JP2000055659A - Position-detecting device of vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent a recognition error of a traveling line such as a traffic lane dividing line with a road surface indication such as a restriction speed indication and to accurately detect a vehicle position against the traveling line. SOLUTION: A traveling line 3 at a vehicle side is photographed with a camera 2 by both of a short time exposure and a long time exposure. A temporary position XO of the traveling line 3 is detected from a picture photographed by the long time exposure. A final position X of the traveling line is determined from a picture photographed by the short time exposure making the above temporary position as a standard. A vehicle position against the traveling line 3 is measured from the final position X of the traveling line 3 thus obtained.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a vehicle position detecting device.

[0002]

2. Description of the Related Art In order to detect a position of a vehicle on a traveling road, for example, a position (lateral position) of the vehicle with respect to a lane marking displayed on a road surface indicating a traveling area, a lateral image of the vehicle is imaged by a camera. The actual lateral position of the lane marking and the vehicle, that is, the lateral distance is determined from the position of the lane marking on the image. JP 6
Japanese Patent Application Laid-Open No. 4-6115 proposes determining a yaw angle of a vehicle based on an image obtained from a camera that captures an image in a lateral direction of the vehicle. Further, Japanese Patent Application Laid-Open No. 4-299710
Japanese Patent Application Laid-Open Publication No. H11-163873 discloses that even when the lane markings are displayed intermittently, the lane markings are presumed to have continuity in effect, thereby preventing erroneous detection of the vehicle position. I have.

[0003]

By the way, in many cases, a road surface such as a speed limit display is often displayed in the vicinity of a traveling line for determining a traveling area, particularly in the vicinity of a lane marking on a road surface. Where there is such a road marking,
There is a possibility that this road surface display may be erroneously recognized as a lane marking, which may result in an erroneous measurement of the vehicle position with respect to the lane marking.

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and a first object of the present invention is to reliably prevent a situation in which a vehicle position is measured based on a road surface display other than a traveling line. The present invention provides a vehicle position detecting device. A second object of the present invention is to provide a vehicle position detecting device capable of always accurately measuring a vehicle position with respect to a traveling line while clearly distinguishing a traveling line from a road surface display.

[0005]

In order to achieve the first object, the present invention has the following solution. That is, as described in claim 1 of the claims, a camera captures an image of a travel line that determines a travel region of the vehicle, and a position of the travel line on the captured image is used to determine a vehicle relative to the travel line. In the vehicle position detection device configured to measure a position, the shutter speed of the camera is sufficiently slower than usual, so that a long-time exposed image is obtained, and an image obtained by the long-time exposure is obtained. In, the position of the traveling line is determined. In order to achieve the second object, the present invention is as follows as a first solution. That is, as described in claim 2 of the claims, the imaging unit captures an image of the travel line that determines the travel area of the vehicle, and the position of the travel line on the captured image is relative to the travel line. In a vehicle position detecting device that measures a vehicle position,
First imaging means for obtaining a long-time exposed image with a reduced shutter speed, and second imaging means for obtaining a short-time exposed image with a shutter speed sufficiently faster than the first imaging means And on the long exposure image,
First position determining means for temporarily determining the position of the traveling line; and second position determining means for determining the position of the traveling line on the short-time exposure image based on the temporary position determined by the first position determining means. And a vehicle position measuring means for measuring a vehicle position based on the position of the traveling line on the short-time exposure image determined by the second position determining means. Preferred embodiments based on the above solution are as described in claims 3 to 8 in the claims.

