15.

  The in-vehicle camera 13 is mounted forward in the vehicle in a state of being directed to the driver's face, and captures a face image of the driver. The in-vehicle camera 13 transmits the signal of the face image of the driver to the ECU 15. As the in-vehicle camera 13, a stereo camera, a CCD camera, a monocular camera or the like is used.

  The ECU 15 has an input interface circuit for inputting a signal from each device, an output interface circuit for outputting a request signal to each device, a CPU for processing the input signal, a memory, and the like for operating these. It consists of a program (not shown). The ECU 15 is communicably connected to each device, and executes various image analysis, various calculations, storage of various data, various determinations, and the notification device 17 and / or the automatic driving support device 18 based on the signals received from each device. Output request signal to The ECU 15 functions as a data analysis unit 19, a storage unit 21, a driver state determination unit 23, and a traffic jam determination unit 25 by the action of a built-in CPU or the like.

  The data analysis unit 19 calculates various data based on the signals received from the respective devices (the external camera 3, the vehicle speed sensor 5, the radar 7, the traveling environment information acquisition unit 9, the brake sensor 11, and the in-vehicle camera 13). Specifically, the data analysis unit 19 determines the distance (offset distance) by which the vehicle is away from the reference position on the traveling road based on the image captured by the camera 13 outside the vehicle and the signal from the radar 7 (offset distance) And the relative velocity between the vehicle and the object. Here, the reference position of the offset distance is a virtual center line at the center in the lateral direction of the road surface on which the vehicle is traveling (the white line which is the dividing line and the inner portion of the white line). The offset distance is the distance in the lateral direction (perpendicular to the imaginary center line) from the imaginary center line to the reference point of the vehicle (for example, the center point of the vehicle, the center of gravity). The reference position may be based on a white line which is a dividing line, or may be based on a target travel route on a travel lane calculated based on data obtained from the travel path information acquisition unit 9 or the like.

  The storage unit 21 stores, in real time, data obtained from each device and data calculated by the data analysis unit 19.

  The driver state determination unit 23 detects various data (vehicle speed, offset distance, inter-vehicle distance (distance between the preceding vehicle and the vehicle), brake reaction time (detects the lighting of the brake lamp of the preceding vehicle by the camera outside the vehicle and Based on the time until the driver's brake operation is detected by the sensor), the driver's face image, the speed of the preceding vehicle, etc., it is determined whether the driver is in an abnormal state. Here, the driver's abnormal state is a state in which the driver can not drive normally in accordance with traffic rules, for example, a state in which the driver's awakening level or awareness level is low (for example, sleeping state, cardiopulmonary stop) State of vision loss) and brain disease.

  The traffic congestion determination unit 25 determines whether the traveling route on which the vehicle is traveling is congested (for example, the preceding vehicle exists) based on various data (the vehicle speed of the own vehicle, the vehicle speed of the preceding vehicle, etc.) It is determined whether the vehicle speed is slower than 15 km per hour). Note that the traffic information provided by a public organization or the like may be acquired by the traveling environment information acquisition unit 9 or the like to determine whether the traveling path is congested.

  The notification device 17 (risk avoidance means) is a display or a speaker mounted in the front of the vehicle. When the notification device 17 receives a request signal from the ECU 15, the notification device 17 displays a warning screen on a display or sounds a warning sound from a speaker to perform a notification process for putting the driver in an abnormal state into a normal state. The display or the speaker may double as the display or the speaker of the car navigation system.

  The automatic driving support device 18 (risk avoiding means) includes various sensors mounted on the vehicle, a steering actuator, a brake actuator and the like (above, not shown). When receiving a request signal from the ECU 15, the automatic driving support device 18 executes speed / steering control by each actuator. As a result, the collision prevention function, the lane departure prevention function, the automatic driving function, and various other functions are realized to execute the automatic driving support processing.

  Next, with reference to FIG. 2, the technical idea of the driver state determination device 1 according to the present embodiment of the present invention will be described. FIG. 2 is a time-series graph of the relationship between the awakening degree (a), the offset distance (b), the vehicle speed (c) and the multiplication value (d) when the subject (driver) operates continuously for about 60 minutes. .

