JP4647387B2 - Vehicle driving support device - Google Patents

Description

  The present invention relates to a vehicle driving support device capable of providing an appropriate warning in accordance with a driver's forward attention state and arousal state when a preceding vehicle is present ahead.

  In recent years, as a vehicle driving support device, a vehicle environment such as a vehicle-mounted camera is used to detect a driving environment in front and alarm control is performed for obstacles ahead, and a preceding vehicle is detected from the driving environment. Therefore, technologies for tracking control and alarm control have been developed and put into practical use. Recently, a technique for estimating the driver's attention and changing the alarm according to this attention has been developed.

For example, Japanese Patent Application Laid-Open No. 11-276461 discloses a technology that detects a driver's jumping eye movement, estimates the driver's attention level from this jumping eye movement, and presents information earlier as the attention level is lower. Has been.
JP-A-11-276461

  By the way, when there is a preceding vehicle ahead, the driver needs to give sufficient attention to the preceding vehicle in the forward view. However, depending on the driver's condition, the attention may be vague, or conversely, too much attention may be poured into the preceding vehicle, and attention to other surrounding information may be weakened. Such a change in attention to the preceding vehicle is difficult to distinguish by the above-described prior art, and a technique for appropriately giving a warning to the driver when such a preceding vehicle exists is required.

  SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and provides a vehicle driving support device that can accurately determine a change in the driver's attention when a preceding vehicle is present and can appropriately alert the driver. It is intended to provide.

The present invention includes forward information recognition means for recognizing environmental information in front of the host vehicle, preceding vehicle information detection means for detecting preceding vehicle information from the environmental information in front of the host vehicle, and gaze behavior detection means for detecting gaze behavior. Estimated by a variation value calculating means for calculating a value indicating a variation in line-of-sight behavior with respect to the preceding vehicle, a caution state estimating means for estimating a driving attention state with respect to the preceding vehicle based on the value indicating the variation, and the attention state estimating means When it is determined that the driving attention state for the preceding vehicle is lower than a preset evaluation threshold and the driving attention state for the preceding vehicle is not strong, at least a front obstacle other than the preceding vehicle is targeted. It is characterized by comprising an alarm control means for relaxing an alarm from an alarm performed in a normal state .

  According to the vehicle driving support apparatus of the present invention, it is possible to accurately determine a change in the driver's attention when there is a preceding vehicle. Furthermore, it is possible to appropriately issue an alarm according to the driver's attention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
1 to 7 show an embodiment of the present invention, FIG. 1 is a schematic configuration diagram of a driving support device mounted on a vehicle, FIG. 2 is a flowchart of an alarm control program, and FIG. 3 is a distribution of gaze behavior in a forward view. FIG. 4 is an explanatory diagram of examples of various attention evaluation values, FIG. 5 is an explanatory diagram of vehicle behavior in an arousal state and a low arousal state, and FIG. 6 is a principle of a pop-out warning. FIG. 7 is an explanatory diagram of an example of mitigating forward warning and pop-out warning.

  In FIG. 1, reference numeral 1 denotes a vehicle such as an automobile (own vehicle), and the own vehicle 1 has a function of performing a contact alarm for a preceding vehicle and a contact alarm for a front obstacle other than the preceding vehicle. The driving support device 2 is installed.

  The driving support device 2 includes a stereo camera 3 that captures the front outside the vehicle, a stereo image recognition device 4 that processes a signal from the stereo camera 3, a visual field camera 5 that captures the driver's eye movement, an infrared lamp 6, a visual field camera 5, and an infrared ray. It mainly comprises a gaze state detection device 7 that detects the gaze state of the driver using the lamp 6, a control unit 8, a monitor 9 that displays an alarm, and a sound generator 10 that issues an alarm.

