JP2010257229A - Vehicle periphery monitoring device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a vehicle periphery monitoring device for preventing the possibility of contact between an object and an own vehicle from being erroneously determined when determining the possibility of contact based on the enlargement rate of the image section of the same object extracted from the time-series image of one camera. <P>SOLUTION: The vehicle periphery monitoring device includes: a change rate calculation means 21 for calculating the change rate Rate of the size of the image section of the same object from a time-series image picked up by a single camera 2; a warning determination means 25 for determining whether or not the object is the target of warning processing based on the change rate Rate; a lane recognition means for recognizing the traveling lane of the vehicle in the time-series image; and a warning determination target removal means for, when the image section of the object in the time-series image is positioned in any region other than the image region of the traveling lane of the vehicle in the image, removing the object from the target of the warning processing by the warning determination means. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a vehicle periphery monitoring device that monitors the periphery of a vehicle based on an image captured by an imaging unit mounted on the vehicle.

Conventionally, an image part of the same object is extracted from a time-series image captured by a single camera mounted on a vehicle, and the real space position of the object is obtained from the rate of change of the image part between the images. A vehicle periphery monitoring device is known that determines the possibility of contact between an object and a vehicle (see, for example, Patent Document 1).
In the vehicle periphery monitoring device described in Patent Document 1, when it is determined that the possibility of contact between the object and the vehicle is high, an alarm sound is output by a buzzer, an alarm is displayed on the display, etc. The attention is drawn to the person.

JP 2007-213561 A

  The vehicle periphery monitoring device described in Patent Literature 1 determines that the speed of the vehicle is sufficiently higher than the speed of the object and determines the real space position of the object from the rate of change of the image portion of the object. Therefore, when the object is a stationary object, a pedestrian, etc., the speed of the object is extremely smaller than the speed of the vehicle, and the relative speed of the object and the vehicle substantially matches the speed of the vehicle, the real space of the object The position can be obtained with high accuracy.

  However, as shown in FIG. 10, when the object is, for example, another vehicle B traveling on the oncoming lane 81, the relative speed between the own vehicle A traveling on the traveling lane 80 and the other vehicle B and the own vehicle A The speed difference from the speed increases. Then, the real space position of the other vehicle B calculated from the rate of change of the image portions 95 and 94 of the object between the time series images 90 and 91 is closer to the own vehicle A than the actual position.

In FIG. 10, t = t ₉₁ indicates the time when the image ₉₁ was captured (current control cycle), and t = t ₉₀ indicates the time when the image ₉₀ was captured (the previous control cycle). X ₉₀ indicates the actual position of the other vehicle B in the horizontal direction (the vehicle width direction of the own vehicle A), and Z ₉₀ indicates the actual position of the other vehicle B in the vertical direction (the traveling direction of the own vehicle A). Is shown. X ₉₁ indicates the current calculated position of the other vehicle B in the horizontal direction, and Z ₉₁ indicates the current calculated position of the other vehicle B in the vertical direction. Further, C indicates the calculated position of the other vehicle B virtually.

In the example shown in FIG. 10, the calculated position (X = X ₉₁ , Z = Z ₉₁ ) of the other vehicle B that has no possibility of contact because it is traveling in the oncoming lane 81 is the actual position (X = X ₉₀ , Z = Z ₉₀ ), it is determined that there is a high possibility that the other vehicle B and the own vehicle A come into contact with each other, and an erroneous alarm is issued.

  Therefore, the present invention performs an alarm process for an object based on the rate of change in the size of the image portion of the same object extracted from a time-series image captured by a single camera mounted on the vehicle. It is an object of the present invention to provide a vehicle periphery monitoring device that suppresses an erroneous alarm when determining whether or not.

  The present invention has been made to achieve the above object, and is a vehicle periphery monitoring device that monitors the periphery of a vehicle using an image captured by a single imaging means mounted on the vehicle, the imaging An object extraction means for extracting an image portion of the object from the image captured by the means, and the same object extracted by the object extraction means from a plurality of images captured by the imaging means at predetermined time intervals A rate-of-change calculating unit that calculates a rate of change in the size of the image portion of the object, and an alarm determining unit that determines whether or not the object is to be subjected to a predetermined alarm process based on the rate of change. The present invention relates to a vehicle periphery monitoring device.