  FIG. 2A shows the result of analyzing the captured driver's face image and evaluating the awakening degree at predetermined time intervals. The driver's face image is continuously taken for about 60 minutes by the in-vehicle camera, and based on this face image, the awakening level is from level 1 (high awakening level (woke up state)) to level 5 (awake level). The level of awakening is low (sleeping state). FIG. 2B is an integral value obtained by integrating the fluctuation amount of the vehicle speed for each predetermined time with respect to the vehicle speed according to the driver's accelerator or brake operation. FIG. 2C is an integral value obtained by integrating the variation amount of the offset distance at predetermined time intervals with respect to the offset distance according to the driver's steering. The offset distance here is the lateral distance from the virtual center line at the lateral center of the traveling path to the reference point of the vehicle. FIG. 2D is a multiplication value obtained by multiplying the integral value of the vehicle speed and the integral value of the offset distance at predetermined time intervals at the same timing.

  In (b) and (c) in FIG. 2, the integrated value of the vehicle speed or the offset distance repeatedly fluctuates with a large fluctuation range in the time zone of level 5 of alertness (within frame A) as compared to other time zones. There is. On the other hand, there are several time zones in which the integrated value of the vehicle speed or the offset distance repeats fluctuation with a relatively large fluctuation range even in the time zone of level 3 (within the frame B). In this time zone (within the frame B), if the driver's condition is determined by only one of the integral value of the vehicle speed and the integral value of the offset, it is erroneously determined that the driver is abnormal although it is normal. There is a fear.

  On the other hand, in FIG. 2D, in the time zone of level 5 of alertness (within frame A), the multiplication value repeats fluctuation with a large fluctuation range as compared with other time zones. In addition, in the time zone of level 3 of alertness (within frame B), the multiplication value fluctuates with a smaller fluctuation range as compared to the time zone of level 5. In the multiplication value, the difference between the magnitude of the fluctuation at level 5 and the magnitude of the fluctuation at level 3 clearly appears as compared with the case of the vehicle speed or the offset distance. That is, the multiplication value can determine the driver's condition with high accuracy as compared with the vehicle speed or the offset distance. Thus, the present inventors have found that the accuracy can be improved by using the multiplication value in the driver's state determination.

  The flow of the driver state determination process according to the first embodiment of the present invention will be described with reference to FIGS. 3 and 4. FIG. 3 is a flowchart of the driver condition determination process, and FIG. 4 is a calculation image diagram in the driver condition determination process. In FIG. 3, S indicates each step.

  As shown in FIG. 3, first, in S1, the driver condition determination unit 23 stores various data (vehicle speed, offset distance, inter-vehicle distance, brake reaction time, driver's face image, leading) stored in the storage unit 21. Load the vehicle speed etc.).

  Next, in S2, the driver state determination unit 23 determines whether or not the current offset distance is equal to or greater than a threshold (first threshold) of the offset distance. If the offset distance is equal to or greater than the first threshold (S2; Yes), the process proceeds to the next step to execute the driver state determination process. If the offset distance is smaller than the first threshold (S2; No), the driver is in a normal state, and the present flow ends. The first threshold is set to a value of 0.1 m to 0.7 m, preferably 0.2 m to 0.4 m, in consideration of the influence of the vehicle rolling due to the vibration transmitted from the road surface during traveling.

  In S3, the driver state determination unit 23 calculates an integral value of the fluctuation amount of the vehicle speed. Specifically, referring to FIG. 4, first, the driver state determination unit 23 extracts data (sample data) of the latest predetermined time (for example, 30 seconds) from the measurement data of the vehicle speed (FIG. )reference). The predetermined time is set to a length capable of analyzing the fluctuation characteristic of the vehicle speed. Next, the driver state determination unit 23 performs a smoothing process on the sample data to remove a locally abrupt change, and create smooth data (smoothed data) as a whole ( See FIG. 4 (b)). Specifically, the smoothing process is, for example, a moving average process that calculates moving averages at short intervals to create smooth data as a whole, or extracts only low periodic fluctuation components of a predetermined cycle or more to obtain an overall Low periodic variation extraction processing that creates smooth data. Next, the driver state determination unit 23 executes subtraction processing of subtracting the smoothing data from the sample data to extract data (fluctuation data) from which only the fluctuation amount of the vehicle speed (portion where the vehicle speed increases or decreases) is extracted. Calculate (see FIG. 4 (c)). Next, the driver state determination unit 23 executes difference processing on the fluctuation data on the basis of 0 (see FIG. 4 (d)), and then executes integration processing on the absolute value of the difference to change the vehicle speed. The integral value of the amount (vehicle speed fluctuation integral value) is calculated.

