JPH0911772A - Dozing driving detecting device - Google Patents

Abstract

PURPOSE: To detect the condition of a dozing driving rapidly, by carrying out the detection depending on the feature that a meandering is made larger gradually to the running lane in a dozing driving time, and then a radical steering is followed thereafter. CONSTITUTION: A pair of CCD cameras 20 to take an image at the front side and to input front image signals I and J; and various sensors and the like 40 to detect the operating condition of a vehicle 10; are provided. To the various sensors and the like 40, an accelerator operating switch to output the accelerator operating condition of ON and OFF according to the operating condition of the accelerator; a brake operating switch to output the operating condition of a brake; a longitudinal acceleration sensor to detect the acceleration making the running direction of the vehicle as the positive side; and a car speed sensor to detect and output the car speed; are included. And those detected signals are delivered to a dozing driving detecting device. And the dozing driving detecting device produces a dozing warning according to the deciding result, and delivers it to a warning device 60 and the like.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a drowsy driving detection device, and more particularly, to a drowsy driving detection device for detecting a drowsy driving state in relation to a preceding vehicle or a lane.

[0002]

2. Description of the Related Art Conventionally, as a dozing driving detection device, those disclosed in JP-A-5-162562 and JP-A-5-69757 are known.

The former device is, in short, for detecting the state of drowsiness driving in relation to the preceding vehicle. For this reason, when there is a preceding vehicle, the distance between the preceding vehicle and the preceding vehicle is measured for a predetermined period. The standard deviation is calculated with respect to the change in the inter-vehicle distance over (5 minutes), and when the standard deviation exceeds a predetermined threshold value, it is determined that the driver is dozing.

The latter device is, in short, for detecting the state of drowsy driving in relation to the lane. For this reason,
The lateral deviation in the traveling zone is measured by using the light receiving and emitting devices provided in the door mirrors, and the standard deviation is calculated for the change in the lateral displacement over a predetermined period (4 to 5 minutes). When the deviation exceeds a predetermined threshold value, it is determined that the driver is dozing.

When any of the devices detects that the standard deviation of the measured values over a predetermined period exceeds a threshold value and the driving state of the vehicle is a dozing driving state, an alarm is given to the driver. Emit.

[0006]

However, since such a conventional drowsy driving detection device detects drowsy driving based on the standard deviation of measured values, it is determined whether or not the vehicle is in a drowsy driving state. Inevitably, a fixed time lapse of a few minutes before this cannot be avoided.

Therefore, it is possible to wake up the driver promptly without waiting for the elapse of a fixed period of time, and it is possible to detect the dozing driving without requiring a fixed fixed period of time. The development of new equipment is an important issue.

[0008] Therefore, the inventor lacks the agility in the situation judgment and the driving operation when the driver's awakening level becomes low, that is, when the consciousness level is weakened. We paid attention to the characteristic that the amount of operation tends to increase in order to compensate for this delay as well as the delay.

As a result of a specific investigation, in relation to the preceding vehicle, when driving in a state of low awakening, the deceleration operation such as operating the brake is delayed with respect to the deceleration of the preceding vehicle, and the inter-vehicle distance is delayed. Tended to be extremely short, and it became clear that the brake was applied too hard afterwards in an attempt to regain this delay.

Regarding the relationship with the lane, when the vehicle laterally displaces with respect to the traveling lane of the vehicle due to lateral movement depending on the road surface condition, the degree of bend of the curve, etc., the vehicle is laterally displaced. It was also clarified that the displacement was delayed in correction, and this delay became larger with a decrease in arousal level, and the meandering gradually became larger. Moreover, when such a meandering drive approaches the boundary of the lane, or even exceeds this, or if it sticks out on the shoulder, etc.,
When I noticed this, I also found that I was in a hurry to suddenly operate the steering wheel in an attempt to return my vehicle to the center of the lane.

The present invention has been made in view of the above point, and can quickly detect the state of the dozing driving based on the deceleration operation such as the braking operation in relation to the preceding vehicle. An object is to provide a detection device. Another object of the present invention is to provide a drowsy driving detection device capable of quickly detecting the state of drowsy driving based on the steering characteristics in relation to the lane.