In order to achieve the second object, the present invention is as follows as a second solution. That is, as described in claim 9 in the claims,
In a vehicle position detection device configured to image a traveling line that determines a traveling region of a vehicle by an imaging unit and measure a vehicle position relative to the traveling line from a position of the traveling line on the captured image, a shutter is provided. A first imaging means for obtaining a long-exposure image with a reduced speed; and a second imaging means for obtaining a short-exposure image with a shutter speed sufficiently faster than the first imaging means. A first position determining means for temporarily determining the position of the traveling line on the long-time exposure image; and a weighting coefficient which is a ratio between the density value at the temporary determination position and the maximum value of the density on the long-time exposure image. Estimating means for estimating a deviation from a true travel line position based on the density gradient at the tentatively determined position, and the tentatively determined position and the estimated Second position determining means for determining the position of the traveling line from the deviation, and vehicle position measuring means for measuring the vehicle position based on the position of the traveling line on the short-time exposure image determined by the second position determining means And that there is.

[0007] In the long-time exposure image, the traveling line and the road surface display can be clearly distinguished. However, in the long-time exposure image, the running line is blurred, so that in the long-time exposure image, only the temporary position of the running line is determined. In the short-time exposure image, while the image of the traveling line or the like is not blurred, the distinction between the traveling line and the road surface display is difficult. Then, in the short-time exposure image, the traveling line is identified as a road surface display based on the temporary position (determination of the final traveling line position), and based on the identified traveling line on the short-time exposure image. The vehicle position is accurately measured.

[0008]

According to the first aspect of the present invention, the traveling line is reliably identified as a road surface display or the like, and a situation in which the road surface display is erroneously recognized as the traveling line is prevented, and the vehicle position can be largely measured. An error can be prevented from occurring.

According to the second aspect, in addition to the effect corresponding to the first aspect, it is possible to accurately determine the position of the traveling line on the short-time exposure image and always accurately measure the vehicle position with respect to the traveling line. it can.

According to the third aspect, it is preferable to measure the position of the vehicle in the lateral direction with respect to the traveling line in the lateral direction of the vehicle. According to the fourth aspect, the vehicle position can be accurately determined with respect to the lane marking, which is general as a traveling line and the road surface is often displayed nearby.

According to the fifth aspect, it is possible to obtain an optimum shutter speed for long-time exposure so that the traveling line and the road surface display can be clearly distinguished according to the road surface brightness. According to the sixth aspect, an optimal shutter speed for short-time exposure according to the vehicle speed can be obtained.

According to the seventh aspect, a long exposure image and a short exposure image can be obtained by effectively using one camera. According to the eighth aspect, a long-time exposure image and a short-time exposure image can be obtained in one image frame.

According to the ninth aspect, the effect corresponding to the second aspect can be obtained, and the true traveling line position on the short-time exposure image is determined extremely accurately, and finally the vehicle with respect to the traveling line is determined. The position can be measured very accurately.

[0014]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS First, the overall lateral position determination of a vehicle to which the present invention is applied will be described with reference to FIGS. 1 to 14, and thereafter, a long exposure image and a short exposure image will be described. FIG. 1 shows the detection (measurement) of the vehicle position based on
Description will be made with reference to 5 and below.

Description of FIGS. 1 to 7 In FIG. 1, a camera (video camera in the embodiment) 2 as a position detecting sensor is installed on the side of an automobile 1 as a vehicle. The camera 2 captures an image of a road surface condition in a lateral direction and a downward direction. More specifically, the camera 2 captures an image of a lane marking 3 (shown as a white line in the drawing) in the lateral direction of the automobile 1. FIG. 1 shows a case where the camera 2 is provided only on the left side of the car 1, but the camera 2 is also provided on the right side (for right side imaging). . From the image captured by the camera 2 (the image of the lane marking), the lateral distance (relative distance) Y between the car 1 and the captured lane marking 3 is determined as described below.

