JPH05289743A - Line detecting device - Google Patents

Abstract

PURPOSE:To provide a line detecting device which can detect a traveling guideline at a high speed and can reduce the influence of the pitching, etc. CONSTITUTION:The image obtained by a CCD camera 10 is processed and a white line is detected. The image signal is binarized in black and white and the white line is detected based on the changing state of the binarization data for only the image signal that are included in a prescribed range. In order to decide a processing range of the preceding detection, the positions of plural past detected white lines are moved and averaged at each time. Based on these average values, the subsequent white line positions are estimated. Then a prescribed range near each of estimated white line positions is defined as a processing range.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a line detecting device for detecting a guideline provided along a road for automatic driving of a vehicle or the like.

[0002]

2. Description of the Related Art Conventionally, various driving control devices have been mounted on a vehicle in order to reduce the burden on the driver. Among them, research has been conducted on automatic driving in which steering operation is also performed automatically, and it is considered to install a mechanism that enables automatic driving even in a normal automobile.

For this automatic driving, the position of the vehicle with respect to the road (road) must be constantly grasped and the vehicle must be controlled so as to travel along the road.

As a method of detecting the running road, it has been proposed to photograph a white line formed along the running road with a television camera and detect the position of the vehicle with respect to the running road from the position of the white line.

[0005] A road is usually provided with a center line, a line dividing a lane, and the like. If the position detection for automatic driving is performed by the white line detection, the equipment on the road side can be very simple. it is conceivable that.

[0006] For example, Japanese Patent Laid-Open No. 63-40913 discloses a method of detecting a front white line using a CCD camera mounted on a vehicle. That is, in this example, a portion where the brightness of the road surface obtained by the CCD camera is equal to or higher than a predetermined value is determined as a white line. In a normal road, white lines are formed on black areas such as asphalt, and the brightness of the white areas is sufficiently higher than that of other areas, so that the white areas can be detected.

[0007]

However, when the vehicle is traveling, the posture of the vehicle may change significantly. In such a case, in the conventional device, the white line may be out of the field of view and may be lost.

In order to solve this, it is possible to widen the field of view of the CCD camera. However, if the viewing angle is widened, a plurality of white lines will come into view on a road having a plurality of lanes. That is, the width of one lane is about 3.
In the case of 7 m, if the road surface with a width of 4 m is viewed, two white lines are captured, and if the road surface with a width of 8 m is viewed, three white lines are captured. Therefore, it is necessary to always discriminate the white line that the vehicle should follow from among the plurality of white lines.

Related Art In order to solve such a problem, the present inventor predicted the line position in Japanese Patent Application No. 2-294774.
It is proposed to perform line detection processing only in the prediction range.

That is, the current detection line position wL, the previous detection line position wL1, the previous detection line position w
The next line position wLL is calculated from L0 by the following equation. wLL = 3 (wL-wL1) + wL0 Then, only the data within a predetermined range before and after this predicted line position is the target of the line detection processing.

Therefore, such prediction can reduce the number of target data of the line detection processing and can surely detect the line.

However, when such prediction processing is performed,
When the line detection position greatly changes due to vehicle pitching or the like, this influence may be large and the predicted position may be greatly different.

That is, when there is a depression on the road as shown in FIG. 14 and pitching of the vehicle occurs here, the predicted line position greatly differs from the actual line position, and the line is the processing target range. There was a problem that the line could not be detected because it was out of the range. Note that the detected lane width w is shown in FIG. 14 because the detected lane width w changes according to pitching.

An object The present invention has been made as a problem to solve the above problems, and minimize the pitching effects, and to provide a line detection device capable of performing line detection by efficient data processing The purpose is to

[0015]

A line detection device according to the present invention is a line detection device which is mounted on a vehicle and detects a guide line provided along a road, and repeatedly outputs an image of a road in a predetermined range. A camera, a line detection means for processing an image output once from the camera to detect a guideline, a line position storage means for storing the line position detected by the line detection means for a plurality of times, and An average line position calculating means for moving and averaging a plurality of line positions stored in the line position storing means to calculate a plurality of average line positions according to the passage of time, and a time obtained by the average line position calculating means. Line position predicting means for predicting the line position detected this time from a plurality of change states of the line position according to the progress of the line, and this line position predicting means Thus a line selecting means for selecting the closest detection line to the predicted positions obtained, characterized by characterized by having a.

[0016]

In the line detecting apparatus according to the present invention, a line is detected by processing the image obtained by the camera for each time, and the line position storing means stores the line position for at least a plurality of times. Then, a plurality of moving averages of the line position data of a plurality of times are calculated according to the passage of time to calculate a plurality of time-series average line positions.

