JP6426455B2 - Approaching vehicle detection device - Google Patents

Description

  The present invention relates to an approaching vehicle detection device which is installed in a vehicle and detects an approaching vehicle traveling in an adjacent lane at the time of a lane change, and performs an alarm.

  In recent years, a rear side monitoring function (BSW (Blind Spot (BSW (Blind Spot) detects a approaching vehicle from an image obtained by installing a camera on the vehicle and capturing an image of the rear side of the vehicle that is blind) A technique related to Warning) has been proposed.

  For example, in the notification device for a rear side vehicle described in Patent Document 1, a moving object present in an adjacent lane adjacent to a traveling lane in which the vehicle is traveling and a lane marker on the far side from the vehicle in the adjacent lane And a method of detecting another vehicle traveling in an adjacent lane based on the detection results.

Unexamined-Japanese-Patent No. 9-240397

  However, in the notification device of such a conventional rear side vehicle, for example, at night, when the light of the headlight of the other vehicle traveling on the lane adjacent to the second lane is reflected on the road surface, it is as if adjacent An image is captured as if there are other vehicles in the lane. Therefore, there is a possibility that it may be erroneously detected that there is another vehicle traveling in the adjacent lane.

  The present invention has been made in view of the above problems, and another vehicle traveling on a lane next to the traveling lane on which the vehicle is traveling is traveling on an adjacent lane adjacent to the traveling lane. An object of the present invention is to provide an approaching vehicle detection device which does not erroneously detect a vehicle.

  In order to solve the above-mentioned problem, the approaching vehicle detection device according to the present invention, from the running vehicle, turns on the headlight of the adjacent lane of the lane in which the vehicle is traveling, and approaches from behind An approaching vehicle detection device that detects and gives notification, and an imaging unit that picks up an image including a road surface on the rear side of the vehicle, and a position in the image corresponding to the rear side region of the vehicle A window setting unit for setting at least one window of a predetermined size having a predetermined positional relationship with the vehicle, and determining whether a headlight of another vehicle is detected in a predetermined area of the image When the headlight detection unit and the headlight detection unit detect headlights of other vehicles, the brightness evaluation in each of the windows is performed based on the brightness value of the area corresponding to each of the windows of the image A luminance distribution calculation unit that calculates a value, and The other vehicle is present in the adjacent lane adjacent to the lane in which the vehicle is traveling, or adjacent to the adjacent lane on the far side of the vehicle based on the brightness evaluation value in the window. It is characterized by having the other vehicle travel lane determination part which determines whether it exists in an adjacent lane.

  According to the approaching vehicle detection device according to the present invention configured as described above, with the above configuration, it is reliably determined whether the approaching vehicle is traveling in the adjacent lane or traveling in the adjacent adjacent lane. can do. Therefore, since the approaching vehicle traveling on the adjacent adjacent lane is not erroneously detected as the approaching vehicle traveling on the adjacent lane, the presence of the approaching vehicle can be notified more accurately.

It is a 1st figure explaining the road environment where the approaching vehicle detection device which is one embodiment of the present invention is applied. It is a 2nd figure explaining the road environment where the approaching vehicle detection device which is one embodiment of the present invention is applied. It is a block diagram which shows the hardware constitutions in the approaching vehicle detection apparatus of Example 1 which is one embodiment of this invention. It is a functional block diagram showing the functional composition in the approaching vehicle detection device of Example 1 which is one embodiment of the present invention. In Example 1, it is a figure explaining processing which detects a headlight of other vehicles. FIG. 8 is a diagram for explaining an example of a window set by the window setting unit in the first embodiment. In Example 1, it is a 1st figure explaining the method to determine the travel lane of another vehicle by luminance distribution in a window. It is a 2nd figure explaining the method to determine the travel lane of another vehicle by luminance distribution in a window in Example 1. 5 is a flowchart showing a flow of a series of processes implemented in the first embodiment. It is a flowchart which shows the detailed flow of the other vehicle travel lane determination processing shown to the flowchart of FIG. It is a functional block diagram showing the functional composition in the approaching vehicle detection device of Example 2 which is one embodiment of the present invention. In Example 2, it is a figure explaining the method to determine the travel lane of another vehicle by luminance distribution in a window. It is a flowchart which shows the detailed flow of the other vehicle travel lane determination processing performed in Example 2. FIG.

  Hereinafter, embodiments of an approaching vehicle detection device according to the present invention will be described with reference to the drawings.

The present embodiment monitors the road behind the running vehicle according to the present invention, and the driver changes lanes when the approaching vehicle is within a predetermined distance range behind the adjacent lane. The present invention is applied to an approaching vehicle detection device provided with a BSW function, which outputs an alarm to warn when an intention is indicated.
(Description of application scene of approaching vehicle detection device)

  First, the outline of the approaching vehicle detection device 100a (see FIG. 2) and the road environment to which the approaching vehicle detection device 100a is applied will be described using FIGS. 1A and 1B. The approaching vehicle detection device 100a operates while traveling on a road having three lanes or more per side. The approaching vehicle detection device 100a operates day and night, but in particular, by applying the present invention, it can operate more effectively at night.