FIG. 2 is a block diagram showing a control system for determining the distance between the automobile 1 and the lane marking 3 and performing a predetermined safety control based on the determined distance. In FIG. 2, U is a control unit (controller) configured using a microcomputer, and the control unit U has a lateral position determination unit 4 and a lane departure determination unit 5. The lateral position determining unit 4 basically determines the car 1 and the lane marking 3 from the lane markings captured by the camera 2.
To determine the lateral distance between In addition, the horizontal position determination unit 4
As will be described later, the traveling locus of the automobile 1 is determined based on the vehicle speed, the yaw rate, and the road shape (the radius of curvature of the road) obtained from the sensors Z1 to Z3 as the detecting means. Based on this, the horizontal position obtained by using the camera 2 is corrected. Note that the sensor Z3 for detecting the road shape receives the road shape information transmitted from outside the vehicle, and the sources of the road shape information include navigation (artificial satellites) and magnetic information embedded in the road. There are nails, transmitting antennas installed on the side of the road, and the like.

The lane departure judging unit 5 determines whether the car 1 is in the lane marking based on the current running conditions based on the lateral position determined by the lateral position determining unit 4 (y after correcting the lateral distance Y). 3 is determined. When the lane departure determining unit 5 determines that the possibility of the lane departure is high, the alarm device 6 such as a buzzer is activated, and when the possibility of the lane departure is extremely high, the brake 7 is automatically activated. The vehicle 1 is decelerated. The above-mentioned components 5 to 7 are described for the purpose of illustrating how to use the lateral distance between the automobile 1 and the lane marking 3. The method is not limited to this.

Next, a case will be described in which the running locus of the vehicle 1 is theoretically obtained based on the vehicle speed and the yaw rate road shape (curvature radius). Now, the lateral deviation of the vehicle 1 in the direction orthogonal to the lane marking 3 is y (t), and the yaw angle is θ.
(T), when the sampling interval is Δt, the lateral deviation y
(T) is given by equation (1), and yaw angle θ (t) is given by equation (2)
As shown in (1), it is represented by a recurrence formula using a yaw rate r (t), a vehicle speed v (t), and a road curvature radius R (t) (t is time). Note that the initial value y0 of the lateral deviation is y (t0),
The initial value of the yaw angle θ0 is θ (t0).

[0019]

(Equation 1)

The time T1 is calculated using the relations of the above equations 1 and 2.
History S1 of the lateral deviation during a predetermined time DT from T2 to T2
Is calculated, for example, as shown in FIG. On the other hand, the history S2 of the lateral deviation measured from the image of the camera 2 is shown in FIG.
It becomes as shown in. Note that S in FIGS. 3 and 4 is the true lateral deviation history of the automobile 1. The history S1 often does not match the true history S due to the initial value error of the recurrence formula and the accumulated error of the sensor signal. The history S2 is
Due to the measurement error due to the vibration of the camera 2 or the stain or blur of the lane marking 3, the actual history S often does not match.

A true lateral deviation history S is estimated by matching the two histories S1 and S2. By this matching, the initial value error, the accumulated error, and the measurement error (variation) are removed, so that highly accurate and highly reliable lateral deviation measurement can be performed. As the matching method, for example, the initial values y0 and θ0 that minimize the error between the histories S1 and S2 are obtained by the least square method, and the horizontal values calculated from the obtained initial values y0 and θ0 and Expressions 1 and 2 are used. The deviation is determined (estimated) as the current lateral deviation y. The lateral deviation y determined in this way is used for determination in the lane departure unit 5 in FIG.

When the time width DT to be subjected to the matching process becomes longer, the accumulated error included in S1 becomes larger. In order to prevent the accumulated error from becoming too large, the relationship between the accumulated error expected value calculated from the sensor specifications and DT is obtained in advance as shown in FIG. The width can be used as DT. Note that the threshold value A can be determined by, for example, setting the threshold value to a fraction of the maximum error value of the measurement by the video camera 2.

Immediately after the start of traveling, since there is no history data, the matching process is not performed, and the measurement result by the camera 2 may be determined as the final lateral deviation (lateral position). When the error between S1 and S2 becomes too large, for example, when the minimum value of the error between S1 and S2 exceeds a predetermined threshold, camera 2 or sensor Z1
In this case, position determination can be stopped and a fail signal indicating a system abnormality can be output.

