JP2002193055A - Car lane deviation alarm device for vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a car lane deviation alarm device for a vehicle which can continuously estimate a car lane deviation without interrupting continuation under all road conditions and running conditions without a sense of incompatibility of a deviation alarm given to a driver even at high speed turn running time. SOLUTION: This device comprises a forward lateral displacement estimation value calculating means for calculating a forward lateral displacement estimation value Xexp in a position of a forward watch point distance Ls of a vehicle by lateral displacement (a) and a yaw angle c, a forward lateral displacement target value calculating means for calculating a forward lateral displacement target value X*exp in a position of the forward watch point distance Ls of the vehicle by the lateral displacement (a) and a car body lateral slide angle β, a car lane deviation decision means deciding whether or not a deviation between the forward lateral displacement estimation value Xexp and the forward lateral displacement target value X*exp is a preset threshold value X or more, and an alarm device 7 informing a driver of car lane deviation when it is decided with the deviation in the preset threshold value X or more.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention belongs to the technical field of a lane departure warning device for a vehicle which predicts that the host vehicle departs from the traveling lane and notifies the driver of this by warning.

[0002]

2. Description of the Related Art Conventionally, as a lane departure warning device for a vehicle, for example, a device described in Japanese Patent Application Laid-Open No. 8-16998 is known.

[0003] This publication discloses a device for improving the running safety of a vehicle, which alerts a driver by a warning or the like when the vehicle deviates from the driving lane due to the carelessness of the driver and warns the driver. A device for prompting has been proposed.

[0004] This device is an image pickup device that picks up various boundary lines that partition both sides of a traveling lane on a road surface, and processes an image picked up by this device to control the yaw angle of the vehicle in the driving lane with respect to the road. And a device for estimating the curvature of the road ahead from the imaging device,
Based on a device that estimates the traveling curvature from the traveling state of the vehicle, the direction of the yaw angle of the vehicle from the road (positive or negative) and the direction of the curvature deviation (positive or negative) obtained by subtracting the estimated road curvature from the estimated traveling road curvature are calculated. When the vehicle crosses the boundary line and deviates from the traveling lane, or when there is a possibility that the vehicle deviates from the traveling lane, the vehicle is configured with a notification device or the like that notifies the driver of this.

Therefore, according to this type of device, a situation in which the vehicle unintentionally deviates from the driving lane and comes into contact with a vehicle traveling in an adjacent lane or an obstacle outside the lane can be avoided. Therefore, traveling safety of the vehicle is improved.

[0006]

However, in the conventional vehicle lane departure warning device, the road estimated curvature RA is determined from the positive and negative directions of the yaw angle α of the vehicle and the estimated travel road curvature Rφ.
Is compared with the positive / negative direction of the curvature deviation (Rφ−RA) obtained by subtracting, and if the positive / negative direction is different, it is determined that there is a possibility of lane departure. When turning on a road, the vehicle has a vehicle side slip angle, and the vehicle is running in a sufficiently constant turning state, and even when the estimated travel route curvature Rφ and the estimated road curvature RA are equal, the vehicle is driven to the corner IN side. There is a problem in that a yaw angle is generated, and an alarm is likely to sound at the corner IN side, which gives the driver an uncomfortable feeling that an alarm sounds when unnecessary.

That is, the vehicle body side slip angle increases as the vehicle speed increases (see FIG. 15 and "Motion and Control of a Car (Third Printing)" by Masato Abe, p. 70, published by Sankaido on May 31, 1996). ).

Although the yaw angle increases with the increase of the vehicle body side slip angle, the paragraph number in Japanese Patent Laid-Open No. 8-16998, which is a prior art, is used.

In the second embodiment described below, when turning on a road with a small turning radius during high-speed running, the estimated travel road curvature Rφ of the own vehicle is smaller than the estimated road curvature RA (cut into the inside of the turn). In this state, a warning is issued when the yaw angle is turned toward the inside of the turn. This means that a departure warning for the inside of the turn is more likely to sound during a high-speed turn.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and has as its object to provide a driver with a feeling of unnaturalness of a departure warning even during high-speed turning, without changing the road conditions and driving conditions. Accordingly, it is an object of the present invention to provide a vehicle lane departure warning device that can predict a lane departure continuously without disconnection.

