JP2003157498A - Obstacle warning device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an obstacle warning device, capable of altering the dimensions of a determination area for determining the possibility of a collision between an own vehicle and an object, which is set on an image photographed by a camera, depending on the distance from the vehicle. SOLUTION: An image processing unit obtains a distance where an extracted object collides within a fixed time as an approach determination area setting depending on the obstacle distance (S17). It is determined whether the obtained distance is equal to or longer than L1 or not (S18). When the obtained distance is equal to or larger than L1, the width X of the approach determination area is set to a distance of X1 from the left car body side (S19). When the obtained distance is shorter than L1, it is determined whether the obtained distance is equal to or longer than L2 or not (S20). When the obtained distance L2 is equal to or longer than L2, the width X of the approach determination area is set to a distance of X2 (X1>X2) from the left car body side (S21). When the obtained distance is equal to or shorter than L2, the width X of the approach determination area is set to a distance of X3 (X2>X3) from the left car body side (S22).

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an obstacle warning device for detecting the presence of an obstacle on a traveling path of a vehicle from an image obtained by an image pickup means.

[0002]

2. Description of the Related Art Conventionally, an image of one or a plurality of infrared cameras mounted in front of a vehicle can be visually observed from a driver's seat in order to notify the driver of an obstacle on a road such as a vehicle or a pedestrian. There are those that are displayed at various positions to assist the driver's forward vision. The image displayed to the driver is, for example, a NAVIDisplay installed on the console of the own vehicle or a HUD (Head Up Display) that displays information at a position in the front window that does not obstruct the driver's forward visibility, and further, the traveling of the own vehicle. It is displayed on an image display device such as a meter-integrated display which is integrated with a meter that represents the state by numbers.
Further, as a peripheral monitoring device for photographing the environment around the vehicle with a camera and displaying it to the driver, for example, a device as disclosed in Japanese Patent Laid-Open No. 2001-6096 is known. This perimeter monitoring device detects and displays living bodies such as pedestrians and animals existing in the vicinity of the vehicle from an infrared image taken by an imaging means provided in the vehicle. To this end, the surroundings monitoring device calculates the distance between the object around the vehicle and the own vehicle from the images obtained by the two infrared cameras, and further moves the object based on the position data of the object obtained in time series. The vector is calculated. Then, the target object that is likely to collide with the host vehicle is extracted and displayed from the relationship between the traveling direction of the host vehicle and the movement vector of the target vehicle.

[0003]

In the conventional device as described above, when there is an object on the traveling line of the vehicle, it is judged that there is a high possibility of collision and an alarm is issued as an obstacle. , An approach determination area in which the vehicle width is extended with reference to the left and right vehicle sides of the host vehicle is set. Thereby, for example, the approach determination area on the left side of the vehicle traveling direction in a traffic system in which the vehicle adopts left-hand traffic is fixed with respect to the vehicle body side, and an alarm is given in the approach determination area,
Depending on the distance to the obstacle, there may be a gap between the driver's lateral safety margin (the amount of deviation from the vehicle running line and the lateral direction). Specifically, when the distance to the obstacle is short, the spatial distance resolution for the driver to recognize the obstacle position is high, so the positional relationship between the own vehicle and the obstacle can be accurately recognized, and the own vehicle and the obstacle are It is possible to accurately determine the side safety margin that does not collide or is not dangerous. However, if the distance to the obstacle is too long, the spatial distance resolution of the driver may be reduced, and the positional relationship between the vehicle and the obstacle may not be recognized accurately, and the side safety margin should be set larger than the short distance. There was a tendency.

The present invention has been made in view of the above-mentioned problems, and the size of the determination area for determining the possibility of collision between the vehicle and the object set on the image captured by the camera is set from the vehicle. It is an object of the present invention to provide an obstacle warning device that changes depending on the distance.

[0005]

In order to solve the above-mentioned problems, an obstacle warning device according to the invention of claim 1 determines a collision between a vehicle and an object on the basis of image information obtained by an image pickup means. In an obstacle warning device for warning an obstacle in the warning judgment area to be performed, the distance from the vehicle deviates from the width of the approach judgment area which is set in the warning judgment area and is used for warning due to the presence of the object. It is characterized in that it further comprises a judgment area setting means for expanding and setting.
In the obstacle warning device having the above configuration, the determination area setting means sets the determination area according to the visual characteristics of the driver of the vehicle by expanding the size of the determination area as the distance from the vehicle increases. be able to.