  The host vehicle 1 is also provided with a vehicle speed sensor 11 that detects the vehicle speed, a handle angle sensor 12 that detects the handle angle, and a yaw rate sensor 13 that detects the yaw rate. The vehicle speed from the vehicle speed sensor 11 is input to the stereo image recognition device 4 and the control unit 8, and the steering wheel angle from the steering wheel angle sensor 12 and the yaw rate from the yaw rate sensor 13 are input to the stereo image recognition device 4.

  The stereo camera 3 is composed of a set of (left and right) CCD cameras using a solid-state imaging device such as a charge coupled device (CCD) as a stereo optical system. These left and right CCD cameras are each mounted at a predetermined interval in front of the ceiling in the passenger compartment, take a stereo image of an object (a three-dimensional object) outside the vehicle from different viewpoints, and output image data to the stereo image recognition device 4.

  The stereo image recognition device 4 receives image data, vehicle speed, steering wheel angle, and yaw rate signals from the stereo camera 3, and based on the image data, forward information such as three-dimensional object data, sidewall data, and white line data in front of the host vehicle 1. And the traveling path of the host vehicle 1 (the host vehicle traveling path) is estimated from the forward information and the driving state of the host vehicle 1. Then, a travel region is set based on the traveling path of the host vehicle, and a preceding vehicle ahead of the host vehicle 1 is identified and extracted according to the presence state of the three-dimensional object in the travel region, and the result is output to the control unit 8. To do.

  The above-described estimation of the own vehicle traveling path is performed as follows, for example. At this time, the three-dimensional coordinate system in the real space is a coordinate system fixed to the own vehicle 1, the left and right (width) direction of the own vehicle 1 is the X coordinate, the up and down direction of the own vehicle 1 is the Y coordinate, and the front and rear of the own vehicle 1. The direction is indicated by the Z coordinate. Then, with the road surface directly below the center of the two CCD cameras constituting the stereo camera 4 as the origin, the right side of the host vehicle 1 is the + side of the X axis, the upper side of the host vehicle 1 is the + side of the Y axis, and the host vehicle 1 Is set as the positive side of the Z axis.

  a. The own vehicle traveling path estimation based on the white line ... If the white line data on both the left and right sides or the left and right sides is obtained, and the shape of the lane in which the vehicle 1 is traveling can be estimated from these white line data, the own vehicle travels The road is formed in parallel with the white line in consideration of the width of the host vehicle 1 and the position of the host vehicle 1 in the current lane.

  b. Self-vehicle travel path estimation based on side data of guardrails, curbs, etc. Side wall data on both the left and right sides or left and right sides is obtained, and the shape of the lane in which the vehicle 1 is traveling is estimated from these side wall data If possible, the own vehicle traveling path is formed in parallel with the side wall in consideration of the width of the own vehicle 1 and the position of the own vehicle 1 in the current lane.

  c. Estimating own vehicle traveling path based on preceding vehicle trajectory: Estimating the own vehicle traveling path based on the past traveling trajectory of the preceding vehicle extracted from the three-dimensional object data.

  d. Estimating own vehicle travel path based on travel path of own vehicle 1 ... Estimating the own vehicle travel path based on the driving state of the own vehicle 1. For example, assuming that the yaw rate is γ, the host vehicle speed is Vo, and the steering wheel angle is θH, the host vehicle traveling path is estimated by the following procedure.

First, it is determined whether the yaw rate sensor 13 is valid. If the yaw rate sensor 13 is valid, the current turning curvature Cua is calculated by the following equation (1).
Cua = γ / Vo (1)

On the other hand, if the yaw rate sensor 13 is invalid, it is determined whether or not the steering angle δ obtained from the steering wheel angle θH is a predetermined value (for example, 0.57 degrees) or more, and the steering angle δ is 0. When the steering is performed at 57 ° or more, the current turning curvature Cua is calculated using the steering angle δ and the host vehicle speed Vo, for example, by the following equations (2) and (3).
Re = (1 + A · V ² ) · (L / δ) (2)
Cua = 1 / Re (3)
Here, Re is a turning radius, A is a vehicle stability factor, and L is a wheelbase.