[0012]

In order to achieve this object, a drowsy driving detection apparatus according to a first aspect of the present invention is directed to an inter-vehicle distance or relative speed with respect to a preceding vehicle, an acceleration of the own vehicle, and a brake or accelerator operation state of the own vehicle. Means for detecting the deceleration of the own vehicle in accordance with the approach of the preceding vehicle and the own vehicle based on the above, and a setting for obtaining the maximum value of the acceleration or the absolute value of the acceleration during the deceleration period of the own vehicle deceleration. Means (S3 to S5), the maximum value obtained by the setting means is equal to or greater than a first threshold value based on acceleration in normal driving, and the inter-vehicle distance at the beginning of detection of the vehicle deceleration is normal driving. Under the same conditions, a discriminating unit (S6) for discriminating that it is smaller than the second threshold value based on the measured inter-vehicle distance is provided, and the dozing driving is detected by the discrimination result of the discriminating unit.

Further, in the doze driving detection apparatus according to the second aspect of the present invention, the lateral displacement of the vehicle or the lateral movement state quantity of the lateral velocity is positively increased and then decreased to a peak value and then to a negative value. The peak value calculating means (56, 57) for calculating the peak value when turning to increase and the absolute value of the peak value calculated by the peak value calculating means monotonically increased over a predetermined number (S21, S22), and that the steering angular velocity of the vehicle is larger than a predetermined threshold value (S2
3) is provided, and the dozing driving is detected based on the determination result of the determining means.

[0014]

In the drowsy driving detection device according to the first aspect of the present invention, when it is detected that the running state of the vehicle is the drowsy driving state, there is a preceding vehicle and the preceding vehicle decelerates. In this case, when the vehicle is in the dozing driving, the deceleration operation is delayed until the inter-vehicle distance becomes abnormally small, while the dozing driving is detected based on the characteristic that the brake is excessively depressed during the deceleration operation.

Specifically, the deceleration of the own vehicle is detected in accordance with the approach of the preceding vehicle and the own vehicle based on the distance between the preceding vehicle and the like, the acceleration of the own vehicle, and the operation state of the brake of the own vehicle. Is
Further, the maximum value of acceleration or the like during the period of deceleration of the own vehicle is also obtained, and then this maximum value and the value of the inter-vehicle distance at the beginning of deceleration of the own vehicle are compared with a predetermined threshold value. Then, the state of the dozing driving that matches the above characteristics is detected by the comparison result.

As a result, a determination result as to whether or not the vehicle is a dozing drive is output during deceleration through processing such as detection and calculation during the deceleration period. Therefore, the judgment result is issued immediately after the deceleration period, which is generally only about several seconds, does not have to wait for a predetermined fixed number of minutes.

Therefore, the doze driving detection apparatus according to the first aspect of the present invention can promptly detect the dozing driving state based on the deceleration operation in relation to the preceding vehicle.

Further, in the drowsy driving detection device according to the second aspect of the present invention, when it is detected that the running state of the vehicle is a drowsy driving state, the meandering gradually increases with respect to the running lane during the dozing driving. And dozing driving is detected on the basis of the characteristic that it is accompanied by rapid steering.

Specifically, positive and negative peak values for lateral displacement and the like are obtained, the absolute value of the peak value monotonically increases over a predetermined number, and the steering angular velocity of the vehicle is higher than a predetermined threshold value. It is determined to be large. Then, according to the result of this determination, the dozing driving that matches the above characteristics is detected.

As a result, a judgment result as to whether or not the vehicle is a dozing driving is output at the time of steep steering after the processing such as detection and calculation during the meandering driving period. Therefore, the judgment result is issued immediately after the meandering operation period, which is generally only several seconds to several tens of seconds, without waiting for a predetermined fixed time of several minutes.

Therefore, the drowsy driving detection device according to the second aspect of the present invention can quickly detect the state of drowsy driving based on the steering characteristics in relation to the lane.