[0011]

According to a first aspect of the present invention, there is provided an image capturing means for capturing an image of the front of a vehicle, and a road shape estimating means for estimating a road shape from an image captured by the image capturing means. A lateral displacement estimating means for estimating a lateral displacement of the own vehicle with respect to the road based on the road shape estimated by the road shape estimating means; and a road of the own vehicle based on the road shape estimated by the road shape estimating means. A yaw angle estimating means for estimating a yaw angle with respect to a vehicle body, a vehicle body slip angle estimating means for estimating a vehicle body slip angle based on a steering angle detection value and a vehicle speed detection value, and a predetermined position ahead of the vehicle based on the lateral displacement and the yaw angle. Forward lateral displacement estimated value calculating means for calculating an estimated forward lateral displacement value; and forward lateral displacement for calculating a forward lateral displacement target value at a predetermined position in front of the vehicle based on the lateral displacement and the vehicle body slip angle. Target value calculation means, threshold value setting means for setting a threshold value for determining whether a deviation between the estimated forward lateral displacement value and the expected forward lateral displacement value is a lane departure tendency, and an estimated forward lateral displacement value; Lane departure determining means for determining whether a deviation from the forward lateral displacement target value is equal to or greater than a set threshold value, and alarm means for notifying the driver of the lane departure when the lane deviation is determined to be greater than or equal to the set threshold value. And characterized in that:

According to a second aspect of the present invention, in the vehicle lane departure warning apparatus according to the first aspect, the threshold value setting means sets the threshold value to a larger value as the curvature of the road ahead increases. Means.

According to a third aspect of the present invention, in the vehicle lane departure warning device according to the first or second aspect, the threshold value setting means increases the threshold value of the curvature of the road ahead in the corner inward direction. It is a means for setting and setting a small threshold value in the direction outside the corner of the curvature of the road ahead.

According to a fourth aspect of the present invention, in the vehicle lane departure warning device according to any one of the first to third aspects, the threshold value setting means reduces the threshold value as the vehicle speed increases. It is a means for setting.

[0015]

According to the first aspect of the present invention, when the vehicle is traveling, the road shape estimating means estimates the road shape from the image taken by the imaging means for imaging the front of the vehicle. The lateral displacement of the own vehicle with respect to the road is estimated based on the road shape estimated by the road shape estimating means, and the yaw angle estimating means calculates the yaw angle of the own vehicle with respect to the road based on the road shape estimated by the road shape estimating means. An angle is estimated.

The vehicle body slip angle estimating means estimates the vehicle body slip angle based on the detected steering angle and the detected vehicle speed, and the estimated forward lateral displacement value calculating means calculates a predetermined value ahead of the vehicle based on the lateral displacement and the yaw angle. An estimated forward lateral displacement value at the position is calculated, and a target forward lateral displacement value calculating means calculates a forward lateral displacement target value at a predetermined position ahead of the vehicle based on the lateral displacement and the vehicle body slip angle.

On the other hand, the threshold value setting means sets a threshold value for determining whether or not the deviation between the estimated forward lateral displacement value and the target forward lateral displacement value is a lane departure tendency. It is determined whether or not the deviation between the forward lateral displacement estimated value and the forward lateral displacement target value is equal to or greater than a set threshold value.
The lane departure is notified to the driver by the alarm means.

That is, the vehicle body slip angle is an angle with respect to the center line in the front-rear direction (travel direction) of the vehicle with respect to the traveling direction of the vehicle, and the yaw angle is the angle with respect to the center line in the front-rear direction of the vehicle body relative to the traveling direction of the road. Therefore, if the vehicle body side slip angle and the yaw angle match, the traveling direction of the vehicle coincides with the traveling direction of the road, which is an ideal traveling state. Therefore, the lane departure is determined by checking the degree of coincidence between the estimated value of the lateral displacement in front of the vehicle (determined by the yaw angle of the vehicle) and the target value of the lateral displacement in front of the vehicle (determined by the vehicle body slip angle). Like that.

Therefore, the lane departure is determined based on the deviation between the estimated forward lateral displacement value and the target lateral lateral displacement, and the lateral displacement target value obtained from the vehicle body side slip angle is used as a reference value for judging lane deviation. Even during a high-speed turning operation in which a side slip angle occurs, if the deviation between the estimated forward lateral displacement value and the desired forward lateral displacement value is small, no departure warning is issued, and the driver does not feel uncomfortable with the departure warning.

