JP3014233B2 - Approaching object detection device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an approaching object detecting device which is mounted on, for example, an automobile and is used for monitoring the surroundings of the vehicle. The present invention relates to an approaching object detection device suitable for preventing an accident.

[0002]

2. Description of the Related Art Generally, when another vehicle approaches a vehicle traveling on a road from behind, it is difficult for a driver of the vehicle in front to notice the accident, which is likely to cause an unexpected large accident. In particular, when a running vehicle changes lanes, if there is a following vehicle approaching the changed lane, a collision may occur depending on the relative speed with the host vehicle. Therefore, in recent years, various devices have been proposed that notify a driver of the approach of a rear vehicle.

For example, as an approaching object detecting device for detecting a following approaching vehicle to a traveling vehicle, a device for measuring an approaching speed by a Doppler radar using an ultrasonic wave or a radio wave, a vehicle in a specific area using a radar. An apparatus for determining
Alternatively, there is an apparatus in which a marker is added to an image displayed using an imaging unit such as a video camera so that the position of a vehicle behind can be confirmed.

FIG. 10 is a block diagram showing a conventional approaching object detection device described in, for example, JP-A-1-321600, which shows an example of a Doppler radar using ultrasonic waves. In the figure, X is a Doppler radar that is provided at the rear of the vehicle and has a function of transmitting and receiving ultrasonic waves, Y is an approach detection device that detects approach of a vehicle behind based on a voltage signal from the Doppler radar X, and Z is an approach. The display device is driven by an output signal from the detection device Y.

The Doppler radar X includes a crystal oscillator 1 for generating an oscillation signal, a frequency divider 2 for dividing the oscillation signal, a transmission amplifier 3 for generating a transmission signal based on the divided signal,
A transmitting piezoelectric vibrator 4 that is driven by a transmission signal to transmit ultrasonic waves, an ultrasonic transmitting unit 4a of the transmitting piezoelectric vibrator 4,
A receiving piezoelectric vibrator 5 for receiving reflected ultrasonic waves from a vehicle behind, an ultrasonic receiving unit 5a of the receiving piezoelectric vibrator 5, and a receiving amplifier for amplifying a reception signal from the receiving piezoelectric vibrator 5. 6
And a frequency conversion circuit 7 for converting the frequency of the received signal based on the frequency-divided signal, and a frequency-voltage conversion circuit 8 for converting the converted frequency into a voltage signal.

The approach detection device Y includes a voltage comparison circuit 9 for comparing a voltage signal from the Doppler radar X with a predetermined voltage,
An output circuit 10 for generating a drive signal for the display device Z based on the comparison result. The display device Z includes, for example, an LED array 11 as illustrated.

FIG. 11 is an explanatory view schematically showing a plurality of running vehicles, wherein A is a vehicle running ahead, B is a vehicle running backward, Va is a running speed of the preceding vehicle A, and Vb is a backward speed. The traveling speed of the vehicle B, fo, is the frequency of the ultrasonic wave transmitted from the vehicle A ahead.

Next, the operation of the conventional approaching object detecting device shown in FIG. 10 will be described with reference to FIG. When the wave transmitting piezoelectric vibrator 4 is driven by the transmission amplifier 3 in the Doppler radar X and the ultrasonic wave of the frequency fo is transmitted from the front vehicle A to the rear vehicle B, the ultrasonic wave reflected by the rear vehicle B becomes: The received wave is received by the piezoelectric vibrator 5.

At this time, a Doppler shift occurs in proportion to the approach speed of the two vehicles A and B, that is, the relative speed ΔV (= Vb−Va). The Doppler shift is extracted by the frequency conversion circuit 7 as a beat between the reception signal and the transmission signal via the reception amplifier 6, and the beat frequency is converted into a voltage signal by the frequency / voltage conversion circuit 8 and output. .

A voltage signal indicating the approach speed of the rear vehicle B to the front vehicle A is compared with a reference voltage by a voltage comparison circuit 9 in the approach detection device Y, and is displayed on the display device Z as a signal indicating the speed.

