JP2009298193A - Driving support device for vehicle - Google Patents

Abstract

[PROBLEMS] To accurately determine the degree of recognition of a vehicle entering an intersection with respect to the own vehicle and appropriately consider the information of the vehicle at the intersection to ensure safety while maintaining a smooth traffic flow. Provide proper driving assistance.
A face direction degree Fi of a driver of the target vehicle is set according to a face direction direction of the driver of the target vehicle, and a recognition degree Ri of the host vehicle is calculated based on the face direction degree Fi of the driver of the target vehicle. If the vehicle's risk Riski is calculated based on the vehicle's perceived degree Ri and the subject vehicle's perceived degree Ri is higher than the threshold Ric and there is only one target vehicle, the host vehicle becomes the target vehicle. On the other hand, when there is a priority running relationship, the risk Ri of the host vehicle is corrected to decrease. Further, when the recognition degree Ri of the own vehicle is equal to or less than the threshold value Ric, or there are a plurality of target vehicles, the light is turned on when the risk Riski of the own vehicle is higher than the threshold Risklt.
[Selection] Figure 1

Description

  The present invention relates to a driving support apparatus for a vehicle that supports driving of a driver in consideration of a situation between vehicles at an intersection.

  2. Description of the Related Art In recent years, in vehicles, various driving systems that recognize driving environments and support driving to enable safe driving based on information obtained from ITS (Intelligent Transport Systems), in-vehicle image processing systems, radar devices, etc. Support devices have been proposed and put into practical use.

In particular, at intersections, various technologies have been proposed from many viewpoints such as prevention of collision with an approaching vehicle, ensuring safety and maintaining a smooth traffic flow. For example, in Japanese Patent Application Laid-Open No. 2007-200052, the vehicle behavior change (speed, speed change amount, vehicle width direction position change amount, etc.) of the crossing other vehicle before and after the start of the own vehicle from the position before the temporary stop line. Based on this, the degree of recognition of the existence of the own vehicle by the driver of the crossing other vehicle is estimated as the degree of recognition, and the higher the estimated degree of recognition, the more the vehicle stops again at the position where it entered the stop intersection. Thus, a technique for providing driving assistance is disclosed.
JP 2007-200052 PR

  However, as in the driving assistance technology at the intersection disclosed in Patent Document 1 described above, the degree of recognition of the other vehicle in the intersection with respect to the host vehicle is changed to the vehicle behavior change (speed, speed change amount, vehicle width of the other vehicle in the intersection). Judgment based on the amount of change in direction and position), it is highly possible that the driving action is in accordance with other objects (other vehicles, pedestrians, road conditions, etc.). Not always. In addition, there are traffic rules peculiar to intersections such as priority roads and left priority at intersections, and drivers of vehicles entering the intersection usually travel according to these traffic rules. It is desirable to provide driving assistance at intersections.

  The present invention has been made in view of the above circumstances, and it is possible to accurately determine the degree of recognition of a vehicle entering the intersection with respect to the own vehicle and appropriately consider the information of the own vehicle at the intersection to ensure smoothness while ensuring safety. An object of the present invention is to provide a vehicle driving support device capable of maintaining a traffic flow and providing natural and appropriate driving support.

  The present invention recognizes an intersection detection means for detecting a forward intersection, vehicle information detection means for detecting forward vehicle information, and a vehicle entering the intersection as a target vehicle, and the degree of recognition of the target vehicle with respect to the host vehicle. The degree of recognition of the subject vehicle, the risk computation means for calculating the risk of the subject vehicle, and when the subject vehicle is at least higher than a preset threshold, When there is a priority traveling relationship with respect to the target vehicle, risk correction setting means for reducing and correcting the risk of the host vehicle, and control execution for executing at least one of alarm control and traveling control based on the risk of the host vehicle And a means.

  According to the vehicle driving support device of the present invention, the degree of recognition of a vehicle entering the intersection with respect to the host vehicle is accurately determined, and smooth traffic is ensured while ensuring safety by appropriately taking into account the information of the host vehicle at the intersection. It is possible to provide natural and appropriate driving support while maintaining the flow of the vehicle.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
1 to 6 show an embodiment of the present invention, FIG. 1 is a functional block diagram of a driving support apparatus at an intersection mounted on a vehicle, FIG. 2 is a flowchart of a driving support control program at the intersection, and FIG. FIG. 4 is an explanatory diagram showing an example of the subject vehicle and the target vehicle entering the intersection, FIG. 5 is an explanatory diagram of the characteristics of the face orientation of the driver of the target vehicle, and FIG. 6 is a characteristic of the intersection approach amount. It is explanatory drawing.