  FIG. 1A is a diagram showing an example of a road 30 to which the approaching vehicle detection device 100a is applied. The road 30 has a traveling lane 20 on which the vehicle 10 on which the approaching vehicle detection device 100a is mounted is traveling, an adjacent lane 22 adjacent to the right side of the vehicle 10, and two adjacent adjacent lanes 22. It consists of three lanes: lane 24 (hereinafter referred to as adjacent adjacent lane 24). The left and right ends of the traveling lane 20 are respectively divided by lane markers L1 and L2, the left and right ends of the adjacent lane 22 are respectively divided by lane markers L2 and L3, and the left and right ends of the adjacent adjacent lane 24 are respectively lane markers L3 and L4. It is divided.

  Now, it is assumed that the vehicle 10 is traveling on the traveling lane 20 of the road 30 in the left direction (the direction of the arrow 10d) of FIG. 1A. At this time, the rear camera 50 installed rearward at the rear end of the vehicle 10 captures an imaging range ω including at least the traveling lane 20, the adjacent lane 22, and the road surface of the adjacent adjacent lane 24. Then, among the captured images, the other vehicle 12 approaching the vehicle 10 (in the direction of the arrow 12 d) exists within the predetermined detection range (window) W1 set to the rear side of the vehicle 10 Detect the progress). Then, when another vehicle 12 approaching the vehicle 10 is detected, and the driver of the vehicle 10 changes the lane of the vehicle 10 to the adjacent lane 22 side despite the other vehicle 12 approaching. When I try, I give a warning by giving an alarm which will be described later.

  Here, the detection range (window) W1 is set to, for example, a range of 3 m to 30 m behind the vehicle 10 and a range of 3 m from the right end of the vehicle 10.

  At this time, it is assumed that the other vehicle 12 lights the headlights 12h and 12h to illuminate the inside of the irradiation range 12r. The other vehicle 14 traveling in the adjacent adjacent lane 24 in the direction of the arrow 14 d lights the headlights 14 h and 14 h to illuminate the inside of the irradiation range 14 r.

  Although FIG. 1A illustrates only the right rear side area of the vehicle 10, the approaching vehicle detection device 100a works similarly on the left rear side area of the vehicle 10. That is, as shown in FIG. 1B, when the vehicle 10 is traveling on the traveling lane 20, the rear camera 50 respectively controls the traveling lane 20 having at least the lane markers L1 and L2 as the left and right ends and the lane markers L5 and L1 respectively. An imaging range ω including the adjacent lane 26 at the end is imaged. Then, in the captured image, the other vehicle 16 approaching the vehicle 10 (in the direction of the arrow 16 d) exists within the predetermined detection range (window) W2 set to the rear side of the vehicle 10 Detect the progress). Then, when another vehicle 16 approaching the vehicle 10 is detected, and the driver of the vehicle 10 changes the lane of the vehicle 10 to the adjacent lane 26 despite the other vehicle 16 approaching. When trying to do so, a warning is issued to warn as described later.

  Here, the detection range (window) W2 is set, for example, in the range of 3 m to 30 m behind the vehicle 10 and in the range of 3 m from the left end of the vehicle 10.

At this time, it is assumed that the other vehicle 16 lights the headlights 16h and 16h to illuminate the inside of the irradiation range 16r. The other vehicle 18 traveling in the direction of the arrow 18d is a lane 28 (hereinafter referred to as the adjacent adjacent lane 28) which is adjacent to the lane marker L6 and L5 at the left and right ends respectively. It lights up and assumes that the inside of irradiation range 18r is illuminated.
(Description of the system configuration of the approaching vehicle detection device)

  Next, the hardware configuration of the approaching vehicle detection device according to the present embodiment will be described with reference to FIG. The approaching vehicle detection device 100a according to the present embodiment is mounted on the vehicle 10, and is disposed rearward of the vehicle 10 near the rear license plate of the vehicle 10, as shown in FIG. It has a rear camera 50 for capturing an image to be included. Further, the ECU 60 has an ECU 60 that detects an approaching vehicle by executing recognition processing of an image captured by the rear camera 50, and controls an alarm for notifying of the presence of the approaching vehicle. The CAN bus 80 disposed inside the vehicle 10 is connected to the ECU 60, and the CAN bus 80 includes a vehicle speed sensor 82 for detecting the vehicle speed v of the vehicle 10 and a winker for detecting the blinker operation of the driver. The switch 84 is connected. Further, the ECU 60 is connected with an indicator 90 for notifying the presence of an approaching vehicle as visual information, and a buzzer 92 for notifying the presence of the approaching vehicle as auditory information.

  The rear camera 50 has an AGC function of automatically changing the gain value according to the ambient brightness. That is, when the surroundings are dark, the gain value is automatically raised to brighten the image, and when the surroundings are bright, the gain value is automatically lowered to darken the image. The rear camera 50 can output the gain value at that time together with the captured image.

  Inside the ECU 60, a plurality of software modules that execute necessary processing are implemented. The nighttime determination unit 61 determines which day or night the surrounding environment in which the approaching vehicle detection device 100a is operating is. The vehicle information acquisition unit 62 acquires, via the CAN bus 80, the vehicle speed v of the vehicle 10 detected by the vehicle speed sensor 82, an operation signal of the turn signal switch 84, and the like. The image recognition processing unit 63 performs detection of a headlight of a vehicle traveling behind the vehicle 10 and detection of an approaching vehicle. The other vehicle travel lane determination unit 64 determines whether the detected other vehicle travels in the adjacent lane or travels in the adjacent adjacent lane. The alarm control unit 65 outputs or suppresses the alarm based on the detection result of the approaching vehicle and the operation of the driver of the vehicle 10. The ECU 60 also includes a software module (not shown in FIG. 2), for example, a module such as an overall control unit that controls the movement of the entire software, and a storage unit that stores necessary images and information.