FIG. 12 is an explanatory view showing a conventional approaching object detecting device described in, for example, Japanese Patent Publication No. 62-29265, showing an example using a radar antenna. In this case, a radar antenna X 'is provided at the side mirror position of the forward vehicle A, a signal received by the radar antenna X' is displayed on a display device (not shown) in the vehicle A, and the presence or absence and the distance of the backward vehicle B are displayed. Is detected.

However, the Doppler radar X shown in FIG.
In addition, since the radar antenna X 'shown in FIG. 12 emits ultrasonic waves and radio waves, it may interfere with ultrasonic waves and radio waves from other vehicles having the same function, making analysis difficult. Further, when there are a plurality of objects, it is difficult to clearly detect which object the reflected signal cannot be determined from.

FIG. 13 is an explanatory view showing a display screen of a conventional approaching object detection device described in, for example, Japanese Patent Publication No. 3-47213, showing an example using a video camera.
In this case, an image a captured by a video camera provided at the rear of the vehicle is displayed on a display device in the vehicle.
At this time, as shown in the drawing, if a marker b indicating the inter-vehicle distance is added in the screen, the approximate distance to the rear vehicle B and the approaching state can be recognized. However, when the image a is displayed in this manner, the driver must always watch the image a irrespective of driving.

[0014]

As described above, the conventional approaching object detection device uses the Doppler radar X (FIG. 10) or the radar antenna X '(FIG. 12) to detect the distance and relative speed with the vehicle B behind. Is detected, or the position of the rear vehicle B is recognized using the image a (FIG. 13) from the video camera and the marker b.

However, when the Doppler radar X or the radar antenna X 'is used, the direction and position of the rear vehicle B cannot be detected, and interference between signals occurs. However, there is a problem that the rear vehicle B cannot be specified and detected.

When the image a from the video camera is used, the apparatus itself does not have a determination function and only displays the image a. Judgment must be made empirically. Accordingly, there is a problem that the presence or absence of danger cannot be reliably determined, and that the driver may not be able to concentrate on driving the own vehicle and may be in danger.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and an object of the present invention is to provide an approaching object detecting device capable of automatically and reliably determining an approaching object.

[0018]

According to a first aspect of the present invention, there is provided an approaching object detection apparatus, comprising: an imaging unit configured to capture an image;
A window processing unit that divides an image into a plurality of window regions, a representative value extraction unit that extracts a feature amount of each window region as a representative value, and a pattern creation unit that creates a pattern corresponding to the image using each representative value as a data string A shift amount calculation unit that calculates a shift amount by comparing each pattern of images at different imaging timings, and a determination unit that generates a determination signal when the shift amount is equal to or greater than a predetermined value indicating the presence of an approaching object. It is provided with.

According to a second aspect of the present invention, there is provided an approaching object detecting apparatus according to the first aspect, wherein the imaging means is installed in the vehicle to photograph a rear image of the vehicle.

According to a third aspect of the present invention, there is provided an approaching object detection apparatus according to the second aspect, wherein the controller generates an alarm drive signal in response to the determination signal, and the alarm means is driven by the alarm drive signal. Is provided.

According to a fourth aspect of the present invention, there is provided an approaching object detecting device according to the third aspect, further comprising switch means which is operated when the traveling direction of the vehicle is changed, and wherein the imaging means corresponds to the traveling direction of the vehicle. A plurality of rear images are imaged, the determination unit generates a determination signal for each rear image, and the controller responds to an operation signal from the switch means to generate an alarm when a determination signal for the changed traveling direction is detected. A drive signal is generated.

According to a fifth aspect of the present invention, there is provided an approaching object detecting apparatus according to any one of the second to fourth aspects.
The vehicle further includes a turning detection unit that detects a turning state of the vehicle, and the window processing unit changes a set position of the window area in response to a turning signal from the turning detection unit.

According to a sixth aspect of the present invention, there is provided an approaching object detecting apparatus according to any one of the first to fifth aspects.
A window area is set along a ray from a gazing point at infinity, and the pattern is a one-dimensional data sequence.

According to a seventh aspect of the present invention, there is provided an approaching object detecting apparatus according to any one of the first to fifth aspects.
A window area is set along a ray from a gazing point at infinity and along a direction perpendicular to the ray, and the pattern is formed of a two-dimensional data string.