[0022]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The construction of a first embodiment of the dozing driving detection device of the present invention will be described. 1 is a schematic configuration diagram, FIG. 2 is a functional block diagram, FIG. 3 is a flowchart of a dozing determination process, and FIG. 4 is a graph showing how to set a reference value referred to by (a) ) Is for the reference inter-vehicle distance Ls, which is the reference value as the first threshold, and (b) is for the reference acceleration Gs, which is the reference value as the second threshold. Note that illustration and description of a very general hardware component such as an A / D conversion circuit will be omitted.

This drowsy driving detection device is a device mounted on the vehicle 10 as the own vehicle. In this vehicle 10,
A pair of CCD cameras 20 provided on the upper part of the vehicle body for capturing a front image seen from there and outputting front image signals I and J, and various sensors 40 for detecting a driving state of the vehicle 10 are provided. ing. An accelerator operation switch 41 that outputs an “ON” or “OFF” accelerator operation state A according to the operation state of the accelerator is provided to the sensor 40.
And "ON" or "OF" depending on the operating state of the brake
A brake operation switch 42 that outputs a brake operation state B of F ″, a longitudinal acceleration sensor 43 that detects an acceleration G in which the traveling direction of the vehicle 10 is positive, and a vehicle speed sensor 44 that detects and outputs a vehicle speed V are included. The detected forward video signals I, J, the accelerator operating state A, etc. are sent to the drowsy driving detection device. The vehicle speed sensor 44 is selectively installed according to the configuration of the drowsy driving detection device.

Further, the vehicle 10 is also provided with an alarm output device 60 such as a speaker for receiving an alarm sound when the doze alarm S is issued, and in response to this, the doze driving detection device responds to the determination result. A drowsiness alarm S is generated and sent to the alarm output device 60 and the like.

The construction of this drowsiness driving detection device is roughly divided into a DSP (digital signal processor) 30 suitable for image processing, an MPU (microprocessor) 50 suitable for general information processing, and a component between them. And an interface (not shown) for transferring various information.

The DSP 30 inputs the front video signals I and J, detects desired information from the front video, and sends this information to the MPU 50. Therefore, for this purpose, the area of the stereo image 31 for receiving and holding the data of the front video signals I and J and the stereo image 31 are accessed to perform a process such as a feature extraction of a box pattern on the preceding vehicle. When there is a vehicle, a preceding vehicle detection unit 32 that detects the vehicle distance and detects the inter-vehicle distance L from the preceding vehicle based on the parallax angle in the stereo image 31 and the like is provided.

The MPU 50 is a one-chip computer having a built-in memory and the like, and a relative speed calculating unit 51 for calculating a relative speed R by performing a process such as a difference from the inter-vehicle distance L detected by the preceding vehicle detecting unit 32. And a sensor signal capturing section 52 for inputting the accelerator operating state A, the brake operating state B, the acceleration G, and the vehicle speed V at a predetermined cycle due to a timer interruption, and the operating state of the vehicle 10 based on these input values. It has a drowsiness determination unit 53 that determines whether or not the vehicle is in a drowsy driving state, and outputs a drowsiness alarm S generated as a result of executing these processes to the alarm output device 60.

Next, the processing of the doze determination section 53 will be described in detail with reference to FIG. The doze determination unit 53 first calculates the logical expression [(R <0) .AND. (G) based on the relative speed R, the acceleration G, the accelerator operating state A, and the brake operating state B.
<0) .AND. {(A: "OFF"). OR. (B: "O"
N ")}] is logically operated (step S1), and by this, an operation corresponding to the approaching vehicle (R <0) between the preceding vehicle and the own vehicle due to deceleration of the preceding vehicle or the like ((A:" OF
F ”), (B:“ ON ”)) The vehicle has been decelerated (G
It is determined whether or not <0). If the result is "true", that is, "YES", it is determined that the deceleration of the own vehicle has been detected, and the process for detecting the dozing driving during this deceleration period (from step S2 onward) is performed. If "false", that is, "NO", processing (step S8 and thereafter) for simply detecting an abnormal approach is performed.

Next, if the above-mentioned determination result is "YES", the inter-vehicle distance at the beginning of detection when the vehicle is decelerating is held in preparation for subsequent processing. Save to Lm (step S2).

After the maximum acceleration Gm is cleared to zero (step S3), the acceleration G continues to be positive (G ≧ 0) (step S5), and the maximum acceleration Gm and the absolute value of the acceleration G are compared. The larger one is substituted for the maximum acceleration Gm (step S4). With this, the maximum absolute value of the acceleration G during the current deceleration period is obtained.

Then, based on the initial inter-vehicle distance Lm, the reference inter-vehicle distance Ls, the maximum acceleration Gm, and the reference acceleration Gs,
The logical expression [(Lm <Ls) .AND. (Gm ≧ Gs)] is logically calculated (step S6) to obtain a value more than the reference inter-vehicle distance Ls determined based on the inter-vehicle distance measured under the same condition in the normal operation. The initial inter-vehicle distance Lm is small, and the maximum acceleration Gm is the reference acceleration G based on the acceleration in normal driving.
It is determined that it is s or more.

Here, the reference inter-vehicle distance Ls corresponds to the fact that the deceleration operation is delayed until the inter-vehicle distance becomes abnormally small when there is a preceding vehicle and the preceding vehicle decelerates while the driver is drowsy driving. , Is set to a value that is sufficiently smaller than the inter-vehicle distance that is normally measured during awakening driving (see FIG. 4A). Further, the reference acceleration Gs is set to a value sufficiently larger than the acceleration normally measured in the awakening operation in response to the excessive depressing of the brake in such deceleration operation (FIG. 4 ( b) Then, the state of the dozing driving is detected based on the deceleration operation in relation to the preceding vehicle.

If the result of the above determination is "YES", it is determined that a drowsy driving is being performed, and a process for sending a drowsy alarm S to the alarm output device 60 (step S
Perform 7). As a result, whether or not the deceleration operation in the deceleration period is the deceleration operation while falling asleep and the warning is issued immediately after the end of the deceleration period. Therefore,
The doze judging section 53 is adapted to promptly detect the state of the dozing driving based on the deceleration operation in relation to the preceding vehicle.

Further, in the processing after step S8, logical expressions [(R <0) .AND. (A: ON) .AND. (B: OF)
F)] is logically operated (step S8), and the result is "Y
In the case of "ES", the approach to the preceding vehicle which is not based on the deceleration operation in relation to the preceding vehicle is detected. In this case, the value obtained by multiplying the vehicle speed V by the safety distance calculation coefficient "2" As the distance La (step S9), the inter-vehicle distance L and the safe inter-vehicle distance La are compared (step S10). As a result, when the inter-vehicle distance L is smaller than the safe inter-vehicle distance La, an approach warning (S) is issued as an alarm output device. (Step S11), which causes the drowsiness determination unit 53 to detect a mere abnormal approach in addition to the detection of a drowsiness driving and give an alarm.

The operation of the doze driving detection apparatus of the first embodiment will be described.

When the driver operates the drowsy driving detection device while the vehicle 10 is traveling, the drowsiness driving detection device performs a predetermined initialization, and when this is completed, the DSP 30 and the MP
Predetermined processing is performed in U50. That is, DSP30
Image processing on the computer and the DSP 30 to MPU of the processing result.
The transfer to 50 and the dozing driving detection process in the MPU 50 are continuously performed.

To explain these processing procedures in detail, the DSP 3
In 0, the stereo image data 31 is first fetched from the front video signals I and J, and then the processing of the preceding vehicle detection unit 32 is performed. As a result, the inter-vehicle distance L is obtained.

Upon receiving this inter-vehicle distance L, the MPU 50
The relative speed R is obtained by the processing of the relative speed calculation unit 51. Further, in the MPU 50, the processing of the sensor signal acquisition unit 52 is also performed, and the accelerator operating state A, the brake operating state B, the acceleration G, and the vehicle speed V are also obtained. Furthermore, the drowsiness determination unit 53 based on these detected values and calculated values
Is also performed at any time or in a time-sharing manner, and a determination result such as a determination as to whether or not the vehicle is in a dozing driving state is issued.

Then, the DSP 30 and the MPU 5
The process of 0 is continuously performed, and when there is a preceding vehicle during the operation of the drowsy driving detection device and the preceding vehicle decelerates, the deceleration operation is delayed because the vehicle is drowsy driving and the inter-vehicle distance is abnormally small. And when you step on the brake excessively,
A drowsiness driving S is detected and a drowsiness alarm S is output by the alarm output device 6
Sent to 0. As a result, the alarm output device 60 is activated during drowsy driving, so that the driver can be alerted.

The configuration of the second embodiment of the doze driving detection apparatus of the present invention will be described.

FIG. 5 is a functional block diagram thereof, FIG. 6 is a flow chart of the dozing judgment processing, and FIG.
(A) is explanatory drawing of the detected value by a lane detection process,
(B) is a figure which shows the typical example of the change pattern of lateral displacement during drowsy driving. Although the structure of the device is the same as that of the first embodiment shown in FIG. 1, the sensor specifically corresponding to the sensor 40 is a steering wheel provided on the steering shaft portion to detect the steering angle θ of the steering wheel. Only the angle sensor 45 is provided.

The configuration of the drowsy driving detection device is the DSP 30.
Area of Stereo Image 31 and Lane Detection Unit 33
The MPU 50 includes an eccentric displacement calculation unit 54, a lateral velocity calculation unit 55, peak detection units 56 and 57, a steering angular velocity calculation unit 58, and a doze determination unit 59.

More specifically, the lane detection unit 33 performs image processing such as extracting the features of the thin line pattern, and detects the lane pattern from the stereo image data 31 by this processing. Further, the lane width W and the lateral displacement D are calculated for this lane pattern (see FIG. 7A). These calculated values are provided to the processing in the doze determination section 59. As a result, the lane detection unit 33 detects the lateral displacement in the lateral movement state amount regarding the traveling state of the own vehicle in the lane.

The eccentric displacement calculation section 54 determines the lane width W and the vehicle width T.
And the calculation formula [Ds = {((WT) / 2) × 50
%}], And the eccentric displacement Ds is calculated by this processing. This calculated value is used for the deviation detection process in the drowsiness determination unit 59.

The lateral speed calculator 55 receives the lateral displacement D in order to calculate the lateral speed of the lateral movement state quantity for the running state of the vehicle in the lane. And the like, and the lateral velocity M is calculated by this processing.

The peak detector 57 receives the lateral displacement D, and when the value of the lateral displacement D changes from negative to positive and then increases and then decreases, [DP1 ← (DP2)] and [DP2 ← (D
P3)] is performed and the peak value at this time is saved in the latest peak value DP3. The same process is performed when the value of the lateral displacement D changes from positive to negative, decreases once, and then starts increasing. By this process, the lateral displacement D
Recent three peak values DP1, DP2, DP for
3 is calculated.

The peak detector 56 receives the lateral velocity M, and when the value of the lateral velocity M changes from negative to positive and then increases and then decreases, [MP1 ← (MP2)] and [MP2 ← (M
P3)] is performed and the peak value at this time is saved in the latest peak value MP3. The same process is also performed when the value of the lateral velocity M changes from positive to negative and then decreases and then increases. By this process, the lateral velocity M
Recent three peak values MP1, MP2, MP3
Is calculated.

The steering angular velocity calculation unit 58 receives the steering angle θ from the steering angle sensor 45, performs a process such as a difference approximating the time derivative, and calculates the steering angular velocity δ by this process.

The drowsiness determination unit 59 determines the deviation displacement Ds, peak values DP1, DP2, DP3, and peak values MP1, MP.
2, MP3 and the steering angular velocity δ are received, and based on these, processing for deviation detection, processing for detecting meandering increase, and processing for rapid steering detection are performed. Then, as a result of these processes, if the traveling state of the own vehicle is in the state of drowsiness driving, this is detected, and further, according to the detection, the drowsiness alarm S is sent to the alarm output device 60. There is. The processing of the doze determination unit 53 will be described in more detail in the following operation description.

The operation of the drowsy driving detection apparatus of the second embodiment having such a configuration will be described.

When the driver operates the drowsy driving detection device while the vehicle 10 is traveling, this drowsiness driving detection device:
After the predetermined initialization is performed, the DSP 30 takes in the stereo image data 31 and processes the lane detection unit 33 to obtain the lane width W and the lateral displacement D.

The MPU 5 receives the lane width W and the lateral displacement D.
At 0, the processing of the deviation displacement calculation unit 54 is performed to obtain the deviation displacement Ds, and the processing of the peak detection unit 57 is performed to obtain the peak values DP1, DP2, DP3 of the lateral displacement D,
The lateral velocity calculation unit 55 and the peak detection unit 56 perform the processing to obtain the peak values MP1, MP2, MP3 of the lateral velocity M.

Further, in the MPU 50, the processing of the steering angular velocity calculation section 58 is performed at the timing of a timer interruption of a constant cycle, and the steering angular velocity δ is also obtained. As a result, the detected and calculated values necessary for the dozing determination are gathered.

Then, the processing of the doze judging section 59 based on these detected values / calculated values is also carried out at any time or in a time division manner. Specifically, the deviation detection process is performed by comparing the lateral displacement D and the deviation displacement Ds (step S20).
As a result, when the lateral displacement D exceeds the deviation displacement Ds,
Since it is found that the deviation, that is, the extreme deviation due to the meandering traveling or the like is performed, the detection processing is further continued (“YES” side).

Then, as processing for detecting the increase in meandering, the absolute values of a series of peak values DP1, DP2, DP3 are compared and the relationship of [| DP1 | <| DP2 | <| DP3 |] (FIG. 7).
It is determined whether or not (see (b)) is satisfied (step S).
21). Alternatively, a series of peak values MP1, MP2, M
The absolute values of P3 are compared and [| MP1 | <| MP2 | <|
It is determined whether or not the relationship of MP3 |] is established (step S22). If at least one of these relationships is established, it is found that the absolute values of the three latest peak values are monotonically increasing, that is, the meandering is gradually increasing, and therefore the detection process is continued. Yes ("YE
S "side).

At this stage, as the processing of the sudden steering detection,
Compare the rudder angular velocity δ with the reference rudder angular velocity δs [δ> δs]
Whether or not it is determined (step S23). Here, the reference steering angular velocity δs is a predetermined value that is set to a value that sufficiently exceeds the general steering angular velocity in normal operation. Therefore, at this stage, when the steering angular velocity δ exceeds the reference steering angular velocity δs, it is determined that the steep steering is followed by the increase in meandering, so it is determined that the running state of the own vehicle is in the dozing driving state, According to this determination result, a drowsy alarm S is sent to the alarm output device 60 (step S24).

While these processes are continuously performed during the operation of the doze driving detection device, if the driver of the vehicle 10 falls asleep during this operation, the dozing driving state is changed according to the above-described processing procedure. To be detected. That is, if the meandering of the own vehicle with respect to the driving lane gradually increases and the own vehicle violently deviates, and if the driver also steers steerably in order to get out of this deviant running, such a driving state Is detected as a dozing driving state. Then, the doze alarm S is sent to the alarm output device. This allows
When the driver is dozing, the alarm output device operates, so that the driver's attention can be called to wake up the driver.

Note that these drowsy driving detection devices are not exclusive to each other or to conventional devices. That is, the above-mentioned means for detecting a drowsiness driving can be integrated and coexist in a single drowsiness driving detection device, and can be coexisting in the device with a conventional detection means. In such a case, although an alarm is generated more frequently, since the respective means complement each other and the number of cases in which the dozing driving can be detected becomes abundant, it acts on a safer side.

[0059]

As is apparent from the above description, in the doze driving detection apparatus according to the first aspect of the present invention, when there is a preceding vehicle and the preceding vehicle is decelerated, when the vehicle is driving dozing, The deceleration operation is delayed until the distance becomes abnormally small, but detection is performed based on the characteristic that excessive brake depression is involved during deceleration operation, so that the judgment result can be obtained immediately after the deceleration period has elapsed without waiting for the fixed time to elapse. Is issued. Therefore, there is an effect that the state of the dozing driving can be promptly detected based on the deceleration operation in relation to the preceding vehicle.