Further, the position of the next detected line is predicted from this time-series average line position, and the line closest to this predicted position is selected.

Therefore, even when there are a plurality of lines in the image obtained by the camera, it is possible to accurately select the line along which the vehicle is to travel and minimize the influence of abnormal data due to pitching or the like. Can be suppressed.

[0019]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A line detecting device according to the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing the structure of a line detecting apparatus according to the present invention, which has a CCD camera 10. The CCD camera 10 includes an optical system including a lens 12 and a diaphragm 14, and a CCD linear sensor 16 having a one-dimensionally arranged photoelectric conversion element. The CCD
The camera 10 is attached to a position where an image in front of the vehicle can be obtained, and outputs information regarding the brightness of each photoelectric element output from the CCD linear sensor 16 as a serial signal.

A white line detection ECU 20 is connected to the CCD camera 10. This white line detection ECU
Reference numeral 20 denotes an amplifier 22, an AD converter 24, which amplifies the signal input from the CCD camera 10 and blunts the waveform.
A CPU 26, a ROM 28 that stores a program for the operation of the CPU 26, a RAM 30 that is used as a storage area during the processing of the CPU 26, and an I / O for input / output operations.
It consists of an O section 32. And this white line detection ECU
Information about the white line detected by 20 is supplied to the vehicle control ECU 40, and this vehicle control ECU 40 controls steering of the vehicle and the like so that the vehicle travels along the detected white line.

Next, the mechanism of white line detection in the CCD camera 10 will be described with reference to FIG.

The CCD camera 10 is installed in the vehicle so as to capture an image of the distance L1 in front of the lens 12. The focal length of the lens 12 is f, and the CCD linear sensor 16 located at a distance L2 behind the lens 12
The image is formed at. Therefore, the width of the front image that can be detected by the width w of the CCD linear sensor 16 is W. Therefore, in the front L1 of the lens 12, if the white line is at a position displaced from the center line by x, CC
In the D linear sensor 16, the position where the white line is imaged is uniquely determined. If the number of elements in the width w of the CCD linear sensor 16 is N and the number of elements from the center of the CCD linear sensor 16 is I,
The distance x from the center of the white line is shown as follows.

First, according to the convex lens formula, 1 / L1 + 1 / L2 = 1 / f, and from the magnification thereof, W = w · L2 / L2.

Therefore, W = w. (L1 + f) / f and x = (W / N). (N / 2-I).

Therefore, the position x of the white line can be detected by detecting in which element of the CCD linear sensor 16 the white line is detected.

Overall Flow Next, the white line detection ECU 2 utilizing the above principle
The signal processing (white line detection) from the CCD camera 10 at 0 will be described.

FIG. 3 is a flow chart for explaining the overall operation of the white line detection processing. First, exposure control is performed so that the exposure amount in the CCD camera 10 falls within a predetermined range (S).
1). Then, since the luminance signal for each element is output as serial data from the CCD camera 10 for which the predetermined exposure control has been performed, this is converted into digital data in the AD converter 24 (S2). Here, CCD camera 1
Since the data output from 0 is determined by the clock supplied to the horizontal output shift register of the CCD linear sensor 16, the clock frequency in the AD converter 24 is also synchronized with this.

Therefore, the respective luminance signals obtained in each of the N elements in the CCD linear sensor 16 are
It is sequentially output from the AD converter 24 as N pieces of digital data. This digital signal is stored in a predetermined location of RAM 30.

Then, the maximum value of the brightness signal thus obtained in the CCD camera 10 is detected and the average value is calculated, and the threshold value is calculated based on the maximum value and the average value (S3).

Next, each of the N digital data obtained by AD conversion using the obtained threshold value is binarized, and from the change state of the binarized data, a white line is drawn. The left and right edge portions are detected (S4). Then, edge correction is performed based on the detected number of left and right edges in consideration of the case where a white line is applied to the image end (S5).

In this way, a plurality of white line edges are detected, and the white line along which the vehicle should follow is detected from among these.
At this time, the white line position of this time is predicted at least from the change state of the white line position of the previous time and the time before the previous time, and the one closest to the predicted position is selected. Then, the coordinates of the selected white line are output (S6).

As described above, the coordinates of this white line correspond to the distance from the center of the white line.
By supplying to the CU 40, the vehicle control ECU 40 performs steering control based on this x, and vehicle traveling along the lane (white line) is achieved.