  Next, in S4, the driver state determination unit 23 calculates an integral value (offset variation integral value) of the variation amount of the offset distance. This calculation method is the same as the method shown in S3 except that data (sample data) for the latest predetermined time (for example, 10 seconds) is taken out from the measurement data of the offset distance. As the sample data of the offset distance, data of the same timing as the sample data of the vehicle speed of S3 is used.

  In S5, the driver state determination unit 23 executes multiplication processing of multiplying the vehicle speed fluctuation integral calculated in S3 and the offset fluctuation integral calculated in S4 to calculate a multiplication value (determination value).

  Next, in S6, the driver state determination unit 23 determines whether the determination value of S5 is larger than the threshold (second threshold) of the determination value. If the determination value is larger than the second threshold (S6; Yes), it is determined that the driver is in an abnormal state, and the process proceeds to S15. If the determination value is less than or equal to the second threshold (S6; No), the driver is in a normal state, and the present flow ends. The second threshold is set to a value that can eliminate the case where the vehicle fluctuates because the driver's driving skill is low.

  In S15, the ECU 15 transmits a request signal to the notification device 17 and / or the automatic driving support device 18. When the notification device 17 receives a request signal, the notification device 17 (display or speaker) is activated to display a warning screen on the display or sound a warning sound from the speaker in order to restore the driver to normal (woke up) Perform notification processing. When the automatic driving support device 18 receives the request signal, the automatic driving support processing for controlling the vehicle is executed by operating the collision prevention function, the lane departure prevention function, the automatic driving function, etc. Move to a place. This completes the flow of the driver state determination process according to the first embodiment.

  The flow of the driver state determination process according to the second embodiment of the present invention will be described with reference to FIGS. 5 and 6. The second embodiment differs from the first embodiment only in that second driver state determination processing (S7 to S13) and third driver state determination processing (S14) are added, and the same reference numerals are used. The steps are the same. Hereinafter, only differences from the first embodiment will be described.

FIG. 5 is an overall flowchart, and FIG. 6 is a flowchart of second driver state determination processing. In FIG. 5 and FIG. 6, S shows each process.
As shown in FIG. 5, in S2 to S6, the driver state determination unit 23 executes the driver state determination process of the first embodiment as a first driver state determination process (first process).

  Next, in S7 to S13, the driver state determination unit 23 executes a second driver state determination process (second process). The second process includes three processes of a driver state determination process at the time of traffic congestion, a driver state determination process by an inter-vehicle distance, and a driver state determination process by a brake reaction time. The second process is performed after the first process is performed to improve the determination accuracy of the first process when there is a preceding vehicle. In the second process of the present embodiment, all the three processes described above are performed. However, only one process may be performed and two processes may be performed by timely selection.

  Next, in S14, the driver state determination unit 23 executes a third driver state determination process (third process). The third process is performed after the first process and the second process are performed, and the first process and the second process are performed by performing the state determination of the driver based on the image of the driver captured by the in-vehicle camera. Is a process for improving the determination accuracy of

  Specifically, in S14, the driver state determination unit 23 stores the driver's line of sight, the number of blinks, the size of the pupil, and the like in advance based on the driver's face image captured by the in-vehicle camera 13 when normal. The driver state determination process (third driver state determination process) as to whether or not the driver is in an abnormal state is executed by comparing with the face image of FIG. For example, based on the driver's face image captured by the in-vehicle camera 13, it is detected that the driver's line of sight is not facing forward, blinks occur a predetermined number of times or more, and the pupil is closed. It is determined that the driver is in an abnormal state. When it is determined that the driver is in the abnormal state (S14; Yes), the process proceeds to S15, and the ECU 15 executes the notification device 17 and / or the automatic driving support device 18. When it is determined that the driver is in the normal state (S14; No), the driver is in the normal state, and the present flow ends. In the present embodiment, the third process is performed in addition to the first process and the second process, but the third process may be omitted and only the first process and the second process may be performed.

Next, the second process will be described in more detail with reference to FIG.
In S7, the driver state determination unit 23 determines whether or not there is a preceding vehicle ahead of the vehicle from the latest measurement data of the inter-vehicle distance. If it is determined that there is a preceding vehicle (S7; Yes), the process proceeds to S8. When it is determined that the preceding vehicle does not exist (S7; No), the process proceeds to the third process of S14. In the present embodiment, it is determined from the inter-vehicle distance whether or not there is a preceding vehicle, but it may be determined from the relative speed with the preceding vehicle measured by the camera 3 outside the vehicle.

