JP3939580B2 - Obstacle alarm device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an obstacle alarm device that issues an alarm by detecting an object that is likely to affect the running of a vehicle from an image taken by an imaging means.
[0002]
[Prior art]
Conventionally, as an apparatus for extracting an object such as a pedestrian having a possibility of collision with a vehicle from an image around the vehicle captured by an imaging means such as an infrared camera and providing the information to the driver of the vehicle. For example, there exists a thing of Unexamined-Japanese-Patent No. 2001-6096.
In this apparatus, the three-dimensional position of the area centroid is calculated for a binarized object obtained by binarizing an image around the vehicle captured by the infrared camera, and the time change of the three-dimensional position of the area centroid is calculated. From this, the relative movement vector of the binarized object is obtained. Further, from the obtained relative movement vector, the relative distance and the relative speed between the vehicle and an object such as a pedestrian are determined, and the possibility of a collision with the vehicle is determined. Then, the object that is determined to possibly collide with the vehicle is displayed on the image display device as a real image with highlighting, and is notified to the driver.
[0003]
[Problems to be solved by the invention]
However, in the conventional apparatus, the object shape extracted from the image is not necessarily stable due to the element resolution of the imaging means, the influence of the background, and the like. In particular, in the case of a method of extracting an object by binarizing an infrared image, as the distance between the vehicle and the object decreases, the difference in the thermal characteristics of each part of the object causes a difference in the captured infrared image. There is a case where one object is separated into a plurality of objects and is regarded as different objects. At this time, any one of the separated objects is recognized as a target object, and the relative movement vector is determined by tracking the time change of the three-dimensional position from the deviation of the area centroid position due to the separation. When obtained, the relative distance and the relative speed change in the relative movement vector regardless of the stationary object.
[0004]
Specifically, for example, the time variation of the object position relative to the host vehicle 10 at the origin O as shown in FIG. 9 will be described with reference to the top view. In FIG. The object extracted from the image is OBJ [t], {t = 0, 1,... N−1}, where t = 0 is currently extracted, and t = N−1 is extracted in the past. The object. In FIG. 9, it is assumed that the object is separated into A and B at time 0, and A is recognized as OBJ [0] as time-series data. Then, the relative movement vector 11 indicates a relative movement vector calculated from the time change of the three-dimensional position of the area centroid 12 of OBJ [t], {t = 0, 1,... N−1}.
At this time, since the relative movement vector 11 has an inward component that enters, even if OBJ [t], {t = 0, 1,... N−1} is a stationary object. There is a problem that it may be judged as an object having an approaching movement.
[0005]
The present invention has been made in view of the above problems, and appropriately recognizes whether or not the current object is the same as a past object, and displays an object display that hinders accurate object recognition by the driver. An object of the present invention is to provide an obstacle alarm device that can be prevented.
[0006]
[Means for Solving the Problems]
In order to solve the above-mentioned problem, the obstacle alarm device according to the invention of claim 1 detects an object from an image obtained by two image pickup means and detects an object that may affect the traveling of the vehicle. the obstacle alarm device for a vehicle that emits, by about the current object captures the past the past object captured currently, comparing a position coordinates of the right and left edges of these past object and present the object, An overlap determination unit that determines an overlap between the past object and the current object in the traveling direction of the vehicle, and the overlap determination unit determines that the past object and the current object overlap each other It is characterized in that the current object was an entry object determining means for determining that it is not the ingress object.
The obstacle alarm device having the above-described configuration uses the same object determination means, and from the position coordinates of the left and right edges of the object captured in time series, the object tracked in the past and the object currently extracted By determining whether or not they are the same object, they can be recognized as one object if they are the same object, and the possibility of affecting the traveling of the vehicle can be verified.
According to a second aspect of the present invention, there is provided an obstacle alarm device according to the first aspect of the present invention, wherein the obstacle alarm device according to the first aspect detects an object that may affect the traveling of the vehicle from the image obtained by the imaging means. And an alarm means for issuing an alarm, wherein the alarm means excludes the current object that is determined not to be an entry object by the entry object determination means from the alarm object.