As described above, according to this embodiment, the white line along which the vehicle is to be predicted is predicted from the plurality of detected white line positions,
Since the selection is made, accurate line white line detection can be performed even when the vehicle attitude changes significantly.

[0035] The operation of the threshold calculating the threshold calculating the present embodiment will be described with reference to FIG.

First, as initial settings, three variables of an average value avb, a maximum value maxd, and an AD conversion data counter adcount which are three variables are reset to 0, and the brightness data obtained by AD conversion is stored in the head of the RAM 30. The address (e000h) is set in the variable A (S101). The values of the variables set here are stored in the RAM 30.

Next, the count is 400h (102
It is determined whether or not 4) has been reached (S102). this is,
This corresponds to the effective number of elements in the CCD linear sensor 16 (the number of elements in the range of the width w), that is, the number of data output from the niAD converter 24 at the time of one shooting. Therefore, when the count reaches 1024, it can be determined that the processing of all data is completed.

If the count is less than 1024, the data processing is not yet completed, and the following data is input to the variables bc, ax, and up (S).
103).

Bc = A, ax = adcount, up = bc + ax Here, an address in the RAM 30 in which the 1024 luminance signals obtained by the CCD linear sensor 16 are stored is sequentially designated as the variable up. Then, the data at the address designated by the variable up is read out and input as the value of the variable DATA (S104).

Next, in order to detect the maximum value, it is determined whether DATA is smaller than the maximum value maxd (S10).
5). Then, when DATA is larger than maxd, this should be the maximum value, and the variable maxd has DA
TA is input to update this value (S106). On the other hand, when DATA is not the maximum value, it is not necessary to update the maximum value maxd, and thus the process proceeds to the next process without passing through S106.

Next, in order to calculate the average value avb, DAT
A value obtained by dividing the value of A by the data number 1024 is sequentially added (S107). Then, 1 is added to the count (S108), and the process returns to S102.

Therefore, the maximum value and the average value are calculated (S10
6, S107) is repeated until the number of data reaches 1024, and when the processing for all (1024) data is completed, YES is obtained in S102,
The threshold thL0 is calculated by the following formula (S10)
9).

ThL0 = (avb + maxd) / 2 In this way, in this embodiment, the intermediate value between the average value and the maximum value of the data in all the elements obtained by the CCD linear sensor 16 is the threshold value thL0. Become.

Binarization and Edge Detection Processing Next, the binarization processing and edge detection processing will be described with reference to FIGS.

First, an initial value is set in each variable as follows. (S201).

White line part continuous count permission flag cok1 =
0, road surface continuation count permission flag cok2 = 0, white line continuation counter fc1 = 0, road surface continuation counter fc2 =
0, white line left edge candidate coordinates wn01 = 0, white line right edge candidate coordinates wn02 = 0, white line detection flag fw1 = 0, white line right edge counter wc1 = 0, road surface detection flag fw2
= 1, white line left edge counter wc2 = 0 Further, similarly to the case of the above threshold value calculation, the start address (e000h) of the luminance data is input to the variable A (S2
02) The AD conversion data counter adcount representing the number of 1024 pieces of data is set to 0 (S2)
03).

First, the count is 1024 (400
In step h), it is determined whether the processing of all data is completed (S204). If the processing is not completed, the variables bc, ax, and up are set to A, adcount, bc.
The value of + ax is substituted and the value of the brightness data of the address determined by up is input to the variable DATA (S2
05).

Next, the binarization process is performed. First, the variable DA
The threshold value thL is compared with TA (S206).

Here, this thL is different from thL1 calculated in S110 described above. That is, this threshold value thL is not the threshold value calculated in this processing but is calculated in the previous processing.

When DATA ≦ thL, the road surface portion is used, and therefore the variable fc1 representing the number of continuously detected white line portions is detected.
= 0, a variable wn01 indicating the detected coordinate of the left edge of the white line =
0, a variable fw2 = 1 indicating road surface detection is set (S2
07).

Further, it is determined whether cok1 is 0 (S208). As described later, cok1 is a flag that becomes 1 when the color changes from black to white (DATA ≦ thL → DATA> thL), and returns to 0 when two white states continue. Therefore, when black is detected (DATA
The fact that cok1 is not 0 in ≦ thL) indicates that the previous white (DATA> thL) detection is completed once. The fact that the detection of white is completed once means that there is a white point that is not a white line on the road surface, and the right edge should not be detected at this time.
Therefore, if cok1 is not 0 in S208, cok1 = 0 and fw1 = 0 are set (S209),
The flag for detecting white is reset to 0, and 1 is added to the count (S21
0), and returns to S204.