An obstacle warning device according to a second aspect of the present invention is the obstacle warning device according to the first aspect, wherein the determination area setting means is provided in a sidewalk direction adjacent to the traveling lane of the vehicle in the determination area. Characterized by expanding the width. The obstacle warning device having the above configuration can change the size of the judgment area in the sidewalk direction in which the living body is likely to exist in the judgment area by the judgment area setting means.

[0007]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing the configuration of an obstacle warning device according to an embodiment of the present invention.
In the present embodiment, a case where a vehicle equipped with an obstacle warning device is used in a traffic format that employs face-to-face traffic in which the vehicle travels to the left will be described as an example. In FIG. 1, reference numeral 1 denotes an image processing unit including a CPU (central processing unit) for controlling the obstacle warning device of the present embodiment, and two infrared cameras 2R and 2L capable of detecting far infrared rays. A yaw rate sensor 3 for detecting a yaw rate of the vehicle, a vehicle speed sensor 4 for detecting a traveling speed (vehicle speed) of the vehicle, and a brake sensor 5 for detecting a brake operation are connected. As a result, the image processing unit 1 detects a moving object such as a pedestrian or an animal in front of the vehicle from the infrared image of the periphery of the vehicle and a signal indicating the traveling state of the vehicle, and determines that the possibility of collision is high. Give an alarm to.

Further, the image processing unit 1 includes a speaker 6 for issuing an alarm by voice and infrared cameras 2R, 2R.
For example, a display integrated with a meter or a display integrated with a meter that displays a running state of the vehicle by a numerical value for displaying an image captured by L so that the driver of the vehicle recognizes an object having a high risk of collision. NAVIDisplay installed on the console of the vehicle, and HUD that displays information in a position that does not obstruct the driver's forward view of the front window
An image display device 7 including (Head Up Display) 7a and the like is connected.

The image processing unit 1 includes an A / D conversion circuit for converting an input analog signal into a digital signal, an image memory for storing a digitized image signal, a CPU (central processing unit) for performing various arithmetic processes, and a CPU. RAM (Random A) used to store data during calculation
ccess Memory), ROM (Read Only Memor) that stores programs executed by the CPU, tables, maps, etc.
y), an output circuit for outputting a driving signal for the speaker 6, a display signal for the HUD 7a, etc., and the infrared camera 2
The output signals of the R, 2L, yaw rate sensor 3, vehicle speed sensor 4, and brake sensor 5 are converted into digital signals and input to the CPU.

Further, as shown in FIG. 2, the infrared camera 2
R and 2L are arranged in the front part of the host vehicle 10 at positions substantially symmetrical to the center of the host vehicle 10 in the vehicle width direction.
The optical axes of the two infrared cameras 2R and 2L are parallel to each other, and they are fixed so that their heights from the road surface are equal. The infrared cameras 2R and 2L have a characteristic that the output signal level thereof increases (luminance increases) as the temperature of the object increases. Also, HUD7a
Is provided so that the display screen is displayed at a position in the front window of the host vehicle 10 that does not hinder the driver's forward visibility.

Next, the operation of this embodiment will be described with reference to the drawings. 3 and 4 are flowcharts showing a processing procedure in the image processing unit 1 of the obstacle warning device according to the present embodiment. First, the image processing unit 1
Acquires an infrared image that is an output signal of the infrared cameras 2R and 2L (step S1), performs A / D conversion (step S2), and stores the grayscale image in an image memory (step S3). Here, the right image is obtained by the infrared camera 2R, and the left image is obtained by the infrared camera 2L. Further, in the right image and the left image, the horizontal position of the same target object on the display screen is displaced, and thus the distance to the target object can be calculated from this displacement (parallax).

Next, the right image obtained by the infrared camera 2R is used as a reference image, and the image signal is binarized, that is, the area brighter than the brightness threshold ITH is set to "1" (white) and the dark area is set to " A process of setting it to "0" (black) is performed (step S4). FIG. 5A shows a grayscale image obtained by the infrared camera 2R, and by binarizing the grayscale image, an image as shown in FIG. 5B is obtained. Note that, in FIG. 5B, for example, an object surrounded by a frame of P1 to P4 is an object displayed as white on the display screen (hereinafter, referred to as “high brightness area”). When binarized image data is acquired from the infrared image, a process of converting the binarized image data into run length data is performed (step S5).