  Next, the functional configuration of the approaching vehicle detection device 100a of the present embodiment, in particular, the detailed configurations of the image recognition processing unit 63 and the alarm control unit 65 will be described with reference to FIG.

  The image recognition processing unit 63 detects the headlights of the other vehicles (12, 14 (FIG. 1A), 16, 18 (FIG. 1B)) from the image captured by the rear camera 50, as shown in FIG. The headlight detection unit 70 is provided. Moreover, the overhead image generation part 71 which converts the image imaged with the rear camera 50 into the overhead image which looked over from the front of the vehicle 10 is provided. And the window setting part 72 which sets detection range (window) W1 (FIG. 1A) and W2 (FIG. 1B) of predetermined | prescribed size to the predetermined position of the converted bird's-eye view image is provided. In addition, a luminance distribution calculation unit 73a that calculates the average value of the luminances of the pixels corresponding to the set detection ranges W1 and W2 in the overhead image is included. The luminance distribution calculating unit 73a is connected to a moving average calculating unit 74 that calculates a moving average value of average luminances in the detection ranges W1 and W2.

  The image recognition processing unit 63 further includes an image alignment unit 75 that aligns the overhead images acquired at different times in the overhead image generation unit 71. Further, it has a difference image generation unit 76 that generates a difference image by performing a frame difference between the aligned overhead images. And the relative velocity calculation part 77 which calculates the relative velocity of the vehicle 10 and a moving object based on the result of having performed frame difference is provided. The three-dimensional object determination unit 78 determines whether the moving object captured in the detection ranges W1 and W2 is another vehicle (12, 14 (FIG. 1A), 16, 18 (FIG. 1B)).

As shown in FIG. 3, when the approaching vehicle is detected and the approaching vehicle is detected, the alarm control unit 65 operates the turn signal and the driver wishes to change lanes. The alarm output unit 66 outputs an alarm when displayed, and an alarm suppression unit 67 that suppresses the output of the alarm when an approaching vehicle is detected in the adjacent lane.
(Description of the operation of the headlight detection unit)

  Next, the operation of the headlight detection unit 70 of the approaching vehicle detection device 100a will be described with reference to FIG.

  The greatest feature of the approaching vehicle detection device 100a shown in the first embodiment is that, when detecting other vehicles (12, 14 (FIG. 1A), 16, 18 (FIG. 1B)) approaching the vehicle 10 from the rear, It is possible to determine whether the other vehicle is traveling in the adjacent lane (22 in FIG. 1A, 26 in FIG. 1B) or in the adjacent adjacent lane (24 in FIG. 1A, 28 in FIG. 1B). And the approaching vehicle detection device 100a exhibits the effect especially at night.

  At night, as shown in FIG. 4, the original image I (t) captured at time t by the rear camera 50 (FIG. 3) is a dark image because the luminance is generally reduced. Therefore, it is very difficult to recognize the body of another vehicle from the original image I (t).

  Therefore, the approaching vehicle detection device 100a recognizes the presence of the other vehicle by detecting the headlight image of the other vehicle. At this time, among the other vehicles, there are other vehicles (corresponding to the headlight image 120 in FIG. 4) traveling on the same traveling lane 20 (FIG. 4) as the vehicle 10. Thus, the other vehicle traveling in the same traveling lane as the vehicle 10 is not a detection target of the approaching vehicle detection device 100a, and thus the headlight image of the other vehicle (for example, FIG. It is necessary to detect the headlight image 122).

  Therefore, in the approaching vehicle detection device 100a, as shown in FIG. 4, headlight detection regions R1 and R2 (predetermined regions) are set on the left and right so as to avoid the traveling lane 20. Then, among the set headlight detection areas R1 and R2, an area having high luminance equal to or higher than a predetermined luminance is detected, and when the corresponding area is detected, it is assumed that it is a headlight image of another vehicle. . That is, in the case of the original image I (t) shown in FIG. 4, the headlight image is not detected inside the headlight detection region R1, and the headlight image 122 is detected inside the headlight detection region R2. Ru. The headlight detection areas R1 and R2 set here are set to at least a range in which a headlight image of another vehicle present in the adjacent lane can be detected. The specific dimensions may be determined beforehand by conducting experiments and the like.

  In the daytime, since the vehicle body of another vehicle can be visually recognized in the image captured by the rear camera 50 (FIG. 3), it is not necessary to perform the above-described headlight image detection processing. Therefore, in the approaching vehicle detection device 100a, it is determined whether the nighttime determination unit 61 (FIG. 3) performs a process of detecting a headlight image.

Specifically, the night time determination unit 61 receives the gain value output when imaging is performed by the rear camera 50, and determines that the surroundings are dark when the gain value is equal to or greater than the predetermined gain, and the front illumination It is assumed that a lamp image detection process is performed.
(Description of the operation of the luminance distribution calculation unit and the moving average calculation unit)

  Next, the operation of the luminance distribution calculation unit 73a and the moving average calculation unit 74 of the approaching vehicle detection device 100a will be described using FIGS. 5 and 6A. Note that the image captured by the rear camera 50 is converted into a bird's-eye view of the vehicle 10 viewed from directly above at the bird's-eye view image generation unit 71, and the processing described below is performed on this bird's-eye view I assume.