On the other hand, when cok1 = 0, the previous detection result is not the abnormal state as described above, so the right edge is detected as follows. First, fw1
It is determined whether or not = 1 (S211). fw1 is S201
Is initially set to 0, and is set to 1 when a white line is detected, that is, when DATA> thL. Therefore, the fact that the data is ≦ thL in S206 and the fw1 is 1 in S208 means that the right edge of the white line has been detected. Therefore, if fw1 = 1 in S211, detection of the road surface has been detected, so fw1 = 0 is set and a variable wn02 = a indicating the detection position of the right edge is set.
dcount, road surface continuation count permission flag cok2 =
It is set to 1 (S212).

If an edge is detected, its ad
The value of count may be stored as the edge position as it is, but in this example, after the right edge is detected, the position is determined to be the right edge only when the next data is also not a white line, and an erroneous determination is generated. Suppress. Therefore, the road surface continuation count permission flag cok2 = 1 is set.

Next, it is determined whether or not the road surface continuation permission flag cok2 is 1 (S213). If cok2 is 1, 1 is added to the road surface continuation counter fc2 (S21
4) If cok2 is not 1, this addition is not performed, and then it is determined whether fc2 is 2 (S21).
5). If this fc2 passes S214 twice in a row,
That is, it is 2 when two pieces of data below the threshold value thL continue. Therefore, when fc2 is 2, the above-mentioned S212 is set in the array variable wn2 [wc2] indicating the white line right edge coordinates specified by the right edge counter wc2.
The value of the white line right edge candidate coordinate wn02 set by is stored. Further, the variables cok2 and fc2 are reset to 0, and 1 is added to the right edge counter wc2 (S
216). Therefore, in the case of the next right edge detection, w
c2 is increased by one. Therefore, the array variable wn
The position of the next right edge can be stored in 2. S2
If fc2 <2 in 15 and the processing of S216 is completed, the processing for the right edge is completed, so 1 is added to the count (S210) and S20.
Return to 4.

On the other hand, in S206, DATA> thL
If it is determined that the white line portion is detected, the left edge is detected as follows.

First, the road surface continuation counter fc2 and the left edge candidate coordinates wn02 are reset to 0, and the white line detection flag f
w1 is set to 1 (S217). That is, fc2
Is a variable indicating the number of consecutive road surface data, and is reset to 0 when the data on the white line is detected.
Also, wn02 is a variable for the right edge candidate coordinates, but it is reset here because it has entered the loop for detecting the left edge. Further, fw1 is a flag indicating that the white line portion is detected, and fw = 1 here.

Further, it is determined whether cok2 is 0 (S218). As described above, cok2 becomes 1 when the color changes from white to black (DATA> thL → DATA) (S212), and 0 when two black states continue.
(S216) flag. Therefore, S206
When white is detected at (DATA> thL), cok
The fact that 2 is not 0 means that the previous black (DATA ≦ th
L) indicates that the detection is completed once. And
The fact that the detection of black is completed once means that there is a faint portion in the white line, and the left edge should not be detected at this time. Therefore, if cok2 is not 0 in S218, cok2 =
0, fw2 = 0 (S219), the flag for detecting black is reset to 0, and adc
One is added to out (S210), and the process returns to S204.

On the other hand, when cok1 = 0, the previous detection result is not the abnormal state as described above, so the right edge is detected as follows. First, fw2
It is determined whether or not = 1 (S216). This fw2 is set to 1 when the road surface is detected. Therefore, when fw2 = 1 here, the fact that the road surface has moved to the white line, that is, the left edge is recognized. And
The variable fw2 indicating that the road surface is detected is reset to 0, the value of “adcount” is input to the left edge candidate coordinate wn01, and the left edge detection counter cok1 is set to 1 (S221).

Then, the white line continuation count permission flag cok1 and the white line continuation counter fc1 are used to determine whether or not two consecutive white line parts have been detected in the right edge.

For this purpose, it is first determined whether cok1 is 1 (S222). If cok1 is 1, the left edge has been detected, so 1 is added to the left edge counter fc1 indicating the number of white lines detected when the left edge is detected (S223). Next, it is determined whether or not fc1 is 2 (S224), and if it is 2, it means that the road surface has moved to the white line, and two white line data have continued, so S22
The value of the candidate coordinate wn01 input in 1 is input in the array variable wn1 [wc1] specified by wc1. As a result, the position of the detected right edge of the white line is stored. Since this input is made, the flag cok1 = 1, f
While resetting to c1 = 0, 1 is added to the variable wc1 indicating the number of right edges (S225). And adc
1 is added to out (S210), and the process returns to S204.