Further, in the drowsy driving detection device according to the second aspect of the present invention, the detection is performed based on the characteristic that the meandering gradually increases with respect to the driving lane during drowsy driving, and the steep steering is performed thereafter. Thus, the determination result is immediately issued after the meandering operation period has elapsed without waiting for the fixed time to elapse. Therefore, there is an effect that the state of the dozing driving can be promptly detected based on the steering characteristics in relation to the lane.

[Brief description of the drawings]

FIG. 1 is a schematic configuration diagram of a dozing driving detection device according to the present invention.

FIG. 2 is a functional block diagram of the first embodiment of the doze driving detection device of the present invention.

FIG. 3 is a flowchart of a dozing determination process for the device of the first embodiment.

FIG. 4 is a graph showing how to set a reference value referred to in the apparatus of the first embodiment.

FIG. 5 is a functional block diagram of a second embodiment of the doze driving detection device of the present invention.

FIG. 6 is a flowchart of a dozing determination process for the device of the second embodiment.

FIG. 7 is an explanatory diagram of a device according to a second embodiment.
(A) is an explanatory view of a detection value by lane detection processing.
(B) is a typical example of lateral displacement during drowsy driving.

[Explanation of symbols]

 10 vehicle (own vehicle) 20 CCD camera 30 DSP (digital signal processor) 31 stereo image 32 preceding vehicle detection unit 33 lane detection unit 40 sensor, etc. 41 accelerator operation switch 42 brake operation switch 43 longitudinal acceleration sensor 44 vehicle speed sensor 45 steering angle sensor 50 MPU: Micro Processing Unit 51 Relative Velocity Calculation Unit 52 Sensor Signal Capture Unit 53 Doze Determination Unit 54 Unbalanced Displacement Calculation Unit 55 Lateral Velocity Calculation Unit 56 Peak Detection Unit 57 Peak Detection Unit 58 Steering Angular Velocity Calculation Unit 59 Doze Determination Unit 60 Alarm Output device A Accelerator operating state B Brake operating state D Lateral displacement (lateral movement state amount) Ds Offset displacement G Acceleration Gm Maximum acceleration Gs Reference acceleration L Inter-vehicle distance Lm Initial inter-vehicle distance Ls Reference inter-vehicle distance La Safe inter-vehicle distance M Lateral speed ( side Dynamic state quantity) R relative speed S dozing warning T vehicle width V vehicle speed W lane width θ steering angle δ steering angular δs reference steering angular DP1, DP2, DP3 peak lateral displacement values MP1, MP2, MP3 lateral speed of the peak value

Claims (2)

[Claims] 1. A drowsy driving detection device for a vehicle, which detects that the running state of the own vehicle is a drowsy driving state, in a vehicle-mounted drowsiness driving detection apparatus, a vehicle-to-vehicle distance or relative speed, an acceleration of the own vehicle, and a brake of the own vehicle. Or, the detection means for detecting the deceleration of the own vehicle according to the approach of the preceding vehicle and the own vehicle based on the operation state of the accelerator, and the acceleration or the maximum value of the absolute value thereof during the period of the own vehicle deceleration. The setting means to be obtained, the maximum value obtained by the setting means is equal to or more than a first threshold value based on the acceleration in normal driving, and the inter-vehicle distance at the beginning of detection of the vehicle deceleration is the same condition in normal driving. A drowsiness driving detection device, characterized in that it is provided with a discrimination means for discriminating that it is smaller than a second threshold value based on an inter-vehicle distance measured below, and drowsiness driving is detected by a result of the discrimination means. . 2. A doze driving detection device for a vehicle, which detects that the running state of the vehicle is a dozing driving state, wherein the lateral displacement or lateral movement state quantity of lateral velocity of the vehicle is positively increased. From the peak value when it turns to a decrease and the peak value when it turns to a negative value and then to an increase, and the absolute value of the peak value obtained by this peak value calculation means over a predetermined number. A drowsy driving detection device, comprising: a determination unit that determines that the steering angle velocity of the host vehicle is monotonically increasing and that the steering angular velocity of the vehicle is greater than a predetermined threshold value, and detects a drowsy driving based on the determination result of the determination unit. .