  The luminance distribution calculating unit 73a calculates an average value (luminance evaluation value) of luminances in the detection ranges (windows) W1 and W2 set by the window setting unit 72. Here, as shown in FIG. 5, the detection range W1 is set on the overhead image so as to extend from the left end of the vehicle 10 to the width wa in the left direction. Further, the distance w is set from the position behind the rear end of the vehicle 10 by a distance d, and the length wb. As the specific values of the width wa, the distance d, and the length wb, for example, wa = 3 m, d = 3 m, and wb = 27 m are set as described above.

  Next, an operation of calculating the luminance distribution inside the detection ranges (windows) W1 and W2 will be described using FIG. 6A.

  As shown in FIG. 6A, the other vehicle 14 and 16 are approaching from the rear of the vehicle 10, and the other vehicle 14 is traveling on the adjacent adjacent lane 24 and the other vehicle 16 is traveling on the adjacent lane 26. It is assumed that Moreover, the other vehicle 14 has lighted the headlight, and the irradiation range is 14r. The other vehicle 16 also lights the headlights, and the irradiation range is 16r.

  At this time, as can be seen from FIG. 6A, the irradiation range 14r of the headlights of the other vehicle 14 partially overlaps the detection range (window) W1. On the other hand, the irradiation range 16r of the headlight of the other vehicle 16 almost overlaps with the detection range (window) W2. Therefore, the traveling lanes of the other vehicles 14 and 16 can be estimated by the magnitude of the average luminance in the detection ranges W1 and W2.

The luminance distribution calculation unit 73a calculates the average luminance (luminance evaluation value) of the pixels inside the area corresponding to each of the detection ranges (windows) W1 and W2 with respect to the overhead image. The average luminance is calculated as a value obtained by dividing the total sum of pixel values in the area corresponding to each of the detection ranges W1 and W2 by the total number of pixels of the detection ranges W1 and W2 in the overhead image. Here, the average luminance of the pixels in the detection range W1 at time t is represented by B _W1 (t), and the average luminance of the pixels in the detection range W2 is represented by B _W2 (t).

The luminance of the road surface of the road 30 has a high value at a place where the road illumination is bright, even at night. Therefore, the average luminances B _W1 (t) and B _W2 (t) calculated by the luminance distribution calculation unit 73a are simply compared with the fixed threshold values, and the detection ranges W1 and W2 and irradiation of the headlights of other vehicles are obtained. It is difficult to determine the overlapping state with the ranges 14r and 16r.

Therefore, the moving average calculation unit 74 calculates the moving average values B _thW1 (t) and B _thW2 (t) of the average luminance B _W1 (t) and B _W2 (t), respectively, and the moving average value B _thW1 (t And B _thW2 (t) are used as threshold values to determine the overlapping state of the detection ranges W1 and W2 and the irradiation ranges 14r and 16r of the headlights of other vehicles. Details will be described later.

In addition, although the time length which calculates moving average value should just set an appropriate value by experiment etc., in order to raise determination accuracy, the headlights of other vehicles are irradiated inside detection ranges W1 and W2 It is desirable to include periods that have not been
(Description of the operation of the other vehicle travel lane determination unit)

  Next, the operation of the other vehicle travel lane determination unit 64 of the approaching vehicle detection device 100a will be described using FIG. 6B.

As shown in FIG. 6B, the other vehicle travel lane determination unit 64 moves the average luminance B _W1 (t) and B _W2 (t) calculated by the luminance distribution calculation unit 73a by the moving average calculation unit 74. The average values B _thW1 (t) and B _thW2 (t) are respectively compared.

When B _W1 (t) ≧ B _{th W1} (t), it is determined that the other vehicle 14 is traveling in the adjacent lane 22. When B _W1 (t) <B _{th W1} (t), it is determined that the other vehicle 14 is traveling in the adjacent lane 24.

Similarly, when B _W2 (t) ≧ B _thW2 (t), it is determined that the other vehicle 16 is traveling in the adjacent lane 26. When B _W2 (t) <B _{th W2} (t), it is determined that the other vehicle 16 is traveling in the adjacent adjacent lane 28.

By using the moving average values B _thW1 (t) and B _thW2 (t) as threshold values in this way, when the road surface brightness changes on the road 30 (FIG. 6A), for example, when the road surface is bright, the moving average Since the values B _thW1 (t) and B _thW2 (t) increase and the moving average values B _thW1 (t) and B _thW2 (t) decrease when the road surface is dark, the luminance of the road surface by the headlights of other vehicles is reduced. Changes can be detected reliably.
(Description of the action of the three-dimensional object detection unit)

  The approaching vehicle detection device 100a processes an image captured by the rear camera 50 to detect an approaching vehicle. An outline of image processing performed at that time will be described. In addition, since a series of processes performed here are applied and implemented in the vehicle in which the BSW function was mounted, description by drawing is abbreviate | omitted and it demonstrates only with a text.

  First, two images captured by the rear camera 50 at different times separated by a time interval Δt are converted into a bird's-eye view image by the bird's-eye view image generation unit 71, respectively.

  Next, in the image alignment unit 75, of the two generated bird's-eye view images, the bird's-eye view image in the past temporally is deformed and superimposed on the temporally new bird's-eye view image. This modification uses the vehicle speed v of the vehicle 10 during the time interval Δt acquired by the vehicle information acquisition unit 62 and the steering angle of the vehicle 10 during the time interval Δt not shown in FIG. To correspond to the behavior of the vehicle 10 during the That is, the overhead image is translated and rotationally moved to correspond to the moving direction and the moving amount of the vehicle 10 at the time interval Δt, respectively, and alignment is performed. By this alignment, the road surface areas of the roads of the two overhead images completely overlap.