Furthermore, the lane departure can be evaluated based on the deviation between the estimated forward lateral displacement value and the target lateral lateral displacement value with the same judgment reference value for a straight road or a curved road. The lane departure prediction can be performed continuously without breaking the connection.

According to the second aspect of the present invention, in the threshold value setting means, as the front road curvature increases,
The threshold is set to a large value.

Therefore, when turning at a small turning radius, in which the vehicle body slip angle tends to be large compared to turning at a large turning radius, at the same vehicle speed, the threshold value increases as the curvature of the road ahead increases. In addition, it is possible to alert the driver to the normal driving feeling without having to worry about taking a course.

According to a third aspect of the present invention, the threshold value setting means sets the threshold value of the curvature of the front road in the corner inside direction to be large, and the threshold value of the curvature of the front road outside the corner is small. Is set.

Therefore, since the threshold value at the corner IN where the deviation tends to be larger than that at the corner OUT during turning is set to a large value, the driving feeling of a normal driver can be improved without concern for the course at the IN side. Alarm can be notified.

According to the invention, the threshold value is set to a smaller value as the vehicle speed increases.

Thus, the arrival time at which the vehicle predicts the departure reaches the front position, the earlier the vehicle speed becomes, the sooner the vehicle arrives. However, by decreasing the threshold value as the vehicle speed increases, the departure prediction time becomes shorter. Can be set so as not to change with vehicle speed.

[0027]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A lane departure warning system for a vehicle according to the present invention is shown in a first embodiment (corresponding to claim 1), a second embodiment (corresponding to claim 2), and a third embodiment (corresponding to claim 3). This will be described with reference to a fourth embodiment (corresponding to claim 4).

(First Embodiment) FIG. 1 is an overall system diagram showing a lane departure warning device of a vehicle according to a first embodiment, wherein 1 is a camera (imaging means), 2 is an image processing device, 3 is a control controller, 4 is a vehicle speed sensor, 5 is a steering angle sensor, 6 is an alarm controller, and 7 is an alarm (alarm means).

The camera 1 is composed of a CCD camera or the like. As shown in FIG. 2, the camera 1 is located at the center in the vehicle width direction and above the front window in the vehicle interior, the optical axis of the lens and the vehicle center line. It is mounted so that the yaw angle is zero and the pitch angle between the optical axis of the lens and the vehicle center line is α, and an image of the road in front of the vehicle is taken.

The image processing device 2 processes an image taken by the camera 1 to detect a white line or the like on a road.

The controller 3 uses a plurality of parameters representing the road shape and the vehicle behavior to represent the shape of the road white line in a mathematical model, and sets the parameters so that the detection result of the road white line matches the white line model. Is updated, the road white line is detected to recognize the road shape. Also, enter the θ current steering angle detected by the vehicle speed V _SP and the steering angle sensor 5 that is detected by the vehicle speed sensor 4,
By comparing the estimated forward lateral displacement value Xexp at the vehicle forward position (determined by the yaw angle c of the vehicle) with the desired forward lateral displacement value X ^* exp (determined by the vehicle body slip angle β) at the forward position of the vehicle, the lane of the own vehicle is obtained. Detecting deviation from the situation.

The alarm controller 6 drives the alarm 7 when it is determined by the traveling state monitoring processing of the controller 3 that the vehicle deviates from the lane, and the alarm 7 emits an alarm sound or Perform an alarm display, etc.
Call attention to the driver.

Next, the operation will be described.

[Road White Line Detection Processing] FIG. 3 is a flowchart showing the flow of the road white line detection processing operation executed by the controller 3, and each step will be described below (road shape estimation means, lateral displacement estimation means, yaw). (Corresponds to angle estimation means).

In step S1, parameters representing the road shape and vehicle behavior (hereinafter simply referred to as road parameters).
Initialize. On a screen coordinate system X, Y as shown in FIG. 4, a white line model is expressed by the following equation (1) using road parameters. X = (a + ie) (Y−d) + b / (Y−d) + c (1) In equation (1), a to e are road parameters, and assuming that the height of the camera 1 from the road surface is constant, Each road parameter represents the following road and white line shapes or vehicle behavior. That is, a is the lateral displacement of the vehicle in the lane, b is the curvature of the road, c is the yaw angle of the vehicle (optical axis of camera 1) with respect to the road, and d is the road of the vehicle (optical axis of camera 1). And e represents the lane width of the road.