The above-described control will be described with reference to the flowchart of FIG. 7. This flowchart corresponds to the control of the horizontal position determining unit 4 of FIG. In the following description, Q indicates a step. First, in Q1, after the history measurement time DT is set, in Q2, the camera 2
The image of the lane marking 3 picked up by is input. Next, in Q3, the lateral deviation Y with respect to the lane marking is detected (measured) on the image.

In Q4, it is determined whether or not a time equal to or longer than DT has elapsed after the start of traveling. YES in this Q4 discrimination
At Q5, the signals from the sensors Z1 to Z3, that is, the vehicle speed v, the yaw rate r, and the road curvature radius R
Is read. In Q6, the history (S1) of the lateral deviation y 'is calculated from the vehicle speed v, the yaw rate r, and the radius of curvature R of the road using Expressions 1 and 2. In Q7, initial values y0 and θ0 are determined by matching the two histories y 'and Y. In Q8, it is determined whether or not the matching error is larger than a predetermined threshold. If the determination in Q8 is NO, in Q9, the initial values y0, θ
The current lateral deviation y is calculated from Equations 1 and 2 using 0. Thereafter, in Q10, the lateral deviation y is output to the lane departure determination unit 5.

If the determination in Q4 is NO, in Q11, the lateral deviation Y determined by using the camera 2 is set as the final lateral deviation y as it is, and the process proceeds to Q10. If the determination in Q8 is YES, the process of determining the horizontal position is interrupted (stopped) in Q12,
Alarms such as lamps and buzzers are activated.

As can be understood from the above description, in FIG. 2, the lateral position determining unit 4 comprises the position determining means, the traveling trajectory determining means, and the correcting means in claim 1 of the present invention. I do. In FIG. 7, Q3 serves as position determining means, Q6 serves as travel path determining means,
7, Q9 is the correction means.

Description of FIGS. 8 to 10 FIGS. 8 to 10 show a method for accurately detecting the lateral position by compensating the roll angle fluctuation of the vehicle body (Q3 in FIG. 7). The lateral distance Y itself is determined with high accuracy). First, in FIG. 8, the lane marking is composed of two lines having a predetermined small interval, and the predetermined interval D is known (D is a true value). Also, car 1
Is rolled by θ toward the lane marking 3. In the state of FIG. 8, the edges of the two lane markings 3 captured by the camera 2 are shown as in FIG. In this case, the actual lateral position of the vehicle 1 with respect to the near lane marking 3 is a1 and the actual lateral position with respect to the far lane marking 3 is a2,
1 is erroneously measured as b1 and a2 as b2.

FIG. 9 is a geometrical representation of FIG.
The height position h of the camera 2 is assumed to be constant regardless of the roll fluctuation. In the geometrical relationship shown in FIG. 9, the following expressions 3 to 6 hold. Since the interval D between the two lane markings 3 is known as a true value, the following Expression 5 is established from Expressions 3 and 4. From Equations 1, 2, and 5, θ, φ
The roll angle θ is obtained by obtaining 1, φ2 by numerical calculation or the like. By using the obtained roll angles θ and φ1, the true lateral deviation a1 is obtained by the following equation 8.

[0030]

(Equation 2)

The interval D as a true value is not limited to the interval between the two lane markings 3 located on one side in the lateral direction of the vehicle 1, and
The distance between the edges of the one lane marking 3 on the side closer to and farther from the car 1 may be the distance between the two lane markings 3 located on the left and right sides of the car 1 with the car 1 interposed therebetween. May be. It should be noted that the calculations by the above equations 2 to 8 (calculation contents in the lateral position determination unit 4 in FIG. 2) indicate the contents of the roll angle determination means and the correction means in claim 8 in the claims. Become.

Description of FIGS. 11 to 14 FIGS. 11 to 14 show a method for accurately detecting the lateral position by compensating the yaw angle fluctuation of the vehicle body (Q3 in FIG. 7). The lateral distance Y itself is determined with high accuracy). First, in FIG. 11, when the center line of the vehicle 1 in the vehicle longitudinal direction is inclined by θ with respect to the lane marking 3 (the yaw angle is θ), the actual lateral position is Y,
The horizontal position obtained based on the image obtained by the camera 2 will measure Y ′ different from Y. The image obtained by the camera 2 is as shown in FIG. 12, but the actual horizontal position Y is the closest distance to the reference point on the screen. As shown in FIG. 12, by making a perpendicular from the reference point on the image (the reference position of the camera 2) to the lane marking 3 on the image, the distance on this perpendicular becomes the minimum distance Y (minimum distance One method of determination).

Further, as shown in FIG. 13, when all the distances from the reference point to the lane marking 3 on the image are measured (change of the scanning angle φ), as shown in FIG. Thus, the minimum distance on FIG. 14 becomes the actual distance Y (another method for determining the minimum distance). Further, the lane marking 3 on the XY-axis plane on the image in FIG. 12 may be determined as a linear function, and the minimum distance Y may be determined from the determined linear function ((min. Yet another method of distance determination).

Description of FIGS. 15 to 18 FIGS. 15 to 18 show lane markings 3 and road surface indications such as speed limit indications displayed on the road surface in the vicinity of the lane markings 3, and the lane markings 3 to 3 are shown. 1 shows a method for accurately measuring the horizontal distance of the object. Therefore, basically, two cameras 2 that image the same position are used (there are two cameras 2 in FIG. 1). One of the cameras performs exposure for a long time according to the brightness of the road surface. As shown in FIG. 25, as the road surface is brighter, the shutter speed is reduced (slower than the normal shutter speed). The other camera performs short-time exposure according to the vehicle speed. As shown in FIG. 18, as the vehicle speed increases, the shutter speed decreases.

The image obtained by the long exposure is shown in FIG.
As shown in (1), it is easy to set the threshold value T for binarization for identifying lane markings that are not affected by the road surface display.
Then, the edge position of the lane marking after binarization by the threshold value T is determined as the provisional position x0. However, the tentative position x0 is based on the lane marking with the edge part blurred due to long exposure, and the tentative position x0
It is difficult for 0 to accurately indicate the lateral distance. on the other hand,
Although the image obtained by the short-time exposure clearly shows an edge portion such as a lane marking, the lane marking is hardly distinguished from the road surface display as shown in FIG. Therefore, on the image obtained by the short-time exposure, after the binarization, a position x closest to the temporary position x0 obtained by the long-time exposure is selected, and the selected position x is set to the final horizontal position. The position indicates the directional distance.

Description of FIGS. 19 and 20 FIGS. 10 and 20 show that two images of short exposure and long exposure are used to compensate for partial loss of the lane marking 3 due to blurring or dirt. An example in which the lateral distance is accurately measured will be described. First, in FIG. 19, the position of the edge portion (blurred) of the lane marking 3 is determined as the temporary position x0 from the image obtained by the long-time exposure. FIG.
Shows an image of a lane marking obtained by short-time exposure, but is partially missing due to blurring or the like. Therefore, on an image obtained by short-time exposure, FIG.
A plurality of detection lines are set as shown in FIG. 3, and a position x closest to the position x0 on the plurality of detection lines is set.
Is determined as the position for the final lateral distance.

Description of FIGS. 21 to 23 FIGS. 21 to 23 show modifications of the examples of FIGS. FIG. 22 corresponds to FIG. 20 and is an image obtained by short-time exposure. The image obtained by the long-time exposure is the same as that in FIG. In FIG. 21, the density value at the temporary position x0 in the long-time exposure image is indicated as v1, the maximum value of the density is indicated as v2, and v1 / v2 is set as the weight coefficient W. Further, the gradient of the density at the tentative position x0 is set as R.

By using the weighting coefficient W and the slope R, it is possible to accurately estimate how far (the edge portion of) the true lane marking is apart from the position x0. That is, in the example of FIG. 20, the position x closest to x0 is finally selected, but as shown by xt in FIG. 22, a position close to the true lane marking can be finally determined. According to this example, W
It is also possible to narrow the search range based on R and R,
This is preferable in terms of speeding up the processing.

FIG. 23 is a flowchart showing a specific method for finally selecting the position xt using the weight coefficient W and the inclination R. In Q31 of FIG. 23, a threshold value T for binarizing a long-time exposure image is set. In Q32, the position x0 is determined from the state after binarization using the threshold value T. In Q33, the density v1 at the position x0 is obtained. In Q34, the maximum value v2 of the density and its position x0 'are obtained.

In Q35, a weight coefficient W which is a ratio between v1 and v2 is calculated. In Q36, the gradient R of the density at the position x0 is calculated. In Q37, W and R are multiplied. W and R for each of the detection lines on the image
Is obtained, the position xt on the detection line that maximizes the multiplied value is finally selected in Q38.

Description of FIG. 24 FIG. 24 shows an example for obtaining a long-time exposure image and a short-time image with one camera. First, a CCD camera is used as the camera 2. Reference numeral 11 denotes a camera driving circuit, which includes a shutter speed switching unit 12, two timing ICs, a shutter control unit 15, and an image reading unit 16. The timing IC 13 is for an even field (or an odd field) of an image, and sets a shutter speed for long-time exposure (for example, 1/100 second). The timing IC 14 is for an odd field (or for an even field) of an image and sets a shutter speed for short-time exposure (for example, 1/300).
Seconds). The control unit 15 controls so as to alternately release the shutter at a predetermined speed (for example, 1/60 second) at the set speed of the timing ICs 13 and 14. The shutter speed is switched in synchronization with the image reading (for example, every 1/60 second) in the image reading unit 16, whereby a long-time exposure image is obtained in an even field and a short-time exposure image is obtained in an odd field. An image is obtained. In addition, since the switching can be performed every frame (1/30 second in the embodiment), the time resolution is reduced to １ ／, but the resolution is not reduced and two shutters having different shutter times of 1/15 second are used. It is possible to obtain an image.

Description of FIGS. 25 to 27 FIGS. 25 to 27 show two vehicles 2 separated in the front-rear direction of the automobile 1.
The yaw angle θ is detected by the correlation processing of the images obtained from the cameras 2A and 2B, and the processing speed is improved. First, in FIG.
An interval between the two cameras 2A and 2B is indicated by a symbol W. FIG. 26 shows an image obtained by the front camera 2A.
The image obtained in B is shown in FIG. 27, and the broken line in FIG. 27 corresponds to the position of the lane marking in the previous image.

The shift amount in the horizontal direction (y direction) of the image is calculated by a correlation process. That is, the calculation shown in the following Expression 9 is performed on the entire image (i = −y... Y). Then, i, which is the minimum value of the obtained F (i), is the shift amount (corresponding to the deviation between the front camera position and the rear camera position with respect to the lane marking 3). Therefore, the yaw angle θ is obtained by the following equation (10).

[0044]

(Equation 3)

Description of FIGS. 28 and 29 FIGS. 28 and 29 show the case where two cameras are used to increase the detection range and ensure sufficient recognition of lane markings. . That is, as shown in FIG. 28, the field of view of one camera is set to a close position (field of view 1),
The field of view of the other camera is set to a distant position (set so as to be continuous with field 1 in field 2). If it is attempted to detect up to the range of the visual field 2 using only one of the cameras that is the visual field 1, the distance resolution is deteriorated as shown by the broken line in FIG.
By sharing the field of view 2 in which the distance resolution is poor with only one camera with the other camera,
It is possible to image a wide detection range between the visual field 1 and the visual field 2 without deteriorating the distance resolution.

