JP4975776B2 - Vehicle periphery monitoring device - Google Patents

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, for example, an image portion of the same object is extracted from a time-series image captured within a predetermined sampling period by a camera mounted on the vehicle, and between the object and the vehicle at the time of capturing each image. There is known a vehicle periphery monitoring device that detects a distance and calculates a relative speed between a vehicle and an object from a degree of change in the distance within a sampling period (see, for example, Patent Document 1).

  In the vehicle periphery monitoring device described in Patent Document 1, the expected time until the object arrives at the vehicle calculated from the distance and relative speed between the vehicle and the object is within a predetermined determination time. Sometimes, it is determined that there is a possibility of contact between the vehicle and the object, and the contact determination process in the next stage is executed.

JP 2001-6096 A

  Patent Document 1 described above does not describe a specific setting of the sampling period of the time-series image used when calculating the relative speed between the vehicle and the object. And when calculating the relative speed between the vehicle and the object using the time-series image of the object, if the sampling period of the time-series image is constant, the longer the distance between the vehicle and the object, the longer the distance in the sampling period Therefore, the relative speed calculation accuracy is lowered.

  Therefore, when the sampling period of the time-series image is made constant, it is necessary to set the sampling period to a relatively long time in order to maintain high calculation accuracy of the relative speed with the object having a long distance from the vehicle.

  However, when the sampling period of the time-series image is set to a long time as described above, the calculation of the relative speed is delayed and the detection of the target is delayed when calculating the relative speed with the target existing near the vehicle. There is a fear.

  Accordingly, an object of the present invention is to provide a vehicle periphery monitoring device that prevents the calculation timing of the relative speed between the vehicle and the object from being delayed.

The present invention has been made to achieve the above object, and relates to a vehicle periphery monitoring apparatus that monitors the periphery of a vehicle using an image captured by a single imaging unit mounted on the vehicle.

In the first aspect of the present invention, the same object detected between the time-series images is detected for the same object detected from the time-series images captured by the imaging unit at different times within a predetermined sampling period. Distance calculation means for calculating the distance between the object and the vehicle at the time of capturing each image using the rate of change in the size of the image portion of the object, the vehicle by the distance calculation means during the sampling period, and the vehicle A relative speed calculation means for calculating a relative speed between the vehicle and the object using a degree of change in the calculated distance from the object; and when the relative speed is equal to or higher than a predetermined speed, the object is monitored. An object excluding means for excluding the vehicle, a vehicle speed detecting means for detecting the vehicle speed of the vehicle, and a sampling period for setting the sampling period to a shorter time as the vehicle speed of the vehicle is lower Characterized by comprising a constant section.

According to the present invention, the sampling period setting means sets the sampling period to a shorter time as the vehicle speed of the vehicle is lower, thereby increasing the vehicle speed of the vehicle as when traveling on a highway. When it is necessary to monitor a distant object, it is possible to maintain the calculation accuracy of the relative speed with the vehicle by setting the sampling period longer. In addition, when the vehicle speed is low and it is necessary to monitor a nearby object, such as when driving on a narrow road in an urban area, the sampling period is set short to calculate the relative speed with the vehicle. Delay in timing can be suppressed.
In the first aspect, the sampling period setting means multiplies the initial value of the preset sampling period by a coefficient that decreases as the vehicle speed of the vehicle decreases, so that the sampling rate decreases as the vehicle speed decreases. The period is set to a short time.

Next, a second embodiment of the present invention, for each predetermined control cycle, for the same object detected from the time-series images captured by the imaging means at different times within a predetermined sampling period, said time Distance calculating means for calculating a distance between the object and the vehicle at the time of capturing each image using a rate of change in the size of the image portion of the same object between the series images ; A relative speed calculating means for calculating a relative speed between the vehicle and the object using a degree of change in a calculated distance between the vehicle and the object by a distance calculating means; and the relative speed is equal to or higher than a predetermined speed. to the exclusion object excluding means the object from the monitoring target, the more pre-times shorter distance between the object and the vehicle calculated by the distance calculation means in a control cycle of, the current control cycle Kicking is characterized in that a sampling period setting means for setting the sampling period short time.