  Thereafter, the difference image generation unit 76 performs inter-frame difference between the two aligned overhead images. At this time, the past bird's-eye view image is subtracted from the temporally new bird's-eye view image. By this difference calculation, a region where a change in luminance occurs during the time interval Δt, that is, a region where a moving object is present is detected.

  Next, the relative speed calculation unit 77 calculates the relative speed between the vehicle 10 and the moving object by obtaining the size (length in the front-rear direction of the vehicle 10) of the area in which the moving object is present.

Then, in the three-dimensional object determination unit 78, it is confirmed that the moving object is another vehicle. In this process, for example, an area is recognized as a moving object on a bird's-eye view image is inversely transformed on the original image I (t) captured by the rear camera 50, and the object is present in the inversely transformed area. It does by judging whether or not. The determination as to whether or not an object is present may be performed by template matching in the vicinity of the inversely transformed region by applying a template that simulates the shape of a vehicle. Alternatively, the luminance of each pixel of the original image I (t) is projected in the vertical direction and the horizontal direction, and a change point exists in a portion corresponding to the inversely transformed region in the obtained luminance projection curve. It may be determined that there is another vehicle after confirming that.
(Description of the operation of the alarm control unit)

  The alarm control unit 65 controls the alarm output to the approaching vehicle based on the detection result of the other vehicle, the vehicle speed v of the vehicle 10, and the operation state of the turn signal switch 84.

  Specifically, when the approaching vehicle is detected on the adjacent lane 22 or the adjacent lane 26 (FIG. 6A) when the vehicle speed v of the vehicle 10 is equal to or higher than a predetermined vehicle speed (for example, 30 km / h), the alarm output unit 66 The indicator 90 is turned on by the action of

  Furthermore, when the driver of the vehicle 10 operates the blinker switch 84 without noticing the lighting of the indicator 90 and turns on the adjacent lane 22 or 26 where the approaching vehicle is detected, the buzzer 92 is further displayed. Make a noise and call attention.

  When the approaching vehicle is detected on the adjacent adjacent lane 24 or the adjacent adjacent lane 28 (FIG. 6A), the control described above is not performed. That is, neither lighting of the indicator 90 nor ringing of the buzzer 92 is performed.

Alternatively, when an approaching vehicle is detected on the adjacent adjacent lane 24 or the adjacent adjacent lane 28 (FIG. 6A), the alarm suppressing unit 67 suppresses the output of the alarm for a certain period of time to turn on the indicator 90. Also, the buzzer 92 may not sound.
(Description of the flow of processing performed by the approaching vehicle detection device)

  Next, the entire flow of the process performed by the approaching vehicle detection device 100a will be described using FIG. In addition, FIG. 3 is referred for description of a structure site | part.

  (Step S10) The vehicle information acquisition unit 62 acquires vehicle information. Specifically, the vehicle speed v of the vehicle 10 obtained by the vehicle speed sensor 82 and the steering angle of the vehicle 10 (not shown in FIG. 3) are acquired.

  (Step S12) An image of the rear of the vehicle 10 taken by the rear camera 50 is input to the image recognition processing unit 63.

  (Step S14) The nighttime determination unit 61 acquires the gain value output from the rear camera 50.

  (Step S16) An overhead image generation unit 71 generates an overhead image from the image input.

  (Step S18) The image alignment unit 75 aligns the two overhead images obtained at different times.

  (Step S20) The difference image generation unit 76 generates a difference image by performing frame difference of the two aligned overhead images.

  (Step S22) The relative velocity calculation unit 77 calculates the relative velocity of the area representing the moving object detected from the difference image.

  (Step S24) The night time determination section 61 performs day and night determination. When it is determined that it is noon, the process proceeds to step S30, and when it is determined that it is night, the process proceeds to step S26.

  (Step S26) The headlight detection unit 70 detects the headlights of other vehicles.

  (Step S28) The other vehicle travel lane determination unit 64 performs the other vehicle travel lane determination processing of determining the lane by the other vehicle traveling. The detailed flow of the other vehicle travel lane determination processing will be described later.

  (Step S30) The three-dimensional object determination unit 78 determines whether there is a three-dimensional object (other vehicle) at the rear.

  (Step S32) The alarm control unit 65 performs predetermined alarm control. The outline of the alarm control is as described above.

  (Step S34) The vehicle speed v of the vehicle 10 acquired by the vehicle information acquisition unit is monitored to determine whether the vehicle speed v of the vehicle 10 falls below a predetermined vehicle speed. When the vehicle speed falls below a predetermined vehicle speed (for example, 30 km / hr), the process of FIG.

In the flowchart of FIG. 7, although the day and night determination is performed in step S24, this day and night determination may be performed after step S14.
(Description of the flow of the other vehicle travel lane determination process)

  Next, the flow of the other vehicle travel lane determination process will be described with reference to FIG. In addition, FIG. 3 is referred for description of a structure site | part.

  (Step S50) The window setting unit 72 sets detection ranges (windows) W1 and W2 on the overhead image.

(Step S52) The brightness distribution calculating unit 73a calculates average brightness B _W1 (t) and B _W2 (t) inside the detection ranges (windows) W1 and W2, respectively.

(Step S54) The moving average calculation unit 74 _updates the moving average values B _thW1 (t) and B _thW2 (t) of the average luminance in the detection ranges (windows) W1 and W2, respectively.

(Step S56) In the other vehicle travel lane determination unit 64, it is determined whether the average brightness B _W1 (t) is equal to or greater than the moving average B _thW1 (t), and the average brightness B _W2 (t) is the moving average B _thW2 (t). ) Or not. If the average luminance is equal to or higher than the moving average value, the process proceeds to step S60. Otherwise, the process proceeds to step S58.

  (Step S58) It is judged that the other vehicle is traveling on the adjacent adjacent lane, and the process returns to the main routine (FIG. 7).

  (Step S60) It is judged that the other vehicle is traveling in the adjacent lane, and the process returns to the main routine (FIG. 7).

Next, a second embodiment of the approaching vehicle detection device according to the present invention will be described with reference to the drawings. In the second embodiment, as in the first embodiment, the present invention is applied to an approaching vehicle detection device having a BSW function.
(Description of the system configuration of the approaching vehicle detection device)

  First, the functional configuration of the approaching vehicle detection device 100b according to this embodiment will be described with reference to FIG. As shown in FIG. 9, the basic functional configuration is the same as the functional configuration of the first embodiment (FIG. 3), but the luminance distribution in the detection ranges (windows) W1 and W2 set by the window setting unit 72 Only the calculation method is different. That is, in place of the luminance distribution calculating unit 73a and the moving average calculating unit 74 included in the first embodiment (FIG. 3), the second embodiment includes a luminance projection distribution calculating unit 73b.

The luminance projection distribution calculation unit 73b is configured to cross the detection ranges W1 and W2 with respect to each of the detection ranges (windows) W1 and W2 set by the window setting unit 72 (in the horizontal direction of the vehicle 10). It has a function of calculating the luminance projection value by accumulating the luminance of the corresponding pixel of the overhead image.
(Description of the operation of the luminance projection distribution calculation unit)

  Next, the operation of the luminance projection distribution calculation unit 73b of the approaching vehicle detection device 100b will be described.

As described above, the luminance projection distribution calculation unit 73b accumulates the luminances of the corresponding pixels of the overhead image along the directions (left and right directions of the vehicle 10) respectively crossing the detection ranges (windows) W1 and W2 (FIG. 6A). Then, the luminance projection values Bp _W1 and Bp _W2 are calculated, and the luminance projection distributions Bp _W1 (Z) and Bp _W2 (Z), which are distribution curves of the luminance projection values extending in the front and back direction of the detection range W1 and W2, respectively are generated. Do. Here, Z is a coordinate which specifies the position of detection range W1 and W2 in the front-rear direction, and is a coordinate representing the rear position of the vehicle 10.

FIG. 10 is a diagram showing an example of the luminance projection distributions Bp _W1 (Z) and Bp _W2 (Z) generated when the vehicle 10 is in the state of FIG. 6A.

As can be seen from FIG. 10, when the other vehicle 16 is in the adjacent lane 26, the luminance projection distribution Bp _W2 (Z) is a substantially uniform distribution over the entire detection range W2. On the other hand, when the other vehicle 14 is in the adjacent adjacent lane 24, the luminance projection distribution Bp _W1 (Z) is a distribution having a luminance projection value projecting at a specific position in the detection range W1. In the example of FIG. 10, the luminance projection value exhibits a high value at the position closest to the vehicle 10 in the detection range W2.

Therefore, for example, when the standard deviation (luminance evaluation value) σ calculated from the luminance projection distributions Bp _W1 (Z) and Bp _W2 (Z) is equal to or greater than a predetermined standard deviation, the other vehicle is traveling in the adjacent lane It can be determined that In addition, when the standard deviation (brightness evaluation value) σ is less than the predetermined standard deviation, it can be determined that the other vehicle is traveling in the adjacent adjacent lane. The predetermined standard deviation serving as the threshold is set to an appropriate value based on an experiment or the like.
(Description of the flow of the other vehicle travel lane determination process in the second embodiment)

  The entire flow of the process performed by the approaching vehicle detection device 100b is substantially the same as the flow of the first embodiment shown in FIG. 7, and only the method of the other vehicle travel lane determination process (step S28 in FIG. 7) is different. . Therefore, illustration of a flowchart showing the flow of the entire process performed in the second embodiment is omitted.

  Hereinafter, the flow of the other vehicle travel lane determination processing performed by the approaching vehicle detection device 100b will be described with reference to FIG. In addition, FIG. 9 is referred for description of a structure site | part.

  (Step S80) The window setting unit 72 sets detection ranges (windows) W1 and W2 on the overhead image.

(Step S82) The luminance projection distribution calculation unit 73b calculates luminance projection distributions Bp _W1 (Z) and Bp _W2 (Z) inside the detection ranges (windows) W1 and W2, respectively.

(Step S84) The other vehicle travel lane determination unit 64 determines whether the standard deviation σ of the luminance projection distributions Bp _W1 (Z) and Bp _W2 (Z) is equal to or greater than a predetermined standard deviation. If it is equal to or greater than the predetermined standard deviation, the process proceeds to step S88, and otherwise, the process proceeds to step S86.

  (Step S86) It is judged that the other vehicle is traveling in the adjacent adjacent lane, and the process returns to the main routine (not shown).

  (Step S88) It is judged that the other vehicle is traveling in the adjacent lane, and the process returns to the main routine (not shown).