FIG. 6 (a) is a diagram for explaining this, and in this figure, the regions turned white by binarization are shown as lines L1 to L8 at the pixel level. Line L1
All of L8 to L8 have a width of one pixel in the y direction, and are actually arranged in the y direction without any gap, but they are shown separated for the sake of explanation. The lines L1 to L8 are
2 pixels, 2 pixels, 3 pixels, 8 pixels in the x direction,
It has a length of 7 pixels, 8 pixels, 8 pixels, and 8 pixels.
The run length data includes the lines L1 to L8 as coordinates of the start point of each line (the left end point of each line) and the length (pixel number) from the start point to the end point (the right end point of each line). It is shown. For example, the line L3 is (x3, y
5), (x4, y5) and (x5, y5), the run length data is (x3, y).
5, 3).

Next, the object is labeled from the image data converted into the run length data (step S).
By performing 6), the process of extracting the object is performed (step S7). That is, among the lines L1 to L8 converted into run length data, as shown in FIG. 6B, the lines L1 to L3 having a portion overlapping in the y direction are regarded as one object 1, and the lines L4 to L8 are set to one. Regarded as two objects 2,
Object labels 1 and 2 are added to the run length data.
By this processing, for example, the high-brightness regions shown in FIG. 5B are recognized as the objects 1 to 4, respectively.

After the extraction of the object is completed, the process shown in FIG.
As shown in (c), the center of gravity G and the area S of the extracted target object
And the aspect ratio ASPECT of the circumscribed quadrangle shown by the broken line is calculated (step S8). Here, the area S is calculated by integrating the lengths of the run length data for the same object by the following formula (1). The run length data of the object of label A is (x [i], y [i], run
[I], A) (i = 0, 1, 2, ... N-1),

[Equation 1] Further, the coordinates (xc, yc) of the center of gravity G of the object A are calculated by the following equations (2) and (3) in consideration of the length of the run length data.

[Equation 2] Further, the aspect ratio ASPECT is calculated as the ratio Dy / Dx between Dy and Dx shown in FIG. As shown in the equations (1), (2), and (3), the run length data is represented by the number of pixels (the number of coordinates) run [i], so the actual length is "-1". There is a need. Further, the position of the center of gravity G may be replaced by the position of the center of gravity of the circumscribing quadrangle.

After the center of gravity of the object, the area, and the aspect ratio of the circumscribed quadrangle can be calculated, the object is time-tracked, that is, the same object is recognized for each sampling cycle (step S9). In the time tracking, the time t as an analog quantity is discretized in the sampling cycle as k, and
When the objects A and B are extracted at time k as shown in (a), the identities of the objects C and D extracted at time (k + 1) and the objects A and B are determined. Specifically, when the following identity determination conditions 1) to 3) are satisfied, it is determined that the objects A and B and the objects C and D are the same, and the objects C and D are respectively the objects. By changing the labels to A and B, time tracking is performed.

1) Object i (= A, B) at time k
The barycentric position coordinates on the image of (xi (k),
yi (k)) and the object j at time (k + 1)
The coordinates of the position of the center of gravity on the image of (= C, D) are represented by (xj (k
+1), yj (k + 1)), | xj (k +
1) -xi (k) | <Δx | yj (k + 1) -yi
(K) | <Δy. However, Δx and Δy are allowable values of the amount of movement on the image in the x direction and the y direction, respectively. 2) Let Si (k) be the area of the object i (= A, B) on the image at time k, and let Sj (be the area of the object j (= C, D) on the image at time (k + 1). k + 1)
Then, Sj (k + 1) / Si (k) <1 ± ΔS. However, ΔS is the allowable value of the area change.
3) Let ASPECTi (k) be the aspect ratio of the circumscribed quadrangle of the object i (= A, B) at time k, and set it to time (k + 1).
Assuming that the aspect ratio of the circumscribed quadrangle of the object j (= C, D) is ASPECTj (k + 1), ASPECTj
(K + 1) / ASPECTi (k) <1 ± ΔASPEC
Be T. However, ΔASPECT is the allowable value of the aspect ratio change.

For example, comparing FIGS. 7 (a) and 7 (b), the size of each target object on the image is large, but the target object A and the target object C have the above-described identity determination conditions. And the object B and the object D satisfy the above-described identity determination condition, the objects C and D are recognized as the objects A and B, respectively. Each object (of the center of gravity) recognized in this way
The position coordinates are stored in the memory as time-series position data and used in the subsequent arithmetic processing. The processes of steps S4 to S9 described above are executed for the binarized reference image (the right image in this embodiment). Next, the vehicle speed VCAR detected by the vehicle speed sensor 4 and the yaw rate YR detected by the yaw rate sensor 3 are read and the yaw rate YR is integrated over time to calculate the turning angle θr of the host vehicle 10 as shown in FIG. (Step S1
0).

On the other hand, in parallel with the processing in steps S9 and S10, in steps S11 to S13, processing for calculating the distance z between the object and the vehicle 10 is performed. Since this calculation requires a longer time than steps S9 and S10, it is executed at a cycle longer than steps S9 and S10 (for example, a cycle about three times the execution cycle of steps S1 to S10). First, by selecting one of the objects tracked by the binarized image of the reference image (right image), the search image R1 from the right image is selected as shown in FIG.
(Here, the entire area surrounded by the circumscribed quadrangle is used as the search image) is extracted (step S11).

Next, a search area for searching an image (hereinafter referred to as "corresponding image") corresponding to the search image from the left image is set, and correlation calculation is executed to extract the corresponding image (step S12). Specifically, as shown in FIG. 9B, a search region R2 is set in the left image according to the coordinates of each vertex of the search image R1, and a high correlation with the search image R1 is set in the search region R2. The brightness difference sum total value C (a, b) indicating the brightness is calculated by the following equation (4), and the area where the sum total value C (a, b) is minimum is extracted as the corresponding image. Note that this correlation calculation is performed using a grayscale image instead of a binarized image. If there is past position data for the same object, a region R2a (shown by a broken line in FIG. 9B) narrower than the search region R2 is set as the search region based on the position data.

[Equation 3] Here, IR (m, n) is the search image R1 shown in FIG.
The brightness value at the position of coordinates (m, n) in
m−M, b + n−N) is the coordinates (a, b) in the search area
The local region R3 having the same shape as the search image R1 with the base point
It is the luminance value at the position of the coordinates (m, n) within. The position of the corresponding image is specified by changing the coordinates (a, b) of the base point and obtaining the position where the luminance difference summation value C (a, b) is the minimum.

Since the search image R1 and the corresponding image R4 corresponding to this object are extracted by the processing of step S12, as shown in FIG. 11, the center of gravity position of the search image R1 and the image center line are next extracted. The distance dR (the number of pixels) from the LCTR and the distance dL (the number of pixels) between the center of gravity of the corresponding image R4 and the image center line LCTR are obtained and applied to the following equation (5) to determine the own vehicle 10 and the object. To calculate the distance z (step S
13).

[Equation 4] Here, B is the baseline length, the horizontal distance between the center position of the image sensor of the infrared camera 2R and the center position of the image sensor of the infrared camera 2L (the distance between the optical axes of both infrared cameras), and F is the infrared camera 2R. , 2L is the focal length of the lens, p is the pixel interval in the image sensor of the infrared camera 2R, 2L, and Δ
d (= dR + dL) is the amount of parallax.

When the calculation of the turning angle θr in step S10 and the calculation of the distance to the object in step S13 are completed, the coordinate z (x, y) in the image and the distance z calculated by the equation (5) are calculated by the following equation (6). ), And transforms into real space coordinates (X, Y, Z) (step S14). Here, the real space coordinates (X, Y, Z) are as shown in FIG.
The position of the midpoint of the mounting position of the infrared cameras 2R, 2L (the position fixed to the vehicle 10) is set as the origin O, and is defined as shown in the figure. The coordinates in the image are the origin of the center of the image and the horizontal direction is x , And the vertical direction is defined as y.

[Equation 5] Here, (xc, yc) is the coordinate (x, y) on the right image.
Is the mounting position of the infrared camera 2R and the real space origin O
Based on the relative positional relationship between the real space origin O and the center of the image, the coordinates are converted into virtual coordinates in the virtual image. Further, f is the ratio of the focal length F and the pixel interval p.

Further, when the real space coordinates are obtained, turning angle correction for correcting the positional deviation on the image due to the turning of the vehicle 10 is performed (step S15). As shown in FIG. 8, when the host vehicle 10 turns, for example, to the left by the turning angle θr during the period from time k to (k + 1), the turning angle correction is performed as shown in FIG.
As shown in (4), it is shifted in the x direction by Δx, and this is the process for correcting this. Specifically, the real space coordinates (X, Y, Z) are applied to the following equation (7) to obtain the corrected coordinates (Xr, Yr,
Zr) is calculated. Calculated real space position data (Xr,
Yr, Zr) is stored in the memory in association with each object. In the following description, the coordinates after the turning angle correction are displayed as (X, Y, Z).

[Equation 6]

After the turning angle correction for the real space coordinates is completed, next, for the same object, N pieces of real space position data after the turning angle correction (for example, about N = 10) obtained within the monitoring period of ΔT. ) That is, the approximate straight line LMV corresponding to the relative movement vector between the object and the vehicle 10 is obtained from the time series data (step S16). Specifically, a direction vector L = (lx, l indicating the direction of the approximate straight line LMV
y, lz) (| L | = 1), a straight line represented by the following equation (8) is obtained.

[Equation 7] Here, u is a parameter that takes an arbitrary value, and Xav,
Yav and Zav are the average value of the X coordinate, the average value of the Y coordinate, and the average value of the Z coordinate of the real space position data string, respectively. Note that the equation (8) becomes the following equation (8a) if the parameter u is deleted. (X-Xav) / lx = (Y-Yav) / ly = (Z-Zav) / lz (8a)

Further, for example, P (0), P (1), P
When (2), ..., P (N-2), P (N-1) indicate the time series data after turning angle correction, the approximate straight line LMV is the average position coordinate Pav = (Xav, Ya
v, Zav), and the average value of the square of the distance from each data point is obtained as a minimum straight line. Here, the numerical value in parentheses attached to P indicating the coordinates of each data point indicates that the data increases as the value increases.
For example, P (0) indicates the latest position coordinate, P (1) indicates the position coordinate one sampling period before, and P (2) indicates the position coordinate two sampling periods before.

Next, the latest position coordinate P (0) = (X
(0), Y (0), Z (0)) and position coordinates P (N-1) = (X (N-) before (N-1) samples (before time ΔT).
1), Y (N-1), Z (N-1)) to the approximate straight line LMV
Correct to the upper position. Specifically, in the formula (8a), Z
By applying the coordinates Z (0) and Z (N-1), that is, by the following formula (9), the corrected position coordinates Pv
(0) = (Xv (0), Yv (0), Zv (0)) and Pv (N-1) = (Xv (N-1), Yv (N-1),
Zv (N-1)) is calculated.

[Equation 8]

The position coordinates Pv (N- calculated by the equation (9)
A relative movement vector is obtained as a vector from 1) to Pv (0). As described above, the influence of the position detection error is reduced by calculating the relative movement vector by calculating the approximate straight line that approximates the relative movement locus of the object with respect to the own vehicle 10 from the plurality (N pieces) of data within the monitoring period ΔT. Therefore, it is possible to more accurately predict the possibility of collision with the object. Further, when the relative movement vector is obtained in step S16, next, in order to determine the possibility of collision between the vehicle 10 and the detected object, an alarm is issued within an area that can be monitored by the infrared cameras 2R and 2L. Set the judgment area.

As shown in FIG. 13, the alarm determination area is, for example, an outer triangular area AR0 indicated by a thick solid line, which is an area that can be monitored by the infrared cameras 2R and 2L, and Z1 = Vs in the area AR0. Areas AR1, AR2, and AR3 that are closer to the host vehicle 10 than xT are set as alarm determination areas. Here, T is a margin time, and is intended to determine the possibility of a collision by a time T before the predicted collision time. Therefore, the allowance time T is set to, for example, about 2 to 5 seconds. Further, the area AR1 is an area having a predetermined width on both sides of the axis of the vehicle width direction central portion of the own vehicle 10, and the approach is determined to have a very high possibility of collision if the object continues to be present. This is a judgment area. On the other hand, the area AR2,
AR3 is an area in which the absolute value of the X coordinate is larger than that of the approach determination area AR1 (outer side of the approach determination area AR1), and the approach collision determination to be described later is performed on an object in this area, so It is called a judgment area. Note that these regions have a predetermined height H that defines the range in the Y direction, that is, the height direction. The predetermined height H is
For example, it is set to about twice the vehicle height of the host vehicle 10.