  According to the present invention, the distance between the vehicle and the object in the current control cycle is assumed to be approximately the same as the distance between the vehicle and the object calculated by the distance calculation unit in the previous control cycle. The The longer the distance between the vehicle and the object, the longer the sampling period and the greater the amount of change in the distance between the vehicle and the object in the sampling period. It is necessary to maintain speed calculation accuracy. On the other hand, when the distance between the vehicle and the object is short, even if the sampling period is set to a short time, the amount of change in the distance between the vehicle and the object during the sampling period becomes large. The accuracy of calculating the relative speed between the object and the object increases.

Therefore, by setting the sampling period in the current control cycle to a shorter time as the distance between the vehicle and the object calculated in the previous control period is shorter by the sampling period setting means, the vehicle and the target are set. When the distance between objects is long, the sampling period is set long to maintain the relative speed calculation accuracy, and when the distance between the vehicle and the object is short, the sampling period is set short to calculate the relative speed. Can be delayed.
Further, in the second aspect, the sampling period setting means sets a coefficient that becomes smaller as the distance between the vehicle and the object calculated in the previous control cycle is shorter than a preset initial value of the sampling period. By multiplying, the shorter the distance between the vehicle and the object calculated in the previous control cycle, the shorter the sampling period in the current control cycle is set.

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 image extraction process by a corresponding image extraction means, and the parallax between images. FIG. 4 is a flowchart of an attention determination process shown in FIG. 3. 6 is a flowchart of monitoring object determination processing shown in FIG. 5. Explanatory drawing of the setting method of a sampling period. Explanatory drawing which showed the change of the calculation error of the relative speed of a vehicle and a target object by the difference in vehicle speed.

  Embodiments of the present invention will be described with reference to FIGS. FIG. 1 is a configuration diagram of a vehicle surroundings monitoring apparatus according to the present invention. The vehicle surroundings monitoring apparatus according to the present invention includes an image processing unit 1. The image processing unit 1 includes infrared cameras 2R and 2L (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 ( (Corresponding to vehicle speed detecting means of the present invention), brake sensor 5 for detecting the amount of brake operation by the driver, speaker 6 for alerting by voice, and images obtained by infrared cameras 2R and 2L are displayed. In addition, a display device 7 is connected for performing a display that allows the driver to visually recognize an object with a high possibility of contact.

  Referring to FIG. 2, infrared cameras 2R and 2L are disposed at the front portion of vehicle 10 at a substantially target position with respect to the center portion of vehicle 10 in the vehicle width direction, and two infrared cameras 2R and 2L are arranged. The optical axes are parallel to each other, and the infrared cameras 2R and 2L are fixed at the same height from the road surface. The infrared cameras 2R and 2L have a characteristic that the output level increases (the luminance increases) as the temperature of the imaged object increases. Further, the display device 7 is provided so 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 converts analog video signals output from infrared cameras 2R and 2L into digital data. The microcomputer has a function of performing various arithmetic processes by the microcomputer with respect to the image in front of the vehicle captured in the image memory (not shown).

  Then, by causing the microcomputer to execute a vehicle monitoring program, the microcomputer extracts the first image portion of the object in real space from the first image captured by the infrared camera 2R. Extraction means 20 and corresponding image extraction means 21 for extracting a second image portion having a correlation with the first image portion from the second image captured by the infrared camera 2L, and the first object extracted by the object extraction means 20 Parallax calculating means 22 for calculating the parallax between the image portion and the second image portion extracted by the corresponding image extracting means 21, distance calculating means 23 for calculating the distance between the vehicle and the object based on the parallax, the vehicle and the object Relative speed calculation means 24 for calculating the relative speed with respect to the object, object exclusion means 25 for excluding an object whose relative speed is equal to or higher than a predetermined speed from the monitoring target, relative speed Sampling period setting means 26 for setting a sampling period for acquiring time-series data of images used when calculating the relative speed by the output means 24, and contact determination means 27 for determining the possibility of contact between the vehicle 10 and the object. Function as.

  Next, monitoring processing around the vehicle 10 by the image processing unit 1 will be described according 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 inputs an analog signal of an infrared image output from the infrared cameras 2R and 2L in STEP1, and then stores a grayscale image obtained by digitizing the analog signal by A / D conversion in an image memory in STEP2. To do.