In the initial state, the shapes of the road and the white line and the behavior of the vehicle are unknown.
For example, a value corresponding to the median is set as an initial value.
That is, for example, the center of the lane is set for the lateral displacement a of the own vehicle in the lane, a straight line is set for the road curvature b, the yaw angle c with respect to the lane is zero degree, and the pitch angle d with respect to the lane is stopped. Is set, and the lane width e is set to the lane width of the expressway indicated in the road structure order.

Next, the process proceeds to step S2, where the initial setting of a small area for detecting a white line candidate point is performed as shown in FIG. In the initial state, it is expected that there is a large gap between the white line model in which the road parameter is set to the initial value and the road white line on the actual screen. Therefore, it is desirable to set a region as large as possible. In the example shown in FIG. 5, a total of ten white line candidate point detection areas are set for each of the left and right white lines. If a road white line has already been detected by the previous processing, the difference between the actual road white line and the white line model is considered to be small.
As shown in FIG. 6, by setting a region as small as possible, the possibility of erroneous detection of something other than the white line is low, and the processing speed can be improved.

Next, the process proceeds to step S3, where an image captured by the camera 1 and processed by the image processing device 2 is input.

Next, the process proceeds to step S4, in which a white line candidate point detection area is set on the road image of the image information input from the image processing device 2 in step S3. At this time, based on the white line candidate point detection area calculated in step S2 and the white line model based on the road parameters corrected in step S1 or step S9 described later, FIG.
As shown in (3), the white line candidate point detection area is set so that the white line model obtained in the previous processing is the center of the area. FIG.
In the example shown in (1), a total of ten white line candidate point detection areas are set, five on each of the left and right white lines. It should be noted that the white line candidate point detection area may be set at a position offset in the change direction of the white line model from the past state of the white line model change.

Next, the process proceeds to step S5, in which a white line candidate point is detected in the white line candidate point detection area. In detecting the white line candidate points, first, a differential image is generated from the input image through a sobel filter or the like. Next, as shown in FIG. 8, for all the line segments formed by connecting one point of the upper base and one point of the lower base of the white line candidate point detection area, as shown in FIG. Measure the number of pixels. Further, of all the line segments, a line segment having the largest number of pixels having a density equal to or higher than a predetermined value is set as a detection straight line, and a start point and an end point of the line segment are set as white line candidate points. At this time, when the number of pixels of the detected density on the straight line is smaller than a predetermined ratio with respect to the length of the detection area, it is determined that the white line candidate point has not been detected.

For example, in a detection area in which the length of the detection area is 15 pixels and pixels having a density equal to or higher than a predetermined value are 以上 or more, ie, if 8 or more pixels are detected, a white line candidate point is detected. If the number of pixels on the line segment having the largest number of pixels having a density equal to or higher than the predetermined value is less than 7 pixels, it is assumed that no white line candidate point has been detected in the detection area. On the other hand, in the case of 9 pixels, it is assumed that a white line candidate point has been detected, and the start point and end point of the line segment are set as detection results.

The above processing is executed for all the white line candidate point detection areas. At this time, the above-described predetermined ratio to the length of the detection region for determining whether or not the white line candidate point is detected may be the same for all regions, or may be set for each detection region. Further, the predetermined value of the density may be the same for all the detection regions, or may be changed for each detection region.

Next, the process proceeds to step S6,
In 6, it is determined whether or not the number of white line candidate points detected in all the white line candidate point detection areas is equal to or greater than a predetermined value. If the number is less than the predetermined value, it is determined that the road white line detection area does not include a road white line. Then, returning to step S2, the white line candidate point detection area is initialized as described above.

On the other hand, if a white line candidate point is detected at a predetermined value or more, the process proceeds to step S7.
As shown in (1), the shift amount between the detected white line candidate point and the point on the white line model obtained by the previous process d is calculated for each point.

Next, the process proceeds to step S8, where the variation amounts 道路 a to △ e of the road parameters are calculated based on the deviation amounts of the respective points. The method of calculating this variation is
For example, a method of calculating by the least square method as shown in Japanese Patent Application Laid-Open No. 8-5388 can be used.