Such operation adcount = 1024
Up to the detected number of positions of the right edge and the left edge can be stored. The detected numbers are stored in wc1 and wc2. Then, when it is determined in S204 that the count reaches 1024, the white line edge detection for all the data is completed, so the binarization and white line edge detection operations are completed, and the detected edge correction processing is performed.

Detected Edge Correction Next, the detected edge correction will be described with reference to FIG. As described above, the positions of the left and right edges are set to the array variable w
When n1 [wc1] and wn2 [wc2] are input, 1 is subtracted from wc1 and wc2. This is because 1 is added to wc1 and wc2 at the time of the above-described edge detection processing (S213, S221), so that the value is returned to wc1 and wc2 actually used for the array variable. (S401).

Then, wc1 and wc2 are compared (S40).
2). When wc1 <wc2, it means that the number of left edges is smaller than the number of right edges, which means that the left edge of the image of the camera has a white line. Therefore, by inserting the left edge at the left end, the white line on the left end of the screen can be recognized.

Therefore, the value of wc1 is substituted for the variable j (S
403), and compares the value of j with 1 (S404). If j> 1, the value of j is substituted into the variable ax, and the value of the array variable wn1 [ax] specified by this ax is substituted into the variable up (S405). Next, j
+1 is substituted and the array variable w specified by this ax
The value of the variable up obtained in S405 is input to n1 [ax] (S406). As a result, the value of wn1 [j] is converted into the value of wn1 [j + 1]. Then, the value of j is subtracted by 1 (S407), and the process returns to S404.

Since this process is repeated until j becomes 1 in this way, the values input to the array variable wn1 [wc1] are converted into wn1 [wc1 + 1], respectively. That is, there are n values as the value of wn1, and this is w
When stored as the values of n1 [1] to wn1 [n], this processing converts the values to wn1 [2] to wn1 [n + 1].

Next, a value of 0 is substituted into wn1 [1] (S407). By this, one is forcibly inserted as the value of the array variable wn1, and this is also inserted even when the left edge cannot be detected.

On the other hand, in S402, wc1 ≧ wc2
If it is, the right edge is missing or both are the same number. Therefore, next, wc2 and wc1 are compared (S
409). Here, when wc2 ≧ wc1,
This means that they are equal, and no correction processing is necessary.

On the other hand, when wc2 is smaller than wc1, correction of right edge insertion must be performed. Therefore, 1 is added to wc2, and 1023 is forcibly inserted into the array variable wn2 [wc2] specified by this wc2. As a result, the value at the right end of the visual field is inserted as the right edge.

In this way, when the left edge is missing, the left edge of the camera field of view is input as the value of the left edge, and when the line reaches the right edge and the right edge is missing, it is the right edge of the camera field of view. The value of 1023 is input as the position of the right edge.

Output of White Line Coordinates / Calculation of Predicted Value Next, regarding output of the white line coordinates and prediction of the next white line position, FIG. 8 to FIG.
It will be described based on 1. When the edge detection is performed as described above, the white line is detected from this and the next white line detection position is predicted. Here, it is first determined whether the variable sc indicating whether or not the control is started is 0 (S3
00) and sc = 0, it is the beginning of control, and therefore the processing by the CCD center priority method described later is performed in order to set the white line near the center of the CCD camera as the white line along which the vehicle should follow.

If sc ≠ 0, normal white line detection processing is performed, so it is determined whether wc1 or wc2 is 0 (S301, S302). This wc1 and w
c2 represents the number of white line position detections, and if either of them is 0, it indicates that the white line cannot be detected. Therefore, in this case, an error processing loop is entered.
Next, wc1 and wc2 are compared (S303). If they are not equal, it is determined that the number of right edges is different from the number of left edges, and accurate white line detection has not been performed, and the process proceeds to an error processing loop.

On the other hand, when wc1 = wc2,
The position of the white line is detected as follows. That is, a variable kn representing the number of detected white line candidates is set to 0 (S3
04), the variable j indicating the number of the white line is set to 1 (S305). Then, this j is compared with the detected number wc1 of white lines (S306). If j is less than or equal to wc1, it is determined that the processing up to this point was normal, and the center coordinates hL of the j-th white line and the width RP2 of the white line are calculated from the left and right edge coordinates of the white line by the following equation (S30).
7).

HL = (wn1 [j] + wn2 [j]) / 2 RP2 = wn2 [j] −wn1 [j] Next, it is determined whether the calculated white line position hL is within a predetermined range. That is, it is determined as follows whether or not it is within a predetermined range (± moff) around the predicted white line position wc calculated and stored in the processing loop before the last time.