Explaining how to specifically determine the warning determination area, the image processing unit 1 first determines the distance at which the extraction target collides within a certain time as the approach determination area setting based on the obstacle distance (step S17). . Next, it is determined whether the obtained distance is L1 or more (step S18).
When the obtained distance is equal to or greater than L1 in step S18 (YES in step S18), the width X of the approach determination area AR1 is set to X1 from the left vehicle body side as shown in FIG.
To the distance (left vehicle side + X1) (step S1)
9). If the obtained distance is shorter than L1 in step S18 (NO in step S18), it is determined whether the obtained distance is L2 or more (step S2).
0).

In step S20, when the obtained distance is L2 or more (YES in step S20),
As shown in FIG. 13, the width X of the approach determination area AR1 is set to a distance X2 from the left vehicle body side (left vehicle body side + X2) (step S21). Further, in step S20, when the obtained distance is shorter than L2 (N in step S20
O), as shown in FIG. 13, the width X of the approach determination area AR1
Is set to a distance X3 from the left vehicle body side (left vehicle body side + X3) (step S22). In this way, by the processing from step S17 to step S22, the approach determination area AR1 is set using the actual space distance from the vehicle 10 side based on the distance at which the extraction target collides within a fixed time.

Further, steps S17 to S22
When the setting of the approach determination area AR1 is performed by the processing of step 1, the collision determination processing of determining the possibility of collision with the detected object is performed (step S23). Step S2
As a result of performing the collision determination process in 3, when it is determined that there is no possibility of collision between the vehicle 10 and the detected object (NO in step S23), the process returns to step S1 and the above process is repeated. When it is determined that there is a possibility of collision between the vehicle 10 and the detected object as a result of the collision determination process in step S23 (step S2).
3), the determination process (step S24) and the approach collision determination process (step S25) of whether or not the vehicle is within the approach determination region for determining the possibility of collision with the detected object are performed in more detail. . Hereinafter, as shown in FIG. 14, from the direction of approximately 90 ° with respect to the traveling direction of the host vehicle 10, the speed V
Taking as an example the case where there is an animal 20 advancing at p, the collision determination process, the determination process of whether or not it is within the approach determination region, and the approach collision determination process will be described in detail.

<Collision Judgment Process> First, the image processing unit 1 calculates the following equation (1) when the animal 20 approaches the distance Zv (0) from the distance Zv (N-1) during the time ΔT.
0) is used to calculate the relative velocity Vs in the Z direction, and the collision determination process is performed. The collision determination process is performed by the following equations (11) and (1
When 2) is established, it is a process of determining that there is a possibility of collision. Vs = (Zv (N−1) −Zv (0)) / ΔT ... (10) Zv (0) / Vs ≦ T ... (11) | Yv (0) | ≦ H ... (12) ) Here, Zv (0) is the latest distance detection value (v is added to indicate that the data is corrected by the approximate straight line LMV, but the Z coordinate is the same value as before correction). And Zv (N-1) is a distance detection value before time ΔT. Further, T and H are respectively the above-mentioned allowance time and Y
Direction, that is, a predetermined height that defines a range in the height direction.

<Determination Processing for Whether or not it is Within Approach Determination Area> Here, the object is step S19 or step S20.
It is determined whether or not it exists within the approach determination area AR1 set in. If the object exists in the approach determination area AR1, it is determined that the possibility of collision with the host vehicle 10 is extremely high if the object continues to exist. Further, when an object exists in the approach determination area AR2 or AR3 whose absolute value of the X coordinate is larger than that of the approach determination area (laterally outside the approach determination area), the following approach collision determination is performed.

<Incoming Collision Judgment Process> Specifically, the incoming collision judgment process is xc which is the latest x coordinate on the image.
(0) (letter c is added to indicate that the center position of the image is corrected to match the real space origin O as described above) and the x coordinate before time ΔT. x
It is determined whether or not the difference from c (N-1) satisfies the following equation (13), and if so, it is determined that the possibility of collision is high.

[Equation 9] Note that, as shown in FIG. 14, when there is an animal 20 traveling from a direction of approximately 90 ° with respect to the traveling direction of the vehicle 10, Xv (N-1) / Zv (N-1) = Xv ( 0) /
When it is Zr (0), in other words, the ratio Vp / Vs of the animal velocity Vp and the relative velocity Vs / Xr (N-1) / Zr (N
In the case of -1), the azimuth angle θd for viewing the animal 20 from the vehicle 10 is constant, and the possibility of collision is high. Formula (13)
Is to determine this possibility in consideration of the vehicle width α of the vehicle 10.

