JPH08178712A - Rambling-drive detection apparatus - Google Patents

Abstract

PURPOSE: To obtain a rambling-drive detection apparatus which judges whether a drive is a rambling drive or not by detecting the visual line of a driver. CONSTITUTION: The visual-line direction of a driver is detected by a visual-line detection sensor 10 which uses an infrared difference image or the like, and a stop position and the stop time are measured by a by-stop-point X-Y- coordinate counter 38 and a within-stop-range stop-time measuring part 28. In a rearview-mirror and side-view-mirror position estimation part 20, the visual- line position on a rearview mirror or a side-view mirror of a driver is estimated on the basis of detected visual-line data, and the number of confirmations is measured by a rearview-mirror and side-view-mirror number-of-confirmations counter 22. In a rambling drive, the number of confirmations is reduced as compared with that in a normal drive. As a result, when the number of confirmations is compared with a prescribed threshold value, a rambling-drive judgment part 40 judges whether a drive is a rambling drive or not, and it drives a warning part 42 so as to generate a warning. A judgment-reference threshold value is changed on the basis of a signal from a preceding-vehicle judgment part 32 or a running-environment judgment part 34, and a judgment reference value according to a running road is set.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an ambush driving detection device, and more particularly to a device for detecting a driver's line of sight to detect an ambush driving.

[0002]

2. Description of the Related Art Conventionally, there has been proposed a structure for detecting a driving state of a vehicle driver to issue an alarm or control a vehicle speed. For example, in Japanese Patent Laid-Open No. 3-260900, C
The face of the vehicle driver is imaged with a CD camera, the coordinate values of the LED attached to the center of the eyeglasses are obtained in the image, and the coordinate values regarding the reference position where the LED should be located when the driver is driving normally are calculated. Disclosed is a configuration in which the direction and angle of the face are obtained from the deviation of the coordinate position, and when the angle is equal to or more than the allowable angle for the allowable time or longer, it is determined that the driver is driving while looking aside or dozing, and an alarm is issued. Has been done.

[0003]

As described above, the side-view driving or the drowsiness driving of the vehicle driver can be detected to some extent by the direction of the face or the awakening level. However, the vehicle driver must think something while driving. It is impossible to unambiguously detect a state where the driver is driving in a casual manner, that is, a so-called silent driving, from the direction of the face. That is, when driving unconsciously, a vehicle driver generally tends to gaze at a certain point in front of him, and the direction of his face hardly changes from that during normal driving. Because there is no change.

The present invention has been made in view of the above problems of the prior art, and an object of the present invention is to provide an ambush driving detection device capable of surely detecting ambush driving and giving more accurate warning and the like. is there.

[0005]

In order to achieve the above object, an ambush driving detecting apparatus of the present invention includes a gaze detecting means for detecting a gaze direction of a driver, and a gaze of a driver based on the detected gaze direction. And a determination means for determining the degree.

In order to achieve the above-mentioned object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 1, wherein the determination means is based on the frequency of the driver's specific line-of-sight direction. It is characterized by judging the degree of inattention.

Further, in order to achieve the above-mentioned object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 2, wherein the specific line-of-sight direction is at least the direction of a rearview mirror or a side mirror of a vehicle. Is characterized in that.

In order to achieve the above-mentioned object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 3, wherein the line-of-sight detecting means has a predetermined direction having a most frequent direction at the line-of-sight center. The case where the driver's line of sight deviates from the gaze range for a certain period of time is specified as the direction of the rearview mirror or the side mirror.

Further, in order to achieve the above object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 1, wherein the determination means is based on a change in the line-of-sight range of the driver. Is determined.

Further, in order to achieve the above object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 5, wherein the change of the line-of-sight range is evaluated by the moving distance of the line-of-sight. Characterize.

Further, in order to achieve the above object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 5, wherein the change of the line-of-sight range has the most frequent direction in the line-of-sight center. The predetermined gaze range is divided into a plurality of areas, and evaluation is made by the ratio of the number of stationary points of the line of sight in each divided area.

Further, in order to achieve the above-mentioned object, the absent-minded driving detecting apparatus of the present invention comprises a dwell time detecting means for detecting a dwell time of the line of sight of the driver and a daze degree of the driver based on the detected dwell time. And a determining means for determining.

In order to achieve the above-mentioned object, the absent-minded driving detecting device of the present invention is the absent-minded driving detecting device according to claim 8, wherein the determining means determines the statistical value of the detected dwell time and a predetermined value. The feature is that the degree of aimlessness is judged by comparing with a threshold value.

Further, in order to achieve the above object, the absent-minded driving detecting device of the present invention is the absent-minded driving detecting device according to claim 8, wherein the determination means determines the detected dwell time by a predetermined threshold value. It is characterized in that the degree of inattention is judged by comparing with.

Further, in order to achieve the above object, the ambush driving detection device of the present invention is the absent driving operation detection device according to claim 9 or 10, wherein the determining means provides the threshold values in a plurality of stages. , It is characterized in that the degree of aimlessness is determined stepwise by comparing with each threshold value.

Further, in order to achieve the above object, the absent-minded driving detecting device of the present invention comprises a line-of-sight detecting means for detecting the line-of-sight direction of the driver, and a dwell-time detecting means for detecting the dwell time of the line-of-sight of the driver. And a determination means for determining the driver's a sense of indifference based on the detected line-of-sight direction and dwell time.

In order to achieve the above object, the ambush driving detection device of the present invention is the absent driving detection device according to claim 1, 8 or 12, further comprising:
It is characterized in that it has environment recognition means for recognizing the traveling environment of the vehicle, and the judging means changes the judgment standard of the absentness degree according to the traveling environment.

In order to achieve the above object, the ambush driving detection device of the present invention is the absent driving detection device according to claim 1, 8 or 12, further comprising:
It is characterized in that it has environment recognition means for recognizing a traveling environment of the vehicle, and the judging means changes an update time of data used for the judgment in accordance with the traveling environment.

In order to achieve the above-mentioned object, the ambush driving detection device of the present invention is the absent driving detection device according to claim 1 or claim 8 or claim 12, further comprising:
It has a standard setting means for setting a judgment standard on the basis of the data at the time of normal operation, and the judgment means is characterized by judging the aimlessness using the set judgment standard.

In order to achieve the above object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 13 or 14, wherein the environment recognition means is
It is characterized by including a preceding vehicle detection means.

In order to achieve the above object, the ambush driving detection device of the present invention is the absent-mind driving detection device according to claim 13 or 14, wherein the environment recognition means is
It is characterized by including a vehicle speed detection means.

Further, in order to achieve the above-mentioned object, the absent-minded driving detection device of the present invention is provided by claim 13 or claim 14.
In the absent-minded driving detection device described above, the environment recognition means includes an identification means for identifying a traveling path.

[0023]

In the ambush driving detection device according to the first aspect of the present invention, attention is paid particularly to the line-of-sight direction of the vehicle driver, and the agitation degree is determined based on the line-of-sight direction. As mentioned above, when driving casually,
The driver tends to gaze at a point in front of the driver, which causes a deviation in the direction of the line of sight. Therefore, by detecting this bias, it is possible to determine whether the vehicle driver is driving blindly.

The line-of-sight direction can be specified by detecting the iris position of the eyes of the vehicle driver as described later.

In the ambush driving detection device according to the second aspect, the agitation degree is determined based on the frequency of the driver's specific line-of-sight direction. As described above, the driver tends to gaze at a point in front of the driver when he or she is aimlessly driving. Therefore, the driver tends not to see the direction that he would normally see during normal driving, and the frequency of the direction tends to decrease. Therefore, it is possible to accurately determine the degree of apathy based on the frequency of the driver's specific line-of-sight direction.