First, the variable ax = wc-moff is set (S308), and it is determined whether or not this ax is 0 (S30).
9). If ax is 0 or more, ax is in the camera visual field range, so that it is left as it is, but if ax <0, ax =
It is set to 0 (S310). Next, ax is compared with the detected white line position hL (S311). When hL <ax, the white line position is not stored because it is outside the prediction range.

On the other hand, when hL ≧ ax, it is necessary to judge whether this hL is equal to or less than a predetermined upper limit value. Therefore, the upper limit of the range is set to bc as bc = wc + moff (S312), and the white line position hL and bc are compared (S313).

If hL ≦ bc, hL
Is within a predetermined range (ax ≧ hL ≧ bc), kn =
kn + 1 (S314), wLk [kn] = hL (S31
5), wLd [kn] = rp2 (S316), the white line coordinates specified by the number of white lines detected in the estimation range, and the width of the white line are array variables wLk [kn] and wL.
Set to d [kn].

Then, in order to determine the next white line, j
= J + 1 and the process returns to (S317, S316). In addition,
In S311, S313, hL <ax or hL>
If it is determined to be bc, the white line position and the white line width are not set and the process directly proceeds to S317.

This process is repeated until the process is completed for all the white lines that have been detected (j> wc), and the position and width of the white line within the predetermined estimation range are set to the array variable wLk.
Set to [kn] and wLd [kn].

In this way, when a white line candidate within the prediction range is detected, the one closest to the estimated value wc is selected from these. First, it is determined whether or not there is a white line in the estimated range by determining whether or not kn is 0 (S
401), if kn is not 0, 0 is set to the variable pit that represents the number of the white line closest to the estimated value wc (S402). Further, the value of the white line position wLk [1] first detected within the estimation range is substituted into ax (S403), and the value of this ax is substituted into hL (S404).

Next, it is determined whether kn is 1 (S40
5) If this is 1, it is not necessary to select a white line, so the process proceeds to the next process. If it is not 1, the following white line selection process is performed.

First, the first white line position ax (wLk is set to the variable wLm to which the white line position closest to the estimated value wc is input.
[1]) is substituted (S406). And ax = ax
As -wc, the distance from the estimated position is once entered in ax (S407), and if this difference ax is 0 or less, 0 is set in ax (S408, S409), and the obtained estimated white line position is obtained. The distance from is substituted into the variable dif (S
410).

Next, in order to substitute the white line position having the smallest difference dif into wLm, the following processing is performed. That is, j2 is set (S411), and it is determined whether this j is kn or less (S412). If j is less than or equal to kn, there is a next white line candidate, so ax = wLk [j] is set and the coordinates of the next white line candidate are substituted into ax (S413).
This ax is substituted into the variable hL (S414). And
The difference ax = ax-wc between the white line position and the predicted value this time is calculated (S415), and if this difference ax is less than or equal to 0, this is set to 0 (S416, S417), and thus calculated. Ax and the difference di required up to the previous time
f is compared (S418). If ax <dif, then the current white line position is closer to the estimated value wc than the other white line positions detected so far, so that dif =
Change dif to a smaller value as ax (S41
9) By substituting the white line position coordinate hL at this time into wLm, the white line position coordinate closest to the estimated value wc at that time is updated to wLm (S420), and j at that time is pit.
To the white line number closest to the estimated value wc (S421).

In this way, when the white line position is updated, or when ax ≧ dif in S418 and there is no need for updating, 1 is added to j (S422), and S is added.
Return to 412. By repeating this process until j> kn, the position of the white line closest to the estimated value wc can be detected from the white line candidates detected within the estimated range, and this value is set to wLm. , HL = w
Lm (S412). As a result, the center position coordinate of the white line closest to the estimated value wc is input to hL.

Next, it is determined whether or not the width of the white line detected as described above is too large. That is, ax = wLd [pit] is set (S501), and a
It is determined whether x is 224 (70h) or more (S50).
2). If the width of the white line is 224 or more as the number of CCDs, it is regarded as an erroneous detection. Therefore, hL = wc is set (S502), and the estimated value wc is used as the white line position coordinate of this time detection instead of the detected white line position. Yes (S502). Also, S
If ax <70h in 502, normal white line detection is performed, and such rewriting of hL is not performed.