  In STEP1 to STEP2, a grayscale image (hereinafter referred to as a right image) obtained by the infrared camera 2R and a grayscale image (hereinafter referred to as a left image) obtained by the infrared camera 2L are acquired. Since the right image and the left image have a shift (parallax) in the horizontal position of the image portion of the same object, the distance from the vehicle 10 to the object in real space can be calculated based on this parallax. it can.

  In subsequent STEP 3, the image processing unit 1 binarizes the right image as a reference image (pixels with luminance equal to or higher than a threshold value are set to “1 (white)”, and pixels smaller than the threshold value are set to “0 (black)”. To generate a binary image. The next STEP 4 to STEP 6 are processes by the object extraction means 20. In STEP 4, the object extraction means 20 converts the image portion of each white area included in the binary image into run length data (data of white pixel lines continuous in the x (horizontal) direction of the binary image). Further, the object extraction unit 20 labels a line having a portion overlapping in the y (vertical) direction of the binary image as one image part in STEP 5, and in STEP 6, the labeled image part is an image candidate of the monitoring object. Extract as

  In the next STEP 7, the image processing unit 1 calculates the gravity center G, area S, and circumscribing aspect ratio ASPECT of each image candidate. Note that a specific calculation method is a general method described in JP 2001-6096 A and the like described above, and thus description thereof is omitted here. Then, the image processing unit 1 executes the following STEP 8 to STEP 9 and STEP 20 to STEP 22 in parallel.

  In STEP 8, the image processing unit 1 performs identity determination on image portions extracted from binary images based on images taken by the infrared cameras 2R and 2L at predetermined sampling periods, and images of the same object The time-series data of the position of the image portion determined to be (centroid position) is stored in the memory (time tracking). In STEP 9, the image processing unit 1 reads the vehicle speed VCAR detected by the vehicle speed sensor 4 and the yaw rate YR detected by the yaw rate sensor 3, and calculates the turning angle θr of the vehicle 10 by time integration of the yaw rate YR. To do.

  Further, STEP 20 to STEP 21 are processes by the corresponding image extraction means 21. Referring to FIG. 4, in step 20, the corresponding image extraction unit 21 selects one of the monitoring subject image candidates extracted by the target object extraction unit 20, and selects from the grayscale image 30 of the right image. A corresponding search image 30a (an image of the entire region surrounded by a circumscribed rectangle of the selected candidate image) is extracted. In subsequent STEP 21, the corresponding image extracting means 20 sets a search area 32 for searching for an image corresponding to the search image 30a from the grayscale image 31 of the left image, executes an interphase operation with the search image 30a, and executes the correlation image 31a. To extract.

  The subsequent STEP 22 is processing by the parallax calculation means 22. The parallax calculation means 22 calculates the difference between the centroid position of the search image 30a and the centroid position of the corresponding image 31a as the parallax dx, and proceeds to STEP10.

  STEP 10 is processing by the distance calculation means 23. The distance calculating unit 23 uses the parallax dx calculated by the parallax calculating unit 22 to calculate the distance between the object in the real space corresponding to the search image 30a and the corresponding image 31a and the vehicle 10 according to the following equation (1). calculate.

  Where Z: distance between the object and the vehicle 10, f: focal length of the infrared cameras 2R and 2L, p: pixel pitch of the infrared cameras 2R and 2L, D: base line length of the infrared cameras 2R and 2L, dx: parallax.

  Subsequent STEP 11 to STEP 14 are processes by the contact determination means 27. In STEP 11, the contact determination means 27 converts the coordinates (x, y) of the search image 30a and the distance z between the object calculated in STEP 10 and the vehicle 10 into real space coordinates (X, Y, Z). Then, the coordinates of the position of the object in the real space corresponding to the search image 10a are calculated. As shown in FIG. 2, the real space coordinates (X, Y, Z) are set such that the midpoint position of the attachment positions of the infrared cameras 2R, 2L is the origin 0, X is the vehicle width direction of the vehicle 10, and Y Is set in the vertical direction, and Z is set in the front direction of the vehicle 10. The image coordinates are set such that the center of the image is the origin, the horizontal direction is x, and the vertical direction is y.

  In the next STEP 12, the contact determination unit 27 performs a turning angle correction for correcting a positional deviation on the image due to the turning of the vehicle 10. Further, in STEP 13, the contact determination means 27 determines the object and the vehicle from the time series data of the real space position of the same object after turning angle correction obtained from a plurality of images captured within a predetermined monitoring period. A relative movement vector with respect to 10 is calculated.

  The specific calculation method of the real space coordinates (X, Y, Z) and the movement vector of the object is described in detail in the above-mentioned Japanese Patent Application Laid-Open No. 2001-6096, and will not be described here.

  In subsequent STEP 14, the contact determination unit 27 determines the possibility of contact between the vehicle 10 and the object, and executes “attention call determination processing” for determining whether or not it is necessary to call attention. In “attention call determination processing”, when it is determined that it is necessary to call attention, an output of a warning sound by the speaker 6 and a warning display on the display device 7 are performed.

  Next, the “attention calling determination process” in STEP 14 of FIG. 3 will be described according to the flowchart shown in FIG.

  In STEP 30 of FIG. 5, the contact determination means 27 determines whether or not the object extracted by the object extraction means 20 and whose movement vector is estimated in STEP 13 of FIG. 3 is a monitoring object. "Object determination processing" is executed. Details of the “monitoring object determination process” will be described later.

  When it is determined by the “monitoring object determination process” that the object is a monitoring object, the process proceeds to STEP 32. On the other hand, when it is determined by the “monitoring object determination process” that the object is not the monitoring object, the process proceeds to STEP 36. In this case, the output of the alert sound by the speaker 6 and the alert display on the display device 7 are as follows. Not done.

  In STEP 32, the contact determination unit 27 determines whether or not the target object exists within the approach determination region set around the vehicle 10. When the object is present in the approach determination area, the process proceeds from the next STEP 33 to STEP 34, and the contact determination unit 27 determines whether it is necessary to call attention.

  In STEP 34, the contact determination unit 27 determines whether or not a brake operation is performed by the driver from the output of the brake sensor 5. When the brake operation is performed and the acceleration of the vehicle 10 (correcting the deceleration direction here) is larger than a preset acceleration threshold value (it is assumed that an appropriate brake operation is performed). It is determined that no alert is required. On the other hand, when the brake operation is not performed or when the acceleration of the vehicle 10 is equal to or less than the acceleration threshold value, it is determined that an alert is necessary.

  When it is determined in STEP 34 that attention is required, the process branches from STEP 35 to STEP 50, and the contact determination unit 27 outputs the warning sound from the speaker 6 and displays the warning on the display device 7. I do. On the other hand, when it is determined in STEP 34 that alerting is unnecessary, the process proceeds from STEP 35 to STEP 36 and returns to STEP 1 in FIG. Therefore, in this case, the contact determination unit 27 does not perform the output of the alert sound by the speaker 6 and the alert display on the display device 7.

  If it is determined in STEP 32 that the object does not exist in the approach determination area, the process branches from STEP 33 to STEP 40. In STEP 40, the contact determination means 27 determines the possibility that the target object enters the access determination area from outside the access determination area and comes into contact with the host vehicle 10 (intrusion contact).

  And when it determines with the possibility of an intrusion contact being high, it progresses to STEP34 from the next STEP41. On the other hand, when it is determined that the possibility of intrusion contact is low, the process proceeds from STEP 41 to STEP 36. In this case, the contact determination unit 27 outputs an alert sound from the speaker 6 and alerts the display device 7. Do not display.

  The details of each process of the approach determination in STEP 32, the alerting output determination in STEP 34, and the intrusion contact determination in STEP 40 are the collision determination, alarm output determination, and intrusion collision described in JP 2001-6096 A mentioned above. Since the process is the same as the determination, detailed description is omitted here.

  Next, the “monitoring object determination process” in STEP 30 of FIG. 5 will be described according to the flowchart shown in FIG.

  STEP 60 in FIG. 6 is processing by the sampling period setting means 26. The sampling period setting means 26 applies the vehicle speed VCAR detected by the vehicle speed sensor 4 to the correspondence map a1 of the vehicle speed (VCAR) and the sampling period (Tw) shown in FIG. The period Tw is acquired. Then, the sampling period setting unit 26 sets the acquired sampling period Tw as a sampling period in the current control cycle.

  Subsequent STEP 61 to STEP 63 are processes by the relative speed calculation means 24. The relative speed calculation means 24 waits for the time series data of the distance between the vehicle 10 and the object in the sampling period Tw or more to be acquired in STEP 61 and proceeds to STEP 62. Then, the relative speed calculation unit 24 removes outliers (data in which the calculated distance is extremely different from other data) from the time series data of the distance in STEP 62.

  Then, the relative speed calculation unit 24 calculates the relative speed Vs between the vehicle 10 and the object by the following equation (2).

  Where Vs: relative speed between the vehicle 10 and the object, Tw: sampling period, Z (0): latest distance calculation value, Z (N-1): Z (0) calculation time before Tw Distance calculated value.

  Here, FIG. 8 is calculated, and the change in the calculation error of the relative speed between the vehicle 10 and the object according to the vehicle speed VCAR will be described. FIG. 8 shows changes in the relative speed calculation error between the vehicle 10 and other vehicles and pedestrians according to the vehicle speed VCAR, with the vertical axis set to speed (V) and the horizontal axis set to the vehicle speed VCAR of the vehicle 10. Is.

  Further, FIG. 8 shows that the other vehicle and the pedestrian are present at positions separated by the monitoring target distance determined according to the setting of the allowance time until contact with the vehicle 10, and the sampling period Tw is set to the assumed vehicle speed. The relative speed between the vehicle 10 and other vehicles and pedestrians is calculated by setting the relative speed calculation error at the maximum value VCAR_max of the VCAR to a constant value within the allowable ranges Wm and Wp.

  In FIG. 8, Vm is the actual relative speed between the vehicle 10 and the other vehicle, Vp is the actual relative speed between the vehicle 10 and the pedestrian, Vs_th is a relative speed determination threshold value, e1, e2 are the vehicle 10 and the other vehicle. , E3 is a calculated value of the relative speed between the vehicle 10 and the other vehicle, Em is a calculation error of the relative speed between the vehicle 10 and the other vehicle, Ep is a calculation of the relative speed between the vehicle 10 and the pedestrian. Indicates an error.

  It can be seen from FIG. 8 that the relative speed calculation errors Em and Ep decrease as the vehicle speed VCAR decreases. For this reason, in the range where the vehicle speed VCAR is low, the sampling period Tw is set such that an accuracy higher than necessary is obtained.

  Therefore, the sampling period setting means 26 sets the sampling period Tw to a shorter time as the vehicle speed VCAR is lower in STEP 60 according to the vehicle speed / sampling period correspondence map a1 shown in FIG. It is possible to maintain high calculation accuracy of the relative speed in the high range and shorten the calculation time of the relative speed in the range where the vehicle speed VCAR is low. Thus, when the vehicle speed VCAR is low, it is possible to suppress a delay in the calculation timing of the relative speed between the vehicle 10 and the object.

  Subsequent STEP 64 to STEP 65 and STEP 70 are processes by the object exclusion means 25. The object excluding means 25 determines whether or not the relative speed Vs between the vehicle 10 and the object is equal to or less than the determination threshold value Vs_th in STEP64.

  When the relative phase Vs is equal to or less than the determination threshold value Vs_th, the process proceeds to STEP 65, and the target object exclusion unit 25 determines that the target object is a monitoring target object. Then, the process proceeds to STEP 66 and returns to the process of FIG. On the other hand, when the relative speed Vs is higher than the determination threshold value Vs_th, the process branches to STEP 70, and the object exclusion means 25 determines that the object is not a monitoring object. Then, the process proceeds to STEP 66 and returns to the process of FIG.

  Here, by setting the sampling period Tw to a shorter time as the vehicle speed VCAR of the vehicle 10 is lower, the processing time of the “monitoring object determination processing” in STEP 30 of FIG. Since the timing is advanced, it is possible to suppress delay in alerting by STEP50.

  In this embodiment, according to the map shown in FIG. 7A, the sampling period Tw is set to be shorter as the vehicle speed VCAR of the vehicle 10 is lower. However, the vehicle speed VCAR is set to the initial value of the preset sampling period. The sampling period Tw may be set to a shorter time as the vehicle speed VCAR of the vehicle speed 10 is lower by multiplying the coefficient k1 (0 <k1 ≦ 1) which becomes smaller as the vehicle speed becomes lower.