Subsequently, the flow shifts to step S9, where step S9 is executed.
In step 9, the road parameters a to e are corrected based on the road parameter fluctuation amounts △ a to △ e calculated in step S8.
For example, in the case of the white line model shown in the above equation (1), the following equation
The road parameters a to e are corrected according to (2). Then, the road parameters a to e thus corrected are
The new white line model is stored in a predetermined storage area as a road parameter. Then, the process returns to step S3, and the above processing is repeated.

[Driving Condition Monitoring Process] Based on the road parameters a to e of the white line model detected from the image information captured by the camera 1 as described above, the controller 3
Then, a running state monitoring process for generating an alarm according to the running state of the own vehicle is performed.

FIG. 10 is a flow chart showing the flow of the driving situation monitoring processing operation executed by the controller 3.
Hereinafter, each step will be described.

In step S10, road parameters a, b, and c of the white line model stored as road parameters of the new white line model are fetched. a: lateral displacement of the vehicle with respect to the road b: curvature of the road c: yaw angle of the vehicle with respect to the road Next, the process proceeds to step S11, where the estimated value of the lateral lateral displacement Xexp at the position of the forward fixation point distance Ls is (Corresponding to a forward lateral displacement estimated value calculating means). Xexp = a + Ls · c (3) The estimated forward lateral displacement value Xexp is, as shown in FIG.
This means the lateral displacement of the vehicle from the center of the road at the position of the forward fixation point distance Ls. If the road is a substantially straight road, it can be determined that the larger the value is, the more likely the lane departure is. Further, the estimated forward lateral displacement value Xexp can be obtained by simply looking at the value as it is under a situation where the vehicle is turning with a sufficiently small vehicle body slip angle even on a road having a curvature as shown in FIG. Also, it can be determined that the larger the value, the more likely the vehicle is to depart from the lane.

[0050] Then, the process proceeds to step S12, in step S12, a vehicle running state data, and θ the current steering angle detected by the steering angle sensor 5, the vehicle speed V _SP detected by the vehicle speed sensor 4 is incorporated .

Next, in step S13, the vehicle body slip angle β is calculated by using the following equation, for example, the vehicle model identification value, the vehicle speed V _SP , the steering wheel angle θ (the front wheel actual steering angle δ). ), Is estimated and calculated using the road curvature b (corresponding to a vehicle body slip angle estimating means). Next, the process proceeds to step S14, in which the forward lateral displacement target value X ^* exp at the position of the forward gazing point distance Ls is calculated by multiplying the forward gazing point distance Ls by the vehicle body side slip angle β (forward). Lateral displacement target value calculating means), the estimated forward lateral displacement value X calculated in step S11.
It is determined whether or not the difference between exp and the forward lateral displacement target value X ^* exp is less than a threshold value Xth for determining whether or not there is a lane departure tendency (corresponding to lane departure determination means). Here, the threshold value Xth is set by giving a fixed value derived from the result of a previously conducted experiment or the like (threshold value setting means).

If it is determined that | Xexp-X ^* exp | <Xth, the flow proceeds to step S15, and no departure warning is issued. On the other hand, if it is determined that | Xexp−X ^* exp | ≧ Xth, the process proceeds to step S16, and a deviation warning is issued.

[Evaluation Point of Lane Departure] FIG. 13 shows a comparison to make it easier to understand the effect of considering the vehicle body slip angle β as an evaluation point of lane deviation.

FIG. 13 shows a case in which both vehicles are traveling in a constant turning state while traveling with the same road curvature, and traveling along the center of the lane neatly. The vehicle shown on the right is shown on the left. It is assumed that the vehicle is traveling at a speed higher than the speed of the vehicle. In other words, both vehicles are in an ideal vehicle running state in the sense that they do not depart from the lane, so that the same evaluation points must be obtained for them.

For example, in a vehicle having a general understeer characteristic, as the vehicle speed increases, the vehicle has a vehicle side slip angle β on the IN side (inward inside the corner) of the corner as the vehicle speed increases. That is, as shown in FIG. 14, when a vehicle having a neutral steer characteristic (NS characteristic) makes a steady circular turn at a constant actual steering angle, the turning angular speed increases linearly with the speed. If the vehicle has an understeer characteristic (US characteristic), the turning angular velocity increases along with the velocity to a certain point, but does not exceed a certain value. However, as shown in FIG. 15, the absolute value of the sideslip angle β of the vehicle center of gravity increases in proportion to the square of the vehicle speed. Thus, the reason that the sideslip angle β of the vehicle center of gravity changes with the speed regardless of the vehicle's steering characteristics is that the vehicle must obtain a lateral force that balances the centrifugal force according to the traveling speed. . The side slip angle β of the vehicle center of gravity is an angle between the front-rear direction of the vehicle and the traveling direction of the vehicle center of gravity, that is, the tangential direction of the turning circle, and indicates the attitude of the vehicle with respect to the turning circle in a steady circle turning. The fact that the side slip angle β becomes negative with the speed and that the absolute value increases indicates that the vehicle has a tendency to make a round turn with the head inside the turning circle as the speed increases.
(See "Motion and Control of Cars (Third Printing)" by Masato Abe, P69-P70, published by Sankaido on May 31, 1996).

Therefore, the left side of FIG.
km / h and the vehicle speed on the right side is 100 km / h.
Has a different meaning.

Therefore, in the first embodiment (the present invention), the reference point of the estimated forward lateral displacement value Xexp is shifted by the vehicle body slip angle β, that is, the target forward lateral displacement value X ^* exp is changed to the forward fixation distance Ls. X The vehicle side slip angle β, and the evaluation point of lane departure is set to Xexp-X ^* exp.

That is, on the left side of FIG. 13, the vehicle traveling direction coincides with the road direction. Therefore, a = c = β = 0
Xexp−X ^* exp = a + Ls · c−Ls · β = a + Ls (c−
β), Xexp−X ^* exp = 0.

On the right side of FIG. 13, the lateral displacement a of the vehicle with respect to the road is a = 0, but the yaw angle c and the vehicle body side slip angle β appear. Substituting this value into the following equation: Xexp−X ^* exp = a + Ls (c−β) gives Xexp−X ^* exp = Ls (c−β), and if the yaw angle c matches the vehicle body slip angle β, , X
exp−X ^* exp = 0.

Therefore, the evaluation point of the lane departure is Xexp-X ^* e
By setting to xp, the deviation from the forward lateral displacement target value X ^* exp can be evaluated as zero in both the left and right states in FIG.

By the way, the right side of FIG.
Since this corresponds to the case of φ-RA = 0 and the yaw angle is on the inside of the turn, an alarm sounds when a deviation of Rφ−RA appears even a little, but in the first embodiment, this is the case. No alarm will sound in any situation.

Next, for comparison with a zero evaluation of lane departure (ideal turning state), an example in which the traveling direction of the vehicle is different from the road direction will be described below.

On the left side of FIG. 13, if the traveling direction of the vehicle is 1
If it is a dotted chain line (too much wraparound), the lateral displacement a = 0, the yaw angle c = 0, and the vehicle body side slip angle β = q (<0) Xexp−X ^* exp = Ls (−q)> 0. On the left side, if the traveling direction of the vehicle is a two-dot chain line (inadequate wraparound), lateral displacement a = 0, yaw angle c = 0, vehicle body side slip angle β = r (> 0) Xexp−X ^* exp = Ls ( −r) <0, and in any case, a deviation occurs, and a warning is issued as the deviation between the traveling direction of the vehicle and the direction of the road increases.

On the right side of FIG. 13, if the traveling direction of the vehicle is 1
In the case of the dashed line, the lateral displacement a = 0, the yaw angle c = m, and the vehicle body side slip angle β = n (<m) Xexp−X ^* exp = Ls (mn)> 0. If the traveling direction of the vehicle is a two-dot chain line, lateral displacement a = 0, yaw angle c = m, vehicle body side slip angle β = p (> m) Xexp−X ^* exp = Ls (mp) <0. In any case, a deviation occurs, and a warning is issued as the deviation between the traveling direction of the vehicle and the direction of the road increases.

Further, as shown by a dotted line on the right side of FIG.
When the traveling direction of the vehicle is largely different from the direction of the road, the lateral displacement a = 0, the yaw angle c = g (<0),
The vehicle body side slip angle β = h (> 0) Xexp−X ^* exp = Ls (gh) <0, and a warning is issued because a deviation occurs.

Next, the effects will be described.