Therefore, in both the determination processing (step S24) and the approach collision determination processing (step S25) whether or not the vehicle is within the approach determination area, there is a possibility of collision between the host vehicle 10 and the detected object. If it is determined that there is not (NO in step S24 and then NO in step S25
Process), the process returns to step S1 and the above-described processing is repeated. Further, when it is determined that there is a possibility of collision between the vehicle 10 and the detected object by one of the determination processing whether the vehicle is in the approach determination area and the approach collision determination processing (YES in step S24, Or YE in step S25
S), and proceeds to the alarm output determination process of step S26.

In step S26, an alarm output determination process, that is, determination of whether or not to output an alarm, is performed as follows (step S26). In the alarm output determination process, first, it is determined from the output BR of the brake sensor 5 whether or not the driver of the vehicle 10 is performing a brake operation. If the driver of the host vehicle 10 is performing a braking operation, the acceleration Gs (the deceleration direction is positive) generated thereby is calculated, and if this acceleration Gs is larger than the predetermined threshold value GTH, the brake is applied. When it is determined that the collision is avoided by the operation, the alarm output determination process ends (NO in step S26), the process returns to step S1, and the above-described process is repeated.
As a result, when an appropriate brake operation is performed, an alarm is not issued, and it is possible to prevent the driver from getting annoyed.

When the acceleration Gs is less than or equal to the predetermined threshold value GTH, or when the driver of the own vehicle 10 is not performing the brake operation, the process immediately proceeds to step S27 (YES in step S26) to contact the object. Therefore, an audio alarm is issued via the speaker 3 (step S27), and an image obtained by, for example, the infrared camera 2R is output to the image display device 7 to detect an approaching object. The image is displayed as a highlighted image for the driver of the vehicle 10 (step S28). here,
The predetermined threshold GTH is defined by the following equation (14). This is because when the acceleration Gs during the brake operation is maintained as it is, the vehicle 10 travels at a travel distance equal to or less than the distance Zv (0).
Is a value corresponding to the condition that stops.

[Equation 10]

In the above-described embodiment, an example of monitoring the front of the host vehicle is shown, but any direction such as the rear of the host vehicle may be monitored. Further, the present invention is not limited to the above-described embodiment, but various modifications can be made. For example, in the above-mentioned embodiment, the infrared camera is used as the image pickup means for obtaining the image of the object, but as shown in, for example, Japanese Patent Laid-Open No. 9-226490, only normal visible light can be detected. You may use a TV camera. However, since the infrared camera can be used to simplify the extraction processing of animals or moving vehicles, it is possible to realize a computing device having a relatively low computing capability. In addition, when driving on a road with few street lights at night, considering the glare to oncoming vehicles and the like, the distance recognizable by irradiation with headlights is 100
Shorter than a night vision camera that uses an infrared camera that can recognize up to the [m] range. Therefore, by using a night vision camera having a long range, it is possible to perform the same recognition even during nighttime driving as during daytime driving.

Further, in the above-described embodiment, the case where the vehicle equipped with the obstacle warning device is used in the traffic form adopting the face-to-face traffic in which the vehicle drives on the left side has been described. When a vehicle equipped with is used in a traffic format in which the vehicle uses right-to-side traffic, the "left body side" and "right body side" of the vehicle described above are referred to as "left body side" and "right body side", respectively. It should be read as "left vehicle side". Further, in the present embodiment, the image processing unit 1 includes a determination area setting unit. More specifically, S17 to S22 in FIG. 4 correspond to the determination area setting means.

As described above, the obstacle warning device of the present embodiment obtains the distance at which the object to be extracted collides within a fixed time in the approach determination area, and the distance is the own vehicle 10
The farther away from the vehicle 10, the more likely it is that an obstacle such as a pedestrian will enter the lane of the vehicle 10 from the sidewalk side of the vehicle 10 (or the left vehicle body side in the case of the left-hand traffic type). It is determined that the driver of the vehicle 10 cannot accurately recognize the positional relationship with the obstacle. Then, the width X of the approach determination area AR1 is extended farther from the left vehicle body side as the distance at which the extraction target collides within a certain time is farther from the own vehicle 10, so that the extraction object exists in an area far from the own vehicle 10. The over-alarm can be suppressed in the vicinity of the vehicle 10 where the driver can accurately recognize the positional relationship of the obstacle while improving the detection rate of the obstacle that is likely to start moving from a substantially stationary state. The effect is obtained. Further, by changing only the width of the approach determination area AR1 on the sidewalk side, it is possible to obtain an effect that it is possible to suppress issuing an alarm to an object other than the alarm target, such as an oncoming vehicle.