  In FIG. 1, reference numeral 1 denotes a driving support device at an intersection mounted on a vehicle. In the driving support device 1, signals from the image recognition device 2 and the navigation device 3 are input to the control unit 4. Signals are output to the light control device 5, the alarm control device 6, and the travel control device 7.

  The image recognition device 2 is, for example, a set of CCD cameras that are mounted at a fixed interval in front of a ceiling in a vehicle interior and that stereo-shoots an object outside the vehicle from different viewpoints, and a stereo image that processes image data from the CCD camera. And a processing device.

  The processing of image data from the CCD camera in the stereo image processing apparatus is performed as follows, for example. First, distance information is obtained from a set of stereo image pairs taken in the traveling direction of the host vehicle captured by the CCD camera from the corresponding positional deviation amount, and a distance image is generated. Then, based on this data, a well-known grouping process is performed, and compared with a frame (window) such as three-dimensional vehicle shape data stored in advance, each vehicle existing ahead is extracted, Calculate the relative speed with the own vehicle from the ratio of the temporal change in the distance to the own vehicle, and calculate the speed of each vehicle by adding the relative speed and the own vehicle speed. (Including image data) is input to the control unit 4. Thus, the image recognition apparatus 2 is provided as vehicle information detection means.

  The navigation device 3 has, for example, an ITS function, and is a well-known device that displays the current position, guides to the destination, and the like. In particular, the navigation device 3 transmits / receives by using intersection information or ITS provided in map information stored in advance. The various road information including the intersection information is input to the control unit 4 together with the current vehicle position information. Thus, the navigation apparatus 3 is provided as an intersection detection means.

  The control unit 4 receives forward vehicle information from the image recognition device 2 described above and forward road information from the navigation device 3, and recognizes a vehicle entering the intersection as a target vehicle based on the input information. Then, the face direction of the driver of the target vehicle is detected, the face direction degree Fi of the driver of the target vehicle is set according to the face direction of the driver of the target vehicle, and the face direction degree Fi of the driver of the target vehicle is set. Based on the recognition degree Ri of the subject vehicle as the recognition degree Ri of the subject vehicle, the risk Risk of the subject vehicle is calculated based on the perceived degree Ri of the subject vehicle, and the perceived degree of the subject vehicle. If Ri is higher than the preset threshold value Ric and there is only one target vehicle, and the host vehicle is in a priority travel relationship with respect to the target vehicle, the risk Ri of the host vehicle is corrected to decrease. In addition, when the recognition degree Ri of the own vehicle is equal to or less than the preset threshold value Ric, or when there are a plurality of target vehicles, and the risk Riski of the own vehicle is higher than the preset threshold value Risklt, a signal is sent to the light control device 5. Output and control to turn on the headlight. Furthermore, in addition to these controls, if the maximum risk Riskmax of the host vehicle is higher than a preset threshold Riskal, a signal is output to the alarm control device 6 to blink the LED in the instrument panel, Activates a predetermined alarm such as vibration addition. Further, according to the maximum value Riskmax of the host vehicle, an intersection approach amount Lalo that is an allowable distance from the stop line to the intersection is set, and the intersection approach amount Lalo is output to the travel control device 7 to be throttled. The opening degree and the brake control are performed.

  That is, as shown in FIG. 1, the control unit 4 includes an intersection determination unit 4a, a face direction detection unit 4b, a face direction degree setting unit 4c, a perceived degree calculation unit 4d, a perceived degree determination unit 4e, and a priority determination unit. 4f, a risk calculation unit 4g, a risk setting unit 4h, a light warning determination unit 4i, a collision warning determination unit 4j, and an intersection approach amount calculation unit 4k.

  The intersection determination unit 4a receives road information ahead from the navigation device 3 and compares the intersection position with the current position of the host vehicle to determine whether the host vehicle enters the intersection. When the vehicle enters the intersection, the determination result that the vehicle enters the intersection is output to the face direction detecting unit 4b together with the information on the intersection.

  The face direction detection unit 4b receives forward vehicle information including image data from the image recognition device 2, and the intersection determination unit 4a receives the determination result of the intersection approach of the host vehicle and information on the approaching intersection. . When it is determined that the own vehicle enters the intersection, the well-known face recognition is further performed on the image in the image data window in each vehicle (hereinafter, the vehicle to be processed is referred to as a target vehicle). For example, the face width is detected, the face part position is detected, the face center is calculated, the face direction is calculated from the ratio of the left and right, and the data of the face direction is set for the face degree. To the unit 4c. For example, as shown in FIG. 4, the face-facing direction is, for each target vehicle, a broken line connecting the host vehicle and the target vehicle having an angle of 0 degrees in the center, a clockwise angle being +, and a counterclockwise angle. Is detected as the angle of the minus sign.

  The face direction degree setting unit 4c receives the driver's face direction for each vehicle from the face direction detection unit 4b. Then, for example, referring to a preset characteristic map (see FIG. 5), the driver's face orientation direction is converted into a face orientation degree Fi (i indicates an ID number for distinguishing the target vehicle), It outputs to the to-be-recognized degree calculation part 4d.

  As shown in FIG. 5, the face orientation degree Fi is set to be smaller as the distance from the center increases. That is, when the driver of the target vehicle faces the direction of the host vehicle, the face orientation degree Fi is set high.

The face recognition degree calculation unit 4d receives the face orientation degree Fi from the face orientation degree setting unit 4c. Then, for example, the degree of recognition of the target vehicle with respect to the subject vehicle is calculated as the degree of recognition Ri of the subject vehicle, and is output to the degree-of-recognition determination unit 4e and the risk calculation unit 4g.
Ri (k) = Ri (k−1) + Fi (k) −D (≧ 0) (1)
Here, D is a preset attenuation (forgetting) coefficient, and k is a calculation counter.

  In other words, even if the driver recognizes it once, it gradually forgets that, and in consideration of this, the driver calculates the degree of recognition Ri by the above-described equation (1) including the attenuation coefficient D.

  The degree-of-recognition determination unit 4e receives the degree-of-recognition Ri from the degree-of-recognition calculation unit 4d. Then, it is determined whether the degree of recognition Ri is greater than a preset threshold value Ric, and whether there is only one target vehicle, and the determination result is output to the risk setting unit 4h. Note that the number of target vehicles is determined based on the number of times the above-described expression (1) is executed or data from the image recognition device 2 this time.

  The priority determination unit 4 f receives forward vehicle information from the image recognition device 2 and forward road information from the navigation device 3. Then, it is determined whether or not the target vehicle exists on the priority road, and the determination result is output to the risk setting unit 4h.

The risk calculation unit 4g receives the degree of recognition Ri from the degree of recognition calculation unit 4d. Then, for example, the risk Riski for the target vehicle of the host vehicle is calculated by the following equation (2) and output to the risk setting unit 4h.
Risk = 1 / Ri (2)
In the risk setting unit 4h, the vehicle information ahead from the image recognition device 2, the recognition level Ri from the recognition level calculation unit 4d, and the determination result regarding the recognition level Ri and the number of target vehicles from the recognition level determination unit 4e. The priority determination result is input from the priority determination unit 4f.

  If the recognition degree Ri is larger than the preset threshold value Ric, and the determination result of only one target vehicle is obtained, and the target vehicle is not on the priority road, the own vehicle Is corrected by multiplying the risk Riski for the target vehicle by a coefficient K1 smaller than 1. In addition, when the degree of recognition Ri is larger than a preset threshold value Ric and the determination result of only one target vehicle is obtained, and the target vehicle is not in the left front, Is corrected by multiplying the risk Riski for the target vehicle by a coefficient K2 smaller than 1. That is, when the host vehicle has a priority traveling relationship with respect to the target vehicle, the risk Riski of the host vehicle is reduced and corrected. As for the risk Riski of the own vehicle thus set, the maximum value Riskmax (maximum value of the risk of the target vehicle existing at the intersection) is calculated and output to the collision warning determination unit 4j and the intersection approach amount calculation unit 4k. On the other hand, when the degree of recognition Ri is equal to or less than a preset threshold Ric, the risk Riski of the host vehicle is output to the light alarm determination unit 4i. In addition, the risk maximum value Riskmax is calculated as described above together with the risk Riski for the target vehicle of the other host vehicle, and is output to the collision warning determination unit 4j and the intersection approach amount calculation unit 4k.

  The light alarm determination unit 4i receives the risk Risk of the host vehicle when the degree of recognition Ri is equal to or less than a preset threshold Ric from the risk setting unit 4h. Then, the risk Risk of the host vehicle is compared with a preset threshold Risklt, and if the risk Risk of the host vehicle exceeds the threshold Risklt, a signal is output to the light control device 5 to output the headlight. Light up.

  The collision warning determination unit 4j receives the maximum risk Riskmax of the host vehicle from the risk setting unit 4h. Then, the maximum risk Riskmax of the host vehicle is compared with a preset threshold Riskal. If the maximum risk Riskmax of the host vehicle is higher than the preset threshold Riskal, a signal is output to the alarm control device 6. Then, a predetermined alarm such as blinking of an LED in the instrument panel, addition of vibration to the handle is activated.

  The intersection approach amount calculation unit 4k receives the maximum risk Riskmax of the host vehicle from the risk setting unit 4h. Then, for example, referring to a map (FIG. 6) set in advance, an intersection approach amount Lalo, which is an allowable distance from the stop line to the intersection, is set according to the maximum risk value Riskmax of the host vehicle. Then, the intersection approaching amount Lalo is output to the travel control device 7 to perform throttle opening and brake control.

  As described above, in the present embodiment, the face direction detection unit 4b, the face direction degree setting unit 4c, and the perceived degree calculation unit 4d constitute a recognized degree calculation unit, and the risk calculation unit 4g constitutes a risk calculation unit. The risk setting unit 4h constitutes a risk correction setting unit, and the light warning determination unit 4i, the collision warning determination unit 4j, and the intersection approach amount calculation unit 4k constitute a control execution unit.

  Next, the driving support control program at the intersection executed by the driving support device 1 will be described with reference to the flowcharts of FIGS. First, in step (hereinafter abbreviated as “S”) 101, necessary parameters are read.

  Next, the process proceeds to S102, where it is determined whether or not the host vehicle is proceeding to the intersection. If the vehicle is not proceeding to the intersection, the program exits. If the vehicle proceeds to the intersection, the process proceeds to S103 and subsequent steps.

  In S103, the face orientation degree setting unit 4c refers to a preset characteristic map (see FIG. 5), converts the face orientation direction of the driver of the target vehicle, and sets the face orientation degree Fi.

  Next, it progresses to S104 and the to-be-recognized degree calculation part 4d calculates the to-be-recognized degree Ri of the own vehicle by the above-mentioned (1) Formula.

  Next, the process proceeds to S105, and the risk calculation unit 4g calculates the risk Risk for the target vehicle of the host vehicle according to the above-described equation (2).

  Then, in S106, the degree-of-recognition determination unit 4e determines whether the degree-of-recognition Ri is larger than a preset threshold value Ric and whether there is only one target vehicle. As a result, when the degree of recognition Ri is larger than a preset threshold value Ric and the determination result of only one target vehicle is obtained, the process proceeds to S107, and priority determination is performed by the risk setting unit 4h. The determination result in the unit 4f is referred to, and it is determined whether the target vehicle is traveling on the priority road. As a result of this determination, if the target vehicle is not traveling on the priority road, the process proceeds to S108, the risk Riski for the target vehicle of the host vehicle is corrected by multiplying by a coefficient K1 smaller than 1, and the process proceeds to S109. If the target vehicle is traveling on the priority road, the process proceeds to S109 without correction.

  In S109, the risk setting unit 4h similarly determines the position of the target vehicle, and determines whether or not the target vehicle exists in the left front. As a result of this determination, if the target vehicle does not exist on the left front, the process proceeds to S110, the risk Riski for the target vehicle of the host vehicle is corrected by multiplying by a coefficient K2 smaller than 1, and the process proceeds to S111. If the target vehicle is present on the left front, the process proceeds to S111 without correction.

  On the other hand, if it is determined in S106 that the degree of recognition Ri is equal to or less than the preset threshold value Ric or that there are a plurality of target vehicles, the process proceeds to S112, and the light warning determination unit 4i The risk Risk and the preset threshold Risklt are compared, and if the risk Riski of the host vehicle exceeds the threshold Risklt, the process proceeds to S113 and the warning light lighting signal ON is turned on to turn on the headlight. The signal is output to the light control device 5, and the process proceeds to S111.

  On the other hand, if the risk Risk of the host vehicle is less than or equal to the threshold Risklt, the process proceeds to S114, and the headlight extinction signal is output to the light control device 5 to turn off the headlight, and the process proceeds to S111.

  When the process proceeds from S109, S110, S113, and S114 to S111, it is determined whether or not the risk has been set for all the target vehicles. If set, the process proceeds to S115, and if not set, the process starts from S103. Repeat the process.

  In S115, the risk maximum value Riskmax set for the target vehicle by the risk setting unit 4h is calculated.

  Then, in S116, the collision warning determination unit 4j compares the maximum risk Riskmax of the host vehicle with the preset threshold Riskal, and the maximum risk Riskmax of the host vehicle is higher than the preset threshold Riskal. In S117, a signal is output to the alarm control device 6 to activate a predetermined alarm (collision alarm) such as blinking of an LED in the instrument panel, addition of vibration to the handle, etc., and the process proceeds to S118. When the maximum risk Riskmax of the host vehicle is equal to or less than the threshold Riskal, the process proceeds to S118 as it is.

  Proceeding to S118, the distance allowed to enter the intersection from the stop line according to the maximum risk Riskmax of the host vehicle with reference to the map (FIG. 6) preset by the intersection approach amount calculation unit 4k The intersection approaching amount Lalo is set.

  In S119, the travel control device 7 performs travel control based on the intersection approach amount Lalo, for example, throttle opening and brake control, and exits the program.

  Thus, according to the embodiment of the present invention, the face direction of the driver of the target vehicle is detected, the face direction degree Fi of the driver of the target vehicle is set according to the face direction of the driver of the target vehicle, Based on the face orientation Fi of the driver of the target vehicle, the recognition degree of the target vehicle with respect to the host vehicle is calculated as the perceived degree Ri of the host vehicle, and the risk Riski of the host vehicle is calculated based on the perceived degree Ri of the host vehicle. When the recognition degree Ri of the own vehicle is higher than a preset threshold value Ric and there is only one target vehicle, when the own vehicle is in a priority traveling relationship with respect to the target vehicle, The risk Ri of the host vehicle is reduced and corrected. In addition, when the recognition degree Ri of the own vehicle is equal to or less than the preset threshold value Ric, or when there are a plurality of target vehicles, and the risk Riski of the own vehicle is higher than the preset threshold value Risklt, a signal is sent to the light control device 5. Output and control to turn on the headlight. For this reason, the degree of recognition of the vehicle entering the intersection is accurately judged, and the information on the vehicle at the intersection is properly taken into account to ensure safety while maintaining a smooth traffic flow. It becomes possible to perform a driving assistance. Thus, for example, in a situation where drivers of multiple vehicles recognize each other, an unnecessary warning that prevents smooth driving is prevented, while in a situation where the host vehicle is not recognized by other vehicles, Since this is an alarm that prompts driving, safety can be improved. In addition, when a plurality of vehicles cross at an intersection, the attention of each driver tends to be directed to the most dangerous target vehicle and tends to be distracted with respect to other vehicles. Since the risk is judged for each vehicle and the vehicle's own vehicle is alarmed, safety is extremely high. Furthermore, alarm control is performed for each target vehicle in consideration of traffic rules. It is possible to realize a simple driving support control.

  In the present embodiment, the direction of the face of the driver of the target vehicle is obtained by performing image processing on image data from a camera mounted on the host vehicle, but the recognition result by the recognition device mounted on the target vehicle. May be received and used by inter-vehicle communication or the like. Further, data of each target vehicle at the intersection and road information (information on the position of the target vehicle, priority road, etc.) may be received and used by inter-vehicle communication or road-to-vehicle communication.

  Further, in the present embodiment, when the degree of recognition Ri is larger than a preset threshold value Ric and there is only one target vehicle, the priority relationship between the target vehicle and the host vehicle is further determined. However, depending on the specification, when the degree of recognition Ri is larger than a preset threshold value Ric, the priority relationship between the target vehicle and the host vehicle may be further determined.

  Furthermore, in the present embodiment, the priority relationship between the target vehicle and the host vehicle is determined based on whether the target vehicle exists on the priority road and whether the target vehicle exists on the left front. Only one of the determinations may be made.

  Further, in the present embodiment, the risk of the target vehicle is obtained by the above-described equation (2). However, the present invention is not limited to this. For example, the vehicle speed of the target vehicle, the distance to the target vehicle, etc. It may be a risk that takes into account.

  Furthermore, in the present embodiment, when the recognition degree Ri of the own vehicle is equal to or less than a preset threshold Ric, or when there are a plurality of target vehicles, the risk Riski of the own vehicle is higher than the preset threshold Risklt, A signal is output to the light control device 5 to control the headlights to be turned on, but in addition to this, the risk Riski of the host vehicle may be increased and corrected. Further, the risk Riski of the host vehicle may be simply increased and corrected without performing an alarm with a headlight.

  In the present embodiment, both the alarm and the variable control of the intersection approach amount are performed according to the risk Risk of the own vehicle, but only one of them may be performed.

Functional block diagram of a driving support device at an intersection mounted on a vehicle Flow chart of driving support control program at intersection Flowchart continuing from FIG. Explanatory drawing which shows an example of the own vehicle and target vehicle which approach an intersection Explanatory diagram of characteristics of driver's face orientation of the target vehicle Illustration of characteristics of intersection approach amount

Explanation of symbols

1 driving support device at intersection 2 image recognition device (vehicle information detection means)
3. Navigation device (intersection detection means)
4 control unit 4a intersection determination unit 4b face direction detection unit (perceived degree calculation means)
4c Face orientation setting unit (perceived degree calculation means)
4d recognizing degree calculation unit (recognizing degree calculating means)
4e Recognized degree determination unit 4f Priority determination unit 4g Risk calculation unit (risk calculation means)
4h Risk setting section (risk correction setting means)
4i Light warning determination unit (control execution means)
4j Collision warning determination unit (control execution means)
4k intersection approach amount calculation unit (control execution means)
5 Light control device 6 Alarm control device 7 Travel control device

Claims (6)

An intersection detection means for detecting a front intersection;
Vehicle information detecting means for detecting vehicle information ahead;
Recognizing degree calculating means for recognizing a vehicle entering the intersection as a target vehicle and calculating the degree of recognition of the target vehicle with respect to the own vehicle;
A risk calculating means for calculating the risk of the own vehicle;
If at least the degree of recognition of the host vehicle is higher than a preset threshold, and if the host vehicle is in a priority running relationship with the target vehicle, a risk correction setting unit that reduces and corrects the risk of the host vehicle;
Control execution means for executing at least one of alarm control and travel control based on the risk of the vehicle,
A vehicle driving support apparatus comprising:   The risk correction setting means has a priority traveling relationship with respect to the target vehicle when the degree of recognition of the own vehicle is higher than a preset threshold and there is only one target vehicle. The vehicle driving support apparatus according to claim 1, wherein the vehicle risk is corrected to decrease.   The risk correction setting means is configured to increase the risk of the own vehicle when the degree of recognition of the own vehicle is equal to or lower than a preset threshold value or when there are a plurality of target vehicles, and to the control execution means. 3. The vehicle driving support apparatus according to claim 2, wherein at least one of turning on a predetermined light in accordance with the risk of the host vehicle is performed.   The priority traveling relationship in the risk correction setting means is at least one of a case where the target vehicle is traveling on a priority road and a case where the target vehicle enters the intersection from the left front of the host vehicle. 4. The vehicle driving support device according to claim 1, wherein the target vehicle is determined to have a priority traveling relationship over the host vehicle. 5.   The perceived degree calculating means detects the face direction of the driver of the target vehicle, sets the face direction of the driver of the target vehicle according to the face direction of the driver of the target vehicle, and at least the target vehicle 5. The vehicle driving support apparatus according to claim 1, wherein the degree of recognition of the host vehicle is calculated based on the degree of face orientation of the driver.   The vehicle driving support device according to any one of claims 1 to 5, wherein the risk calculating means calculates the risk of the host vehicle based on at least the degree of recognition.

Images