[0025]

According to the first aspect of the present invention, a representative value pattern is created based on the feature amount of each window area formed in an image, and the representative value pattern is compared in a time series to calculate the approaching time. Is automatically and reliably determined.

According to a second aspect of the present invention, a rear object approaching a vehicle is automatically and reliably determined.

According to the third aspect of the present invention, the warning means is driven when the rear approaching object is determined, to alert the driver to ensure safety.

According to a fourth aspect of the present invention, when it is determined that there is a rearward object approaching on the changed travel path before the travel direction is changed, the warning means is driven to pay attention to the driver. Encourage safety.

According to a fifth aspect of the present invention, the window area is optimally updated and set in response to the turning direction of the vehicle, and the rear object approaching on the running path after the turning is reliably determined.

According to a sixth aspect of the present invention, a window area is set along a ray from infinity, and an approaching object is determined based on a one-dimensional pattern.

According to a seventh aspect of the present invention, a window area is set along the radiation from infinity and along the direction perpendicular to the radiation, and the approaching object can be trusted based on a two-dimensional pattern. Judge well.

[0032]

【Example】

Embodiment 1 FIG. Hereinafter, a first embodiment (corresponding to claims 1, 2 and 6) of the present invention will be described with reference to the drawings. FIG.
FIG. 1 is a block diagram showing a functional configuration of a first embodiment of the present invention. Reference numeral 20 denotes an approaching object detecting means including the following 21 to 29.

Reference numeral 21 denotes an image pickup means or camera, which is installed at a door mirror section on both sides of the vehicle and takes images G of the rear and side, 22 denotes an image processing section which processes the image G as data,
Reference numeral 23 denotes a display device for displaying the image G subjected to data processing, and 24 denotes a plurality of (n) window areas by further processing the image G.
A window processing unit that divides the feature values into W1 to Wn; 25, a representative value extracting unit that extracts a feature amount for each region as representative values F1 to Fn; and 26, a pattern P corresponding to the image G by patterning the representative values F1 to Fn. Is a pattern creation unit for creating a pattern.

A storage unit 27 stores the pattern P as a previous pattern Po by delaying the pattern P by a predetermined time interval Δt, and a storage unit 28 stores a pattern of each image at a different imaging timing, that is, a storage unit.
A shift amount calculator for comparing the previous pattern Po and the current pattern P in 25 to calculate a pattern shift amount ΔP; 29
Is a determination unit that generates a determination signal D indicating the presence of a rear vehicle approaching the host vehicle when the shift amount ΔP is equal to or greater than a predetermined value. The predetermined value is set in advance to a level indicating the presence of the approaching object (the following approaching vehicle).

Output signal of window processing section 24 and determination section 29
Is input to the display device 23 as necessary, and the states and determination results of the window regions W1 to Wn are displayed on the display screen.

FIG. 2 is an explanatory diagram showing an example of the rear image G captured by the camera 21 and displayed on the display device 23.
W7 is, for example, a window region divided into seven, and B is a rear vehicle photographed so as to fall within the window regions W1 to W7. Here, the case where the rear of the lane side adjacent to the right of the traffic lane of the vehicle is photographed as the image G is shown.
Further, the window areas W1 to W7 are set along the traveling path along the radiation from the gazing point at infinity.

FIG. 3 is an explanatory diagram showing the previous pattern Po and the present pattern P formed based on the representative values F1 to F7 of the respective window areas W1 to W7 in FIG.
The previous pattern Po consisting of representative values f1 to f7 at o,
(b) is the current pattern P including the representative values F1 to F7 at the time to + Δt after the lapse of Δt (for example, 0.1 seconds).

FIG. 4 is a characteristic diagram showing the relationship between the representative value deviation ΔF and the shift correction amount ΔPf of the pattern P, and is used in the processing in the shift amount calculation unit 28. Here, the shift correction amount ΔPf is an integer, and corresponds to, for example, the amount by which the current pattern P in FIG. 3B is shifted in the decreasing direction of the window area number, and the representative value deviation ΔF is each of the window areas W1 to Wn. This corresponds to the sum of deviations between the previous pattern P ′ and the current pattern P for each. Further, a shift correction amount ΔPf that minimizes the representative value deviation ΔF is obtained as a shift amount ΔP.