In the ambush driving detection device according to the third aspect, the agitation degree is determined based on at least the frequency in the direction of the rearview mirror or the side mirror of the vehicle. During normal driving, the driver often looks at the rear by looking at the rear-view mirror or by looking at the side of the vehicle by looking at the side-view mirror.
Therefore, during normal operation, the line of sight occurs in the direction of the rearview mirror or side mirror at a certain frequency. On the other hand, such a rear-view mirror or side-view mirror is not often checked when driving in a casual manner.
Ambush driving can be detected based on the decrease in the frequency of the gaze direction in this direction.

In the ambush driving detection device according to the fourth aspect, attention is paid to the fact that the confirmation of the rearview mirror or the side mirror is outside the forward gaze range during normal driving, and a predetermined gaze with the most frequent direction as the center of the line of sight When the driver's line-of-sight direction deviates from the range for a certain period of time, the direction of the rear-view mirror or side-mirror is specified, and the line-of-sight direction to the rear-view mirror or side-mirror is reliably detected.

In the ambush driving detection device according to the fifth aspect, the agitation degree is determined based on the change of the line-of-sight range of the driver. In the absent-minded driving detection device according to claim 2, the aggression degree is determined based on the frequency of the driver's specific line-of-sight direction. However, in view of the fact that the driver tends to pay attention to a specific direction during involuntary driving, more directly The degree of aimlessness can be determined based on the change in the gaze range.

In the ambush driving detection device according to the sixth aspect, the change in the line-of-sight range is evaluated by the moving distance of the line-of-sight. That is, in normal driving, the line-of-sight range is widened to widely check the surrounding environment of the vehicle, and the line-of-sight movement distance is large. Therefore, it is possible to determine whether or not the driver is aimlessly driving by evaluating the magnitude of the moving distance of the line of sight.

In the absent-minded driving detection device according to the seventh aspect, the gaze range is divided into a plurality of regions, for example, the central region and the left and right regions, and the number of stationary points of the line of sight in each divided region is compared.
During normal operation, the line of sight stops are distributed to each of the divided areas to see a wide range, but at the time of aimless driving, there is a tendency to gaze at a certain point, so the line of sight stops in a specific area, such as the central area. The points will be concentrated. Therefore, by evaluating the ratio of the number of stationary points of the line of sight in each divided area, it is possible to determine whether or not the driver is aimlessly driving. In addition,
“Standing” means a state in which the line of sight remains within a certain limited range for a certain period of time.

In the ambush driving detection device according to the eighth aspect of the present invention, the dwell time of the line of sight is detected, and the daze degree of the driver is determined based on the dwell time. As described above, the driver tends to pay attention to a specific direction while he is driving, and thus the line of sight in the specific direction tends to stay longer than during normal driving. Therefore, the dullness can be reliably detected by detecting the dwell time and comparing it with a predetermined value.

In the absent-minded driving detection device according to claim 9, the stationary time is statistically processed and the statistically processed value is compared with a predetermined threshold value. If the driver is driving continuously for a certain period of time, is the driver's situation normal?
Alternatively, the tendency of being in a dull state can be determined by statistical processing of collected data, and by comparing the statistically processed value with a predetermined threshold value, variations in collected data can be absorbed and a tendency of long-term dumb driving can be secured. Can be detected.

According to the tense driving detection device of the tenth aspect,
Instead of comparing the statistically processed value of the dwell time with a predetermined threshold as in the absent-ride driving detection device according to claim 9, each detected dwell time is compared with a predetermined threshold.
Judge driving in real time. As a result, even if the dwell time for one line of sight suddenly becomes longer, it can be determined that the driver is aimlessly driving, and in an emergency situation such as when the distance from the preceding vehicle is short, the aimlessly driving is determined. it can.

In the absent-minded driving detection device according to claim 11,
A plurality of thresholds for determining whether the vehicle is absent-minded are provided, and statistically processed values of dwell times or individual dwell times are compared with respective predetermined thresholds. This makes it possible to evaluate the degree of inattentiveness stepwise and output an alarm according to the level of inattentiveness.

In the ambush driving detection device according to claim 12,
The driver's apathy is determined based on the line-of-sight direction and the line-of-sight dwell time. As described above, it is possible to determine the aggression degree by either the line-of-sight direction or the dwell time, but by using these two physical quantities together, the agitation degree of the driver can be determined more reliably.

In the absent-minded driving detection device according to claim 13,
When judging the degree of inattentiveness based on the gaze direction and the staying time,
The criteria for the degree of inattention are changed in consideration of the driving environment of the vehicle. The direction of the line of sight and the stopping time of the line of sight differ depending on the city area and highway driving, and also depending on the vehicle speed and the presence or absence of a preceding vehicle.
Therefore, by changing the determination standard of the degree of aggression according to these running environments, the degree of agitation can be reliably determined regardless of the running environment.

In the absent-minded driving detection device according to claim 14,
The update time of the data used for the determination of the absentness is changed according to the running environment of the vehicle. In the case of statistically processing the data of the line-of-sight direction and the staying time of the line-of-sight, and determining the degree of aimlessness based on the statistically processed value, the degree of variation of individual data varies depending on the traveling environment. For example, when driving in an urban area, there is a wide range of objects to be noted, so that the variation in data becomes large. Therefore, it is necessary to collect a large number of data in order to obtain highly reliable data. Therefore, by changing the update time of the data used for the determination according to the traveling environment, the required number of data according to the traveling environment can be acquired, and a quick determination process can be performed.

In the ambush driving detection device according to claim 15,
When judging the degree of aggression based on the line-of-sight direction or the line-of-sight dwell time, instead of using a predetermined threshold value, the threshold value is learned during normal driving, and comparison with this learning threshold value is used to determine whether the driver is aimlessly driving. To determine. As a result, a threshold value can be set according to each driver, and the degree of aimlessness can be determined more adaptively.

In the ambush driving detection device according to the sixteenth to eighteenth aspects, the preceding vehicle, the vehicle speed, and the traveling path are recognized as the traveling environment. When the preceding vehicle is present, the driving task of the driver is smaller than when the preceding vehicle is not present, so that the line-of-sight direction is relatively narrow even during normal driving, and the dwell time tends to be long. Further, the higher the vehicle speed, the narrower the line-of-sight range, and there is a tendency to gaze at one point. Furthermore, the line-of-sight range is narrower and the dwell time tends to be longer when traveling on an expressway than when driving on an urban street.

In this way, the presence / absence of a preceding vehicle, the speed of the vehicle,
Alternatively, it is possible to more adaptively determine the driver's sense of indifference by changing the determination criterion according to the traveling route such as city driving or highway driving.

[0041]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 shows the overall construction of this embodiment. A line-of-sight detection sensor 10 that detects the line of sight of the vehicle driver is provided near the vehicle driver's seat. This line-of-sight detection sensor 1
For example, 0 means that a strong reflection image is obtained from the eye when a light source is placed on the line of sight, and two different infrared wavelengths are applied to the eyes of the vehicle driver, and two characteristic reflections are emitted. The line-of-sight direction can be detected by acquiring an image and extracting the reflection image of the iris portion from the difference image, or by detecting the visible-light direction as in the line-of-sight direction detection method disclosed in Japanese Patent Laid-Open No. 3-165737, for example. It is also possible to detect the gaze direction by extracting the iris part by comparing the difference image between the two images of the camera and the infrared light sensing camera with an appropriate threshold value. The line-of-sight detected by the line-of-sight detection sensor 10 is output to the line-of-sight counter for each XY coordinate, the stop range / stop time condition determination unit 26, and the stop range in-stop time measuring unit 28, respectively.