Furthermore, the obstacle alarm device according to claim 3 is the obstacle alarm device according to claim 1 or 2, wherein the overlap determining means captures position coordinates of right and left edges of the plurality of past objects in time series. If the position coordinates of the left and right edges of the current object are included in the space of the past object in comparison with the position coordinates of the left and right edges of the current object, the past object and the current object overlap. It is determined that
The obstacle alarm device according to claim 4 is the obstacle alarm device according to claim 1 or 2, wherein the overlap determination means at least each time as a feature quantity of the past object and the current object. Based on the distance of the object, the left and right edge coordinates on the screen, the focal length and the pixel pitch of the imaging means, the most left edge coordinate and the most right edge coordinate in real space at each time Further, the leftmost position coordinate and the rightmost position coordinate are calculated from the extreme right edge coordinate and the extreme left edge coordinate in the real space at each calculated time, respectively, and the position coordinate in the real space is calculated. If the size of each of the extreme right edge coordinate, the extreme left edge coordinate, the rightmost position coordinate, and the leftmost position coordinate increases toward the front of the image in the right direction, The relationship between the leftmost position coordinate of the object and the outermost left edge coordinate of the current object, and the relationship between the rightmost position coordinate of the past object and the outermost left edge coordinate of the current object Whether or not the current object's extreme left edge coordinate ≥ past object's leftmost position coordinate and the current object's extreme right edge coordinate ≤ past object's rightmost position coordinate If the relationship of the leftmost edge coordinate of the current object ≧ the leftmost position coordinate of the past object and the rightmost edge coordinate of the current object ≦ the rightmost position coordinate of the past object is satisfied, the past It is determined that the object and the current object overlap.
[0007]
DETAILED DESCRIPTION OF THE INVENTION
Embodiments of the present invention will be described below with reference to the drawings.
FIG. 1 is a block diagram showing a configuration of an obstacle alarm device according to an embodiment of the present invention.
In FIG. 1, reference numeral 1 denotes an image processing unit including a CPU (central processing unit) that controls the obstacle alarm device of the present embodiment, and includes two infrared cameras 2R and 2L that can detect far infrared rays. A yaw rate sensor 3 for detecting the 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. Thus, when the image processing unit 1 detects a moving object such as a pedestrian or an animal in front of the vehicle from an infrared image around the vehicle and a signal indicating the running state of the vehicle, and determines that the possibility of a collision is high Alarm.
[0008]
In addition, the image processing unit 1 displays a speaker 6 for issuing a warning by voice and images taken by the infrared cameras 2R and 2L, and makes the vehicle driver recognize an object having a high risk of collision. For example, a meter-integrated display integrated with a meter that expresses the running state of the host vehicle, a NAVID display installed on the console of the host vehicle, and information displayed at a position on the front window that does not obstruct the driver's front view An image display device 7 including a HUD (Head Up Display) 7a is connected.
[0009]
The image processing unit 1 includes an A / D conversion circuit that converts an input analog signal into a digital signal, an image memory that stores a digitized image signal, a CPU (central processing unit) that performs various arithmetic processes, RAM (Random Access Memory) used to store data, ROM (Read Only Memory) that stores programs and tables executed by the CPU, maps, etc., speaker 6 drive signals, display signals such as HUD7a, etc. The output signals of the infrared cameras 2R and 2L, the yaw rate sensor 3, the vehicle speed sensor 4 and the brake sensor 5 are converted into digital signals and input to the CPU.
[0010]
As shown in FIG. 2, the infrared cameras 2R and 2L are disposed in the front part of the host vehicle 10 at positions that are substantially symmetrical with respect to the center of the host vehicle 10 in the vehicle width direction. The optical axes of 2R and 2L are parallel to each other and are fixed so that the heights from both road surfaces are equal. The infrared cameras 2R and 2L have a characteristic that the output signal level increases (the luminance increases) as the temperature of the object increases.
Further, the HUD 7a is provided so that the display screen is displayed at a position that does not obstruct the driver's front view of the front window of the host vehicle 10.
[0011]
Next, the operation of the present embodiment will be described with reference to the drawings.
FIG. 3 is a flowchart showing an object detection / alarm operation such as a pedestrian in the image processing unit 1 of the obstacle alarm device of the present embodiment.
First, the image processing unit 1 acquires infrared images, which are output signals of the infrared cameras 2R and 2L (step S1), performs A / D conversion (step S2), and stores a grayscale image in an image memory (step S1). S3). Here, the right image is obtained by the infrared camera 2R, and the left image is obtained by the infrared camera 2L. In addition, since the horizontal position of the same object on the display screen is shifted in the right image and the left image, the distance to the object can be calculated from this shift (parallax).
[0012]
If a grayscale image is obtained in step S3, then the right image obtained by the infrared camera 2R is used as a reference image, and binarization processing of the image signal, that is, an area brighter than the luminance threshold value ITH is “1” ( White) and the dark area is set to “0” (black) (step S4).
FIG. 4A shows a grayscale image obtained by the infrared camera 2R, and binarization processing is performed on the grayscale image to obtain an image as shown in FIG. 4B. In FIG. 4B, for example, an object surrounded by a frame from P1 to P4 is an object displayed as white on the display screen (hereinafter referred to as “high luminance region”).
When the binarized image data is acquired from the infrared image, the binarized image data is converted into run-length data (step S5). The line represented by the run-length data is an area that is whitened by binarization at the pixel level, and has a width of one pixel in the y direction, and each has a width in the x direction. It has the length of the pixels constituting the run-length data.
[0013]
Next, the target object is labeled from the image data converted into run-length data (step S6), thereby performing a process of extracting the target object (step S7). That is, of the lines converted into run-length data, a line having a portion overlapping in the y direction is regarded as one object, so that, for example, the high luminance regions P1 to P4 shown in FIG. To be grasped as a value object).
When the extraction of the object is completed, next, the center of gravity G, the area S, and the aspect ratio ASPECT of the circumscribed rectangle of the extracted object are calculated (step S8).
[0014]
Here, the area S is (x [i], y [i], run [i], A) (i = 0, 1, 2,... N−1) ), The length of the run length data (run [i] −1) is calculated for the same object (N pieces of run length data). Also, the coordinates (xc, yc) of the center of gravity G of the object A are the length (run [i] -1) of each run length data and the coordinates x [i] or y [i] of each run length data. Are multiplied by the area S and calculated by multiplying them by the area S.
Further, the aspect ratio ASPECT is calculated as a ratio Dy / Dx between the length Dy in the vertical direction and the length Dx in the horizontal direction of the circumscribed rectangle of the object.
Since the run length data is indicated by the number of pixels (number of coordinates) (= run [i]), the actual length needs to be “−1” (= run [i] −1). Further, the position of the center of gravity G may be substituted by the position of the center of gravity of the circumscribed rectangle.
[0015]
Once the center of gravity, area, and circumscribing aspect ratio of the object can be calculated, next, the object is tracked between times, that is, the same object is recognized for each sampling period (step S9). For tracking between times, the time obtained by discretizing the time t as an analog quantity with the sampling period is set as k. For example, when the objects A and B are extracted at the time k, the objects C and D extracted at the time (k + 1) and the target The identity determination with the objects A and B is performed. When it is determined that the objects A and B and the objects C and D are the same, the objects C and D are changed to labels of the objects A and B, respectively, so that tracking is performed for a time.
Further, the position coordinates (center of gravity) of each object recognized in this way are stored in the memory as time-series position data and used for the subsequent calculation processing.
[0016]
Note that the processes in steps S4 to S9 described above are performed on a binarized reference image (in this embodiment, a right image).
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 turning angle θr of the host vehicle 10 is calculated by integrating the yaw rate YR over time (step S10).
[0017]
On the other hand, in parallel with the processing of step S9 and step S10, in steps S11 to S13, processing for calculating the distance z between the object and the host vehicle 10 is performed. Since this calculation requires a longer time than steps S9 and S10, it is executed in a cycle longer than steps S9 and S11 (for example, a cycle that is 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 (here, the entire region surrounded by the circumscribed rectangle is searched for from the right image). Are extracted (step S11).
[0018]
Next, a search area for searching for an image corresponding to the search image R1 (hereinafter referred to as “corresponding image”) from the left image is set, and a correlation operation is executed to extract the corresponding image (step S12). Specifically, a search area R2 is set in the left image according to each vertex coordinate of the search image R1, and a luminance difference total value C (a indicating the level of correlation with the search image R1 within the search area R2 , B), and a region where the total value C (a, b) is minimum is extracted as a corresponding image. This correlation calculation is performed using a grayscale image instead of a binarized image.
When there is past position data for the same object, an area R2a narrower than the search area R2 is set as a search area based on the position data.
[0019]
The search image R1 is extracted from the reference image (right image) and the corresponding image R4 corresponding to the target object is extracted from the left image by the processing in step S12. Next, the search image R1 corresponds to the center of gravity position of the search image R1. The position of the center of gravity of the image R4 and the parallax Δd (number of pixels) are obtained, and the distance z between the vehicle 10 and the object is calculated from the position (step S13).
Next, when the calculation of the turning angle θr in step S10 and the distance calculation with the object in step S13 are completed, the coordinates (x, y) and the distance z in the image are changed to real space coordinates (X, Y, Z). Conversion is performed (step S14).
Here, the real space coordinates (X, Y, Z) are, as shown in FIG. 2, with the origin O as the midpoint position (position fixed to the host vehicle 10) of the attachment position of the infrared cameras 2R, 2L. The coordinates in the image are determined as shown in the figure, with the center of the image as the origin and the horizontal direction as x and the vertical direction as y.
[0020]
When the real space coordinates are obtained, the turning angle correction for correcting the positional deviation on the image due to the turning of the host vehicle 10 is performed (step S15). In the turning angle correction, 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 range of the image is shifted in the x direction by Δx on the image obtained by the camera. This is a process for correcting this.
In the following description, the coordinates after the turning angle correction are displayed as (X, Y, Z).
[0021]
When the turning angle correction with respect to the real space coordinates is completed, N (for example, about N = 10) real space position data after the turning angle correction obtained during the monitoring period of ΔT for the same object, that is, From the time series data, an approximate straight line LMV corresponding to the relative movement vector between the object and the host vehicle 10 is obtained (step S16).
Next, the latest position coordinates P (0) = (X (0), Y (0), Z (0)) and (N-1) position coordinates P (N−1) before the sample (before time ΔT). = (X (N-1), Y (N-1), Z (N-1)) is corrected to a position on the approximate straight line LMV, and 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)) are obtained.
[0022]
Thereby, a relative movement vector is obtained as a vector from the position coordinates Pv (N−1) to Pv (0).
In this way, by calculating an approximate straight line that approximates the relative movement locus of the object with respect to the host vehicle 10 from a plurality (N) of data within the monitoring period ΔT, the influence of the position detection error is reduced. Thus, the possibility of collision with the object can be predicted more accurately.
[0023]
Further, when the relative movement vector is obtained in step S16, next, the possibility of collision with the detected object is determined, and when there is an object that may collide with the host vehicle 10, for example, A sound alarm is issued via the speaker 6 and an image obtained by, for example, the infrared camera 2R is output to the image display device 7 so that an approaching object is displayed as an emphasized image for the driver of the host vehicle 10. An alarm determination process is performed (step S17).
When the alarm determination process in step S17 is completed, the process returns to step S1 and the above process is repeated.
Details of the alarm determination process will be described later.
[0024]
The above is the object detection / alarm operation in the image processing unit 1 of the obstacle alarm device of the present embodiment. Next, referring to the flowchart shown in FIG. 5, step S17 of the flowchart shown in FIG. The alarm determination process in will be described in more detail.
FIG. 5 is a flowchart showing the alarm determination processing operation of the present embodiment.
The alarm determination process includes the object detected as the host vehicle 10 by the following collision determination process, determination process whether or not the vehicle is in the approach determination area, approach collision determination process, overlap determination process, alarm output determination process, and video input process. This is a process of determining the possibility of a collision with an object and notifying the driver of an object with the possibility of a collision. Hereinafter, as shown in FIG. 6, a case where there is an object 20 traveling at a speed Vp from a direction of approximately 90 ° with respect to the traveling direction of the host vehicle 10 will be described as an example.
[0025]
In FIG. 5, first, the image processing unit 1 performs a collision determination process (step S21). In the collision determination process, in FIG. 6, when the object 20 approaches the distance Zv (0) from the distance Zv (N−1) during the time ΔT, the relative speed Vs in the Z direction with the host vehicle 10 is obtained. This is a process for determining whether or not they collide within the margin time T on the assumption that both move within the height H while maintaining the relative speed Vs. Here, the margin time T is intended to determine the possibility of a collision by a time T before the predicted collision time. Accordingly, the margin time T is set to about 2 to 5 seconds, for example. H is a predetermined height that defines a range in the height direction, and is set to about twice the vehicle height of the host vehicle 10, for example.
[0026]
Next, in step S21, when there is a possibility that the host vehicle 10 and the target object 20 collide within the margin time T (YES in step S21), the image processing unit 1 further increases the reliability of the determination. A determination process is performed as to whether or not the object 20 exists within the approach determination area (step S22). As shown in FIG. 7, if the area that can be monitored by the infrared cameras 2R and 2L is an outer triangular area AR0 indicated by a thick solid line, as shown in FIG. An area AR1 that is closer to the host vehicle 10 than Vs × T and corresponds to a range in which the object 20 adds a margin β (for example, about 50 to 100 cm) on both sides of the vehicle width α of the host vehicle 10, that is, This is a process for determining whether or not the object 20 is present in the approach determination area AR1 where the possibility of a collision with the host vehicle 10 is extremely high if the object 20 continues to exist. The approach determination area AR1 also has a predetermined height H.
[0027]
Furthermore, in step S22, when the target object 20 does not exist in the approach determination area (NO in step S22), the image processing unit 1 may cause the target object 20 to enter the approach determination area and collide with the host vehicle 10. An approach collision determination process is performed to determine whether or not there is (step S23). In the approach collision determination process, the areas AR2 and AR3 having an absolute value of the X coordinate larger than the above-described approach determination area AR1 (outside in the lateral direction of the approach determination area) are referred to as an entry determination area, and the object 20 in this area is This is a process of determining whether or not the vehicle enters the approach determination area AR1 by moving and collides with the host vehicle 10. The entry determination areas AR2 and AR3 also have a predetermined height H.
[0028]
If it is determined in step S23 that the object 20 may enter the approach determination area and collide with the host vehicle 10 (YES in step S23), the real space coordinates of the left and right edges of the object 20 are determined. Are compared with the real space coordinates of the left and right edges of the object recorded in the past, and an overlap determination process is performed to determine whether or not the current object 20 is the entry object based on the degree of overlap between the two (step) S24). The overlap determination process will be described later in detail.
On the other hand, if the target object 20 is present in the approach determination area in step S22 (YES in step S22), or the target object recorded in the past overlaps the current target object 20 in step S24. If the object 20 is the entry object (YES in step S24), an alarm output determination process is performed (step S25).
[0029]
Here, the warning output determination process is a process for determining whether or not to output an alarm by determining whether or not the driver of the host vehicle 10 is performing a brake operation from the output BR of the brake sensor 5. If the driver of the host vehicle 10 performs a braking operation, the acceleration Gs generated by the driver is calculated (the deceleration direction is positive), and the acceleration Gs is equal to or less than a predetermined threshold GTH. Or if the driver of the host vehicle 10 has not performed a brake operation, the process immediately proceeds to step S26 (YES in step S25), and a warning is issued to the driver, for example, via the speaker 6, and An emphasized image for allowing the driver of the host vehicle 10 to recognize the presence of the object 20 is output to the image display device 7 (step S26), and the display target is displayed on the image display device 7. Performs image input processing of inputting the image (step S27), and terminates the alert determination processing. The predetermined threshold GTH corresponds to a condition in which the host vehicle 10 stops at a travel distance equal to or less than the distance Zv (0) between the object 20 and the host vehicle 10 when the acceleration Gs during the brake operation is maintained as it is. Value.
[0030]
In step S21, if there is no possibility that the host vehicle 10 and the object 20 collide within the margin time T (NO in step S21), or in step S23, the object 20 enters the approach determination area. If it is determined that there is no possibility of collision with the host vehicle 10 (NO in step S23), or in step S24, the previously recorded object and the current object 20 are overlapped, and the object 20 Is not an entry object (NO in step S24), and further, in step S25, when the acceleration Gs is larger than the predetermined threshold GTH and the collision with the object 20 is avoided by the brake operation of the driver of the host vehicle 10 If it is determined (NO in step S25), the process proceeds to step S27, and the image to be displayed is input to the image display device 7. Performs image input processing (step S27), and terminates the alert determination processing.
[0031]
Next, the overlap determination process in step S24 of the flowchart shown in FIG. 5 will be described with reference to the drawings.
First, the outline of the overlap determination process will be described. The overlap determination process compares the real space coordinates of the left and right edges of the object 20 with the real space coordinates of the left and right edges of the object 20 recorded in the past. This is a process for determining whether or not the current object 20 is set as an entry object based on the degree of overlap.
Specifically, for example, as shown in FIG. 9, when the time-series data of the object 20 is the object OBJ [t], {t = 0, 1,... Even if the stationary object OBJ [t], {t = 0, 1,... N−1} is separated on the image, the position of the area centroid 12 of the time series data moves with time. The existence position itself in the real space of 20 does not change.
[0032]
At this time, the relationship between the past object (OBJ [t], t ≠ 0) and the current object (A or B of OBJ [0]) is the current object in the existence space of the past object 20. 20 is included. That is, in FIG. 9, it is considered that OBJ [1] = A + B.
Therefore, when the current target object 20 is included in the presence space of the past target object 20, it is determined that the target object 20 is not an approach target object (= a stationary target object), and an approach warning target Can be excluded.
[0033]
This overlap determination process will be described in detail with reference to a flowchart showing the overlap determination processing operation of the present embodiment shown in FIG. 8. First, in FIG. 8, the image processing unit 1 uses the feature 20 as a feature amount. The extreme left edge coordinate (XL [t]) and the extreme right edge coordinate (XR [t]) in the real space at each time are calculated by equation (1) (step S31). In addition, including the following description, it is assumed that the coordinate value of the object 20 calculated by the image processing unit 1 increases as it goes rightward in front of the image.
[0034]
XL [t] = xl [t] · Z [t] · p / f,
XR [t] = xr [t] · Z [t] · p / f (1)
However, the distance of the object 20 at time t is Z [t] (m), the left edge coordinates of the object 20 on the screen are xl [t] (pixel), and the right edge coordinates are xr [t] (pixel). The camera focal length is f (m) and the pixel pitch is p (m / pixel).
[0035]
Next, from the time t = N−1 to the time t = 1, the leftmost position coordinate XL_MAX and the rightmost position coordinate XR_MAX are calculated from the edge coordinate value of the object 20 calculated by Expression (1). Is calculated (step S32).
Finally, the left coordinate (XL [0]) and the right coordinate (XR [0]) of the object 20 at time t = 0 (current) satisfy Expression (2), and the object 20 recorded in the past It is determined whether or not the current object 20 overlaps (step S33).
XL [0] ≧ XL_MAX and XR [0] ≦ XR_MAX (2)
[0036]
In step S33, the left coordinate (XL [0]) and the right coordinate (XR [0]) of the object 20 at time t = 0 (current) satisfy Expression (2), and the object 20 recorded in the past is recorded. If the current object 20 overlaps the current object 20 (YES in step S33), the object 20 is not regarded as an entry object, and the process returns to NO in step S24 in FIG. 5 (step S34).
In step S33, the left coordinate (XL [0]) and the right coordinate (XR [0]) of the object 20 at time t = 0 (current) are not recorded in the past without satisfying the equation (2). If the object 20 and the current object 20 do not overlap (NO in step S33), the object 20 is set as an entry object, and the process returns to YES in step S24 in FIG. 5 (step S35).
[0038]
As described above, the obstacle alarm device of the present embodiment captures the position coordinates of the left and right edges of the target object 20 in time series, and the current position coordinates of the left and right edges of the target object 20 are recorded in the past. Compared with the position coordinates of the left and right edges of the object 20, if the position coordinates of the left and right edges of the current object 20 are included in the presence space of the object 20 recorded in the past, the object 20 is entered. It is determined that the object is not an object (= a stationary object), and can be excluded from the entry warning target.