As described above, in the vehicle lane departure warning system of the first embodiment, the target forward lateral displacement value X ^* exp obtained from the vehicle body slip angle β is used as a reference value for judging lane departure. Since the lane departure is determined based on the deviation between the estimated forward lateral displacement value Xexp and the desired forward lateral displacement value X ^* exp, the estimated forward lateral displacement value Xexp and the forward direction are obtained even during high-speed turning in which the vehicle body slip angle β occurs. Lateral displacement target value X
^* If the deviation from exp is small, a departure warning will not be issued, and the driver will not feel uncomfortable with the departure warning.

Further, the evaluation point of the lane departure is Xexp-X ^* e.
Since it is set to xp, the lane departure can be evaluated by the same evaluation point Xexp-X ^* exp on both straight roads and curved roads, so that the connection is continuous without interruption under all road conditions and running conditions. To predict the lane departure.

(Second Embodiment) In the vehicle lane departure warning system according to the second embodiment, the threshold value Xth is given by a fixed value in the first embodiment, but as shown in FIG. In this example, the threshold value Xth is set to a constant value up to b1 and the threshold value Xth is set to a proportionally larger value as the road curvature b increases when b exceeds b1.

The other structure, operation, and effect are the same as those of the first embodiment, so that illustration and description are omitted.

Therefore, in the vehicle lane departure warning device of the second embodiment, when the vehicle speed is the same, the vehicle turns with a small turning radius in which the vehicle body slip angle β tends to be larger than when turning with a large turning radius. Sometimes the road curvature b ahead
Becomes larger, the threshold value Xth becomes larger.
At a corner with a small radius, a relatively free driver's course can be tolerated, so that an alarm suitable for a normal driver's driving feeling can be notified without worrying about the course.

(Third Embodiment) In the vehicle lane departure warning device of the third embodiment, the threshold value Xth is given by a fixed value in the first embodiment device, but as shown in FIG. The threshold value Xth in the outside direction is a constant value, and the threshold value Xth in the corner inside direction is a constant value when the front road curvature b is up to b1, and the road curvature b becomes large when the road curvature b is from b1 to b2. In this example, the threshold value Xth is proportionally set to a large value, and the road curvature b is set to a large value when it exceeds b2.

The other structure, operation, and effect are the same as those of the first embodiment, so that illustration and description are omitted.

Therefore, in the vehicle lane departure warning system of the third embodiment, the corner IN where the deviation Xexp−X ^* exp tends to be larger than the corner OUT during turning.
Because the threshold value Xth on the side is set to be large, it is possible to allow a driver to prefer a course at the corner of a small radius more than the normal driver on the IN side.
It is possible to alert the driver to the normal driving feeling without having to worry about the IN side course.

(Fourth Embodiment) In the vehicle lane departure warning system according to the fourth embodiment, the threshold value Xth is given by a fixed value in the first embodiment, while the vehicle speed is increased as shown in FIG. V
_{In this} example, the threshold value Xth is inversely set to a smaller value as the _SP becomes higher.

The other structure, operation, and effect are the same as those of the first embodiment, so that illustration and description are omitted.

Therefore, in the vehicle lane departure warning system of the fourth embodiment, the distance of the gazing point ahead of the vehicle predicting the departure.
Time to reach Ls is so that the vehicle speed V _SP reaches fast as is faster, by reducing the threshold Xth accordance speed V _SP becomes higher, the vehicle speed V and the estimated time of departure
It can be set so as not to be changed by the _SP .

(Other Embodiments) Although the first to fourth embodiments have been described above, the specific structure is not limited to each embodiment, and the gist of the invention according to claim 1 is described. Even a design change that does not deviate is included in the present invention.

For example, of the threshold value settings shown in the second to fourth embodiments, the threshold value may be set by combining two setting methods or by combining all three.

[Brief description of the drawings]

FIG. 1 is an overall system diagram showing a lane departure warning device for a vehicle in a first embodiment.

FIG. 2 is an explanatory diagram showing a camera mounting position in the first embodiment device.

FIG. 3 is a flowchart illustrating an example of a road white line detection process performed by a controller of the apparatus according to the first embodiment;

FIG. 4 is a diagram illustrating a white line model.

FIG. 5 is a diagram for explaining a method of setting an initial value of a white line candidate point detection area.

FIG. 6 is a diagram for explaining a method of setting an initial value of a white line candidate point detection area when a road white line has already been detected.

FIG. 7 is a diagram for explaining a method of setting a white line candidate point detection area on a captured road screen.

FIG. 8 is a diagram for explaining a method of detecting a white line candidate point.