The line-of-sight counter 24 for each XY coordinate supplies the position in the line-of-sight direction from the sampling timer 36 with the line-of-sight detection range shown in FIG. 4 as the horizontal direction (X direction) and the vertical direction (Y direction) as the orthogonal coordinates. The number of line-of-sight points for each coordinate is counted. Thereby, the count value within each predetermined time at each coordinate point is obtained. In addition, the stopping range / stopping time condition determining unit 26 determines whether or not a set of line-of-sight points has passed a predetermined time or more within a predetermined range, that is, whether or not it can be determined as a stopping point. It outputs to the stationary point XY coordinate counter 38. When the stop range / stop time condition determination unit 26 determines that the stop point is reached, the stop range within stop time measuring unit 28 measures the time of the stop point. If it is determined that the station is not the stop point, the measurement time data is discarded. The staying time within the staying range measuring unit 28 sequentially measures the staying time within a predetermined staying range. The rear-view mirror / side-mirror position estimation unit 20 estimates the position in the line-of-sight direction that the vehicle driver would obtain when he / she looks at the rear-view mirror or side-view mirror. Since the line-of-sight detection sensor 10 performs line-of-sight detection by utilizing the corneal reflection of the eye as described above, it is necessary to perform the correction for each driver in consideration of the fact that the curvature of the cornea differs depending on the individual driver. However, it is difficult to automatically and accurately correct the absolute coordinates of the line of sight, and therefore it is necessary to estimate the positions of the rearview mirror and the side mirror that differ for each driver. Therefore, in the rear-view mirror / side-mirror position estimation unit 20,
The fact that not only the line of sight but also the face move at the same time when checking the rearview mirror and side mirrors, unlike the case of looking forward, the fact that the detected gaze direction deviates greatly from the time of looking forward is used. FIG. 4 shows the line-of-sight detection range when the visual field range during normal traveling is ± 10 ° in the vertical direction and 20 ° in the horizontal direction. The case where the deviation largely deviates in a specific direction is shown by diagonal lines in the figure. Of course, these rear-view mirror detection expected ranges and side-mirror detection expected ranges differ depending on individual drivers, so it is necessary to estimate these expected ranges from the number of acquired data within a predetermined time after the start of driving. Further, the rear-view mirror / side-mirror confirmation frequency counter 22 determines whether or not the rear-view mirror / side-mirror position estimation unit 20 estimates the rear-view mirror detection range and the detected line-of-sight direction within the side-mirror detection range. It is determined whether or not it exists, and if it exists, the count value is sequentially incremented and the number of confirmations is counted. The outputs of the stop point XY coordinate-specific counter 38 and the stop range in-stop time measuring unit 28 are input to the rear-view mirror / side-mirror position estimating unit 20. The count value from the rear-view mirror / side-mirror confirmation frequency counter 22 and X
The count value from the line-of-sight counter 24 for each Y coordinate, the evaluation value from the counter 38 for each stop point X-Y coordinate, and the stop time value from the stop time measuring unit within the stop range 28 are objective driving determination unit 4.
It is output to 0, a determination process described below is performed to determine the degree of apathy, and when absent-minded driving is detected, a control signal is output to the alarm unit 42 to issue an alarm.

On the other hand, a steering angle sensor 12, a vehicle speed sensor 14, and a front monitoring sensor 16 are provided as means for recognizing the traveling environment of the vehicle. As the front monitoring sensor 16, for example, a CCD camera or the like is used. These detection signals are the same as the above-described detection signals from the line-of-sight detection sensor 10 and signals from the timer 18, and the driver's line-of-sight characteristic recording unit 3
It is output to 0, is stored as a personal characteristic, and the line-of-sight center coordinates of the driver are calculated. The line-of-sight center coordinates are output to the above-mentioned rear-view mirror / side-mirror position estimation unit 20. In addition, the detection signal from the front monitoring sensor 16 is output to the preceding vehicle determination unit 32, and the presence or absence of the preceding vehicle is detected. Further, the steering angle sensor 12, the vehicle speed sensor 1
4. The detection signal from the front monitoring sensor 16 is output to the traveling environment determination unit 34, and it is identified whether the traveling path on which the vehicle is traveling is a downtown area, an urban area, a national road (prefectural road), or an expressway. . In addition to the identification from the sensor, the traveling road information for identifying the traveling road receives information indicating the road environment from the map data of the navigation system and the infrastructure such as beacons installed on the road by radio waves or the like. The method is also good. Driver line-of-sight characteristics recording unit 3
Each signal from 0, the preceding vehicle determination unit 32, the vehicle speed sensor 14, and the traveling environment determination unit 34 is output to the aimless driving determination unit 40,
The threshold value is set according to the driver, and the threshold value is changed depending on the presence or absence of a preceding vehicle and the traveling environment, and the degree of absentness is determined. The traveling environment estimating unit 34 outputs a reset signal to the driver's line-of-sight characteristic recording unit 30 when the traveling road changes, and the data is accumulated for each traveling road.

Hereinafter, the processing performed by the aimless driving determination section 40 will be described based on the direction of the line of sight, the processing based on the dwell time,
The processing based on the line-of-sight direction + stopping time will be roughly described.

Processing by line-of-sight direction During conscious driving, most of the consciousness is occupied by the part other than driving (thinking) and forward gaze. Therefore, it is expected that rear-view confirmation by the rear-view mirror and rear-side monitoring by the side-view mirror will be neglected. FIG. 2 shows the number of times the rearview mirror and side mirrors are checked (value for 10 minutes) during normal driving and aimless driving. It can be seen that the number of times the rear-view mirror and side-view mirrors are checked is drastically reduced during involuntary driving compared to normal driving. Therefore, for example, 60% of the number of times the rear-view mirror and the side-view mirror are checked during normal operation is set as a determination threshold value, and by comparing with this threshold value, it can be determined whether or not the vehicle is involuntary operation.

FIG. 3 shows a processing flowchart for judging the ambush driving based on the number of times the rearview mirror and the side mirror are confirmed. In FIG. 3, first, based on the detection signal from the line-of-sight detection sensor 10, the rear-view mirror / side-mirror confirmation number counter 22 counts the number of confirmations of the rear-view mirror and the side mirror within a fixed time (S101). This counting is performed depending on whether the line-of-sight direction is located at the rear-view mirror position and the side-mirror position estimated by the rear-view mirror / side-mirror position estimating unit 20 as described above, and details thereof will be described later. Then, the initial stage of driving (for example, 10 minutes) is learned as the number of confirmations during normal driving and recorded in the driver's line-of-sight characteristic recording unit 30 (S102). Next, the absent-minded driving determination unit 40 calculates 60% (learning value × 0.6) of the count value during normal driving stored in the driver's line-of-sight characteristic recording unit 30, and sets this threshold as a threshold value. The value is compared with the latest confirmation count for 10 minutes (S103). If the number of times the latest rearview mirrors and sideview mirrors have been confirmed for the last 10 minutes is less than or equal to the threshold value, it is determined that the driver is in a dull driving state, a control signal is output to the alarm unit 42, and an alarm is generated. Do (S
104). On the other hand, if the latest number of confirmations in 10 minutes is larger than the threshold value, it is determined that the rearview mirror and the side mirror are confirmed as in the normal operation, and no alarm is output.

As described above, the number of confirmations of the rearview mirror and the side mirrors is counted and compared with the threshold value calculated based on the number of confirmations during the normal operation, so that it can be surely determined whether or not the driving is aimless. You can

In this way, in the structure in which the number of confirmation times of the rear-view mirror and the side mirror is counted to judge the aimless driving, it is essential to accurately detect the line-of-sight direction at the time of confirming the rear-view mirror and the side mirror. Is important to. In this embodiment, the positions of the rear-view mirror and side-mirror position estimating section 20 in the line-of-sight range of the rear-view mirror and side-mirror are estimated as described above, and the details are as follows.

FIG. 5 shows a processing flowchart for estimating the positions of the rearview mirror and the sideview mirror in the rearview mirror / sideview mirror position estimating section 20.
The basic principle of this process flow chart is that the driver's line of sight during normal driving is approximately ± 10 ° in the vertical direction and ± 20 ° in the horizontal direction. This is based on the fact that the line-of-sight direction exceeds the detection range of such vertical, horizontal, and visual field ranges because the whole moves (see FIG. 4).
On the other hand, in order to confirm the rear or side, it is necessary to look toward the rearview mirror or the sideview mirror and continue to look at the rearview mirror or the sideview mirror for a certain period of time. So, whether you confirmed the rearview mirror or the side mirror,
Coordinates that deviate from the predetermined line-of-sight detection range (± 10 ° in the upper limit direction, ± 20 ° in the left-right direction), and have a fixed time or more for a fixed time and a fixed number of gazes for the rear-view mirror or side Recognize as the mirror position. That is, in FIG. 5, it is determined whether or not the detected line-of-sight angle (line-of-sight direction) exceeds the detection range (S201), and if it exceeds ± 10 ° in the vertical direction and ± 20 ° in the horizontal direction, Next, it is determined whether or not it is within the rear-view mirror detection expected range or the side-mirror detection expected range (S20).
2). The assumed range is set in advance.
When the detected line-of-sight angle is within the rear-view mirror detection expected range or the side-mirror detection expected range, it is next determined whether or not the line-of-sight stop time is a fixed time (for example, 0.3 seconds) or more. (S203). This determination is made based on the output from the staying time within stop range measuring unit 28. If the stop time is more than a certain time, the stop point X
The number counted by the Y-coordinate counter 38 is stored in the memory for each XY coordinate (S204), and it is determined whether the number of line-of-sight retention stored in the memory exceeds a predetermined number (for example, 20). (S205). When the line-of-sight detection range is exceeded, and the dwell time is a certain time or more, and if it occurs repeatedly, it is determined that the line-of-sight direction is due to the confirmation of the rear-view mirror or side-mirror, and the respective coordinates are rear-view mirror coordinates, It is recognized as the side mirror coordinates (S206).

In this way, the rear-view mirror coordinates and the side-mirror coordinates are recognized, and when the rear-view mirror / side-mirror confirmation frequency counter 22 detects the detected coordinates in the line-of-sight direction within the predetermined error range. Determines that the rearview mirror and side mirror have been confirmed, and sequentially increments the count value and counts the number of confirmations.

In order to determine the visual axis detection range shown in FIG. 4, it is necessary to extract the center of the visual axis of the driver. Since the center point of the line of sight differs depending on the vehicle driver, it cannot be uniformly determined, and it is necessary to collect the line of sight data of the actual driver and extract the center point from the data.

In FIG. 6, the operation is performed by the driver's line-of-sight characteristic recording unit 30. A process flow chart for extracting the line-of-sight center point is shown. In FIG. 6, first, based on the detection signal from the front monitoring sensor 16, the preceding vehicle determination unit 32 determines whether or not there is a preceding vehicle (S301). When there is a preceding vehicle, the steering angle is within a predetermined angle (for example, ±±) based on the detection signal from the steering angle sensor 12.
Within 5 °) (S302), if it is determined that the steering angle is going straight within a predetermined angle, the vehicle is further detected based on the detection signal from the vehicle speed sensor 14. It is determined whether or not the vehicle is traveling at a predetermined speed (for example, 40 km / h) or more (S303). When there is a preceding vehicle, the vehicle is straight ahead, and the vehicle speed is equal to or higher than the predetermined speed, the driver's visual line characteristic recording unit 30 displays the visual line data detected by the visual line detection sensor 10 at a predetermined frequency (for example, 30 Hz). Sampling is performed and the line-of-sight coordinates are stored in the memory (S304). When the number of samplings exceeds a predetermined number (for example, 10,000), the 10,000
The coordinate with the highest frequency is recognized as the line-of-sight center coordinate from the sampling data (S305, S306).
The line-of-sight center coordinates recognized in this way are output to the rear-view mirror / side-mirror position estimation unit 20 and set as the center point of the line-of-sight detection range shown in FIG. And
The horizontal direction ± 20 ° and the vertical direction ± 10 ° are determined as the line-of-sight range (front center range).

As described above, the number of times the rearview mirror and the side mirror are checked is counted based on the detected line-of-sight direction and compared with a predetermined threshold value to determine whether or not the driver is intently driving. It is also possible to make a determination using any of the number of confirmation times, and not only the front monitoring sensor 16 but also the rear monitoring sensor is provided, and when the following vehicle is detected, only the number of confirmations of the rear-view mirror is monitored. It is also possible to adopt a configuration in which it is determined whether or not it is driving. It is also possible to monitor the number of confirmations in a certain direction instead of the rearview mirror or side mirror,
The point is that it is possible to use that the frequency in a specific line-of-sight direction changes.

In the above-described embodiment, the number of confirmations of the rearview mirror and the side mirror is counted from the detected line-of-sight direction. However, the range of the line-of-sight changes between normal driving and aimless driving, and is generally aimless. The line of sight tends to be narrower during operation than during normal operation. FIG. 7 shows the line-of-sight range during normal driving (A) and during aimless driving (B). In the figure, the horizontal axis and the vertical axis are bar graphs showing the frequency of appearance at each coordinate of the horizontal and vertical line-of-sight angles (the center point of the line-of-sight being 0 °). It can be seen that the frequency of the vicinity of the center increases during the ambush driving and the gaze range tends to become extremely narrower than during the normal driving. Therefore, for example, paying attention to the horizontal line-of-sight angle,
Whether or not the driver is aimlessly driving can be determined depending on whether or not the line-of-sight angle is within a predetermined range.

FIG. 8 shows a processing flow chart for determining whether or not the driver is intently driving based on the line-of-sight range. In FIG. 8, first, a detection signal from the line-of-sight detection sensor 10 is sampled at a predetermined frequency (for example, 30 Hz) to store the line-of-sight coordinates in the memory (S401).
Specifically, the line-of-sight counter for each XY coordinate calculates the coordinates of the line-of-sight direction based on the timing signal from the sampling timer 36, outputs it to the driver's line-of-sight characteristic recording unit 30, and stores it in the memory. Next, of the obtained line-of-sight coordinates,
The positive and negative maximum values of the line-of-sight angle in the horizontal direction (X direction) are detected and stored in the memory. Then, the average value a is calculated from the absolute values of the obtained positive and negative maximum values. Note that this calculation is performed using the latest 10 minutes of data (S402). Next, it is determined whether or not a predetermined time period (10 minutes after the start of operation and 1 minute thereafter) has elapsed (S403). When the predetermined time has elapsed, the traveling environment determination unit 34 further determines whether the vehicle is It is determined according to the recognized traveling environment by recognizing the traveling road (for example, a downtown area, an urban area, a national road, an expressway) or the presence / absence of a preceding vehicle in the preceding vehicle determination unit 32 (S404). The determination value b is compared with the average value a obtained by the calculation, and the magnitude is compared (S405). The judgment value b is set, for example, to about 15 ° on an urban road, and when the average value a is smaller than this judgment value, it is judged that the vehicle is driving aimlessly and an alarm is output (S406). The reason why the judgment value b is changed according to the traveling environment is that the line-of-sight range changes during normal operation according to the road, etc., as will be described later. On national highways and highways, the line of sight during normal driving tends to narrow.

In the process of FIG. 8, it is determined whether the driver's driving is intentional based on the range of the line-of-sight angle in the horizontal direction. Of course, the range of the line-of-sight angle in the vertical direction is detected and compared with the determination value. It is also possible to determine whether or not it is driving.

On the other hand, the fact that the line-of-sight range changes between the ambush driving and the normal driving in this way means that there is a difference in the moving distance of the line of sight, and the moving distance during the agile driving is smaller than that during the normal driving. It means that there is a tendency to become. Therefore, it is possible to determine whether or not the driver is aimlessly driving by calculating the total of the moving distance of the line of sight (moving distance of the XY coordinate points) within a predetermined time and comparing the total moving distance with a threshold value. It is possible.

FIG. 9 shows a processing flow chart for determining whether or not the driver is aimlessly driving based on the total movement distance. In FIG. 9, first, the line-of-sight detection sensor 10
Based on the detection signal from, the line-of-sight coordinates are stored in the memory at a predetermined sampling frequency (S501). Then, the moving distance of the detected line-of-sight coordinates is calculated (502). When this moving distance is the line-of-sight coordinates (x1, y1) at a certain sampling timing and the line-of-sight coordinates (x2, y2) at the next sampling timing, ((x2-
x1) ² + (y2-y1) ² ) ^0.5 .
Then, the calculated moving distances are sequentially added to obtain the latest 10
The total sum a during the minute is calculated (S503). Next, it is determined whether or not a predetermined time (for example, 10 minutes in the initial stage after the start of operation and thereafter updated every 1 minute) has elapsed (S504), and the traveling environment determination unit 34 or the preceding vehicle determination unit 32 determines. After recognizing the traveling environment (S505), the magnitude of the set value b set based on the recognized traveling environment and the addition sum a are compared (S506). Then, when the addition sum a is smaller than the set value b, it is determined that the vehicle is in an absent-minded driving state, and an alarm is output (S507). Note that changing the set value b according to the recognized running environment is
This is because the moving distance changes depending on the traveling road, as in the case of the determination value b in FIG. 8, and generally, the moving distance tends to be smaller on an expressway than in the case of an urban area or a downtown area.

FIG. 10 shows another processing flowchart using the moving distance. Steps S601 to S603 are the same as steps S501 to S503 in FIG. 9, and in FIG. 10, the cumulative frequency at the stationary point is further calculated, and the maximum frequency b for the latest 10 minutes is calculated and stored in the memory (S604).
Then, it is determined whether or not a predetermined time has elapsed (S60
5), the sum total value a of the calculated movement distances is set to the maximum frequency b.
A value c divided by is calculated, and the value c is compared with the set value d according to the traveling environment (S608). In absent-minded driving, the total sum becomes smaller, but the maximum frequency becomes larger because it concentrates near the center. Therefore, the value of c = a / b becomes even smaller during involuntary driving, and the difference from normal driving becomes clear. Therefore, the aimless driving can be detected more reliably. Although the determination is made based on the line-of-sight data with the sampling timing in FIGS. 8 and 9, only the stationary point data may be extracted from the line-of-sight data to make the determination based on the stationary point.

On the other hand, instead of calculating the total value of the moving distance and comparing it with the threshold value, the line-of-sight detection range is divided into a plurality of regions, and the detection frequencies in the divided regions are counted and compared. By doing so, it is also possible to determine whether or not the driver is aimlessly driving. FIG. 11 shows an example in which the line-of-sight detection range is divided into three areas, that is, a central area, a left area, and a right area. Then, it is possible to determine whether or not the driver is aimlessly driving by calculating the total value of the stationary points of the line of sight in the left region and the right region / the number of stationary points of the line of sight in the central region and comparing them with a threshold value. As described above, the line-of-sight range is narrowed during aimless driving, so that the line-of-sight stop points tend to be concentrated in the central region as compared with the left and right regions. Therefore, the value of (left area + right area) / (center area) becomes smaller during the involuntary driving than in the normal operation, and it can be used to determine whether or not the involuntary driving.

FIG. 12 shows a processing flow chart for determining absent-minded driving by using the divided areas shown in FIG. First, based on the detection signal from the line-of-sight detection sensor 10, the stop-point XY coordinate-by-coordinate counter 38 detects the line-of-sight coordinates of the stopping point and stores it in the memory (S701). The number of stop points located is added to calculate an added total a (S702). Next, the number of stationary points located in the central area is added from the line-of-sight coordinates, and the added total value b is calculated (S703). Then, it is determined whether or not a predetermined time or more has elapsed (S704), and the ratio c = a / b of the number of stationary points in the central region to the number of stationary points in the left and right regions is calculated (S705). Then, the set values d and c corresponding to the traveling environment are compared (S706, S707), and when c is smaller than d, it is determined that the stationary points are concentrated in the central region and the line-of-sight range is narrowed. To output an alarm (S70
8).

The stationary point used in FIGS. 11 and 12 is when the line of sight is within a certain limited range (for example, 2 × 2 °) around a certain start point for a certain time (for example, 0.3 seconds). It is assumed that the line of sight exists at the same place, and this point is defined as the stop point. FIG. 13 shows an example of a stationary point detected by such a definition,
In normal operation, they appear dispersed in the horizontal and vertical directions.

Stopping time In the above-described embodiment of the line-of-sight direction, whether or not the driver is aimlessly driving is determined based on the frequency and range in the specific direction. This is how much the driver pays attention to the surroundings. It focuses on the fact that there is a difference between normal driving and aimless driving. On the other hand, there is a fact that the dwell time of one line of sight is different between normal driving and aimless driving. That is, when the driver is looking intently forward, the length of time per stationary point of one line of sight tends to increase as compared with that during normal driving.

In view of the above facts, an example of determining whether or not the vehicle is driving aimlessly based on the stop time will be described below.

FIG. 14 is a plot of the ratios of all the detected stopping times for each stopping time. FIG. 14A shows the ratios during normal operation, and FIG. Is the ratio. In both figures, the vertical axis shows the dwell time every 0.1 seconds, and the horizontal axis shows the ratio (%) in each dwell time. It can be seen that during dull driving, long dwell times that do not appear during normal driving also appear, and the dwell times tend to be longer as a whole. Therefore, by monitoring the dwell time, it becomes possible to uniquely determine whether the driving is normal driving or aimless driving.

FIG. 15 shows a processing flow chart for determining whether or not the driver is involuntarily driven based on the stop time. First, based on the detection signal from the line-of-sight detection sensor 10, the stationary point XY coordinate counter 38 detects the coordinates of the stationary point and stores them in the memory (S801). Then, the staying time in the set staying range (for example, 2 × 2 °) is measured by the staying time within the staying range measuring unit 28, and the measured value is stored in the memory (S802). Then, it is determined whether or not a predetermined time or more has elapsed (S803), and if it has elapsed, the variance value a of the dwell time and its average value b are calculated. Note that both a and b are calculated values of the latest data for 10 minutes. Then, the traveling environment determination unit 34 or the preceding vehicle determination unit 32 recognizes the traveling environment, sets the reference dispersion value c and the reference average value d according to the traveling environment, and calculates the dispersion value a calculated by these. , The average value b is compared (S806, S807). Then, the variance value a and the average value b
If both are larger than the set reference value, it is determined that the pattern shown in FIG.
An alarm is output (S808).

It should be noted that, in the present processing as well, setting the reference variance value and the reference average value according to the running environment tends to result in a shorter dwell time than in highway running even in normal operation and in city driving. It is considered that the variance value and the average value thereof are smaller in the city driving than in the highway driving.

FIG. 16 shows another processing flowchart for determining whether or not the vehicle is driving in a dash by using the stop time.
From S901 to S903, the above-described S801 to S803
Similarly, the respective stay times detected next are compared with the set time, and the number a longer and the number b shorter than the set time are calculated. The set time is set to 1.00 second, for example, and it is preferable to change the set time according to the traveling environment. After the long number a and the short number b are calculated, their ratio is calculated (S905), and the threshold values d and c set according to the traveling environment are compared (S907). If there are many numbers a longer than the set time and c is greater than d,
4 (B) pattern, that is, it is determined that the driver is involuntary driving, and an alarm is output (S908). In the present embodiment, it is possible to compare only a or only b with the threshold value.

The processing for determining whether or not the driver is involuntary driving based on the stop time has been described above. These are processes for determining whether or not the vehicle is involuntary driving based on data for a predetermined time (10 minutes in this embodiment). Therefore, the long-term tendency of whether the driver's condition is normal or absent is determined. On the other hand, in addition to determining the driver's long-term tendency and outputting an alarm in this way, it is also very effective to detect a momentary absent-minded state and give an alarm. That is, when there is a preceding vehicle, it is possible that a momentary state of inattentiveness may lead to a dangerous situation.In such a case, rather than the tendency of inattentive driving within a predetermined time, the state of inattentiveness at that moment is The judgment of is very important. Therefore, in addition to the long-term tendency of the driver, it is necessary to determine the momentary ambushed state when the length of the stopping time per stopping point exceeds a set threshold value.

17 and 18 show a process for making an instant judgment of a casual driving in addition to such a long-term tendency. In this process, as shown in FIG. 17, a reference dwell time serving as a threshold is set according to the magnitude of the ambush operation level, and an alarm is issued depending on whether or not the detected instantaneous dwell time exceeds this reference dwell time. Determine whether to give. In the present embodiment, as shown in FIG. 17, the aimless driving level is divided into four stages, and the standard dwell time is set to 2 seconds, 3 seconds, 4 seconds and 5 seconds for each stage. It should be noted that the magnitude of the aimless driving level is determined by providing a plurality of standard setting values (for example, four) in each process shown in FIGS. 15 and 16, and calculating the threshold value and the calculated variance or average value, or the long number. Can be evaluated stepwise by comparing the ratios of the short numbers with.

FIG. 18 shows a processing flowchart in this processing. First, according to the processing shown in FIG. 15 and FIG. 16, it is judged whether or not the driver is in a long-term unconscious driving state and its level. (S1001). When it is determined that the driver is in a long-term dull driving state, the current stop time is then measured by the stop time within stop range measuring unit 28 (S1002), and the measured stop time is shown in FIG. It is determined whether or not the value corresponding to the level shown in is satisfied (S1003). For example, in S1001, the driver is in a long-term absent-minded driving state, and the absent-minded driving level is 1
If the measured dwell time is 5 seconds,
Since the values shown in FIG. 17 are satisfied, it is determined that a momentary absent-minded state has appeared, and an alarm is output (S1004).

As described above, it is possible to further improve the safety by detecting the momentary involuntary state in addition to the tendency of involuntary driving for a long time.

Gaze direction + stop time In the above embodiment, an example of determining whether the driver is aimlessly driving based on the sight line direction or the dwell time is shown. It is also possible to determine whether or not, and it is possible to more reliably determine whether or not the driver is involuntary driving.

As an example of the determination using both the line-of-sight direction and the dwell time, for example, as shown in FIG. 19, the front visual field range (line-of-sight detection range = see FIG. 4) is concentrically divided into a plurality of regions and the center is divided. The points are graded so that they gradually increase as they approach, and the line-of-sight range is quantitatively evaluated based on these points. In FIG. 19, the front visual field range is divided into four regions, which are sequentially scored as 1, 2, 3, 4 from the outside toward the center. Then, the stopping time of each stopping point is measured, and the stopping position of the stopping point is scored according to the range of FIG. 19,
The score is used as a weight to multiply the dwell time, and the evaluation is performed in consideration of the visual field range and dwell time. According to this evaluation method, the evaluation value increases as the line-of-sight direction is closer to the center and as the dwell time increases, which indicates that the evaluation value increases as the degree of aimlessness increases. Therefore, it is possible to determine whether the driving is normal driving or aimless driving based on the magnitude of the evaluation value.

FIG. 20 shows a flowchart of processing based on the above concept. In FIG. 20, first, based on the detection signal from the line-of-sight detection sensor 10,
The line-of-sight counter 38 for each stationary point XY coordinate calculates the line-of-sight coordinates and stores them in the memory of the aimless driving determination unit 40 (S11).
01). Next, the set stop range (eg 2 × 2 °)
The stop time at is measured by the stop time within stop range measuring unit 28, and the stop point coordinates and stop time at each stop point are stored in the memory (S1102). Then, based on the detected stationary point coordinates and the score map for each line-of-sight range shown in FIG. 19, the score in the visual field coordinates is calculated (S110).
3) The evaluation value X is calculated by multiplying the score by the staying time (S1104). The evaluation values X are sequentially added (S1
005), when the predetermined time has elapsed, the sum Y of evaluation values is divided by the total number of stopping points to calculate an evaluation value Z per stopping point (S1106, S1107). Then, the threshold value A set according to the traveling environment and the evaluation value Z per position stop point are compared in magnitude, and when the evaluation value Z is larger than the threshold value A, the line-of-sight direction is likely to gather in the center. In addition, it is determined that the vehicle is in an absent-minded driving state in which the stop time increases, and an alarm is output (S1109, S1110).

Although the front visual field range is concentrically divided into four regions in FIG. 19, it is also possible to divide the region more finely, and the points assigned to each region are discontinuous from the periphery. It is also possible to set it so that it increases toward the center. Further, the area division method is not concentric, and for example, as shown in FIG. 11, it is also possible to divide into three areas of a central area and left and right areas for scoring.

Further, as a method for judging the ambush driving based on the line-of-sight direction and the dwell time, for example, the logical product of the processes of FIGS. 9 and 15 is taken and an alarm is output only when the ambush driving is judged in both processes. It is also possible to do so.

As described above, the method based on the line-of-sight direction and the dwell time has been described as a method for determining whether or not the driver is intently driving. One of the features of these processes is whether or not the driver is intently driving depending on the driving environment. The point is to change the threshold value for determining whether or not. These are, for example, S405 in FIG.
Process, the process of S506 in FIG. 9, and the processes of S806 and S807 in FIG. Here, as the traveling environment, the type of traveling path, for example, a downtown area or an urban area,
It is possible to distinguish between national roads and expressways, and it is also possible to consider whether there is a preceding vehicle or whether the vehicle speed is high or low. Hereinafter, the process of setting the determination reference value according to the traveling environment will be described in detail.

FIG. 21 shows the process of setting the judgment reference value when the presence or absence of the preceding vehicle is taken into consideration as the traveling environment.
First, the preceding vehicle determination unit 32 detects the presence or absence of a preceding vehicle based on the signal from the front monitoring sensor 16 (S1201), and when there is a preceding vehicle, it is further determined whether or not it is the personal characteristic learning period (S1202). , S1203). The personal characteristic learning period can be set to, for example, 10 minutes. In the personal characteristic learning period, data is collected and processed as a personal characteristic value when a preceding vehicle exists. Collection and processing of data, specifically, calculation of the center coordinates of the line of sight, the number of confirmations of the rearview mirror and side mirrors, the average value and the variance value of the line of sight range,
Stop time etc. Then, after the end of the individual characteristic learning period, when there is a preceding vehicle, the reference threshold value for the intentional driving determination is changed to the case where the preceding vehicle is present, and it is determined whether or not the vehicle is intentional driving (S1205). On the other hand, even when there is no preceding vehicle, it is similarly determined whether or not it is during the individual characteristic learning period (S1206), and when it is within the individual characteristic learning period, the line-of-sight direction and the dwell time are set under the condition that no preceding vehicle exists. Data is collected and processed (S1207), and after the personal characteristic learning period has elapsed, it is determined whether or not the vehicle is driving indiscriminately using the determination reference value under the condition without the preceding vehicle (S1208).

Generally, the driver drives while paying attention to various places when there is no preceding vehicle, but when there is a preceding vehicle, pay attention to the distance between the preceding vehicle and acceleration / deceleration. Most of them face it, and tend to rely on the preceding vehicle for other safety checks. Therefore, in this way, the reference threshold value for determination is changed depending on the presence or absence of the preceding vehicle, and when the preceding vehicle exists, the reference value is relaxed as compared with the case where the preceding vehicle does not exist (specifically, Set the threshold for the line-of-sight range to a small value and set the threshold value for the dwell time to a long value) to prevent erroneous judgment that the driver is aimlessly driving even if the vehicle is normally following the preceding vehicle. be able to.

As described above, in the case of determining whether the vehicle is driving blindly based on the number of rear-view mirrors only, a rear monitoring sensor is newly provided, and the rear-view mirror is used depending on whether or not there is a following vehicle. It is conceivable to change the reference value when determining whether the vehicle is driving indiscriminately based on the number of times of confirmation, specifically, when the following vehicle is present, the reference value for the determination is increased as compared with the case where it is not present ( It is conceivable to set the number of times).

FIG. 22 shows an example in which the vehicle speed is used as the traveling environment. In FIG. 22, the horizontal axis represents the vehicle speed, and the vertical axis represents the rate of change in the horizontal line-of-sight angle of each vehicle speed based on 80 km / h. The higher the vehicle speed, the smaller the horizontal line-of-sight angle, It can be seen that there is a tendency to focus on one point. Therefore, for example, S4 in FIG.
The judgment value b of the processing in 05 is changed according to the vehicle speed,
As the vehicle speed increases, b can be set smaller, and it is possible to prevent erroneous determination as casual driving even though normal driving is performed at high speed.

Although FIG. 22 shows the relationship between the vehicle speed and the horizontal line-of-sight angle change rate, the same applies to the vehicle speed and the vertical line-of-sight angle change rate. For example, in FIG. It is possible to set the reference threshold value so that it becomes smaller as the vehicle speed becomes higher, when determining whether or not the vehicle is driving aimlessly using direction coordinates.

FIG. 23 shows another processing flowchart for changing the determination reference value according to the vehicle speed. As described above, the reference threshold value for determination may be increased / decreased according to the vehicle speed, but the line-of-sight data detected by the line-of-sight detection sensor 10 is used as a reference vehicle speed (for example, 80 k
It is also possible to remove the influence of the vehicle speed by converting the data into m / h) and comparing it with a certain reference threshold value. That is, based on the vehicle speed data obtained by the vehicle speed sensor 14 (S1301), the data regarding the line-of-sight range from the line-of-sight detection sensor 10 is normalized to the data of the reference vehicle speed 80 km / h using the relationship shown in FIG. S1
302), and it is determined whether or not the driver is aimlessly driving based on the normalized data (S1303).

As described above, by converting the individual line-of-sight data into data at the reference vehicle speed and processing the data, it is possible to reliably detect whether the vehicle is in normal driving or aimless driving, for example, in a traveling environment in which the vehicle speed changes variously. Becomes

FIG. 24 shows an example of processing when a traveling road is used as the traveling environment. In FIG. 24, the horizontal axis represents four types of travel routes including downtown, urban areas, national roads, and highways, and the vertical axis represents the rate of change when the line-of-sight range in the urban area is used as a reference. Generally, the visual field range (including the number of confirmations) becomes larger in the order of highway, national road, urban area, and downtown area due to the difference in visual stimulus amount, information amount, and the like. Therefore,
By changing the determination value b in S405 of FIG. 8 according to the traveling road based on the relationship of FIG. 24, it is possible to reliably determine whether or not the vehicle is driving aimlessly regardless of the traveling road. Note that, instead of changing the determination reference value according to the travel route, as shown in the processing flowchart of FIG. 23, the detection data from the line-of-sight detection sensor 10 is converted into data in urban areas, and the converted data is used in urban areas. By comparing with the threshold value, it is possible to remove the influence of the road.

Similar to FIG. 24, FIG. 25 shows a processing example in which a traveling road is used as the traveling environment. The horizontal axis is the traveling road, and the vertical axis is the stop time in the city as a reference value. The rate of change of the dwell time on each of the traveled routes is shown. As in the case of FIG. 24, the stopping time tends to increase in the order of downtown, urban area, national road, and highway based on the difference in visual stimulus amount and information amount. Therefore, for example, in FIG.
By changing the reference average value d in S807 of 5 according to the traveling road in accordance with the relationship of FIG. 25, it is possible to reliably determine whether or not the driver is absent-minded based on the dwell time regardless of the traveling road. In this case as well, as in the case of FIG. 24, the line-of-sight data obtained by the line-of-sight detection sensor 10 is converted into urban area data, and the converted data is compared with the reference time in the urban area, so that The effect can be eliminated.

The example in which the judgment reference value is changed according to the presence or absence of a preceding vehicle, the vehicle speed, the traveling environment such as the traveling path has been described above.
Since the reliability of the line-of-sight data obtained by the line-of-sight detection sensor 10 differs depending on the traveling road, it may be possible to change the aimless driving determination start time and the data update time depending on the traveling road. That is, for example, like the process of S403 in FIG. 8, the process of determining whether or not the vehicle is involuntary driving is not performed for 10 minutes after the start of driving, but it is conceivable that this time is also changed according to the traveling road.

FIG. 26 shows the rate of change in the involuntary driving determination start time and the data update time (based on the urban area) when a travel road is used as the travel environment. This change is based on the fact that the line-of-sight data obtained in the order of the downtown area, the urban area, the national road, and the expressway has little variation, and highly reliable data is easily obtained. Therefore, for example, S403 in FIG.
In the processing in (1), it is possible to determine whether or not the driver is aimlessly driving 10 minutes after the start of driving in the case of urban driving, but it is possible to determine whether or not the driver is intentionally driving in a shorter time on a highway. As for the data update time, in the urban area, the data is updated every 1 minute after 10 minutes have passed,
It is also possible to determine whether or not the vehicle is driving aimlessly with a shorter data update time.

Note that FIG. 26 shows an example in which the involuntary driving determination start time and the data update time are changed according to the running road. Of course, the individual characteristic learning period of the process of S1203 in FIG. 21 is changed according to the running road. It is also possible to change it.

27 and 28 show a processing flow chart and a specific learning time setting in this case. FIG. 27 shows how the learning time changes on each road when the city area is taken as the reference (10 minutes). This change is based on the fact that there is little variation in the data obtained in the order of the downtown area, the urban area, the national road, and the expressway as described above, and reliable data is easily obtained. Taking advantage of this,
As shown in FIG. 28, the traveling environment is recognized (S140
1) If it is determined whether or not there is a change in the traveling environment and the traveling path changes, for example, from an urban area to a national road, the learning time is changed from 10 minutes in the urban area to about 8 minutes in the national road. The processing of S1203 and S1206 of FIG. 21 is performed (S1402, S1403, S1404).