[0041]

As described above, according to the obstacle warning device of the first aspect, the driver of the vehicle is extended by expanding the size of the determination area as the distance from the vehicle is increased by the determination area setting means. It is possible to set the determination area according to the visual characteristics of. Therefore, in the area where the driver of the vehicle can accurately determine the lateral safety margin, that is, in the area near the vehicle, the size of the determination area is set to the minimum necessary size, and the vehicle driver accurately determines the lateral safety margin. Difficult areas,
That is, by increasing the size of the determination region in a region farther from the vehicle, it is possible to suppress an over-alarm in a region near the vehicle and to perform a sufficient alarm determination in a region distant from the vehicle.

According to the obstacle warning device of the second aspect, the size of the judgment area in the sidewalk direction in which there is a high possibility that a living body exists particularly in the judgment area can be changed by the judgment area setting means. . Therefore, while sufficiently performing the warning judgment on the sidewalk where the living body is likely to exist, an operation that recognizes an object other than the warning target such as an oncoming vehicle existing on the opposite lane side on the opposite side as an obstacle and issues a warning The effect of being able to suppress is obtained.

[Brief description of drawings]

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

FIG. 2 is a diagram showing mounting positions of an infrared camera, a sensor, a display and the like in a vehicle.

FIG. 3 is a flowchart showing the overall operation of the obstacle warning device of the same embodiment.

FIG. 4 is a flowchart showing the overall operation of the obstacle warning device of the same embodiment.

FIG. 5 is a diagram showing a grayscale image obtained by an infrared camera and a binarized image thereof.

FIG. 6 is a diagram showing conversion processing to run length data and labeling.

FIG. 7 is a diagram showing time tracking of an object.

FIG. 8 is a diagram showing a turning angle correction of an object image.

FIG. 9 is a diagram showing a search image in the right image and a search area set in the left image.

FIG. 10 is a diagram showing a correlation calculation process for a search area.

[Fig. 11] Fig. 11 is a diagram illustrating a method of calculating an object parallax in calculating an object distance.

FIG. 12 is a diagram showing a displacement of an object position on an image caused by turning of a vehicle.

FIG. 13 is a diagram showing an area division in front of the vehicle.

FIG. 14 is a diagram showing a case where a collision easily occurs.

[Explanation of symbols]

1 Image processing unit 2R, 2L infrared camera 3 Yaw rate sensor 4 vehicle speed sensor 5 Brake sensor 6 speakers 7 Image display device 10 own vehicle S17 to S22 determination area setting means

Front page continuation (51) Int.Cl. ⁷ identification code FI theme code (reference) G06T 7/60 180 G06T 7/60 180B G08B 21/00 G08B 21/00 E H04N 7/18 H04N 7/18 J (72 ) Inventor Shinji Nagaoka 1-4-1 Chuo, Wako City, Saitama Prefecture Honda R & D Co., Ltd. (72) Inventor Hiroshi Hattori 1-4-1 Chuo, Wako City Saitama Prefecture F-term in Honda R & D Co., Ltd. (Reference) 5B057 AA16 CH01 DA06 DA15 DA16 DC30 5C054 CA05 CC05 CH02 EA05 EB05 FA00 FC01 FC05 FC12 FD07 FE09 FE28 FF03 FF06 HA30 5C086 AA52 BA22 CA28 CB36 DA02 EA40 FA02 5H180 AA01 CC02 BA06 LL02 BA07 LL01 BA02 BA04 LL01 BA02

Claims (2)

[Claims] 1. An obstacle warning device for warning an obstacle in an alarm judgment area for judging a collision between a vehicle and an object based on image information obtained by an image pickup means, wherein the obstacle warning device is set in the warning judgment area. An obstacle warning device comprising a judgment area setting means for setting the width of the approach judgment area for issuing an alarm due to the presence of the target object so as to be expanded as the distance from the vehicle increases. 2. The obstacle warning device according to claim 1, wherein the judgment area setting means expands the width in the sidewalk direction adjacent to the traveling lane of the vehicle in the judgment area.