Description of FIGS. 30 and 31 FIGS. 30 and 31 show examples in which two cameras are used so that lane markings can be clearly identified regardless of the road surface reflection state. In this example, both cameras capture images through the respective deflection filters. However, the deflection direction of the deflection filter between the two cameras is set to be different from each other (one for vertical deflection and the other for horizontal deflection). In such a case, for example, in the density distribution of the image obtained by one camera, even when the noise due to road surface reflection is large as shown in FIG. 31, the density distribution of the image obtained by the other camera is as shown in FIG. As shown in FIG. The lane marking can be clearly identified (recognized) using the image of the density distribution with less noise.

Although the embodiment has been described above, in order to prevent the road surface display from being erroneously recognized as a lane marking,
You can also do the following: That is, as described with reference to FIGS. 3 to 7, the current horizontal position is narrowed down to a predetermined range from the theoretical traveling locus and the previous horizontal position (lane lane marking position) detected by the camera. (Prediction) It is possible to reliably exclude the road surface display outside the narrowed range and to recognize the lane marking more accurately.

Various members such as each step or sensor shown in the flowchart can be expressed by adding a name of a means to a higher-level expression of its function. In addition, the object of the present invention is not limited to what is explicitly specified, but also implicitly includes providing what is expressed as substantially preferable or advantageous. Further, the present invention can be expressed as a position detection method.

[Brief description of the drawings]

FIG. 1 is a plan view showing a camera mounted on an automobile and lane markings.

FIG. 2 is a control system diagram for determining a lateral position.

FIG. 3 is a diagram showing an example of a traveling trajectory obtained theoretically.

FIG. 4 is a diagram showing an example of a horizontal position obtained from a camera image.

FIG. 5 is a diagram showing matching between the traveling locus of FIG. 3 and the history of the lateral position of FIG. 4;

FIG. 6 is a diagram for explaining an example of setting a time for calculating a traveling locus.

FIG. 7 is a flowchart for determining a final lateral position based on a traveling locus and a lateral position obtained from a camera image.

FIG. 8 is an explanatory diagram for determining a lateral position in consideration of roll angle fluctuation.

FIG. 9 is a diagram showing two lane markings on an image.

FIG. 10 is a view geometrically showing FIG. 8;

FIG. 11 is an explanatory diagram for determining a lateral position in consideration of yaw angle fluctuation.

FIG. 12 is a diagram showing an example of determining a horizontal position from an image obtained when there is a yaw angle.

FIG. 13 is an explanatory diagram showing another example of determining a horizontal position from an image obtained when there is a yaw angle.

FIG. 14 is an explanatory diagram when the horizontal position is finally determined in the example of FIG. 13;

FIG. 15 is a diagram showing an image and density during long-time exposure.

FIG. 16 is a diagram illustrating an image and a density during short-time exposure.

FIG. 17 is a diagram illustrating an example of setting a shutter speed during long-time exposure.

FIG. 18 is a diagram showing an example of setting a shutter speed during short-time exposure.

FIG. 19 is a diagram showing an example of a long-time exposure image.

FIG. 20 is a partially enlarged view of FIG. 19;

FIG. 21 is a diagram showing a density distribution in a long-time exposure image.

FIG. 22 is a partially enlarged view of a short-time exposure image.

FIG. 23 is a flowchart used to accurately determine a horizontal position using the density distribution of FIG. 21;

FIG. 24 is a diagram showing a configuration example for obtaining a long exposure image and a short exposure image with one camera.

FIG. 25 is an explanatory diagram for determining a yaw angle using two cameras.

FIG. 26 is a diagram showing an image obtained from the front camera of FIG. 25.

FIG. 27 is a diagram showing an image obtained from the rear camera of FIG. 25.

FIG. 28 is a diagram showing an example of a case where the fields of view between two cameras are different.

FIG. 29 is a view showing a distance resolution of each camera in the setting example of FIG. 28;

FIG. 30 is a diagram showing an example in which imaging is performed using a deflection filter.

FIG. 31 is a diagram illustrating an example in which imaging is performed using a deflection filter whose deflection direction is different from that in FIG. 30;

[Explanation of symbols]

 1: automobile 2: camera 2A: camera 2B: camera 3: lane marking 4: lateral position determination unit Z1: vehicle speed sensor Z2: yaw rate sensor Z3: road shape detection sensor

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI theme coat ゛ (Reference) H04N 7/18 H04N 7/18 J F term (Reference) 2F065 AA02 AA06 CC11 DD11 FF04 FF65 JJ03 JJ05 JJ07 JJ26 LL21 MM22 QQ38 UU05 2F112 AD03 BA20 CA05 DA19 FA38 FA45 5C054 CE11 CH00 FC15 HA30 5H301 AA03 CC03 DD07 EE07 GG01 HH01

Claims (9)

[Claims] 1. A vehicle position detection system in which a camera captures an image of a travel line that determines a travel area of a vehicle, and measures a vehicle position relative to the travel line from a position of the travel line on the captured image. In the apparatus, the shutter speed of the camera is made sufficiently slower than usual to obtain a long-exposure image, and a position of a traveling line is determined on the image obtained by the long exposure. A position detecting device for a vehicle. 2. A vehicle position in which a traveling line for determining a traveling area of a vehicle is imaged by an imaging means, and a vehicle position relative to the traveling line is measured from a position of the traveling line on the captured image. A first imaging unit configured to obtain a long-time exposed image with a reduced shutter speed; and a first exposure unit configured to obtain a short-time exposed image with a shutter speed sufficiently higher than the first imaging unit. A second imaging unit; a first position determining unit for temporarily determining a position of the traveling line on the long exposure image; and a first position determining unit for determining the position of the traveling line on the short exposure image. Second position determining means for determining the temporary position as a reference, and a vehicle position based on the position of the traveling line on the short-time exposure image determined by the second position determining means. Position detecting apparatus for a vehicle, characterized in that it and a vehicle position measuring unit for measuring. 3. The vehicle position detecting device according to claim 2, wherein each of said image pickup means is set so as to take an image in a lateral direction of the vehicle. 4. The vehicle position detecting device according to claim 3, wherein the traveling line is a traveling dividing line displayed on a road surface. 5. The vehicle position detecting device according to claim 2, wherein a shutter speed of the first image pickup means is changed so as to be slower as the road surface is brighter. 6. The vehicle position detecting device according to claim 2, wherein the shutter speed of the second imaging means is changed so as to decrease as the vehicle speed increases. 7. The apparatus according to claim 2, further comprising one camera, wherein the first imaging means and the second imaging means alternately switch the shutter speed of the one camera between a fast state and a slow state to capture an image. A position detection device for a vehicle, characterized in that the position detection device is configured as a vehicle. 8. The vehicle position detecting device according to claim 7, wherein the two kinds of images having different shutter speeds are picked up in an odd field and an even field in one image frame. . 9. A vehicle position in which a traveling line for determining a traveling area of a vehicle is imaged by an imaging means, and a vehicle position relative to the traveling line is measured from a position of the traveling line on the captured image. A first imaging unit configured to obtain a long-time exposed image with a reduced shutter speed; and a first exposure unit configured to obtain a short-time exposed image with a shutter speed sufficiently higher than the first imaging unit. A second imaging unit; a first position determining unit for temporarily determining a position of the traveling line on the long-time exposure image; and a density value at the temporary determination position and a maximum value of the density on the long-time exposure image. Estimating means for estimating a deviation from a true travel line position based on a weighting coefficient serving as a ratio and a gradient of density at the tentatively determined position; Second position determining means for determining the position of the traveling line from the estimated displacement and measuring the vehicle position based on the position of the traveling line on the short-time exposure image determined by the second position determining means And a vehicle position measuring means.