  Steps S8 to S10 are a flow for determining the driver's condition at the time of the traffic congestion considering the case where the traveling path is congested. The reason for executing this determination flow is that the vehicle in traffic congestion is traveling at a low speed (for example, 15 km / hour), so the amount of fluctuation in the vehicle speed and the offset distance is small. It is difficult to determine the state of Here, a traffic jam means that a train of vehicles which travels or stops / starts at a low speed equal to or lower than a predetermined vehicle speed (for example, 40 km / h) continues for a predetermined distance (for example, 1 km) or a predetermined time (for example, 15 minutes) It means the condition of the road.

  First, in S8, the traffic congestion determination unit 25 determines whether or not the current vehicle speed of the host vehicle is equal to or higher than the threshold (third threshold) of the vehicle speed. If the vehicle speed is smaller than the third threshold (S8; No), it is determined that there is a possibility that traffic congestion is occurring, and the process proceeds to S9. If it is equal to or higher than the third threshold (S8; Yes), traffic congestion occurs It determines with not carrying out and transfers to S11. The third threshold is set to a low speed, for example, 15 km per hour.

  Next, in S9, the traffic congestion determination unit 25 calculates the integral value of the fluctuation amount of the vehicle speed of the preceding vehicle (the vehicle speed fluctuation integral of the preceding vehicle). This calculation method is the same as the method shown in S3 of the first embodiment except that the latest predetermined time data (sample data) is taken out from the measurement data of the vehicle speed of the preceding vehicle. The traffic congestion determination unit 25 determines whether the vehicle speed fluctuation integrated value of the preceding vehicle is larger than a threshold (fourth threshold value) of the vehicle speed fluctuation integrated value of the preceding vehicle. If the integrated value of the vehicle speed fluctuation of the preceding vehicle is larger than the fourth threshold (S9; Yes), it is determined that the vehicle is congested and the process proceeds to S10. If it is equal to or less than the fourth threshold (S9; No), it is determined that no traffic congestion has occurred, and the process proceeds to S11. In the present embodiment, the traffic congestion is determined using the integrated vehicle speed fluctuation value of the preceding vehicle, but the vehicle speed of the preceding vehicle at a certain time is extracted to calculate the fluctuation amount, and the traffic congestion judgment is performed using this fluctuation amount You may

  In S10, the driver state determination unit 23 compares the cycle in which the vehicle speed of the preceding vehicle fluctuates (the vehicle speed cycle of the preceding vehicle) with the cycle in which the vehicle speed of the host vehicle fluctuates (the vehicle speed cycle). It is determined whether the characteristics are substantially the same (whether or not they substantially match). Specifically, the driver state determination unit 23 compares the vehicle speed cycles of the preceding vehicle and the own vehicle to calculate the deviation, and determines whether the absolute value of the deviation is equal to or less than a fifth threshold (second Processing; Driver state determination processing at the time of traffic congestion). When comparing the vehicle speed cycles of the preceding vehicle and the own vehicle, the time lag elapses with respect to the vehicle speed cycle of the preceding vehicle in a predetermined time, taking into consideration that the own vehicle moves behind the movement of the preceding vehicle (time lag) The comparison is made for the own vehicle cycle at a later predetermined time. If the vehicle speed cycles of the preceding vehicle and the own vehicle are substantially the same (if the absolute value of the deviation is equal to or less than the fifth threshold) (S10; Yes), the driver is in a normal state, and this flow ends. If the vehicle speed cycles of the preceding vehicle and the own vehicle are different (if the absolute value of the deviation is larger than the fifth threshold) (S10; No), it is determined that the driver is abnormal and the process proceeds to S11.

  Next, in S11, the driver state determination unit 23 calculates an integral value (inter-vehicle distance variation integral value) of the variation amount of the inter-vehicle distance between the preceding vehicle and the host vehicle. This calculation method is the same as the method shown in S3 of the first embodiment except that the latest predetermined time data (sample data) is taken out from the measurement data of the inter-vehicle distance. The driver state determination unit 23 determines whether the inter-vehicle distance change integral value is larger than a threshold (sixth threshold value) of the inter-vehicle distance change integral value (second process; driver state determination process by inter-vehicle distance) . If the inter-vehicle distance fluctuation integral value is larger than the sixth threshold (S11; Yes), it is determined that the driver is in an abnormal state, and the process proceeds to S12. If it is equal to or less than the sixth threshold (S11; No), the driver is in a normal state, and the present flow ends. In the present embodiment, although the determination is made using the inter-vehicle distance variation integral value, the inter-vehicle distance at a certain time is extracted to calculate the variation amount, and the driver's state is determined using this variation amount. Good.

  In S12, the driver state determination unit 23 obtains information on the current traveling environment (highway, city area, etc.) from the traveling environment information acquisition unit 9, and determines whether the vehicle is traveling in the city area. If the vehicle is traveling in the city (S12; Yes), the process proceeds to S13. When the vehicle is traveling outside the city area (for example, a highway, a mountain road, etc.) (S12; No), the process proceeds to S14 of the third process.

  Next, in S13, the driver state determination unit 23 determines whether the brake reaction time is larger than the threshold (the seventh threshold) of the brake reaction time (second process; driver state determination based on the brake reaction time) processing). If the brake reaction time is larger than the seventh threshold (S13; Yes), it is determined that the driver is in an abnormal state, and the process proceeds to S14 of the third process. If it is equal to or less than the seventh threshold (S13; No), the driver is in a normal state, and the present flow ends.

  Here, the reason for performing S12 before performing the process of S13 will be described. When traveling outside the city area (highway, mountain road, etc.), the driver travels away from the preceding vehicle, so in most cases the driver performs the brake operation quite late after the brake lamp of the preceding vehicle is lit. is there. If S12 is not executed and the driver state determination process of S13 is executed, the brake reaction time will be longer when traveling outside the city area, so the driver is in an abnormal state regardless of the normal state. There is a risk of falsely determining that there is. For this reason, before performing the driver state determination of S13, the determination accuracy of S13 is improved by excluding in advance the case of traveling outside the city area (highway, mountain road, etc.) in S12.

Next, the (action) effect of the present embodiment will be described.
In the driver state determination device 1 of the present embodiment, a determination value (multiplied value obtained by multiplying the integral value of the variation amount of the vehicle speed and the integral value of the variation amount of the offset distance within a predetermined time by the driver condition determination unit 23 The first driver state determination process is performed to determine whether the driver is in an abnormal state based on the above (S6). In this embodiment, compared to the conventional method, the driver's state can be determined with high accuracy without being influenced by the driver's face characteristics and temporary symptoms, and the driver's steering skill. . In addition, processing is easier as compared with the conventional driver state determination method using image processing, processing speed can be improved, and power consumption of the apparatus can be suppressed.

  In the present embodiment, preferably, the driver state determination unit 23 executes the first driver state determination process when the offset distance is equal to or greater than the first threshold (S2; Yes) (S6). ). In the present embodiment configured as described above, the first driver state determination process can be executed excluding in advance the case where the driver is in the normal state. For this reason, the number of times of execution of the first driver state determination process can be reduced, and power consumption of the device can be suppressed.

  In the present embodiment, after the driver state determination device 1 determines that the driver is in the abnormal state by the first driver state determination process, it is determined whether the travel path of the vehicle is congested or not. A determination unit 25 is provided. If the traffic congestion determination unit 25 determines that there is a traffic congestion (S9; Yes), the driver state determination unit 23 compares the cycle of the vehicle speed fluctuation of the preceding vehicle with the cycle of the vehicle speed fluctuation of the vehicle. The driver state determination process at the time of traffic congestion is executed (S10). When the traveling road is congested, the first driver condition determination process determines the driver's abnormal condition because the variation amount of the vehicle speed and the offset distance used in the first driver condition determination process is small. Is difficult. However, in this embodiment configured as described above, when the traveling road is congested, the abnormal condition of the driver is accurately determined in order to compare and determine the period of the vehicle speed fluctuation of the preceding vehicle and the vehicle. can do.

  Further, in the present embodiment, preferably, the driver condition determination device 1 further includes an inter-vehicle distance measurement unit (the radar 7 and / or the camera 3 outside the vehicle), the brake sensor 11, and the in-vehicle camera 13. After determining that the driver is in an abnormal state by the first driver state determination processing, the driver state determination unit 23 calculates an integrated value of the variation amount of the inter-vehicle distance obtained from each device, a brake reaction time, Based on the determination result of the driver's captured image by the in-vehicle camera, it is determined whether or not the driver is in an abnormal state (driver condition determination process S11 by inter-vehicle distance, driver condition determination process S13 by brake reaction time, Third driver determination processing S14). In such an embodiment, the state of the driver can be determined more accurately.

  In the present embodiment, preferably, the driver state determination device 1 performs automatic driving support processing on the notification device 17 that performs notification processing for causing the driver to perform normal driving and / or the vehicle. A support device 18 is provided. When it is determined by the driver state determination unit 23 that the driver is in an abnormal state, the notification device 17 executes notification processing or / and the automatic driving support device 18 executes automatic driving support processing. In the present embodiment configured as described above, the notification device 17 and / or the automatic driving support device 18 can be accurately executed to cause the driver to drive normally or drive assistance can be performed automatically.

  Without being limited to the above-described embodiment of the present invention, various changes and modifications are possible within the scope of the technical idea described in the claims.

DESCRIPTION OF SYMBOLS 1 Driver state determination apparatus 3 Outside camera 5 Vehicle speed sensor 7 Radar 9 Driving environment information acquisition part 11 Brake sensor 13 In-vehicle camera 15 ECU
17 notification device 18 automatic driving support device 19 data analysis unit 21 storage unit 23 driver state determination unit 25 traffic congestion determination unit

Claims (8)

A driver state determination device that determines an abnormal state of a driver driving a vehicle,
An outside camera for imaging the front of the vehicle;
A vehicle speed sensor for detecting the vehicle speed of the vehicle;
A data analysis unit that calculates an offset distance of the vehicle in the lateral direction with respect to a reference position on the traveling road based on the image captured by the camera outside the vehicle;
And a driver state determination unit that determines an abnormal state of the driver based on the vehicle speed and the offset distance.
The driver state determination unit determines the driver's abnormal state based on a determination value obtained by multiplying an integral value of the variation amount of the vehicle speed and an integral value of the variation amount of the offset distance within a predetermined time. A driver's condition determination apparatus characterized in that it is configured to execute a person's condition determination process.   The driver state determination device according to claim 1, wherein the driver state determination unit is configured to execute the driver state determination process when the offset distance is equal to or more than a predetermined threshold. After the driver state determination process determines that the driver is in an abnormal state, a traffic congestion determination unit that determines whether the travel path of the vehicle is congested or not is included,
When it is determined that the traffic jam determination unit is congested, the driver state determination unit further performs driving based on the result of comparing the cycle of the vehicle speed fluctuation of the preceding vehicle and the cycle of the vehicle speed fluctuation of the vehicle. The driver state determination device according to claim 1, wherein the driver state determination device is configured to determine an abnormal state of a person. The traffic jam determining unit determines whether or not the travel path is congested based on the vehicle speed of the vehicle and the integral value of the fluctuation amount of the vehicle speed of the preceding vehicle at a predetermined time,
The driver state determination unit is configured to determine that the driver is in the normal state when the cycle of the vehicle speed fluctuation of the preceding vehicle and the cycle of the vehicle speed fluctuation of the vehicle are substantially the same. The driver state determination device according to claim 3. An inter-vehicle distance measuring unit that measures an inter-vehicle distance between the vehicle and the preceding vehicle;
After the driver state determination processing determines that the driver is in the abnormal state, the driver state determination unit further determines the driver abnormality based on the integral value of the variation amount of the inter-vehicle distance in a predetermined time. The driver state determination device according to any one of claims 1 to 4, which is configured to determine a state. It has a brake sensor which detects the brake operation of the driver of the above-mentioned vehicle,
After the driver state determination process determines that the driver is in the abnormal state by the driver state determination process, the driver state determination unit further detects the lighting of the brake lamp of the preceding vehicle by the camera outside the vehicle and then the brake sensor by the brake sensor. The driver state determination device according to any one of claims 1 to 5, wherein the driver's abnormal state is determined based on a brake reaction time until detection of the brake operation. Has an in-vehicle camera to image the driver,
After the driver state determination processing determines that the driver is in the abnormal state, the driver state determination unit further determines the driver's abnormal state based on the image of the driver captured by the in-vehicle camera. The driver state determination device according to any one of claims 1 to 6, wherein the driver state determination device is configured to determine The vehicle includes a warning process for causing the driver to drive normally and / or risk avoiding means for executing an automatic driving support process for the vehicle,
8. The danger avoidance means executes the notification process or / and the automatic driving support process when the driver state determination unit determines that the driver is in an abnormal state. The driver state determination device according to item 5.

Images