As a result, an appropriate learning time can be set according to the traveling road, and unnecessary learning periods can be eliminated to quickly and casually judge driving.

[0094]

As described above, according to the absent-minded driving detection device of the present invention, it is possible to reliably determine whether or not the driver is absent-minded driving based on the line of sight of the driver, and give an alarm or the like based on the determination result. As a result, it is possible to further improve safety.

[Brief description of drawings]

FIG. 1 is a configuration block diagram of an embodiment of the present invention.

FIG. 2 is a graph showing the number of times the rearview mirror and side mirrors are checked during normal driving and aimless driving in the same example.

FIG. 3 is a flowchart of an ambush determination process based on the number of times the rearview mirror and side mirrors are confirmed in the same embodiment.

FIG. 4 is an explanatory diagram of a line-of-sight detection range and an assumed detection range of a rearview mirror and a side mirror in the embodiment.

FIG. 5 is a flowchart of processing for detecting rear-view mirror coordinates and side-mirror coordinates in the embodiment.

FIG. 6 is a flowchart of a line-of-sight center coordinate detection process according to the embodiment.

FIG. 7 is an explanatory diagram of a line-of-sight range during normal driving and aimless driving in the same example.

FIG. 8 is a flowchart of a casual determination process based on a line-of-sight range in the embodiment.

FIG. 9 is a flowchart of an ambush determination process based on the line-of-sight movement distance in the embodiment.

FIG. 10 is a flowchart of an ambush determination process based on the line-of-sight movement distance in the embodiment.

FIG. 11 is an explanatory diagram of area division of the line-of-sight detection range in the embodiment.

FIG. 12 is a flowchart of an ambush determination process based on area division in the embodiment.

FIG. 13 is an explanatory diagram of stationary points in the example.

FIG. 14 is a histogram diagram showing a ratio of dwell times at the time of normal driving and dull driving in the example.

FIG. 15 is a flow chart showing an aimlessness determination process based on a dwell time in the embodiment.

FIG. 16 is a flowchart of a casual driving process based on the ratio of dwell times in the embodiment.

FIG. 17 is an explanatory diagram showing a relationship between the aimless driving level and the reference dwell time in the example.

FIG. 18 is a flowchart of a casual driving determination process based on an instantaneous value of dwell time in the example.

FIG. 19 is an explanatory diagram of scoring the visual field range in the example.

FIG. 20 is a flow chart of a casual driving process based on a visual field range and a dwell time in the example.

FIG. 21 is a flowchart of a judgment reference threshold value changing process by a preceding vehicle in the embodiment.

FIG. 22 is an explanatory diagram of changing the determination reference value according to the vehicle speed in the example.

FIG. 23 is a flowchart of a judgment reference value changing process depending on vehicle speed in the embodiment.

FIG. 24 is a graph showing a change in the line-of-sight range according to the traveling road in the example.

FIG. 25 is a graph showing a change in dwell time depending on a traveling path in the example.

FIG. 26 is a graph showing the changes in the involuntary driving determination start time and the data update time depending on the travel route in the example.

FIG. 27 is a graph showing a change in the line-of-sight characteristic learning time according to the traveling route in the example.

FIG. 28 is a flowchart for learning time change processing according to the traveling path in the embodiment.

[Explanation of symbols]

10 line-of-sight detection sensor, 12 steering angle sensor, 14 vehicle speed sensor, 16 forward monitoring sensor, 18 timer, 20
Rear-view mirror / side-mirror position estimation unit, 22 Rear-view mirror / side-mirror confirmation counter, 24 X-
Line-of-sight counter for each Y-coordinate, 26 Stop range / stop time condition determination unit, 28 Stop-time within stop range measurement unit, 30 Driver's line-of-sight characteristic recording unit, 32 Preceding vehicle determination unit, 34 Running environment determination unit, 36 Sampling timer, 38 Stop point X
-Y-coordinate-specific counters, 40 casual driving determination units, 42 alarm units.

Claims (18)

[Claims] 1. An absent-minded driving detecting device comprising: a gaze detecting means for detecting a driver's gaze direction; and a judging means for judging a driver's gaze degree based on the detected gaze direction. 2. The absent-minded driving detection device according to claim 1, wherein the determination means determines a degree of abstinence based on the frequency of the driver's specific gaze direction. 3. The ambush driving detection device according to claim 2, wherein the specific line-of-sight direction is at least a direction of a rearview mirror or a side mirror of a vehicle. 4. The absent-minded driving detecting device according to claim 3, wherein the line-of-sight detecting means detects the case where the line-of-sight of the driver deviates from a predetermined gazing range having the most frequent direction as the center of the line of sight for a certain period of time. An absent-minded driving detection device characterized by specifying the direction of a mirror or a side mirror. 5. The absent-minded drive detection device according to claim 1, wherein the determination means determines a degree of a sense of agitation based on a change in the line-of-sight range of the driver. 6. The absent-minded driving detection device according to claim 5, wherein the change in the line-of-sight range is evaluated by the moving distance of the line-of-sight. 7. The ambush driving detection device according to claim 5, wherein the change of the line-of-sight range is performed by dividing a predetermined gaze range having the most frequent direction as the center of the line-of-sight into a plurality of regions and changing the line-of-sight in each divided region. The unmanned driving detection device characterized by being evaluated by the ratio of the number of stationary points. 8. A drowsiness driving detection comprising: a dwell time detection means for detecting a dwell time of a driver's line of sight; and a determination means for judging a daze degree of the driver based on the detected dwell time. apparatus. 9. The absent-minded driving detection device according to claim 8, wherein the determination means determines the agitation degree by comparing a statistically processed value of the detected dwell time with a predetermined threshold value. An unmanned driving detection device. 10. The absent-minded driving detection device according to claim 8, wherein the determination means determines a degree of agitation by comparing each of the detected dwell times with a predetermined threshold value. Detection device. 11. The absent-minded driving detection device according to claim 9 or 10, wherein the determination means provides the threshold values in a plurality of stages, and compares the threshold values with the threshold values to gradually increase the aggression level. An absent-minded driving detection device characterized by making a judgment. 12. A line-of-sight detecting means for detecting a driver's line-of-sight direction, a staying time detecting means for detecting a staying time of the driver's line-of-sight, and a driver's inattentiveness based on the detected line-of-sight direction and staying time. A determination device for determining, and an absent-minded driving detection device comprising: 13. The absent-minded driving detection device according to claim 1, 8 or 12, further comprising environment recognition means for recognizing a traveling environment of the vehicle, and the determination means according to the traveling environment. An absent-minded driving detection device characterized by changing a criterion of abstinence degree. 14. The absent-minded driving detection device according to claim 1, 8 or 12, further comprising an environment recognition means for recognizing a traveling environment of the vehicle, and the determination means according to the traveling environment. An absent-minded driving detection device characterized by changing an update time of data used for determination. 15. The absent-minded driving detection device according to claim 1, 8 or 12, further comprising a reference setting means for setting a determination reference based on data during normal operation, wherein the determination means comprises: An absent-minded driving detection device characterized in that the aggression degree is judged using a set judgment criterion. 16. The ambush driving detection device according to claim 13 or 14, wherein the environment recognition means includes a preceding vehicle detection means. 17. The absent-minded driving detection device according to claim 13 or 14, wherein the environment recognition means includes a vehicle speed detection means. 18. The absent-minded driving detection device according to claim 13 or 14, wherein the environment recognition means includes an identification means for identifying a traveling path.