  Moreover, it calculates with the last control cycle by the correspondence map of the distance L (n-1) between the vehicle 10 and the object calculated with the previous control cycle and the sampling period Tw shown in FIG. 7B. The shorter the distance L (n−1) between the vehicle 10 and the target object, the shorter the sampling period Tw in the current control cycle may be set. In this case, since the calculated distance L (n-1) includes an error, the sampling period Tw may be set stepwise as shown in b3, for example, in consideration of this error.

  Further, the initial value of the preset sampling period is multiplied by a coefficient k2 (0 <k2 ≦ 1) that becomes smaller as the distance L (n−1) between the vehicle 10 and the object calculated in the previous control cycle becomes shorter. Accordingly, the sampling period Tw in the current control cycle may be set to a shorter time as the distance L (n−1) between the vehicle 10 and the object calculated in the previous control cycle is shorter.

  In the present embodiment, the distance calculation unit 23 includes two infrared cameras 2R and 2L, and uses the parallax of the image portion of the same object between the right image and the left image, and the vehicle 10 and the object. For example, as described in Japanese Patent Application Laid-Open No. 2007-213561, the rate of change in the size of the image portion of the same object between time-series images captured by one camera is calculated. It may be used to calculate the distance between the vehicle and the object.

  Moreover, in this Embodiment, although the structure which images a vehicle front was shown, you may make it judge the contact possibility with a target object by imaging other directions, such as back and a side of a vehicle. .

  Further, in the present embodiment, the infrared cameras 2R and 2L are used as the imaging means of the present invention, but a visible camera that captures a visible image may be used.

  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 ... Display apparatus, 20 ... Object extraction means, 21 ... Corresponding image extraction means , 22 ... parallax calculation means, 23 ... distance calculation means, 24 ... relative speed calculation means, 25 ... object extraction means, 26 ... sampling period setting means, 27 ... contact determination means.

Claims (4)

A vehicle periphery monitoring device that monitors the periphery of a vehicle using an image captured by a single imaging unit mounted on the vehicle,
For the same object detected from the time-series images captured by the imaging means at different times within a predetermined sampling period, the rate of change in the size of the image portion of the same object between the time-series images is calculated. using a distance calculation means for calculating the distance between the object and the vehicle at the time of imaging of the image,
Relative speed calculation means for calculating a relative speed between the vehicle and the object using the degree of change in the calculated distance between the vehicle and the object by the distance calculation means during the sampling period;
Object exclusion means for excluding the object from the monitoring object when the relative speed is equal to or higher than a predetermined speed;
Vehicle speed detecting means for detecting the vehicle speed of the vehicle;
A vehicle periphery monitoring device, comprising: a sampling period setting means for setting the sampling period to a shorter time as the vehicle speed of the vehicle is lower. In the vehicle periphery monitoring device according to claim 1,
The sampling period setting means sets the sampling period to a shorter time as the vehicle speed of the vehicle decreases by multiplying a preset initial value of the sampling period by a coefficient that decreases as the vehicle speed of the vehicle decreases. A vehicle periphery monitoring device.   A vehicle periphery monitoring device that monitors the periphery of a vehicle using an image captured by a single imaging unit mounted on the vehicle,
  For the same object detected from the time-series images captured by the imaging means at different times within a predetermined sampling period for each predetermined control period, the image portion of the same object between the time-series images A distance calculating means for calculating a distance between the object and the vehicle at the time of capturing each image using a rate of change in the size of each image;
  Relative speed calculation means for calculating a relative speed between the vehicle and the object using the degree of change in the calculated distance between the vehicle and the object by the distance calculation means during the sampling period;
  Object exclusion means for excluding the object from the monitoring object when the relative speed is equal to or higher than a predetermined speed;
  Sampling period setting means for setting the sampling period in the current control cycle to a shorter time as the distance between the object and the vehicle calculated by the distance calculation unit in the previous control cycle is shorter. A vehicle periphery monitoring device.   In the vehicle periphery monitoring device according to claim 3,
  The sampling period setting means multiplies the initial value of the preset sampling period by a coefficient that becomes smaller as the distance between the vehicle and the object calculated in the previous control period is shorter. The vehicle periphery monitoring apparatus, wherein the sampling period in the current control cycle is set to a shorter time as the calculated distance between the vehicle and the object is shorter.

Images