Next, the operation of the first embodiment of the present invention shown in FIG. 1 will be described with reference to FIGS. The image G captured by the camera 21 is converted into luminance information for each pixel by the image processing unit 22, then displayed on the display device 23 and input to the window processing unit 24.

The window processing unit 24 includes n window areas.
W1 to Wn, for example, seven window regions W1 to W7 as shown in FIG.
Are input to the display device 23 to be displayed on the image G, and are also input to the representative value extracting unit 25. As described above, the window areas W1 to Wn are set along the radiation road from the gazing point at infinity on the traveling lane.

The representative value extracting unit 25 calculates, for example, the feature value for each of the window regions W1 to Wn at a certain time to, that is, the representative values F1 to Fn, for example, the average of the brightness of all the pixels in each of the window regions W1 to Wn. Extract the extracted value.

Further, the pattern creating section 26 controls each window area.
FIG. 3 shows representative values F1 to Fn for each of W1 to Wn as a one-dimensional data string.
And a pattern P is created as shown in FIG.
And the shift amount calculation unit 28. This pattern P
In the shift amount calculating section 28, the current pattern P including the representative values F1 to Fn is compared with the previous pattern Po and stored in the storage section.
In 27, it is stored as the previous pattern Po composed of the representative values f1 to fn.

Similarly, with respect to the image G at the time point to + Δt, which has elapsed by the minute time Δt (about 0.1 second), the window area W1
A pattern P consisting of representative values F1 to Fn for each of ~ Wn is created,
The data is input to the storage unit 27 and the shift amount calculation unit 28. continue,
The shift amount calculating unit 28 compares the current pattern P with the previous pattern Po in the storage unit 27 at every minute time Δt, and performs an operation for obtaining the shift amount ΔP.

That is, the pattern P of different imaging timing
For each representative value of Po and P, the representative value deviation ΔF is sequentially calculated while changing the shift correction amount ΔPf for the current pattern P, and the shift correction amount ΔPf for minimizing the representative value deviation ΔF matches each pattern Po and P. Is obtained as a shift amount ΔP for causing the shift. The calculation of each representative value deviation ΔF is as follows.
It is expressed by the summation formula (1) with k = 1 to n as follows.

ΔF = (1 / n) Σ | f (k) −F (k + ΔPf) | (1)

In equation (1), f (k) is the value of the previous pattern P
o, the representative value of the k-th window area Wk, F (k + ΔP
f) is the k + ΔPf-th representative value of the current pattern P. Therefore, the representative value deviation ΔF is the same as the previous pattern Po when the current pattern P is shifted by the shift correction amount ΔPf.
Represents a value obtained by normalizing the sum of deviations of the representative values for each window region with respect to.

In this way, by repeatedly calculating equation (1) while changing the shift correction amount ΔPf, the characteristic diagram of FIG. 4 is obtained, and the shift amount Δ that minimizes the representative value deviation ΔF is obtained.
P is required. This shift amount ΔP is equal to each pattern Po.
And P are the values that make the most match.

Subsequently, the determination unit 29 determines that the rear vehicle B is a vehicle separated from the host vehicle when the shift amount ΔP is a positive value, and determines the rear vehicle B when the shift amount ΔP is negative. It is determined that the vehicle is approaching. If the shift amount ΔP is equal to or greater than a predetermined value and the approaching rear vehicle B is detected, a determination signal D indicating the presence of an approaching object is generated. This determination signal D is used to notify the driver of danger as described later.

In detail, taking the image G in FIG. 2 as an example, assuming that the reflected light on the road surface is small, the previous pattern Po at the time to is, as shown in FIG.
Representative value f3 near the window areas W3 and W4 corresponding to the position
And f4 become maximal. Assuming that the following vehicle B is approaching the own vehicle, the current pattern P at the time to + Δt becomes the front window in the image G as shown in FIG.
The representative values F2 and F3 near W2 and W3 are maximized.

At this time, the shift amount ΔP is substantially “−1”.
By comparing the absolute value of the shift amount ΔP with a predetermined value (for example, 1), | ΔP | ≧ 1. Therefore, the determination unit 29
Generates a determination signal D indicating that the following vehicle B is approaching because the shift amount ΔP is equal to or greater than the predetermined value.