  And when the image part of the object in the image imaged by the imaging means is located outside the determination image area corresponding to the image area of the traveling lane of the vehicle set on the image, And an alarm determination exclusion means for excluding an object from a determination target of whether or not the alarm determination means is an object of the alarm processing.

  According to the present invention, when the object is located outside the determination image area, the object may be another vehicle traveling in the oncoming lane. In this case, based on the rate of change, for example, the time until the object reaches the vehicle, the change in the real space position of the object, and the like are calculated as the object is a stationary object. Then, the calculation error increases due to the influence of the speed of the other vehicle. Therefore, it is not possible to correctly determine whether or not the object is a target for alarm processing.

  Therefore, when the image determination part determines whether or not the object is to be subjected to alarm processing by the alarm determination unit when the image portion of the object is located outside the determination image region by the alarm determination unit. By excluding it, it is possible to prevent an erroneous alarm process from being performed when the moving speed is high as when the object is another vehicle.

  Further, the image portion of the lane marking is detected from the image captured by the imaging means, the image area of the traveling lane of the vehicle is recognized based on the detected marking line, and the determination image area is set. A determination image region setting unit is provided.

  According to the present invention, the travel lane recognition means extracts the image portion of the lane marking, thereby more accurately recognizing the travel lane image area of the vehicle and setting the determination image area. Can do.

  Further, the vehicle includes a determination image region setting unit that sets the determination image region by perspective-transforming an approach determination region in the traveling direction of the vehicle in a preset real space onto a captured image by the imaging unit. It is characterized by that.

  According to the present invention, it is possible to easily set the determination image region from a preset approach determination region in real space. Further, the determination image region can be set even when the lane marking is lost and it is difficult to detect the lane marking from the image.

  In addition, the warning determination exclusion unit may be configured such that the image portion of the object is located outside the determination image region when the vertical lowermost portion of the image portion of the object is outside the determination image region. It is characterized by judging.

  According to the present invention, the lowest part in the vertical direction of the image portion of the object is the position on the image corresponding to the intersection position of the object and the road surface in the real space. Therefore, by using the lowermost part of the image portion of the object, it can be more reliably determined whether or not the object exists outside the traveling lane of the vehicle.

The block diagram of the vehicle periphery monitoring apparatus of this invention. Explanatory drawing of the attachment aspect to the vehicle of the vehicle periphery monitoring apparatus shown in FIG. 3 is a flowchart showing a processing procedure in the image processing unit shown in FIG. 1. Explanatory drawing of the calculation process of the change rate of the magnitude | size of the image part of the same target object. Explanatory drawing of the estimation process of the movement vector of the target object in real space. Explanatory drawing of the setting process of a determination image area | region. Explanatory drawing of the process which calculates | requires the position on the image corresponding to the intersection of a target object and a road surface. Explanatory drawing of judgment whether the image part of a target object exists out of the determination image area | region. Explanatory drawing of the other calculation process of the change rate of the magnitude | size of the image part of the same target object. Explanatory drawing of the malfunction which may arise when judging the contact possibility of a target object and a vehicle based on the change rate of the image part of a target object.

  Embodiments of the present invention will be described with reference to FIGS. Referring to FIG. 1, the vehicle periphery monitoring device of the present embodiment is configured by an image processing unit 1. The image processing unit 1 includes an infrared camera 2 (corresponding to the imaging means of the present invention) that can detect far infrared rays, a yaw rate sensor 3 that detects the yaw rate of the vehicle, and a vehicle speed sensor 4 that detects the traveling speed of the vehicle (the present invention). Display the image obtained by the brake sensor 5 for detecting the amount of brake operation by the driver, the speaker 6 for alerting by voice, and the infrared camera 2, and the contact. A head up display (hereinafter referred to as “HUD”) 7 is connected to display an object that is likely to be displayed to the driver.

  Referring to FIG. 2, the infrared camera 2 is disposed in the front portion of the vehicle 10 and has a characteristic that the output level increases (the luminance increases) as the temperature of the imaged object increases. Further, the HUD 7 is provided such that the screen 7 a is displayed at a front position on the driver side of the front window of the vehicle 10.

  Referring to FIG. 1, an image processing unit 1 is an electronic unit composed of a microcomputer (not shown) and the like, and converts an analog video signal output from an infrared camera 2 into digital data to generate an image. The microcomputer has a function of performing various arithmetic processes by the microcomputer with respect to an image in front of the vehicle, which is taken into a memory (not shown) and taken into the image memory.

  Then, by causing the microcomputer to execute a vehicle monitoring program, the microcomputer extracts an image portion of an object in real space from an image captured by the infrared camera 2, Change rate calculation means 21 for calculating the rate of change in the size of the image portion of the same object between images taken at a predetermined time interval by the infrared camera 2, and the object reaches the vehicle 10 using this rate of change. Arrival time estimation means 22 for estimating the time until the object, real space position calculation means 23 for calculating the real space position of the object, movement vector calculation means 24 for calculating the movement vector of the object in the real space, and based on this movement vector Warning judgment means 25 for judging whether or not the object is to be alerted, a judgment image corresponding to the traveling lane of the vehicle 10 on the image And a determination image area setting unit 26, and whether or not to exclude the warning determining excluding means 27 determines the target of interest of the warning by the warning judging means an object to set the region.

  Next, a series of object monitoring processes by the image processing unit 1 will be described with reference to the flowchart shown in FIG. The image processing unit 1 monitors the periphery of the vehicle 10 by executing the process according to the flowchart shown in FIG.

  The image processing unit 1 first receives an analog video signal output from the infrared camera 2 in STEP 1 and takes in a grayscale image obtained by converting the video signal into digital gradation (luminance) data into an image memory.

  The subsequent STEP 2 is processing by the object extraction means 20. For each pixel of the grayscale image, the object extraction unit 20 sets a pixel having a luminance equal to or higher than a predetermined threshold to “1” (white), and sets a pixel having a luminance lower than the threshold to “0” (black) 2 A binarization process is performed to obtain a binary image. Then, the object extraction means 20 calculates the run length data of each white region in the binary image, performs a labeling process or the like, and extracts the image portion of the object.

The next STEP 3 is processing by the change rate calculation means 21. As shown in FIG. 4, the rate-of-change calculating means 21 includes an image Im1 picked up in the previous control cycle (image pickup time t ₁₁ ) and an image Im2 picked up in the current control cycle (image pickup time t ₁₂ ). The processing for tracking the image portion of the same object is performed. Note that this tracking process is described in detail in the above-mentioned Japanese Patent Application Laid-Open No. 2007-213561, and thus the description thereof is omitted here.

Then, the change rate calculating unit 21, by the following equation (1), by dividing the width w ₁₁ of the image portion 51 in the image Im3 width w ₁₂ of the image portion 52 in the image Im 4, calculates a change rate Rate. The relative speed Vs between the vehicle 10 and the object is approximated by the traveling speed of the vehicle 10 detected by the vehicle speed sensor 4.

However, w ₁₁ : the width of the image portion of the object at the time of previous imaging (imaging time t ₁₁ ), w ₁₂ : the width of the image portion of the object at the time of current imaging (imaging time t ₁₂ ), f: f = F (focal length of the infrared camera 2) / p (pixel pitch of the captured image), W: width of the object in real space, Z ₁ : from the vehicle 10 to the object at the time of previous imaging (imaging time t ₁₁ ) Distance, Z ₂ : Distance from the vehicle 10 to the object at the time of the current imaging (imaging time t ₁₂ ), Vs: Relative speed between the vehicle and the object, dT: Imaging interval, Tr: Time of arrival of the vehicle (object) Estimated time until the vehicle 10 reaches the vehicle 10).

Subsequent STEP 23 to STEP 24 are processes by the real space position calculating means 23. The real space position calculation means 23 is STEP4, and in the above formula (1), the relative speed Vs between the vehicle 10 and the object (= the traveling speed Vj of the vehicle 10 + the moving speed Vd of the object) is the traveling speed of the vehicle 10. Assuming that Vj is sufficiently higher than the moving speed Vd of the object, the distance Z from the vehicle 10 to the object at the time of the current imaging is calculated by the following equation (2) that is replaced with the traveling speed Vj of the vehicle 10 and deformed. ₂ is calculated.

However, Z ₂ : distance from the vehicle 10 to the object at the time of the current imaging, Rate: rate of change, Vj: travel speed of the vehicle 10, dT: imaging interval.

Moreover, the real space position calculation means 23 calculates the distance Z ₁ from the vehicle 10 to the object at the time of the previous imaging by the following equation (3).

Where Z ₁ is the distance from the vehicle 10 to the object at the time of the previous imaging, Z ₂ is the distance from the vehicle 10 to the object at the time of the current imaging, Vj is the traveling speed of the vehicle 10, and dT is the imaging interval.

  The subsequent STEP 5 is processing by the real space position calculation means 23. The real space position calculation means 23 calculates the real space position of the object at the time of the current and previous imaging from the position of the image portion of the object in the current and previous binary images.

Here, FIG. 6A shows the position Pi_2 (x ₁₂ , y ₁₂ ) of the image portion of the current object on the binary image Im5 and the position Pi_1 (x ₁₁ , y of the image portion of the previous object. ₁₁ ), the vertical axis y is set in the vertical direction of the image, and the horizontal axis x is set in the horizontal direction of the image.

FIG. 6B shows the movement of the object in real space, where the Z axis is set in the traveling direction of the vehicle 10 and the X axis is set in the direction orthogonal to the Z axis. In the figure, Pr_2 (X ₁₂ , Y ₁₂ , Z ₁₂ ) indicates the position of the object at the time of the current imaging, and Pr_1 (X ₁₁ , Y ₁₁ , Z ₁₁ ) indicates the position of the object at the time of the previous imaging. Show. Vm is a movement vector of an object in real space estimated from Pr_2 and Pr_1.

The real space position calculation means 23 calculates the real space coordinates Pr_2 (X ₁₂ , Y ₁₂ , Z ₁₂ ) of the object at the time of the current imaging by the following formula (4), and the previous formula (5) The real space coordinates Pr_1 (X ₁₁ , Y ₁₁ , Z ₁₁ ) of the monitored object at the time of imaging are calculated. Note that Z ₁₁ = Z ₁ and Z ₁₂ = Z ₂ .

Where X ₁₂ , Y ₁₂ are real space coordinate values of the object at the time of the current imaging, x ₁₂ , y ₁₂ are coordinate values of the image portion of the object in the current binary image, and Z _{2 is} at the time of the current imaging. Distance from vehicle to object, f: f = F (focal length of infrared camera) / p (pixel pitch of captured image).

However, X ₁₁ , Y ₁₁ : Real space coordinate value of the object at the previous imaging, x ₁₁ , y ₁₁ : Coordinate value of the image part of the object in the previous binary image, Z ₁ : At the previous imaging Distance from vehicle to object, f: f = F (focal length of infrared camera) / p (pixel pitch of captured image).

  Further, the real space position calculation means 23 performs a turning angle correction for correcting a positional shift on the image due to the turning of the vehicle 10 based on the turning angle recognized from the detection signal YR of the yaw rate sensor 3. Specifically, when the turning angle of the vehicle 10 from the previous imaging to the current imaging is θr, the real space coordinate value is corrected by the following equation (6).

  However, Xr, Yr, Zr: real space coordinate value after turning angle correction, θr: turning angle, Xo, Yo, Zo: real space coordinate value before turning angle correction.

  The subsequent STEP 6 is processing by the movement vector calculation means 24. As shown in FIG. 6 (b), the movement vector calculation means 24 calculates the object and the host vehicle from the real space position Pr_1 at the previous imaging time and the real space position Pr_2 at the current imaging time for the same object. An approximate straight line Vm corresponding to the relative movement vector with respect to 10 is obtained.

  Note that the relative movement vector may be obtained using the real space position of the object at a plurality of past time points. Moreover, the concrete calculation process of a recent straight line is based on the method described in Unexamined-Japanese-Patent No. 2001-6096, for example.

  The subsequent STEP 7 is processing by the determination image region setting means 26. The determination image region setting unit 26 performs a process of setting a determination image region on the image according to the position of the traveling lane of the vehicle 10.

  FIG. 6A shows an approach determination area Ar1 in the real space set to determine the possibility of contact between the object and the vehicle 10 by the alarm determination means 25 described later, and left and right of the approach determination area Ar1. The intrusion determination areas Ar2 and Ar3 thus set are shown with the traveling direction of the vehicle 10 as Z and the direction orthogonal to Z (the vehicle width direction of the vehicle 10) as X. Lr1 is a dividing line on the right side of the traveling lane of the vehicle 10, Lr2 is a dividing line on the left side of the traveling lane of the vehicle 10, and W is a dividing line Lr1 with the vehicle 10 when the vehicle 10 is traveling in the center of the traveling lane. , Lr2.

  The alarm determination means 25 is configured to detect when the object is in the approach determination area Ar1, or when the object is in the intrusion determination area Ar2 or Ar3 and the movement vector of the object is in the approach determination area Ar1. This object is set as an alarm target.

  Here, as shown in FIG. 6 (b), the dividing lines (straight lines) Lr1 and Lr2 shown in FIG. 6 (a) are changed to the mounting parameters (mounting height H, mounting pan angle θ, mounting of the infrared camera 2). When projected onto the image Im6 in FIG. 6B by perspective transformation using the pitch angle φ), straight lines Li1 and Li2 are obtained. Then, the determination image area setting unit 26 sets an area ar1 sandwiched between the straight lines Li1 and Li2 in FIG. 6B as a determination image area.

  Note that the determination image region may be set assuming a position corresponding to the approach determination region in the real space on the image without using the perspective transformation as illustrated in FIG. Alternatively, the image portion of the lane marking of the travel lane may be detected from the image to recognize the travel lane image area, and the determination image area may be set according to the travel lane image area.

  Subsequent STEP 8 and STEP 9 are processes by the alarm judgment exclusion means 27. The alarm judgment exclusion means 27 is provided between the image portion of the gray scale image of the current object shown in FIG. 7A and the image portion of the gray scale image of the previous object shown in FIG. Thus, by performing correlation calculation, the position on the image corresponding to the intersection of the object and the road surface in the real space is recognized.

  First, the alarm judgment excluding means 27 includes 50 mask areas M1 (M1 (0,0), M1 (1.0) in a matrix around the part A1 of the image portion of the current object in FIG. ),..., M1 (5,8)). Note that the black dot in each mask area indicates the position of the center of gravity of each mask area.

  Then, the alarm target exclusion unit 27 extracts the image portion of the target object from the previous gray scale image. Specifically, a comparison pattern obtained by affine transforming each of the mask areas M1 (0,0) to M1 (5,8) shown in FIG. Perform pattern matching processing.

  FIG. 7B shows the result of pattern matching. Twelve regions M2 (1,3 including B2 corresponding to the image B1 of the trunk and legs of the pedestrian in FIG. 7A are shown. ), M2 (2,3), M2 (3,3), M2 (4,3), M2 (1,4), M2 (2,4), M2 (3,4), M2 (4,4) , M2 (2,5), M2 (3,5), M2 (2,6), and M2 (3,6) are extracted. For example, M2 (1,3) in FIG. 7B shows a region extracted by a comparison pattern obtained by affine transformation of M1 (1,3) in FIG. 7A, and M2 in FIG. 7B. (4,3) indicates a region extracted by a comparison pattern obtained by affine transformation of M1 (4,3) in FIG.

  The black dots in FIG. 7B are the mask regions M1 (1,3), M1 (2,3), M1 (3,3), M1 (4,3), M1 (1, 4), M1 (2,4), M1 (3,4), M1 (4,4), M1 (2,5), M1 (3,5), M1 (2,6), M1 (3,6 ) Corresponding to each centroid position (the centroid position of the area obtained by reducing the mask area M1 at the rate of change Rate with respect to A2). Further, the x point in FIG. 7B indicates the barycentric position of each region M2 extracted by pattern matching.

  The object extraction means 20 uses the following equation (7) to extract the centroid position (xm (i, j), ym (i, j)) of each area extracted by pattern matching and the centroid position corresponding to the mask area. It is determined whether or not the deviation amount D from (xb (i, j), yb (i, j)) is smaller than the threshold value TH. Here, i and j indicate the index of the mask area.

  However, D: deviation | shift amount of the gravity center position corresponding to a mask area | region and the gravity center position of the area | region extracted by pattern matching, TH: threshold value.

  Then, the warning determination exclusion unit 27 extracts a region where the deviation amount D is smaller than the threshold value TH as a part of the image portion of the object. In the example of FIG. 7B, twelve areas including the image B2 of the pedestrian's torso and legs are extracted as part of the image portion of the object. Therefore, in the example of FIG. 7B, A2, M2 (1,3), M2 (2,3), M2 (3,3), M2 (4,3), M2 (1,4), M2 ( 2,4), M2 (3,4), M2 (4,4), M2 (2,5), M2 (3,5), M2 (2,6), M2 (3,6) region S2 Are extracted as the image portion of the object.

  The alarm judgment exclusion means 27 recognizes the lowest position Pobj of the image portion S2 of the object extracted in this way as the position on the image corresponding to the intersection position between the object and the road surface in the real space. Note that the position of the lowermost pixel Popj does not have to be strictly the position of the lowermost pixel in the vertical direction, and may be set near the lowermost pixel.

  Then, in subsequent STEP 9, the alarm determination exclusion means 27 determines whether or not the lowest position Pobj of the image portion S2 of the object is outside the determination image area ar1, as shown in FIG. FIG. 8 shows a case where the object is another vehicle traveling in the opposite lane, and the lowest position Pobj of the image portion S2 of the object is outside the determination image area ar1.

  In this case, since there is a low possibility that the vehicle 10 and the object (another vehicle traveling in the opposite lane) are in contact with each other, the alarm determination exclusion unit 27 is the target of the alarm by the alarm determination unit 25. The process proceeds to STEP11. Thus, when the difference between the relative speed between the vehicle 10 and the object and the traveling speed of the vehicle 10 is large, and the error when calculating the real space position of the object based on the rate of change Rate becomes large, The object is excluded from the alarm target to prevent an erroneous alarm.

  On the other hand, when the lowermost position Pobj of the image portion S2 of the object is in the determination image area ar1, the object is a pedestrian or the like existing in the travel lane of the vehicle 10, and the moving speed thereof is the vehicle 10. It is assumed that it is negligible with respect to the traveling speed. Therefore, in this case, the process proceeds from STEP 9 to STEP 10.

  STEP 10, STEP 20, and STEP 30 to STEP 31 are processes by the alarm determination means 25.

  In step 10, the alarm determination means 25 is either (a) the object is present in the approach determination area, or (b) the object is present in the intrusion determination area, and the movement vector of the countermeasure is toward the approach determination area. When the condition of is satisfied, it is determined that the object is an alarm target, and the process branches to STEP 20. On the other hand, when neither of the above conditions (a) and (b) is satisfied, the process proceeds to STEP11.

  In STEP 20, the alarm determination unit 25 determines whether or not a brake operation is performed by the driver from the output of the brake sensor 5. Then, when the brake operation is performed and the acceleration of the vehicle 10 (9 where the deceleration direction is positive is larger than a preset acceleration threshold value (it is assumed that an appropriate brake operation is performed by the driver). Determines that no alarm output is required, and proceeds to STEP11.

  On the other hand, if the brake operation is not performed or the acceleration of the vehicle 10 is equal to or less than the acceleration threshold value, the process branches to STEP30. Then, the alarm determination means 20 outputs an alarm sound from the speaker 6 at STEP 30, and displays an emphasized image of the object on the HUD 7 at STEP 31, and proceeds to STEP 11.

  In the present embodiment, the change rate calculation means 21 calculates the change rate Rate by the time tracking process of the image portion of the same object between the binary images shown in FIG. 5, but the target shown in FIG. You may make it calculate change rate Rate by the calculation of the phase of the image part of a thing. Referring to FIG. 9, Im8 is a gray scale image at the time of previous imaging, and 51 indicates an image portion of the object. Im9 is a grayscale image at the time of the current imaging, and 52 indicates an image portion of the object.