Then, ax = hL is set (S503), and ax
= Ax-w1 (S504), the difference between the previously detected white line position and the presently detected white line position is obtained. If the difference thus obtained is negative, it is returned to 0 (S
505, S506), and it is determined whether this value is 160 or less (S507). The fact that the previous detection value and the current detection value greatly deviate (160 or more) cannot be considered in reality, and in this case, an error occurs, and the process proceeds to the next white line position prediction loop only within the predetermined range.

Calculation of Estimated Value wc First, the latest average white line position coordinate is calculated by moving-averaging the white line coordinate hL detected this time and the white line coordinates wL and w1 of the past two times (S601). The moving average coordinate data including the latest average position coordinate calculated in this way
Send (S602). By this, ws0, ws1,
The moving average coordinates of the previous time, the previous time, and the current time are input to wsL.

Further, the detected white line position coordinates are also fed (S603). By this, w0, w1, wL
2 times before, respectively, the white line position coordinates detected last time and this time are input.

Then, the above three moving average coordinates ws
The estimated value wc of the next white line coordinate is calculated by the following equation using 0, ws1, and wsL.

Wc = 3 × (wsL-ws1) + ws0 This is schematically shown in FIG. That is, ws0 is calculated from the results of w1 to w3, ws1 is calculated from the results of w2 to w4, and wsL is calculated from the values of w3 to w5.
Is calculated. Then, wc is calculated using the results of these ws0 to wsL, and this becomes the estimated value wc for detecting the white line coordinates w6 of the magnetic field.

Here, a calculation formula for calculating the estimated value of the next white line position coordinate from the three moving average values will be described with reference to FIG.

The time required for one processing routine in the white line detection ECU 20 is Δt, the horizontal axis represents time, and the vertical axis represents C.
The position of the white line detected by the CD camera 10 is taken. Then, consider the case where the vehicle curves to the left as shown in FIG.

The following calculation is performed from the five detected positions w1, w2, w3, w4, w5 obtained for each processing cycle Δt, and the current moving average position wsL, the previous position ws1, and the two-preceding position ws0 are obtained.

Ws0 = (w1 + w2 + w3) / 3 ws2 = (w2 + w3 + w4) / 3 ws3 = (w3 + w4 + w5) / 3 Then, the position two times before the previous position → the difference Δ1 between the previous positions → the current position Δ2, this time → the next predicted If the difference is Δ3,
It may be better to estimate that the change amount of Δ2 → Δ3 is the same as the change amount of Δ1 → Δ2. That is, the processing cycle Δt is minute, and before and after the time Δt,
The steering amount may be the same. Then, if the steering amount is the same, the change amount of the white line detection position is the same. Therefore, as shown in FIG. 11B, if time is plotted on the horizontal axis and differences Δ1 to Δ3 are plotted on the vertical axis, it is estimated that Δ3 is located on the straight line connecting the straight lines Δ1 and Δ2.

Therefore, Δ3 is expressed as follows.

Δ3 = {(Δ2-Δ1) / Δt} · Δt + Δ2 = Δ2-Δ1 + Δ2 Then, wc is expressed as follows, and using this equation,
wc is calculated (S611).

Wc = wsL + Δ3 = wsL + 2 · Δ2-Δ1 = wsL + 2 (wsL-ws1)-(ws1-ws0) = 3 (wsL-ws1) + ws0 Thus, the predicted white line position wLL to be used in the next processing loop. Can be calculated, and the white line can be selected using this, so that accurate white line position detection can always be performed.

Then, it is determined whether the calculated estimated value wc is within a predetermined range (255 or less), and the actual wc is determined (S604 to S606).

On the other hand, the white line position coordinates obtained this time are input to wL as described above, and this value is a 16-bit value. Therefore, this is converted into 8-bit data and converted into a value representing the center position of the lane (S607, S608). Then, since the normal white line detection is performed, the error counter is cleared to 0 (S
609), and the white line position coordinate wLc of the conversion result is output (S610).

Error Processing On the other hand, when the white line detection is not normally performed in the above processing, the error processing is performed as follows.

That is, as shown in FIG. 12, first, the moving average value wsL of this time which cannot be detected or calculated, the detected position wL of this time, the white line position w1 of the previous time, and the predicted white line position w.
The previously calculated predicted value ws1 is substituted for c (S
701). Then, wLc is calculated based on this value (S702, S703), and 1 is added to the error counter (S704). Then, it is determined whether or not the value of the error counter reaches 16, and if it is 16 or less, wL
In addition to outputting c (S706), w in S610
Return to the serial output of Lc. On the other hand, the error counter is 1
If the number is 6 or more, it is considered that the number of times the error continues is a predetermined number or more, and an error code is output (S70).
7) The error counter is cleared to 0 (S708).