FIG. 9 is a diagram showing a shift amount between a white line candidate point detected this time and a point on the white line model obtained last time.

FIG. 10 is a flowchart illustrating an example of a traveling state monitoring process performed by a controller of the first embodiment.

FIG. 11 is a diagram illustrating an estimated forward lateral displacement value Xexp on a straight road in the first embodiment.

FIG. 12 is a diagram illustrating an estimated forward lateral displacement value Xexp on a curved road in the first embodiment.

FIG. 13 is a diagram illustrating evaluation points of lane departure during low-speed turning and high-speed turning in the first embodiment.

FIG. 14 is a characteristic diagram showing a relationship between a turning angular speed and a traveling speed.

FIG. 15 is a characteristic diagram showing a relationship between a side slip angle of a center of gravity and a speed.

FIG. 16 is a diagram showing a threshold value setting map in the vehicle lane departure warning device of the second embodiment.

FIG. 17 is a diagram showing a threshold value setting map in the vehicle lane departure warning device of the third embodiment.

FIG. 18 is a diagram showing a threshold value setting map in the vehicle lane departure warning device of the fourth embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Camera (imaging means) 2 Image processing device 3 Control controller 4 Vehicle speed sensor 5 Steering angle sensor 6 Alarm controller 7 Alarm (alarm means)

──────────────────────────────────────────────────の Continued on the front page (51) Int.Cl. ⁷ Identification FI FI Theme Court ゛ (Reference) G06T 7/60 200 G06T 7/60 200J G08G 1/16 G08G 1/16 CD (72) Inventor Masayasu Shimakage Nissan Motor Co., Ltd. (72) Inventor Hiroshi Kawazoe Nissan Motor Co., Ltd. (72) Inside Nissan Motor Co., Ltd. (72) Inventor Hiroshi Kawazoe Nissan Motor Co., Ltd. (72) Inventor Atsushi Sadano Takaracho, Kanagawa Ward, Yokohama, Kanagawa No. 2 Nissan Motor Co., Ltd. F term (reference) 5B057 AA16 BA02 BA30 CH08 CH18 DA07 DA08 DA15 DC07 DC09 5H180 AA01 CC04 LL06 LL15 5L096 BA04 CA02 DA03 EA41 FA13 FA66 FA67 FA68 GA02 GA06 GA19 GA28 GA32 GA51 JA11

Claims (4)

[Claims] 1. An image pickup means for picking up an image of the front of a vehicle, a road shape estimating means for estimating a road shape from an image picked up by the image pickup means, and a vehicle shape based on the road shape estimated by the road shape estimating means. A lateral displacement estimating means for estimating a lateral displacement with respect to the road, and a road shape estimated by the road shape estimating means,
A yaw angle estimating means for estimating a yaw angle of the host vehicle with respect to a road; a vehicle body slip angle estimating means for estimating a vehicle body slip angle based on a steering angle detection value and a vehicle speed detection value; Forward lateral displacement estimated value calculating means for calculating an estimated forward lateral displacement value at a predetermined position, and a desired forward lateral displacement value calculating means for calculating a desired forward lateral displacement value at a predetermined position ahead of the vehicle based on the lateral displacement and the vehicle body slip angle. Threshold setting means for setting a threshold value for determining whether or not a deviation between the estimated forward lateral displacement value and the desired forward lateral displacement value is a lane departure tendency; and an estimated forward lateral displacement value and a desired forward lateral displacement value. A lane departure determining means for determining whether a deviation from the value is equal to or greater than a set threshold, and an alarm notifying the driver of a lane departure when the lane departure is determined to be greater than or equal to the set threshold Lane departure warning system for a vehicle, characterized in that it comprises a stage, a. 2. The lane departure warning device for a vehicle according to claim 1, wherein the threshold value setting unit sets the threshold value to a larger value as the curvature of the road ahead increases. Lane departure warning device for vehicles. 3. The lane departure warning device for a vehicle according to claim 1, wherein the threshold value setting means sets a threshold value of the curvature of the front road in the corner inward direction to be large, and sets the curvature of the front road curvature. A lane departure warning device for a vehicle, characterized in that the threshold value in a direction outside a corner of the vehicle is set small. 4. The lane departure warning device for a vehicle according to claim 1, wherein the threshold value setting unit sets the threshold value to a smaller value as the vehicle speed increases. A lane departure warning device for a vehicle.