If the rear vehicle B does not exist, each of the window areas W1 to Wn exclusively displays the road surface. Therefore, even if the patterns Po and P are compared while changing the shift correction amount ΔPf, the representative value deviation is obtained. A minimum point of ΔF (see FIG. 4) does not occur. Therefore, a non-existent approaching object is not erroneously detected.

When a shadow or the like exists on the road surface,
Although the movement of the shadow is detected based on the change in the pattern P, the position of the minimum point of the representative value deviation ΔF, that is, the shift amount ΔP is positive because the own vehicle is running, and there is no erroneous detection as an approaching object.

As described above, a plurality of windows W1 to Wn are set in the image G from the camera 21, and the representative value of each window area is set.
By creating a pattern P based on (brightness) and calculating the shift amount ΔP based on the time-series correlation processing of the pattern P, the following vehicle B approaching, or the object moving away can be automatically and accurately determined. Can be determined.

Since the image G of the camera 21 is automatically analyzed, signals such as ultrasonic waves and radio waves are not radiated, so that erroneous detection due to interference or interference does not occur. Further, even when there are a plurality of objects, since the minimum value of the representative value deviation ΔF occurs at a plurality of places, it is possible to determine the approaching state of each object.

Embodiment 2 FIG. In the above-described first embodiment, the case where the approaching object detecting means 20 is installed in the vehicle and the approaching rear vehicle B is detected has been described as an example. However, it is necessary to detect the approaching object. Needless to say, it is applicable in other fields. For example, it can be used for detection and determination of an approaching object at an intersection, and the determination signal D when an approaching object is detected is not limited to display or warning, but can be used arbitrarily.

Embodiment 3 FIG. Further, the approaching object detection means 20 simply generates the determination signal D. However, when the approaching rear vehicle B is determined, the determination result based on the determination signal D is displayed on the display device 23 as necessary. An alarm may be displayed. For example, a red marker or the like may be added so that the rear vehicle B in the display image G is easily noticed, and the marker may be blinked.

Embodiment 4 FIG. Although not shown, in addition to the display device 23, an alarm means capable of notifying by sound or the like and a controller for generating a drive signal of the alarm means in response to the determination signal D are provided. When the rear vehicle B indicates a very dangerous state, the warning means may be driven in response to the determination signal D. This makes it possible to reliably notify the driver of a particularly dangerous approaching object.

Embodiment 5 FIG. In the fourth embodiment, the alarm drive signal is generated based only on the determination signal D without particularly considering the driving state of the own vehicle. An alarm drive signal may be generated in response to a change in direction. FIG. 5 is a block diagram showing a fifth embodiment of the present invention, in which reference numeral 20 is the same as described above.

Reference numeral 31 denotes a switch means operated when the traveling direction of the vehicle changes, that is, a blinker switch; 32, a controller which determines the presence or absence of a determination signal D in response to an operation signal S from the blinker switch 31; The alarm means is driven by an alarm drive signal E from the controller.

In this case, the determination signal D includes a plurality of determination results for each image G in different directions. In addition, the controller 32 selectively detects the determination signal D for the changed traveling direction in response to the operation signal S, and generates the alarm drive signal E when the determination signal D is detected. .

For example, when the driver intends to change the course to the passing lane on the right side in the running direction of the own vehicle, when the driver operates the blinker switch 31 to instruct the change of the running direction, an operation signal S indicating a right turn is issued. , The controller 32 detects the presence or absence of the determination signal D based on the right rear image.

At this time, if an approaching object, that is, a rear vehicle B (see FIG. 2) exists in the right lane, an alarm drive signal E is generated in response to the determination signal D, and the alarm means 33 is driven. The driver is alerted by voice or the like. Therefore, the driver
When the blinker switch 31 is operated, it is recognized that there is a following vehicle B approaching on the lane after the change, and the vehicle immediately stops turning right, thereby preventing a particularly dangerous accident when the lane is changed. it can. Further, in order to further prevent an accident, it may be difficult to turn the steering wheel rightward in response to the determination signal D.

Embodiment 6 FIG. (Corresponding to claim 5) Also, the predetermined wind area is set assuming that the own vehicle travels straight. However, the wind area may be updated and set according to the road condition that requires natural turning. desirable.