Therefore, it is possible to easily perform object determination without performing complicated calculations and determinations such as whether the plurality of extracted objects 20 are equidistant or close to each other and remain stationary in the real space. For the target object 20, even if a change in the relative distance and the relative speed occurs in the relative movement vector of the target object 20 obtained from the image, it is correctly determined that the target object is a stationary target object, and attention is paid to the driver. By not displaying as a required object, it prevents the object display that hinders the driver's accurate object recognition, and allows the driver to accurately grasp the position of the alarm object that really needs to be paid attention to. The effect is obtained.
[0039]
【The invention's effect】
As described above, according to the obstacle alarm device according to claim 1, if the object tracked in the past and the currently extracted object are the same object, they are recognized as one object, It is possible to verify the possibility of affecting the running of the vehicle. Therefore, it is possible to easily perform object determination without performing complicated calculations and determinations such as whether the plurality of extracted objects are present at equal distances or close to each other, for example, a stationary object With respect to, there is an effect that it is possible to perform appropriate processing such as omitting verification of the possibility of affecting the running of the vehicle.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of an obstacle alarm device according to an embodiment of the present invention.
FIG. 2 is a diagram showing attachment positions of an infrared camera, a sensor, a display, and the like in a vehicle.
FIG. 3 is a flowchart showing an object detection / alarm operation of the obstacle alarm device according to the embodiment;
FIG. 4 is a diagram illustrating a grayscale image obtained by an infrared camera and a binarized image thereof.
FIG. 5 is a flowchart showing an alarm determination processing operation according to the embodiment;
FIG. 6 is a diagram illustrating a case where a collision is likely to occur.
FIG. 7 is a diagram showing a region division in front of the vehicle.
FIG. 8 is a flowchart showing an overlap determination processing operation according to the embodiment;
FIG. 9 is a diagram showing a relative movement vector generated when one object is separated and extracted.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 Image processing unit 2R, 2L Infrared camera 3 Yaw rate sensor 4 Vehicle speed sensor 5 Brake sensor 6 Speaker 7 Image display apparatus 10 Own vehicle S24, S31-S35 Same object judgment means

Claims (4)

In an obstacle alarm device for a vehicle that detects an object that may affect the running of a vehicle from an image obtained by two imaging means and issues an alarm,
For the past the past object captured the current object that is currently captured, by comparing the position coordinates of the right and left edges of these past object and current object, and the last object in the traveling direction of the vehicle Overlap determination means for determining an overlap with the current object ;
An entry object judging means for judging that the current object is not an entry object when the overlap judging means determines that the past object and the current object overlap. Obstacle alarm device featuring. From the image obtained by the imaging means, comprising an alarm means for detecting an object that may affect the running of the vehicle and issuing an alarm,
  The obstacle alarm device according to claim 1, wherein the alarm means excludes the current object that is determined not to be an entry object by the entry object determination means from the alarm object. The overlap determining means captures the position coordinates of the left and right edges of the plurality of past objects in time series, compares the position coordinates with the position coordinates of the left and right edges of the current object, and determines the left and right edges of the current object in the presence space of the past object. 3. The obstacle alarm device according to claim 1, wherein when an edge position coordinate is included, the past object and the current object are determined to overlap each other. The overlap determining means includes, as feature quantities of the past object and the current object, at least the distance of the object at each time, the left and right edge coordinates on the screen, the focal length and the pixel pitch of the imaging means Based on, calculate the extreme left edge coordinate and the extreme right edge coordinate in real space at each time,
Further, the rightmost position coordinate and the leftmost position coordinate are calculated from the most right edge coordinate and the most left edge coordinate in the real space at each calculated time,
The size of each of the rightmost edge coordinate, the leftmost edge coordinate, the rightmost position coordinate, and the leftmost position coordinate in the real space increases as it goes rightward toward the front of the image. A relationship between a leftmost position coordinate in the past object and an outermost left edge coordinate of the current object, and a rightmost position coordinate in the past object and an outermost left edge coordinate of the current object Whether the current object's leftmost edge coordinate ≥ the leftmost position coordinate of the past object and the current object's rightmost edge coordinate ≤ the rightmost position coordinate of the past object Determine whether
The leftmost edge coordinate of the current object ≧ the leftmost position coordinate of the past object, and the rightmost edge coordinate of the current object ≦ the rightmost position coordinate of the past object,
3. The obstacle alarm device according to claim 1, wherein when the relationship is satisfied, it is determined that the past object and the current object overlap each other.

Images