  Then, the change rate calculation means 21 reduces or enlarges the size of the image portion 50 of the target object in the current grayscale image Im8 (when the target object approaches the host vehicle) or enlarges the target object (the target object is the host vehicle). And the degree of correlation with the image portion 51 of the object at the previous imaging is calculated. Specifically, as shown in the figure, an image 60 obtained by multiplying the image portion 50 by 1.5, an image 61 by 1.25 times, an image 62 by 1.0 times, an image 63 by 0.75 times, and a 0.5 times image. The degree of correlation between the obtained image 64 and the image portion 51 is calculated. Then, the change rate calculation means 21 determines the magnification of the image portion 50 when the degree of correlation is the highest as the change rate Rate.

  In the present embodiment, the movement vector calculation means 24 obtains the movement vector in the real space of the object and determines whether or not the object is to be alarmed. The following equation (7) The time (vehicle arrival time) Tr until the vehicle reaches the object is calculated, and when the vehicle arrival time Tr is equal to or less than a preset margin time, the object is set as an alarm target. May be.

  However, Tr: own vehicle arrival time, dT: imaging interval, Rate: rate of change.

  Further, in the present embodiment, when the image portion of the target object is located outside the determination image area, the alarm determination excluding unit 27 excludes the target object from the determination target as to whether or not the target is an alarm target. However, you may make it judge separately whether it is set as the object of a warning by another method. For example, the moving speed of the object may be detected, the actual space position of the object may be calculated in consideration of the moving speed of the object, and the possibility of contact between the vehicle and the object may be determined.

  In the present embodiment, the infrared camera 2 is used as the imaging means of the present invention, but a normal video camera capable of detecting only visible light may be used.

  Further, in the present embodiment, the configuration in which the front of the vehicle is imaged is shown, but it is also possible to determine the possibility of contact with the monitoring object by imaging other directions such as the rear and side of the vehicle. Good.

  DESCRIPTION OF SYMBOLS 1 ... Image processing unit, 2 ... Infrared camera (imaging means), 3 ... Yaw rate sensor, 4 ... Vehicle speed sensor, 5 ... Brake sensor, 6 ... Speaker, 7 ... HUD, 20 ... Object extraction means, 21 ... Change rate calculation Means 22: arrival time estimation means 23 ... real space position calculation means 24 ... movement vector calculation means 25 ... warning judgment means 26 ... judgment image area setting means 27 ... warning judgment exclusion means

Claims (4)

A vehicle periphery monitoring device that monitors the periphery of a vehicle using an image captured by a single imaging means mounted on the vehicle,
Object extraction means for extracting an image portion of the object from the image captured by the imaging means;
A change rate calculating means for calculating a change rate of the size of the image portion of the same object extracted by the object extracting means from a plurality of images taken by the imaging means at a predetermined time interval;
In a vehicle periphery monitoring device comprising alarm judgment means for judging whether or not the object is a target of a predetermined alarm process based on the rate of change,
When the image portion of the object in the image captured by the imaging means is located outside the determination image area corresponding to the image area of the vehicle lane set on the image, the object A vehicle periphery monitoring apparatus, comprising: an alarm determination excluding unit that excludes an alarm from a determination target of whether or not the alarm determination unit performs the alarm processing. The vehicle periphery monitoring device according to claim 1,
Determination of detecting an image portion of a lane marking from an image captured by the imaging unit, recognizing an image area of a traveling lane of the vehicle based on the detected marking line, and setting the determination image area A vehicle periphery monitoring device comprising image area setting means. The vehicle periphery monitoring device according to claim 1,
A determination image region setting unit configured to set the determination image region by perspective-converting an approach determination region in the traveling direction of the vehicle in a preset real space onto a captured image by the imaging unit; A vehicle periphery monitoring device. In the vehicle periphery monitoring device according to any one of claims 1 to 3,
The warning determination excluding means determines that the image portion of the object is located outside the determination image region when the lowest vertical portion of the image portion of the object is outside the determination image region. The vehicle periphery monitoring apparatus characterized by the above-mentioned.

Images