Center Priority Method Next, at the start of the operation of the line detection device, the white line along which the vehicle should follow must be selected from the white lines reflected. Therefore, when the operation of the line detection device is started, CC
A white line near the center coordinates of the D linear sensor is selected. This is because, in a normal case, it is considered that the driver often gives an instruction to start the line detection operation when the vehicle is traveling straight ahead. The operation flow of this CCD center priority method will be described with reference to FIG.

First, the number of times that the center-priority method should be performed is decremented by 1 with sc = sc-1 (S801). here,
This variable sc is set to a value of about 6 as an initial setting. As a result, 6 processing loops (Δ
For the time t × 6), the method based on the above-described estimated value is not used, but detection of the white line near the center has priority. Next, j is set to 1 (S802), and it is determined whether j is larger than wc1 (S803). This wc1 is the number of detected left edges (the number of detected right edges is also equal),
If j ≦ wc1, the center coordinates of the white line are detected by the following equation (S804).

Ax = (wn1 [j] + wn2 [j]) / 2 The white line position ax thus calculated is suL.
Compare with. This suL is set to a value about half the number of CCD pixels. Then, this suL is the lower limit value for searching for the minimum white line. Therefore, if ax is smaller than suL, 1 is added to j (S80
6) On the other hand, if ax ≧ suL, then ws0 =
ws1, ws1 = wsL, wsL = ax (S80
7), while updating the value of the moving average, w0 = w1, w
With 1 = wL and wL = ax (S808), the data on the white line coordinates are updated.

Thus, while in the loop of the center priority method, the moving average is not performed, and the white line detection value is also input to the variable for the moving average value.

Then, with wLb = wL / 8, the current detected white line position is converted into an 8-bit value and substituted into the variable wLb (S810). Furthermore, wLc = wLb + coff
As (S811), the width of the lane is 1 from the position of the white line to wLc.
/ 2 Enter the coordinate value of the lane center position away.

On the other hand, when j becomes larger than wc1 in S803, the white line is not detected anymore, so suL = suL-8 is set and the value of suL is decreased (S
812) After widening the detection range and returning the value of sc to sc = sc + 1 (S813), wLc is output (S814).

As described above, in the case of the CCD center priority method, the one near the center is selected from the detected white line coordinates and set as the white line coordinates.

[0108]

As described above, according to the line detecting apparatus of the present invention, the next white line position is predicted from the moving average of the past detected white line positions, and the line detection is performed according to this prediction result. Since the processing target is limited, the processing efficiency is increased, high-speed processing is possible, and it is possible to prevent the vehicle from losing sight of the line along which it should follow.

[Brief description of drawings]

FIG. 1 is a configuration block diagram showing an embodiment of a line detection device according to the present invention.

FIG. 2 is an explanatory diagram for explaining position detection in a CCD camera.

FIG. 3 is a flowchart for explaining a processing operation in a white line detection ECU.

FIG. 4 is a flowchart showing the operation of threshold calculation.

FIG. 5 is a flowchart showing operations of edge detection and binarization processing.

FIG. 6 is a flowchart showing operations of edge detection and binarization processing.

FIG. 7 is a flowchart showing an edge correction operation.

FIG. 8 is a flowchart showing operations of white line coordinate output and white line position prediction.

FIG. 9 is a flowchart showing operations of white line coordinate output and white line position prediction.

FIG. 10 is a flowchart showing operations of white line coordinate output and white line position prediction.

FIG. 11 is an explanatory diagram showing a white line position prediction method.

FIG. 12 is a flowchart showing an operation of error processing.

FIG. 13 is a flow chart showing the operation of the CCD central wired method.

FIG. 14 is an explanatory diagram showing an example of white line position prediction.

[Explanation of symbols]

 10 CCD camera 20 White line detection ECU 24 AD converter 26 CPU

Claims (1)

[Claims] 1. A line detection device mounted on a vehicle for detecting a guideline provided along a road, the camera repeatedly outputting an image of a road in a predetermined range, and each time output from the camera. Line detecting means for processing the image of the line and detecting the guideline, a line position storing means for storing the line positions detected by the line detecting means a plurality of times, and a plurality of line positions stored in the line position storing means. A moving average of the average line position calculation means for calculating a plurality of average line positions according to the passage of time, and a change state of the plurality of line positions according to the passage of time obtained by the average line position calculation means. The line position predicting means for predicting the line position of this time detection, and the detection line closest to the predicted position obtained by this line position predicting means. Line detection apparatus characterized by having a line selection means for selecting.