  When the steering angle δ is smaller than 0.57 degrees, the current turning curvature Cua is set to 0 (straight running state).

  In this way, the average turning curvature is calculated from the turning curvature of the past predetermined time (for example, about 0.3 seconds) to which the obtained current turning curvature Cua is added, and the own vehicle traveling path is estimated.

  Even when the yaw rate sensor 13 is valid and the current turning curvature Cua is calculated by the above-described equation (1), if the steering angle δ is smaller than 0.57 degrees, the current turning curvature is Cua may be corrected to 0 (straight running state).

  For example, a width of about 1.1 m on the left and right sides is set as the travel region of the host vehicle, with the host vehicle traveling path estimated as described above approximately as the center.

  The processing of the image data from the stereo camera 3 in the stereo image recognition device 4 is performed as follows, for example. First, a process for obtaining distance information based on the principle of triangulation is performed on the stereo image pair in front of the host vehicle 1 captured by the CCD camera of the stereo camera 3 to express a three-dimensional distance distribution. Generate a distance image. Then, based on this data, a well-known grouping process is performed and compared with frames (windows) such as three-dimensional road shape data, side wall data, and three-dimensional object data stored in advance. Sidewall data such as guardrails and curbs, and three-dimensional object data such as vehicles are extracted.

  The white line data, the side wall data, and the three-dimensional object data extracted in this way are assigned different numbers for each data. Further, regarding the three-dimensional object data, the stopped object and the order of moving in the same direction as the own vehicle 1 are determined from the relationship between the relative change in the distance from the own vehicle 1 and the vehicle speed of the own vehicle 1. It is classified and output as a moving object. Then, for example, among the forward moving objects protruding into the own vehicle traveling area, the three-dimensional object closest to the own vehicle 1 is registered as a preceding vehicle, which is detected continuously for a predetermined time.

  Thus, in the present embodiment, the stereo camera 3 and the stereo image recognition device 4 constitute a front information recognition unit and a preceding vehicle information detection unit.

  On the other hand, the gaze behavior of the driver in the present embodiment is detected by a so-called pupil / corneal reflection method. Therefore, the visual field camera 5 is a camera equipped with an infrared CCD, and the infrared lamp 6 is an LED lamp. The line-of-sight state detection device 7 detects the center of the pupil while simultaneously detecting the center of the pupil by the visual camera 5 while the virtual image by the infrared lamp 6 on the cornea is translated by the eye movement due to the difference between the rotation centers of the cornea and the eyeball. Detecting eye movements as a reference makes it possible to detect gaze behavior. Note that the detection of the gaze behavior is not limited to this detection method, and if possible, other detection methods (EOG (Electro-Oculography) method, scleral reflection method, corneal reflection method, search coil method, etc.) It may be detected. That is, the visual field camera 5, the infrared lamp 6, and the visual line state detection device 7 are provided as visual line behavior detection means.

  The control unit 8 receives from the stereo image recognition device 4 the own vehicle traveling path, traveling region, preceding vehicle information, and three-dimensional object information other than the preceding vehicle, and the gaze state detection device 7 receives the driver's gaze behavior signal (unit: angle). The vehicle speed is input from the vehicle speed sensor 11.

  At this time, as shown in FIG. 3, the width information of the preceding vehicle from the stereo image recognition device 4 is given in length units (W in FIG. 3), and the driver's line-of-sight behavior is given in angle units. In order to enable calculation, as shown in FIG. 4, the width W of the preceding vehicle is converted into a value α in angular units.

This conversion formula is based on the following formula (4).
α = 2 · arctan ((W / 2) / L) (4)
Here, L is the inter-vehicle distance.

Further, from the driver's line-of-sight behavior signal input to the control unit 8, a dispersion value β is calculated by the following equation (5) as a value indicating the variation in the line-of-sight behavior with respect to the preceding vehicle. That is, the point of gaze on the virtual plane is calculated based on the rotation angle of the eyeball. The horizontal component of the gazing point on the virtual plane is set to xi, a certain time span [t1, t2] (for example, 30 to 60 seconds) is set, and the horizontal dispersion value β of the gazing point in the meantime is
β = (1 / (t2−t1 + 1)) · Σ _{j = t1} ^t2 (xj ² −xa ² ) (5)
Here, xa is an average value and is obtained by the following equation (6).

xa = (1 / (t2−t1 + 1)) · Σ _{j = t1} ^t2 xj (6)

Note that the standard deviation sx may be used as a value indicating the variation in the line-of-sight behavior with respect to the preceding vehicle.
sx = ((1 / n) · Σ _{j = t1} ^t2 (xj ² −xa ² )) ^1/2 (7)

  Then, the ratio of the width α of the preceding vehicle to the variance value β of the driver's line-of-sight behavior is calculated as the attention evaluation value Sh representing the attention state (Sh = α / β), and this attention evaluation value Sh is calculated in advance. When the evaluation threshold value Shc (for example, 0.1) is equal to or higher than the set evaluation threshold value Shc (for example, in the case of β1 in FIG. 4), it is determined that the attention state of driving with respect to the preceding vehicle is strong and The warning for the vehicle (forward warning) is relaxed from the warning in the normal state (note that the warning for the front obstacle other than the preceding vehicle (jumping warning) remains as it is).

  Further, when the attention evaluation value Sh is smaller than the preset evaluation threshold Shc (for example, in the case of β2 in FIG. 4), the driving attention state with respect to the preceding vehicle is not strong (a casual state). ). In the case of this mood state, a wakefulness evaluation value Kh indicating the driver's wakefulness level is further calculated, and if the wakefulness evaluation value Kh is equal to or greater than a preset value Khc, it is determined that the state is awakening and a pop-up warning is issued. Is relaxed from the alarm that is performed in the normal state (note that the forward alarm remains unchanged).

  Further, when the arousal evaluation value Kh is lower than the preset value Khc and it is determined that the arousal is in a lowered state during this state of ambiguity, the forward warning and the pop-out warning are also left as they are.

Here, the arousal evaluation value Kh is calculated by, for example, the following equation (8).
Kh = (Number of blinks for a long time) / (Total number of blinks) (8)

  Note that the evaluation of the degree of arousal may be determined not by the arousal evaluation value Kh obtained by the above equation (8) but by the vehicle driving state (handle operation) of the driver as shown in FIG. That is, in the awake state, as shown in FIG. 5 (a), a vehicle behavior with a high frequency and a small amplitude is generated, whereas in the awake state, the frequency is changed as shown in FIG. 5 (b). This produces low wandering with large amplitude. You may judge this and evaluate arousal level.

  And the control unit 8 gives the following warnings as a front warning for the preceding vehicle, for example. A warning distance is set ahead according to the relative speed with the preceding vehicle (the longer the speed at which the vehicle 1 approaches the preceding vehicle, the longer), and when the preceding vehicle exists at this warning distance, a forward warning flag is set. Is set on the control logic, the alarm display on the monitor 9 blinks at a predetermined frequency to give an alarm, and the audio generator 10 generates an audio alarm at predetermined intervals.

  Moreover, the control unit 8 gives the following warning as a jumping warning for front obstacles other than the preceding vehicle, for example. As shown in FIG. 6, a jump warning area is set in advance outside the vehicle running area, and when a front obstacle is present in the jump warning area, the jump warning flag is set on the control logic. The alarm display on the monitor 9 is flashed at a predetermined frequency to give an alarm, and an audio alarm is generated from the audio generator 10 at predetermined intervals.

  The forward warning and the pop-out warning described above are merely examples, and other forms of alarm control may be used.

  Thus, in the present embodiment, the control unit 8 is configured to have functions as a variation value calculating means, a caution state estimating means, a wakefulness estimating means, and an alarm control means.

  Next, the above-described alarm control program will be described with reference to the flowchart of FIG. First, in step (hereinafter abbreviated as “S”) 101, necessary parameters are read.

  Next, the process proceeds to S102, the preceding vehicle is extracted by the stereo camera 3 and the stereo image recognition device 4, and the process proceeds to S103, where the control unit 8 converts the width information of the preceding vehicle into an angle α.

  Thereafter, the process proceeds to S104, where the control unit 8 calculates an average value of the driver's line-of-sight behavior and a variance value β from the average value, and proceeds to S105 to determine the width of the preceding vehicle in the driver's line-of-sight behavior variance value β. The ratio of α is calculated as the attention evaluation value Sh representing the attention state (Sh = α / β).

  Then, the process proceeds to S106, where the attention evaluation value Sh is compared with a preset evaluation threshold Shc. If the attention evaluation value Sh is equal to or greater than the evaluation threshold Shc, the attention state of driving with respect to the preceding vehicle is strong. The process proceeds to S107, and the forward warning is relaxed from the warning performed in the normal state, and the program is exited (note that the pop-out warning is left as it is). Specifically, as shown in FIG. 7 (a), even if the forward warning flag is set, it is thinned out without warning with all the flags. Instead of the thinning-out method as shown in FIG. 7A, the alarm display blinking period of the monitor 9 may be lengthened, or the frequency of alarms issued from the sound generator 10 may be reduced. That is, in this state, it is considered that the driver is paying sufficient attention to the preceding vehicle, and therefore, if a normal forward warning is given, it may be annoying. Therefore, mitigating the forward warning prevents the driver from interfering more than necessary.

  On the other hand, when it is determined that the attention evaluation value Sh is smaller than the evaluation threshold value Shc as a result of the determination in S106, it is determined that the attention state of the driving with respect to the preceding vehicle is not strong (a state of randomness), and the process proceeds to S108. The wakefulness evaluation value Kh is calculated by the equation (5).

  Then, the process proceeds to S109, where the wakefulness evaluation value Kh is compared with a preset value Khc, and if it is determined that the wakefulness evaluation value Kh is equal to or greater than the set value Khc, it is determined that the wakefulness is present, and the process proceeds to S110. Then, the pop-up warning is relaxed from the warning that is performed in the normal state, and the program is exited (the forward warning is left as it is). Specifically, as shown in FIG. 7 (b), even if a pop-out warning flag is set, it is thinned out without warning with all the flags. It should be noted that the blinking cycle of the alarm display on the monitor 9 may be lengthened, or the frequency of alarms issued from the sound generator 10 may be reduced. That is, in this state, it is considered that the driver is paying sufficient attention to obstacles other than the preceding vehicle. Therefore, by mitigating the pop-out warning, it is possible to prevent the driver from interfering more than necessary.

  If the result of determination in S109 is that the arousal evaluation value Kh is determined to be lower than the set value Khc, it is determined that the arousal has fallen, and the process proceeds to S111. . That is, as shown in FIG. 7C, when the forward warning flag and the pop-out warning flag are set, all alarms are issued. In this state, it is preferable to alert the driver as quickly as possible. Therefore, the smaller the arousal evaluation value Kh, the faster the alarm display on the monitor 9 blinks, and the alarm generated from the sound generator 10 The frequency may be increased.

  As described above, in this embodiment, when the attention evaluation value Sh is equal to or greater than the evaluation threshold value Shc, it is determined that the attention state of driving with respect to the preceding vehicle is strong, and the forward warning is more relaxed than the warning performed in the normal state. . When it is determined that the attention evaluation value Sh is smaller than the evaluation threshold value Shc, it is determined that the attention state of driving with respect to the preceding vehicle is not strong (a state of randomness), and the wakefulness evaluation value Kh is determined to be greater than or equal to the set value Khc. In this case, it is determined that the state is awakening, and the popping-out warning is relaxed from the warning performed in the normal state, and when it is determined that the wakefulness evaluation value Kh is lower than the set value Khc, it is determined that the wakefulness is reduced, the forward warning, Both pop-out alarms are normal alarms. Accordingly, it is possible to accurately determine a change in the driver's attention when there is a preceding vehicle and to appropriately issue an alarm to the driver.

  In this embodiment, when it is determined that the attention evaluation value Sh is smaller than the evaluation threshold value Shc, the alarm control is further changed according to the wakefulness evaluation value Kh. It may be simplified to omit the case classification with the arousal evaluation value Kh and to ease the pop-out alarm from the alarm performed in the normal state.

  Further, in this embodiment, in order to obtain the attention evaluation value Sh, the width W of the preceding vehicle is converted into an angle, but conversely, the variance value β of the driver's line-of-sight behavior is calculated as the preceding vehicle. The same result can be obtained even if the attention evaluation value Sh is calculated in terms of the length dimension at the position.

  Furthermore, in the present embodiment, the preceding vehicle is recognized based on the image from the stereo camera. However, other technologies such as those that recognize based on information from the millimeter wave radar and the monocular camera are used. It may be.

Schematic configuration diagram of a driving support device mounted on a vehicle Flow chart of alarm control program Explanatory diagram of variance of gaze behavior in front view and width of preceding vehicle Illustration of examples of various attention evaluation values Illustration of vehicle behavior in wakefulness and wakefulness declined states Explanatory diagram of the principle of pop-out warning Illustration of mitigation examples of forward warning and pop-out warning

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Own vehicle 2 Driving assistance apparatus 3 Stereo camera (front information recognition means, preceding vehicle information detection means)
4 Stereo image recognition device (forward information recognition means, preceding vehicle information detection means)
5 Field of view camera (Gaze behavior detection means)
6 Infrared lamp (Gaze behavior detection means)
7 Gaze state detection device (Gaze behavior detection means)
8 Control unit (variation value calculation means, attention state estimation means, arousal level estimation means, alarm control means)
9 Monitor 10 Sound generator

Claims (4)

Forward information recognition means for recognizing environmental information ahead of the vehicle;
Preceding vehicle information detection means for detecting preceding vehicle information from environmental information ahead of the host vehicle;
Gaze behavior detecting means for detecting gaze behavior,
A variation value calculating means for calculating a value indicating variation in the line-of-sight behavior with respect to the preceding vehicle;
Caution state estimating means for estimating a caution state of driving with respect to the preceding vehicle by a value indicating the variation;
When it is determined that the driving attention state for the preceding vehicle estimated by the attention state estimating means is lower than a preset evaluation threshold and the driving attention state for the preceding vehicle is not strong, at least other than the preceding vehicle An alarm control means for mitigating an alarm for a front obstacle in a normal state ; and
A vehicle driving support apparatus comprising:   When the warning control means determines that the driving attention state for the preceding vehicle estimated by the attention state estimation means is equal to or higher than a preset evaluation threshold and the driving attention state for the preceding vehicle is strong, at least the above The vehicle driving support device according to claim 1, wherein a warning for a preceding vehicle is more relaxed than a warning that is issued in a normal state. Having an arousal level estimation means for estimating arousal level during driving;
The alarm control means, in the case where attention state of operation with respect to the preceding vehicle estimated by the attention state estimating means determines that strong wards and, awake to satisfy the condition that the degree of awakening is preset The vehicle driving support device according to claim 1 or 2, wherein an alarm for at least a front obstacle other than the preceding vehicle is more relaxed than an alarm that is issued in a normal state. The vehicle driving support according to any one of claims 1 to 3, wherein the value indicating the variation in the line-of-sight behavior is one of a dispersion value and a standard deviation of the horizontal movement of the line of sight. apparatus.

Images