When the other vehicle 14 is in the adjacent lane 24, the projecting position of the luminance projection distribution Bp _W1 (Z) changes with time according to the relative speed of the vehicle 10 and the other vehicle 14. Therefore, it is also possible to use the projecting position of the luminance projection distribution Bp _W1 (Z) as the luminance evaluation value. That is, the standard deviation σ is less than a predetermined standard deviation of the luminance projection distribution Bp W1 _(Z), yet, when the luminance projection distribution Bp W1 of projecting position of the _(Z) is moving with time, other vehicles 14 The determination accuracy can be improved by determining that the vehicle is traveling in the adjacent adjacent lane.

As described above, according to the approaching vehicle detection device 100a according to the first embodiment of the present invention configured as described above, the road surface on the rear side of the vehicle 10 captured by the rear camera 50 (imaging unit) is included. When the headlight detection unit 70 detects the headlights of other vehicles from the original image I (t), the luminance distribution calculation unit 73a generates an overhead image of the original image I (t) that has been overhead converted Calculate the average brightness B _W1 (t) (B _W2 (t)) (brightness evaluation value) inside the detection range W1 (W2) (window) of the predetermined size set by the window setting unit 72 during the other vehicle Based on the average brightness B _W1 (t) (B _W2 (t)) (brightness evaluation value), the traveling lane determination unit 64 travels in the adjacent lane 22 (26) of the lane where the vehicle 10 is traveling To determine if you are traveling in the adjacent lane 24 (28) Because, the approaching vehicle traveling the next adjacent lane 24 (28), there is no erroneously detected as the approaching vehicle traveling on the next lane 22 (26).

Further, according to the approaching vehicle detection device 100a according to the first embodiment of the present invention configured as described above, the luminance distribution calculation unit 73a determines the average luminance in the detection range W1 (W2) (window) as the luminance evaluation value. The other vehicle travel lane determination unit 64 calculates B _W1 (t) (B _W2 (t)), the average brightness B _W1 (t) (B _W2 (t)) is the moving average value B _thW1 (t) ( When it is larger than B _thW2 (t) (predetermined average value), it is determined that the other vehicle is traveling in the adjacent lane 22 (26). Otherwise, the other vehicle is adjacent the adjacent lane 24 (28) Since it is determined that the vehicle is traveling, the traveling lanes of other vehicles can be reliably determined in a short time by a simple arithmetic process.

Then, according to the approaching vehicle detection device 100a according to the first embodiment of the present invention configured as described above, the average brightness B _W1 (t) (B _W2 (t)) for determining the traveling lane of another vehicle Since the threshold value (predetermined average value) is the moving average value B _thW1 (t) (B _thW2 (t)) of the average luminance B _W1 (t) (B _W2 (t)), the brightness of the road surface of the road 30 Even when there is a fluctuation in the brightness, it is possible to reliably detect the change in the luminance of the road surface due to the headlights of other vehicles.

  Furthermore, according to the approaching vehicle detection device 100a according to the first embodiment of the present invention configured as described above, the window setting unit 72 is an overhead view of the image captured by the rear camera 50 (imaging unit) from directly above. In order to convert into an image and set at least one detection range W1 (W2) (window) of at least one predetermined size in this overhead image, the detection range W1 (W2) (window) of a predetermined size is easily and reliably set can do. In particular, even if the attachment position of the rear camera 50 is different for each vehicle, the window having the same shape may be set at the same position on the overhead image as long as conversion to the overhead image can be performed. There is no need to prepare different programs.

  Further, according to the approaching vehicle detection device 100a according to the first embodiment of the present invention configured as described above, the headlight detection unit 70 detects the vehicle 10 in the image captured by the rear camera 50 (imaging unit). The headlights of other vehicles are detected within the headlight detection areas R1 and R2 (predetermined area) set in the range where the headlights of other vehicles traveling on the adjacent lane or adjacent adjacent lane are observed Therefore, by narrowing down the detection range of the headlights, it is possible to reliably detect the necessary headlights in a short time.

  Then, according to the approaching vehicle detection device 100a according to the first embodiment of the present invention configured as described above, the other vehicle travel lane determination unit 64 determines that the other vehicle is traveling in the adjacent adjacent lane. In addition, since it is determined that there is no other vehicle on the side of the adjacent adjacent lane, it is possible to reliably prevent the false notification of the warning.

  Furthermore, according to the approaching vehicle detection device 100a according to the first embodiment of the present invention configured as described above, when it is determined that the other vehicle is traveling in the adjacent lane adjacent to the vehicle 10, the vehicle 10 is Since the alarm suppressing portion 67 for suppressing the alarm output when trying to change lanes is provided on the side of the adjacent adjacent lane side, erroneous notification of an alarm is surely prevented when another vehicle is traveling on the adjacent adjacent lane. Can.

In addition, according to the approaching vehicle detection device 100b according to the second embodiment of the present invention configured as described above, the luminance evaluation value corresponds to the luminance value in the detection range W1 (W2) (window) in the left-right direction of the vehicle 10. Is the standard deviation σ of the luminance projection distribution Bp _W1 (Z) (Bp _W2 (Z)) accumulated along the side, and the other vehicle travel lane determination unit 64 determines that the standard deviation σ is larger than a predetermined standard deviation. Because it is determined that the other vehicle is traveling in the adjacent lane, and it is determined that the other vehicle is traveling in the adjacent adjacent lane when it is other than that, the other operation is surely performed in a short time by a simple calculation process. The traffic lane of the vehicle can be determined.

  In the first and second embodiments, the detection ranges W1 and W2 are both set. However, in FIG. 5, the detection is performed when the vehicle 10 is traveling to the right of the road 30 (adjacent lane 22, adjacent adjacent lane 24). Only the range W2 may be set, and only the detection range W1 may be set when the vehicle 10 is traveling on the left of the road 30 (adjacent lane 26, adjacent 28). Whether the vehicle 10 is traveling to the right or to the left of the road 30 is not described in the first and second embodiments. For example, a lane marker drawn at the end of the lane of the road is detected and its arrangement is analyzed. It can be determined by

  Moreover, although the example which processes only using the image imaged with the rear camera 50 was shown in Example 1, Example 2, in addition to the rear camera 50, right and left incorporated in the left and right door mirrors of the vehicle 10 further. It is also possible to perform the same processing using an image captured from a wider range using a rear side camera.

  Although the embodiments of the present invention have been described in detail with reference to the drawings, the embodiments are merely examples of the present invention, and therefore, the present invention is not limited to only the constitutions of the embodiments. Needless to say, even if there are design changes and the like within the scope of the present invention, they are included in the present invention.

10: Vehicle 50: Rear camera 61: Night judgment unit 62: Vehicle information acquisition unit 63: Image recognition processing unit 64: Other vehicle travel lane judgment unit 65 · · · alarm control unit 66 · · · alarm output unit 67 · · · alarm suppression unit 70 · · · headlight detection unit 71 · · · · eyelid image generation unit 72 · · · · · · Unit 73a: luminance distribution calculation unit 74: moving average calculation unit 75: image registration unit 76: difference image generation unit 77: relative speed calculation unit 78: Three-dimensional object determination unit 82 · · · Vehicle speed sensor 84 · · · Turn signal switch 90 · · · Indicator 92 · · · Buzzer 100a · · · approaching vehicle detection device

Claims (7)

It is an approaching vehicle detection device that detects and notifies other vehicles approaching from the rear by turning on the headlights of the adjacent lane of the lane in which the vehicle is traveling from the traveling vehicle,
An imaging unit configured to capture an image including a road surface on the rear side of the vehicle;
A window setting unit configured to set at least one window of a predetermined size having a predetermined positional relationship with the vehicle at a position corresponding to a rear side area of the vehicle in the image;
A headlamp detection unit that determines whether a headlamp of another vehicle is detected in a predetermined area of the image;
When the headlight detection unit detects the headlights of the other vehicle, the brightness distribution calculation of calculating the brightness evaluation value in each window based on the brightness value of the area corresponding to the window of the image Department,
The other vehicle is present in an adjacent lane adjacent to the lane in which the vehicle is traveling, or adjacent to a distant side of the vehicle with respect to the adjacent lane based on the brightness evaluation value in each window either present next adjacent lane to have, and other vehicle travel lane determining unit determines,
The luminance evaluation value is an average value of luminance values of regions corresponding to the respective windows, and
The other vehicle travel lane determination unit determines that the other vehicle is traveling in the adjacent lane when the average luminance is larger than a predetermined average value, and in the other cases, the other vehicle is adjacent to the adjacent lane. traveling to have the decision to approaching vehicle detection device according to claim Rukoto. The approaching vehicle detection device according to claim 1, wherein the predetermined average value is a moving average value of luminance values of areas corresponding to the respective windows. It is an approaching vehicle detection device that detects and notifies other vehicles approaching from the rear by turning on the headlights of the adjacent lane of the lane in which the vehicle is traveling from the traveling vehicle,
An imaging unit configured to capture an image including a road surface on the rear side of the vehicle;
A window setting unit configured to set at least one window of a predetermined size having a predetermined positional relationship with the vehicle at a position corresponding to a rear side area of the vehicle in the image;
A headlamp detection unit that determines whether a headlamp of another vehicle is detected in a predetermined area of the image;
When the headlight detection unit detects the headlights of the other vehicle, the brightness distribution calculation of calculating the brightness evaluation value in each window based on the brightness value of the area corresponding to the window of the image Department,
The other vehicle is present in an adjacent lane adjacent to the lane in which the vehicle is traveling, or adjacent to a distant side of the vehicle with respect to the adjacent lane based on the brightness evaluation value in each window either present next adjacent lane to have, and other vehicle travel lane determining unit determines,
The brightness evaluation value is a standard deviation of a brightness projection distribution obtained by accumulating the brightness values in each of the windows along the lateral direction of the vehicle,
The other vehicle travel lane determination unit determines that the other vehicle is traveling in the adjacent lane when the standard deviation is larger than a predetermined standard deviation, and when the other vehicle is traveling in the other lane, the other vehicle is approaching vehicle detection device which is characterized that you determined to be traveling on the next adjacent lane. The window setting unit is configured to convert the image captured by the imaging unit into a bird's-eye view image viewed from directly above, and set at least one window of a predetermined size in the bird's-eye view image. The approaching vehicle detection device according to any one of claims 1 to 3 . The said predetermined area | region is set to the range where the headlight of the other vehicle which is drive | working the adjacent lane of the said vehicle, or the adjacent lane in the said image is observed. The approaching vehicle detection device according to any one of Items 4 . The other vehicle travel lane determination unit is characterized in that when it is determined that the other vehicle is traveling in the adjacent lane, the other vehicle is determined not to be present on the adjacent adjacent lane side. The approaching vehicle detection device according to any one of claims 1 to 5 . The vehicle includes an alarm suppressing unit that suppresses an alarm output when the vehicle tries to change lanes to the adjacent adjacent lane side when it is determined that the other vehicle is traveling in the adjacent adjacent lane. An approaching vehicle detection device according to any one of claims 1 to 5 , characterized by: