JP2005309660A - Device supporting vehicle in turning right or left - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To prevent a vehicle from getting in contact with a pedestrian on a crosswalk which the vehicle reaches by turning to the right or left without infrastructural improvement for each intersection. <P>SOLUTION: A picked-up image taken by an image pickup means is processed to detect the existence of pedestrians walking on a crosswalk which a vehicle reaches by turning the right, and it is determined whether the vehicle keeps waiting so as to turn the right until an oncoming vehicle passes. When the vehicle is determined to keep waiting so as to turn the right and the pedestrians are detected, a warning is issued in case that the driver's will to start the vehicle is detected. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a device that supports a driver's right and left turn operation.

  There is known a pedestrian detection device that detects a pedestrian on a pedestrian crossing at an intersection and displays the presence of the pedestrian on a panel installed near the intersection or on a screen of a navigation device (for example, Patent References 1 to 5).

Prior art documents related to the invention of this application include the following.
JP 05-0667293, JP-A-07-105477, JP-A-11-056393, JP 2000-346657 A, JP 2001-195698 A

  However, in the conventional pedestrian detection device described above, a pedestrian detection device must be installed at each intersection, and a large amount of capital investment is required for infrastructure development.

  The captured image by the imaging means is processed to detect the presence of a pedestrian crossing the pedestrian crossing at the right turn destination, and whether the vehicle is in a state of waiting for a right turn waiting for a passing vehicle to pass by. When it is determined that the vehicle is waiting for a right turn and a pedestrian is detected, a warning is issued when the driver's intention to start the vehicle is detected.

  According to the present invention, it is possible to prevent contact with a pedestrian on a right turn pedestrian crossing only by a system mounted on a vehicle without performing infrastructure maintenance for each intersection.

  When making a right turn at an intersection, the driver makes a decision to start a right turn by confirming multiple points, but if there are many oncoming vehicles that pass each other, pay attention to finding a possible right turn. Attention to pedestrians on pedestrian crossings tends to be neglected. In particular, it is difficult for an elderly driver to pay attention to a plurality of places at the same time, and attention to pedestrians on the right turn pedestrian crossing is neglected. Therefore, the present invention is applied to a device that detects and warns a pedestrian or bicycle on a pedestrian crossing at a right turn destination, particularly a pedestrian or bicycle approaching from the rear of the vehicle, and assists the driver in turning right. An embodiment will be described.

<< First Embodiment >>
FIG. 1 shows the configuration of the first embodiment. The camera 201 images the right side of the vehicle and outputs the image. In the first embodiment, at a general intersection, a camera 201 having an angle of view on a pedestrian crossing at a right turn and a pedestrian or bicycle in the vicinity of the right turn is used, and on a pedestrian crossing at a right turn. In addition, the optical axis direction of the camera 201 is set so that pedestrians and bicycles in the vicinity thereof are in the imaging range. Since the camera 201 images the right side of the vehicle, the camera 201 captures images of pedestrians and bicycles around the right-hand pedestrian crossing, and also images oncoming vehicles passing each other while waiting for a right turn, and outputs an image of the vehicle passing by the pedestrian.

  The image processing apparatus 202 processes an image captured by the camera 201 to detect an oncoming vehicle and a pedestrian and a bicycle around a right-turn pedestrian crossing while waiting for a right turn. The control device 203 includes a CPU and peripheral components such as a memory and an A / D converter, and detects a pedestrian (including a bicycle) at the right turn by executing a control program described later. The warning device 204 is a device that warns by voice the presence of a pedestrian at the right turn, and a buzzer, a speaker, or the like can be used. In addition to the image processing device 202 and the warning device 204, the control device 203 includes a vehicle speed sensor 205 for detecting the vehicle speed, a turn signal switch 206 for turning on and off the turn signal lamp, and a brake switch 207 for detecting the depression state of the brake pedal. Etc. are connected.

  FIG. 2 is a flowchart showing the pedestrian detection program according to the first embodiment. The control device 203 repeatedly executes this pedestrian detection program while an ignition switch (not shown) of the vehicle is on. In step 301, it is confirmed whether or not the vehicle speed detected by the vehicle speed sensor 205 is 0 km / h. Usually, when you can turn right by reducing the vehicle speed, there are many cases where there is a relatively large margin between oncoming vehicles, and the initial speed at the start of the right turn is not 0km / h, so the time required for a right turn is short. Since it is easy to identify pedestrians and bicycles that are about to cross the right turn pedestrian crossing when approaching an intersection, it is not necessary to support right turn by detecting pedestrians when the vehicle speed is not 0 km / h. The process waits at step 301 until the vehicle speed reaches 0 km / h, and proceeds to step 302 when the vehicle speed reaches 0 km / h. Note that the vehicle speed “0 km / h” in this case is a reference value for determining whether or not the vehicle is stopped. Therefore, even if the vehicle speed is not strictly 0 km / h, it may be a low vehicle speed value that can be regarded as being stopped. Good.

  In the next step 302, it is confirmed whether or not the right turn signal switch 206 is on. When the right turn signal switch 206 is not turned on, there is no need for right turn support, so the routine returns to step 301. When the right turn signal switch 206 is turned on, the routine proceeds to step 303. In step 303, a subroutine to be described later is executed to process an image captured by the camera 201 and detect an oncoming vehicle that passes by when making a right turn. The oncoming vehicle detection process that passes each other when making a right turn will be described later.

  In the subsequent step 304, it is determined whether the detection state of the passing oncoming vehicle satisfies a predetermined condition, that is, whether the driver is watching the right turn. When the passing state of the oncoming vehicle is overcrowded, that is, when the passing frequency of the oncoming vehicle is high, it is determined that the driver is looking at the right turn. In addition, what is necessary is just to set the passing frequency of the oncoming vehicle which can be judged that the driver | operator is looking at the time of a right turn as a predetermined condition. Details of this determination will be described later. If the detection state of the passing oncoming vehicle satisfies the predetermined condition, the process proceeds to step 305. Otherwise, the process returns to step 301 and the above-described processing is repeated.

  In step 305, a subroutine to be described later is executed to process an image captured by the camera 201 and detect an approaching person to the right turn pedestrian crossing. The detection of an approaching person to the right turn pedestrian crossing will be described later. Next, in step 306, it is confirmed whether or not an approaching person to the right turn pedestrian crossing has been detected. If an approaching person is detected, the process proceeds to step 307. If an approaching person is not detected, the process returns to step 301 and described above. Repeat the process.

  When the driver is waiting for a right turn while looking at the distance between the oncoming vehicles, if a pedestrian (including a bicycle) approaching the right-hand pedestrian crossing is detected, the brake switch 207 is turned on in step 307. To see if the brake pedal that was depressed was released. If release of the brake pedal is detected, the process proceeds to step 308; otherwise, the process returns to step 301 and the above-described processing is repeated. When the brake pedal that has been depressed is released, it is determined that the driver is willing to start a right turn, and in step 308, the warning device 204 warns that there is a possibility of contacting the pedestrian at the right crossing. .

  Note that the driver's intention to start a right turn with the brake switch 207 is appropriate because the vehicle starts to move at an extremely low speed due to the creeping phenomenon even in an automatic transmission vehicle immediately after releasing the foot from the brake pedal. The driver can be alerted to the presence of a pedestrian at the timing.

  FIG. 3 shows a subroutine for detecting an oncoming vehicle passing by when making a right turn. This subroutine is executed in step 303 of FIG. In step 401, an image is input from the camera 201 that captures the right side of the vehicle.

  Usually, when turning right at an intersection, the driver concentrates his attention on the oncoming vehicle. The camera 201 is installed so as to compensate for the viewing angle of the driver when the driver is looking at the oncoming vehicle passing each other when turning right at the intersection. As shown in FIG. 4, the general driver's left and right viewing angles are about 200 degrees in total, which is 100 degrees left and right with respect to the front. However, the range in which the driver can watch is only a very small area, and the range in which the color can be confirmed with both eyes is about 70 degrees. Therefore, it is difficult to check pedestrians and bicycles approaching the right-hand pedestrian crossing in a state where the oncoming vehicles are passing each other.

  FIG. 5 shows the installation position and orientation of the camera (the direction of the optical axis of the photographing lens) that compensates for the viewing angle of the driver. “A” in the figure shows the pedestrians around the pedestrian crossing at the right turn in addition to the viewing angle that allows the driver to check the color with both eyes when the driver is gazing at the oncoming vehicle as shown in FIG. The imaging range is set so that it can be confirmed by the camera 201. In this example, the horizontal angle (view angle) of the camera 201 is 90 degrees of a general wide-angle lens.

  In addition, “B” in FIG. 5 is a camera for detecting a passing vehicle and a pedestrian at the time of a right turn as a camera of a front side view monitor used for confirming a road condition where the vehicle intersects when passing an intersection with poor visibility. This is also an example. As shown in FIG. 7, even if the front side view monitor camera is also used, it can be sufficiently used as the imaging range of the passing vehicle and the pedestrian detection camera when turning right.

  “C” in FIG. 5 is an example in which the camera 201 is attached to the front end of the vehicle and the direction (the optical axis direction of the photographing lens) is directed to the right rear side. In this way, as shown in FIG. 8, it is possible to deal with a relatively fast bicycle and the like, and it is possible to capture a pedestrian and a bicycle who are about to cross a right-turn pedestrian crossing within the imaging range of the camera 201. .

  FIG. 9 shows an example in which a near-infrared lamp is installed near the camera 201 so that a pedestrian or bicycle on the right side can be detected even at night.

  After inputting the image of the camera 201 in step 401 in FIG. 3, it is determined in step 402 whether or not the vehicle detection initial condition flag is ON. Since the flag is OFF in the initial state, the process proceeds to step 403, and it is determined whether or not a “difference satisfying a predetermined condition” has occurred in the left end region of the camera image.

  Here, “difference satisfying a predetermined condition” means that each time between images when a passing vehicle enters the imaging range of the camera 201 and a time-series camera image as shown in FIG. 10 is captured. This is a density difference greater than a predetermined value generated in a pixel. Further, hereinafter, a “difference” pixel area where a density difference of a predetermined value or more has occurred is referred to as a “difference occurrence area”.

  When a passing vehicle enters the imaging range of the camera 201, difference areas are generated in order from the first time-series image as shown in FIG. The difference generation area due to the passing vehicle is generated from the left end of the screen, is enlarged to the entire image, and then moves to the right end and disappears. The determination in step 403 captures an initial difference phenomenon that occurs due to a passing vehicle. If no difference occurs in the left end region of the image, the process returns to step 401. On the other hand, if a difference that satisfies the predetermined condition occurs in the left end area of the image, the process proceeds to step 404, the vehicle detection initial condition flag is turned ON, and the corresponding image is set as n frames in the memory (not shown) of the control device 203. Remember. Thereafter, the process returns to step 401 to input the next image.

  If there is a difference in the left end region of the camera image, the vehicle detection initial condition flag is ON, so the routine proceeds from step 402 to 405, where the vehicle detection image frame counter is counted up. The vehicle detection image frame counter is a counter configured in a software form of the CPU of the control device 203, and counts the number of image frames in which a difference has occurred.

  In step 406, it is determined whether or not there is a difference occurrence area that satisfies a predetermined condition in an image frame (n + α) counted up from an image frame n in which a difference first occurs in the left end area of the camera image.

  Here, the predetermined condition of the difference generation region is, for example, based on a reference area (number of pixels) for determining whether or not there is an oncoming vehicle in which the area (number of pixels) of the difference generation region passes on the screen. And the difference occurrence area is moved to the right by a distance corresponding to the count-up number α from the image frame n.

  If it is determined in step 406 that there is no difference generation area that satisfies the predetermined condition, the process proceeds to step 407, where the difference in the left end area of the image generated in step 403 does not correspond to a passing vehicle, and vehicle detection is performed. While turning off the initial condition flag, the vehicle detection image frame counter is cleared and the process returns to step 401.

  On the other hand, if it is determined in step 406 that there is a difference occurrence area that satisfies the predetermined condition, the process proceeds to step 408, and it is determined whether or not a difference that satisfies the predetermined condition has occurred in the right end area of the image. As described above, the “difference satisfying the predetermined condition” means that when a passing vehicle enters the imaging range of the camera 201 and a time-series camera image as shown in FIG. The density difference of a predetermined value or more generated in each pixel. In the final stage when the vehicle passes through the imaging range of the camera 201, a difference occurs only in the right end region of the image.

  While a difference occurs in the entire image, the process returns to step 401 and the above-described processing is repeated. However, if a difference occurs only in the right end area of the image, the process proceeds to step 409, and the count value of the vehicle detection image frame counter is set to a predetermined value. It is determined whether or not the value is greater than or equal to. This predetermined value is a criterion value for judging whether or not there is a passing oncoming vehicle, and an appropriate value is set in consideration of the influence of the vehicle type of the passing vehicle, particularly the size and length, the passing speed, etc. To do.

  If the count value of the vehicle detection image frame counter is equal to or greater than the predetermined value, the process proceeds to step 410, and a passing vehicle is detected. The process returns to step 401 and the above-described passing vehicle detection process is repeated. On the other hand, if the count value of the image frame counter is less than the predetermined value, the process proceeds to step 407, the vehicle detection initial condition flag is turned OFF, the image frame counter is cleared, and the process returns to step 401. repeat.

  FIG. 11 shows a difference occurrence state in the camera image when different types of vehicles pass each other. In step 304 of FIG. 3 for determining whether or not the vehicle is waiting for a right turn at the intersection, based on the change in the total number of difference occurrence pixels in each image frame in which the passing vehicle is detected by the passing vehicle detection process described above. Can be determined. The total number of difference occurrence pixels per image capture time interval 1/30 second is measured as vehicle A or D in the case of a passenger car, and is measured as vehicle B in the case of a one-box type vehicle. In the case, it is measured like the vehicle C. Since the time interval at which the difference occurs is known from this measured value, the passing frequency and the inter-vehicle distance of the passing vehicle can be detected, and can be used for determining the right turn waiting state in the intersection.

  FIG. 12 shows a subroutine for detecting an approaching person to the right turn pedestrian crossing. This subroutine is executed in step 305 in FIG. In step 1301, a captured image is input from the camera 201, and in a subsequent step 1302, it is confirmed whether or not the approaching person detection initial condition flag is ON. Since the flag is OFF in the initial state, the process advances to step 1303 to determine whether or not a difference area that satisfies a predetermined condition has occurred.

  FIG. 13 is a time-series image of a pedestrian approaching the pedestrian crossing at the right turn taken by the camera 201 from the rear of the vehicle. When there is a pedestrian (including a bicycle) approaching the right turn destination pedestrian crossing, the above-described difference areas are generated in order from the first one in the time-series image shown in FIG. In this case, since it is assumed that a pedestrian approaches from the rear of the vehicle, it occurs in the right end region of the image and sequentially moves to the left end of the image. The area (number of pixels) of the difference area generated in the image is compared with a criterion value set in advance to determine the presence or absence of pedestrians (including bicycles), and the area (number of pixels) of the difference area is determined. If it is equal to or greater than the reference value, it is determined that there is a pedestrian approaching the right-hand pedestrian crossing.

  If no difference satisfying the predetermined condition has occurred in step 1303, the process returns to step 1301, and the camera image is input again. If a difference that satisfies the predetermined condition has occurred and it is confirmed that there is a pedestrian approaching the right-hand pedestrian crossing, the process proceeds to step 1304, and the approaching detection initial condition flag is turned ON. In the subsequent step 1305, the first captured image of the pedestrian approaching the right turn pedestrian crossing is stored as n frames in the memory of the control device 203, and the position where the difference occurs is stored in the memory. Thereafter, the process returns to step 1301 to input the next image.

  If a pedestrian difference area is generated in the camera image, the approaching person detection initial condition flag is ON, so that the process proceeds from step 1302 to 1306 and the approaching person detection image frame counter is counted up. This approaching person detection image frame counter is a counter configured in a software form of the CPU of the control device 203, and counts the number of image frames in which a pedestrian difference area is generated.

  In step 1307, it is determined whether or not there is a difference generation area that satisfies a predetermined condition in an image frame (n + α) counted up from an image frame n in which a difference first occurs in the camera image.

  The predetermined condition is that the area (number of pixels) of the difference generation area is compared with a determination reference value set in advance to determine the presence or absence of a pedestrian (including a bicycle), and the area (pixels) of the difference generation area Number) is equal to or greater than the determination reference value, and the position of the difference generation area on the image frame (n + α) is predetermined from the position of the difference generation area on the image frame n where the difference first occurs in the camera image. The condition is that the image moves leftward within the range. In other words, the conditions are based on the movement characteristics of pedestrians and bicycles.

  If it is determined in step 1307 that there is no difference generation area that satisfies the predetermined condition, the image frame n in which the difference first occurs in the camera image is not an image capturing a pedestrian or a bicycle, that is, a detection target object Since it is not a dangerous object that touches on a pedestrian crossing, the process proceeds to step 1310, the approaching person detection initial condition flag is turned OFF, the approaching person detection image frame counter is cleared, and the process returns to step 1301.

  On the other hand, if it is determined in step 1307 that there is a difference occurrence area that satisfies the predetermined condition, the process proceeds to step 1308 to determine whether or not the count value of the approaching person detection image frame counter is equal to or larger than the predetermined value. If the count value of the image frame counter is equal to or larger than the predetermined value, the process proceeds to step 1309, and the process returns to step 1301 because a pedestrian or bicycle is detected. On the other hand, if the count value of the image frame counter is less than the predetermined value, the process returns to step 1301.

  In Steps 1303 and 1307, when it is determined that there is a range of reference values for determining the presence or absence of pedestrians (including bicycles) and that there are more than a predetermined amount of pedestrians and bicycles around the pedestrian crossing Since there are many pedestrians and bicycles on the right turn pedestrian crossing and there is little risk of overlooking them when turning right, the warning output may be limited without detecting pedestrians.

  Next, an example will be described in which an optical flow between time-series images is used for image processing for detecting an oncoming vehicle passing when waiting for a right turn or detecting an approaching person on a right turn pedestrian crossing. This method has an advantage that the detection performance can be further improved because the image area can be arbitrarily divided and the weight can be freely set, and the moving direction and moving speed of the detection target in the area can be determined.

  The optical flow is a method for detecting a motion in an image by a set of vector quantities having a size and a direction. In the image processing apparatus, image data and area data are input, and an optical flow is output. The area data is represented by the position (tx, ty) and size (tw, th) of the reference area and the position (sx, sy) and size (sw, wh) of the search area as shown in FIG. It is data. In order to calculate the optical flow, at least one reference region (X coordinate tx, Y coordinate ty, width tw pixels, height th pixels) is set for a face image filtered at a certain time t, and the time The same number of search areas (X coordinate sx, Y coordinate sy, width sw pixel, height sh pixel) as the reference area set for the (t + 1) filtered face image are set. In these two areas, the reference area is set inside the search area as shown in FIG.

In the calculation of the optical flow of this embodiment, a technique called a block matching method is generally used, and an area having the highest similarity to the reference area of the previous frame is calculated from the search area of the current frame. As shown in FIGS. 14 and 15, the similarity is calculated by calculating the grayscale data in the reference area as T, an arbitrary position (xd, yd) in the search area,
-(sw-tw) / 2 〈xd 〈(sw-tw) / 2,
-(sh-th) / 2 <yd <(sh-th) / 2 (1)
Assuming that the grayscale data having the same size as the reference area cut out from the candidate area S (xd, yd), the similarity θ is defined as the angle θ formed by the reference area T and the candidate area S by the following equation.
cos θ (xd, yd) = T · S (xd, yd) / (| T | · | S (xd, yd) |) (2)

  The similarity θ between the reference area and the candidate area is obtained at all positions in the search area. The coordinate (xd, yd) that maximizes the similarity θ is taken as the motion vector (xd, yd) of the reference region. In addition to the method described in this embodiment, the optical flow (motion detection) calculation method is supervised by Nobuyuki Yagi “Digital Video Processing” (Edition of the Video Information Media Society, pp129-139, 2000, published by Ohm) A number of techniques for detecting motion from moving images have been introduced in the literature, and can be used.

  FIG. 16 is a graph showing the output state of the optical flow in the left-right direction of the movement of the passing vehicle and the pedestrian in time series. The calculation result of FIG. 16 is obtained by integrating the amount of movement in the left-right direction generated in all reference regions arranged in the entire image as shown in FIG. 14, but the method using an optical flow as an image processing apparatus is as follows. As shown in FIG. 17, it is possible to limit to the A region and the B region in order to obtain the movement vector of the passing vehicle, and the speed and size of the passing vehicle can be determined by calculating the movement vector. Further, the reference area for pedestrian detection can be limited to the C area and the D area, and the degree of risk can be determined by the movement amount generated in the C area and the movement amount generated in the D area.

<< Second Embodiment of the Invention >>
A second embodiment will be described in which a preceding vehicle is detected by a laser radar so that the risk of contact with a pedestrian on a right-hand pedestrian crossing can be determined more accurately when turning right at an intersection.

  FIG. 18 shows the configuration of the second embodiment. In the second embodiment, a laser radar 1908 is added to the configuration of the first embodiment shown in FIG. The laser radar 1908 detects the preceding vehicle and the distance to the preceding vehicle. 18, devices 1901 to 1907 other than the radar laser 1908 are the same as the devices 201 to 207 shown in FIG.

  FIG. 19 is a flowchart illustrating a pedestrian detection program according to the second embodiment. As shown in FIG. 20, when the presence of a preceding vehicle is detected while stopping while looking at the distance between oncoming vehicles when making a right turn, the position of the pedestrian who is about to cross the right crossing pedestrian is driving If the preceding vehicle is detected when waiting for a right turn in step 2003, the step without passing the vehicle and detecting the pedestrian is performed. Return to 2001. In this case, no warning is issued. 19 is the same as the process of each corresponding step in FIG. 2 except for the above-described process in step 2003, and a description thereof will be omitted.

<< Third Embodiment of the Invention >>
A third embodiment will be described in which it is determined whether or not there is a preceding vehicle when waiting for a right turn based on the steering angle of the host vehicle, and no pedestrian detection warning is issued when there is a preceding vehicle.

  FIG. 21 shows the configuration of the third embodiment. In the third embodiment, a snake angle sensor 2208 is added to the configuration of the first embodiment shown in FIG. Snake angle sensor 2208 detects the steering angle of the vehicle. In FIG. 21, devices 2201 to 2207 other than the steering angle sensor 2208 are the same as the devices 201 to 207 shown in FIG.

  FIG. 22 is a flowchart showing a pedestrian detection program according to the third embodiment. If the presence of a preceding vehicle is detected while stopping while looking at the distance between oncoming vehicles when turning right, the position of the pedestrian trying to cross the pedestrian crossing at the right turn is easy to see even from the driver's viewing angle. Therefore, if the steering wheel is not turned to the right by a predetermined angle or more in step 2303, it is determined that there is a preceding vehicle waiting for a right turn and the passing vehicle is detected. And return to step 2001 without performing pedestrian detection. In this case, no warning is issued. 22 is the same as the process of each corresponding step in FIG. 2 except for the above-described process in step 2303, and the description thereof will be omitted.

<< Fourth Embodiment of the Invention >>
In addition to giving a warning when a pedestrian approaching the right turn pedestrian crossing is detected, the driver prohibits the throttle valve from opening even if the driver steps from the brake pedal to the accelerator pedal, and the driver watches the right rear. A fourth embodiment in which the start of the right turn operation is delayed by an appropriate time until it is confirmed that there are no pedestrians or bicycles approaching the right turn destination pedestrian crossing will be described.

  FIG. 23 shows the configuration of the fourth embodiment. In the fourth embodiment, an accelerator control device 2508 is added to the configuration of the first embodiment shown in FIG. The accelerator control device 2508 normally opens and closes the throttle valve in response to depression of the accelerator pedal, but when the pedestrian detection signal at the time of right turn is output from the control device 2503, the driver switches from the brake pedal to the accelerator pedal. However, the throttle valve is not opened immediately and the opening of the throttle valve is prohibited for a predetermined time. The accelerator control device 2508 may not be able to depress the accelerator pedal. In FIG. 23, the devices 2501 to 2507 other than the accelerator control device 2508 are the same as the devices 201 to 207 shown in FIG.

  Thus, according to one embodiment, the state of waiting for a right turn waiting for the passing of a passing vehicle to pass while detecting the presence of a pedestrian crossing the pedestrian crossing to the right turn by processing the image captured by the camera If it is determined that the vehicle is waiting for a right turn and a pedestrian is detected, a warning is issued if the driver's intention to start the vehicle is detected. Therefore, it is possible to prevent contact with pedestrians on the right turn pedestrian crossing by using only the system installed in the vehicle, without performing infrastructure maintenance at each intersection.

  Further, according to one embodiment, a captured vehicle image is processed to detect a passing vehicle, a vehicle stop state is detected, the turn signal switch is operated to the right turn side, and the vehicle passes by image processing. When a facing vehicle is detected, it is determined that the vehicle is in a right turn waiting state, so that it is possible to accurately detect that the vehicle is in a right turn waiting state.

  According to one embodiment, if a preceding vehicle is detected when it is determined that the vehicle is waiting for a right turn, no warning is issued even if the driver's intention to start is detected. As a result, unnecessary warnings can be avoided.

  According to an embodiment, when it is determined that the vehicle is waiting for a right turn and a pedestrian is detected, if the driver's intention to start the vehicle is detected, a warning is given and the vehicle Since the acceleration of the vehicle is prohibited, the contact with the pedestrian on the right turn pedestrian crossing can be surely prevented.

  According to one embodiment, when the presence of a pedestrian exceeding a predetermined amount is detected, the warning and the acceleration of the vehicle are not prohibited, so that unnecessary warning and the prohibition of acceleration can be prevented. it can.

  The correspondence between the constituent elements of the claims and the constituent elements of the embodiment is as follows. That is, the cameras 201, 1901, 2012, 2501 are imaging means, the image processing devices 202, 1902, 2202, 2502 are pedestrian detection means and facing vehicle detection means, and the control devices 203, 1903, 2203, 2503 are waiting for a right turn. Judgment means and control means, brake switches 207, 1907, 2207, 2507 are start intention detection means, warning devices 204, 1904, 2204, 2504 are warning means, and vehicle speed sensors 205, 1905, 2205, 2505 are stop detection means. The laser radar 1908 and the snake angle sensor 2208 constitute preceding vehicle detection means, and the accelerator control device 2508 constitutes vehicle acceleration means. In addition, unless the characteristic function of this invention is impaired, each component is not limited to the said structure.

  In the above-described embodiment, an example in which the present invention is applied to a device that supports a driver's right turn operation in a left-hand traffic system has been described. However, a driver's left turn operation in a right-hand traffic system is supported. The same effect can be obtained.

  In the above-described embodiment, the facing image is detected by processing the image captured by the camera, the stop state of the vehicle is detected, the turn signal switch is operated to the right turn side, and the facing each other by the camera image processing. Although an example of determining that the vehicle is in a right turn waiting state when a vehicle is detected has been shown, except for a passing vehicle detection condition by camera image processing from among the determination conditions for a right turn waiting state, the stop state of the vehicle is If it is detected and the turn signal switch is operated to the right turn side, it may be determined that the vehicle is in a right turn waiting state.

It is a figure which shows the structure of 1st Embodiment. It is a flowchart which shows the pedestrian detection program of 1st Embodiment. It is a flowchart which shows the subroutine for detecting the oncoming vehicle which passes each other at the time of a right turn. It is a figure which shows a driver | operator's right-and-left viewing angle. It is a figure which shows the installation position and direction of a camera which supplement a driver | operator's viewing angle. It is a figure which shows the relationship between the driver | operator's visual field at the time of a right turn, and the imaging range of a camera. It is a figure which shows the relationship between the driver | operator's visual field at the time of a right turn, and the imaging range of a camera. It is a figure which shows the relationship between the driver | operator's visual field at the time of a right turn, and the imaging range of a camera. It is a figure which shows the example which installed the near-infrared lamp near the camera which detects a passing vehicle and a pedestrian. It is a figure which shows the time-sequential image of the passing vehicle imaged with the camera. It is a figure which shows the difference generation | occurrence | production situation in a camera image when vehicles of different types pass at the time of a right turn. It is a flowchart which shows the subroutine for detecting the approaching person to the right turn destination pedestrian crossing. It is a figure which shows the time series image of the pedestrian who approaches the right turn destination pedestrian crossing imaged with the camera from the vehicle back. It is explanatory drawing regarding the application method of an optical flow. It is explanatory drawing regarding the application method of an optical flow. It is explanatory drawing regarding the application method of an optical flow. It is explanatory drawing regarding the application method of an optical flow. It is a figure which shows the structure of 2nd Embodiment. It is a flowchart which shows the pedestrian detection program of 2nd Embodiment. It is a figure explaining the situation when a preceding vehicle exists at the time of a right turn. It is a figure which shows the structure of 3rd Embodiment. It is a flowchart which shows the pedestrian detection program of 3rd Embodiment. It is a figure which shows the structure of 4th Embodiment.

Explanation of symbols

201, 1901, 2201, 2501 Camera 202, 1902, 2202, 2502 Image processing devices 203, 1903, 2203, 2503 Control devices 204, 1904, 2204, 2504 Warning devices 205, 1905, 2205, 2505 Vehicle speed sensors 206, 1906, 2206 , 2506 Turn signal switch 207, 1907, 2207, 2507 Brake switch 1908 Laser radar 2208 Snake angle sensor 2508 Accelerator control device

Claims (10)

Imaging means for imaging the surroundings of the vehicle;
A pedestrian detection means for detecting the presence of a pedestrian crossing a pedestrian crossing at a right turn by processing a captured image by the imaging means;
A right turn waiting state determination means for determining whether or not the vehicle is in a state of waiting for a right turn waiting for passing a passing vehicle;
A starting intention detection means for detecting a driver's intention to start the vehicle;
When it is determined by the right turn waiting state determination means that the vehicle is in a right turn waiting state and a pedestrian is detected by the pedestrian detection means, the start intention detection means detects the driver's intention to start A vehicle right / left turn assisting device, comprising: control means for warning by warning means. The vehicle left / right support device according to claim 1,
The right turn waiting state determination means includes a stop detection means for detecting a stop state. When the stop state is detected by the stop detection means and the turn signal switch is operated to the right turn side, the vehicle waits for a right turn. It is determined that the vehicle is in a state. The vehicle left / right support device according to claim 1,
The right turn waiting state determination unit includes a facing vehicle detection unit that detects a facing vehicle by processing an image captured by the imaging unit and a stop detection unit that detects a stop state, and the stop state is detected by the stop detection unit. When the vehicle is detected and the turn signal switch is operated to the right turn side and a facing vehicle is detected by the facing vehicle detection means, it is determined that the vehicle is in a right turn waiting state. Right / left turn support device. In the vehicle left / right turn assist device according to any one of claims 1 to 3,
The vehicle right / left turn assisting device according to claim 1, wherein the start intention detecting means determines that the driver has a start intention when release of a brake pedal or release of a parking brake is detected by a brake switch. In the vehicle left / right turn assist device according to any one of claims 1 to 4,
A preceding vehicle detection means for detecting the presence or absence of a preceding vehicle,
When the preceding vehicle is detected by the preceding vehicle detecting means when the vehicle is determined to be in the right turn waiting state by the right turn waiting state determining means, the control means is a driver of the start intention detecting means. The vehicle right / left turn assisting device is characterized in that no warning is issued by the warning means even if a starting intention is detected. In the vehicle left / right turn assist device according to any one of claims 1 to 5,
When the vehicle is in a right turn waiting state by the right turn waiting state determining unit and a pedestrian is detected by the pedestrian detecting unit, the control unit starts the driver by the start intention detecting unit. A vehicle right / left turn assisting device that, when a will is detected, warns by the warning means and prohibits acceleration of the vehicle by the vehicle acceleration means. In the vehicle left / right turn assist device according to any one of claims 1 to 6,
The control means does not perform a warning and prohibition of acceleration of the vehicle when the presence of a pedestrian exceeding a predetermined amount is detected by the pedestrian detection means. In the vehicle left / right turn assist device according to any one of claims 1 to 7,
A vehicle left / right turn support device, wherein the imaging means is a camera of a front side view monitor used for checking a road condition that intersects when passing an intersection with poor visibility. In the vehicle left / right turn assist device according to any one of claims 1 to 8,
The pedestrian detection unit and the facing vehicle detection unit process a time-series image captured by the imaging unit by a difference calculation, and detect a pedestrian and a facing vehicle. In the vehicle left / right turn assist device according to any one of claims 1 to 8,
The pedestrian detection means and the facing vehicle detection means process a time-series image captured by the imaging means by optical flow calculation to detect a pedestrian and a facing vehicle, and a vehicle left / right turn assist device .

Images