In this case, a steering wheel angle sensor, a yaw rate sensor (not shown) or the like (not shown) is used as a turning detecting means for detecting a turning state, and a window processing unit 24 (see FIG. 1) in the approaching object detecting means 20 is used. ), The set position of the window area may be changed in response to a turning signal from the turning detecting means.

FIG. 6 is an explanatory view showing the window areas W1 to W7 when the vehicle turns right following a right curve road. The window areas W1 to W3 close to the own vehicle are turned right in the image G. Or compressed. That is, the window processing unit 24 sets each of the window regions W1 to W7 assuming an image G that relatively turns, according to the turning signal of the own vehicle.

As described above, by setting the window area according to the actual turning amount or turning speed by operating the steering wheel, the following vehicle B can be optimally detected regardless of the road condition. Therefore, the approaching object detecting means 20
Can accurately detect the movement of the rear vehicle B with respect to the host vehicle. For example, when the rear vehicle B may collide with the host vehicle at the time of turning, the determination signal D can be generated immediately. it can.

Embodiment 7 FIG. Further, in order to easily identify the movement of the rear vehicle B, the window areas W1 to Wn are set along the radiation road as shown in FIG. 2, but may be set along any direction as required. it can.

Although the case where the number n of the window areas W1 to Wn is seven has been described as an example, it can be set to an arbitrary number. At this time, the determination accuracy of the rear vehicle B is improved as the number n of the window areas is set to be larger. Is set to an appropriate value.

Embodiment 8 FIG. Also, 1 for one display image
Set the window areas W1 to Wn of the block and set the representative values F1 to Fn
Although only one data string is generated for the pattern P, the window areas W1 to Wn may be divided into a plurality of blocks and a pattern may be set for each block. In this case, the movement of the rear vehicle existing in each block can be individually divided and monitored with high accuracy.

Embodiment 9 FIG. Also, the average value of the brightness of the pixels in the window area was adopted as the representative value F1 to Fn of each window area W1 to Wn, but the maximum value of the brightness, the minimum value, the difference between the maximum value and the minimum value, or , The ratio of the maximum value to the minimum value is represented by a representative value F1 to
It may be adopted as Fn. In particular, at night, etc., only the headlight part is brightened by turning on the headlight,
In order to make the feature amount for each of the window regions W1 to Wn remarkable, it is desirable to set the maximum value as the representative value F1 to Fn rather than the average value of the brightness.

Embodiment 10 FIG. (Corresponding to claim 7) In addition, the window areas W1 to Wn are set to be one-dimensional and each representative value F1
Although the pattern P composed of a one-dimensional data string from Fn to Fn is created, a pattern composed of a two-dimensional data string may be created by setting the window area to two-dimensional.

FIG. 7 shows a two-dimensional window region W11 to Wnm.
FIG. 15 is an explanatory diagram showing an image G according to the sixth embodiment in which (for example, W11 to W76) is set, and here, seven images G along the road direction;
An example is shown in which only six are set along a direction perpendicular to the road surface. FIG. 8 shows a two-dimensional pattern P by the rear vehicle B in FIG.
8A and 8B are explanatory diagrams showing o 'and P', wherein a pattern Po 'in FIG. 8A is a previous pattern at time to, and a pattern P' in FIG. 8B is a current pattern at time to + Δt.

FIG. 9 shows the shift correction amount ΔPf of the pattern P ′.
FIG. 9 is a characteristic diagram showing a relationship between the representative value deviation ΔF ′ with respect to n and ΔPfm, and a shift correction amount (ΔPfm, ΔPfm) that minimizes the representative value deviation ΔF ′ is obtained as a shift amount (ΔPn, ΔPm) composed of two-dimensional coordinates. Can be

In this case, the shift amount calculating section 28 determines whether the pattern Po 'at a certain time to and the time Po after a short time Δt
+ Δt and shift amount from pattern P ′ (ΔPn, ΔPm)
Is obtained as shown in FIG. 9, so that the two-dimensional shift correction amount
The following calculation of the representative value deviation ΔF ′ is repeatedly performed while changing (ΔPfn, ΔPfm).

ΔF ′ = (1 / n) (1 / m) ΣΣ | f ′ (k, j) −F ′ (k + ΔPfn, j + ΔPfm) | (2)

However, in the equation (2), k = 1 to n and j =
1 to m, and f ′ (k, j) is the value of the previous pattern Po ′.
The representative value of the (k, j) -th window area Wkj, F '(k +
ΔPfn, j + ΔPfm) is (k + ΔPfn,
(j + ΔPfm) -th representative value. Therefore, the representative value deviation Δ
F ′ is the shift correction amount (ΔPfn, ΔPf
It shows a value obtained by normalizing the sum of the deviations of the representative values for each window area when the position is shifted by m).

As shown in equation (2), by repeatedly performing the calculation while changing the shift correction amount (ΔPfn, ΔPfm) in the direction of the radiation road and in the vertical direction, the characteristic diagram of FIG. 9 is obtained.
As a result, a two-dimensional shift amount (ΔPn, ΔPm) that minimizes the representative value deviation ΔF ′ is obtained, and this shift amount (ΔPn
n, ΔPm) is a value that most closely matches the previous pattern Po ′ with the current pattern P ′.

Therefore, the rear vehicle B has moved by the vector V in FIG. 9 during the short time Δt, and as described above, if the vector V shows the positive direction, the vector V becomes negative during the separation. If the direction is indicated, it is determined that the vehicle is approaching.
As described above, by using the two-dimensional pattern P ′, the movement of the target object can be grasped in more detail, and the reliability of determination of the approaching object is improved.

[0079]

As described above, according to the first aspect of the present invention, an image pickup means for photographing an image, a window processing section for dividing the image into a plurality of window areas, and a feature value for each window area are represented by a representative value. A representative value extracting unit, a pattern creating unit that creates a pattern corresponding to an image by using each representative value as a data string, and a shift amount operation that calculates a shift amount by comparing each pattern of the image at different imaging timings And a determination unit that generates a determination signal when the shift amount is equal to or greater than a predetermined value indicating the presence of the approaching object, so that the approaching object can be automatically and reliably determined. There is an effect that the device can be obtained.

According to a second aspect of the present invention, in the first aspect, the image pickup means is installed in the vehicle to capture an image behind the vehicle, so that an approaching object from behind the vehicle can be automatically detected. There is an effect that an approaching object detection device that can accurately and reliably determine is obtained.

According to a third aspect of the present invention, in the second aspect, a controller for generating an alarm drive signal in response to the determination signal and an alarm means driven by the alarm drive signal are provided. The warning means is activated when it determines the approaching object, and the driver is alerted. Therefore, the approaching object that automatically and reliably determines the approaching object from behind the vehicle to ensure safety There is an effect that an object detection device can be obtained.

According to a fourth aspect of the present invention, in the third aspect, there is provided a switch means which is operated when the traveling direction of the vehicle is changed, and wherein the imaging means is capable of displaying a plurality of rear images corresponding to the traveling direction of the vehicle. Imaging, the determination unit generates a determination signal for each rear image, and the controller generates an alarm drive signal when a determination signal for the changed traveling direction is detected in response to an operation signal from the switch means. Therefore, an approaching object detecting device that automatically and surely determines the approaching object on the changed travel path, notifies the danger, and secures the safety can be obtained.

According to a fifth aspect of the present invention, in any one of the second to fourth aspects, the vehicle further comprises a turning detecting means for detecting a turning state of the vehicle, and The set position of the window area is changed in response to the turning signal to detect the following object approaching on the running road after turning, so that the approaching object is automatically and reliably determined regardless of the road condition. Thus, there is an effect that an approaching object detection device that ensures safety can be obtained.

According to a sixth aspect of the present invention, in any one of the first to fifth aspects, the window area is set along a ray from a gazing point at infinity, and the representative value pattern is one-dimensional. Since the data string is used, an approaching object detecting device that can automatically and reliably determine the approaching object can be obtained.

According to a seventh aspect of the present invention, in any one of the first to fifth aspects, the window area is set along a ray from a gazing point at infinity. Since the setting is made along the vertical direction and the representative value pattern is a two-dimensional data sequence, an approaching object detection device that can automatically and reliably determine the approaching object is obtained.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a functional configuration of an approaching object detection unit according to a first embodiment of the present invention.

FIG. 2 is an explanatory diagram showing a window area set together with an image according to the first embodiment of the present invention;

FIG. 3 is an explanatory diagram showing a pattern created according to the first embodiment of the present invention.

FIG. 4 is a characteristic diagram showing a change in a representative value deviation with respect to a shift correction amount calculated according to the first embodiment of the present invention.

FIG. 5 is a block diagram illustrating a functional configuration according to a fifth embodiment of the present invention.

FIG. 6 is an explanatory diagram showing a window area set according to a sixth embodiment of the present invention.

FIG. 7 is an explanatory diagram showing a window area set according to a tenth embodiment of the present invention together with an image.

FIG. 8 is an explanatory diagram showing a pattern created by Embodiment 10 of the present invention.

FIG. 9 is a characteristic diagram showing a change in a representative value deviation with respect to a shift correction amount calculated according to the tenth embodiment of the present invention.

FIG. 10 is a block diagram showing an example of a conventional approaching object detection device.

11 is an explanatory diagram showing an approaching object detection operation by the device of FIG. 10;

FIG. 12 is an explanatory diagram showing an operation of a second example of the conventional approaching object detection device.

FIG. 13 is an explanatory diagram showing a display image according to a third example of the conventional approaching object detection device.

[Explanation of symbols]

 Reference Signs List 21 camera (imaging means) 24 window processing section 25 representative value extracting section 26 pattern creating section 28 shift amount calculating section 29 determining section 31 blinker switch (switching means) 32 controller 33 warning means G image B rear vehicle D determination signal E warning drive Signal S Operation signal F1 to Fn Representative value P, P 'Current pattern Po, Po' Previous pattern ΔP, ΔPn, ΔPm Shift amount W1 to Wn Window area

────────────────────────────────────────────────── ─── Continuation of the front page (56) References JP-A-6-293236 (JP, A) JP-A-3-41599 (JP, A) JP-A-6-247246 (JP, A) JP-A-6-247246 314340 (JP, A) JP-A-2-241855 (JP, A) JP-A-5-278541 (JP, A) JP-A-1-161507 (JP, A) JP-B-6-92976 (JP, B2) Patent 2887039 (JP, B2) (58) Fields investigated (Int. Cl. ⁷ , DB name) G01S 11/12 G01S 3/782 G01S 17/93 H04N 7/18 G08G 1/16 G06T 7/00

Claims (7)

(57) [Claims] An imaging unit that captures an image; a window processing unit that divides the image into a plurality of window regions; a representative value extraction unit that extracts a feature amount of each of the window regions as a representative value; A pattern creation unit that creates a pattern corresponding to the image using a value as a data string; a shift amount calculation unit that compares each pattern of the image at different imaging timings to calculate a shift amount; and the shift amount is a predetermined value. A determination unit configured to generate a determination signal at the time of the above, wherein the predetermined value is set to a level indicating the presence of the target approaching the imaging unit. 2. The approaching object detecting device according to claim 1, wherein said image pickup means is installed in a vehicle to photograph a rear image of said vehicle. 3. The approaching object detecting device according to claim 2, further comprising: a controller that generates an alarm drive signal in response to the determination signal; and an alarm unit that is driven by the alarm drive signal. 4. A switch which is operated when the traveling direction of the vehicle is changed, wherein the imaging unit captures a plurality of rear images corresponding to the traveling direction of the vehicle, and wherein the determination unit comprises: The controller generates a determination signal for an image, and the controller generates the alarm drive signal when a determination signal for the changed traveling direction is detected in response to an operation signal from the switch unit. The approaching object detecting device according to claim 3, wherein 5. The vehicle according to claim 1, further comprising: a turning detection unit that detects a turning state of the vehicle, wherein the window processing unit changes a set position of the window area in response to a turning signal from the turning detection unit. The approaching object detection device according to any one of claims 2 to 4. 6. The method according to claim 1, wherein the window area is set along a ray from a gazing point at infinity, and the pattern includes a one-dimensional data sequence. Approaching object detection device. 7. The window area is set along a ray from a gazing point at infinity and along a direction perpendicular to the ray, and the pattern is formed from a two-dimensional data sequence. The approaching object detecting device according to any one of claims 1 to 5, wherein: