JP4425669B2 - Vehicle driving support device - Google Patents

Description

  The present invention recognizes out-of-vehicle information based on detection information by radar means such as millimeter wave radar and infrared radar and detection information by imaging means such as a stereo camera and a monocular camera, and performs various driving operations based on the recognized out-of-vehicle information. The present invention relates to a vehicle driving support device that performs support control.

  In recent years, radar information such as millimeter wave radar and infrared laser radar and imaging means such as a stereo camera and a monocular camera are used in combination to recognize information outside the vehicle in front of the vehicle, and control of the own vehicle based on the recognized information outside the vehicle. Various proposals have been made for a vehicle driving support device that performs the above-mentioned, in particular, in this type of vehicle driving support device, constant speed traveling control and follow-up traveling control for the preceding vehicle are performed according to the recognition result of the preceding vehicle. The inter-vehicle distance control cruise control (ACC) function is widely put into practical use.

  In this case, in the vehicle driving support apparatus, in general, the own vehicle travel lane is estimated based on the image information captured by the imaging unit. In general, since the radar means is superior to the imaging means in the distance measurement accuracy of the three-dimensional object, the information on the preceding vehicle (preceding vehicle speed, inter-vehicle distance, etc.) detected on the own vehicle traveling lane is usually obtained from the radar. It is detected based on the measurement result of the means.

By the way, in the radar means, detection of the preceding vehicle information and the like may be temporarily disabled due to the emitted infrared rays, the three-dimensional object of the laser, irregular reflection on the side wall, or the like. In response to this, for example, in Patent Document 1, when distance measurement by a laser radar (radar unit) becomes impossible, instead of recognizing preceding vehicle information (inter-vehicle distance) based on the measurement result of the laser radar. A technique for recognizing preceding vehicle information based on an input image from an image input device (imaging means) is disclosed.
Japanese Patent Laid-Open No. 11-44533

  However, since there may be an error between the preceding vehicle information based on the measurement result of the radar unit and the preceding vehicle information based on the captured image from the imaging unit, in the above technique, the recognition method is switched. Sometimes the preceding vehicle information fluctuates greatly, and there is a risk that the ACC control or the like becomes temporarily unnatural.

  In particular, when there is a preceding vehicle or the like in the distance, the preceding vehicle information based on the captured image may become unstable due to image fluctuation or the like, and based on such unstable preceding vehicle information. If ACC control or the like is performed, the control may become unnatural.

  The present invention has been made in view of the above circumstances, and is a vehicle driving support device capable of stably recognizing preceding vehicle information by appropriately combining information obtained by a radar unit and information obtained by an imaging unit. The purpose is to provide.

  The present invention provides a vehicle driving support apparatus that recognizes preceding vehicle information using a radar unit and an imaging unit in combination, and detects a first preceding vehicle information based on a measurement result of the radar unit. Information detecting means; second preceding vehicle information detecting means for detecting second preceding vehicle information based on an image captured by the imaging means; and the first preceding vehicle information or the second preceding vehicle information. The preceding vehicle information recognizing means for recognizing the final preceding vehicle information based on any of the above, and the preceding vehicle information serving as a basis for recognizing the final preceding vehicle information based on the first condition Preceding vehicle information switching means for selectively switching to either the preceding preceding vehicle information or the second preceding vehicle information, and the preceding vehicle information recognizing means includes the second preceding vehicle information from the first preceding vehicle information. When switching to car information and the second destination When the vehicle information is switched to the first preceding vehicle information, the final preceding vehicle information is gradually converged to the newly selected preceding vehicle information over a preset transition time. Features.

  According to the vehicle driving support device of the present invention, stable preceding vehicle information can be recognized by appropriate fusion of information obtained by the radar means and information obtained by the imaging means.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. The drawings relate to an embodiment of the present invention, FIG. 1 is a schematic configuration diagram of a vehicle equipped with a driving support device, FIG. 2 is a functional block diagram showing a schematic configuration of the vehicle driving support device, and FIG. FIGS. 4 and 5 are flow charts showing a preceding vehicle information recognition routine, and FIG. 6 is a chart showing a state when the preceding vehicle information is switched.

  In FIG. 1, reference numeral 1 denotes a vehicle such as an automobile (own vehicle), and a driving assistance device (ADA: Active Drive Assist system) 2 is mounted on the vehicle 1. As shown in FIG. 2, the driving support apparatus 2 includes a stereo camera 3 as an imaging unit, a millimeter wave radar 4 as a radar unit, an image processing unit (IPU) 5, a preview control unit (PCU) 6, An engine control unit (ECU) 7, a vehicle dynamics control unit (VDC) 8, and an integrated unit 9 are connected through a multiplex communication system such as a CAN (Controller Area Network). Moreover, the center display 10, the combination meter 11, and the audio apparatus 12 are connected to the integrated unit 9 via other communication systems (vehicle body side communication systems) having different communication speeds, for example.

  The stereo camera 3 has a set of (left and right) CCD cameras using a solid-state image sensor such as a charge coupled device (CCD). These left and right CCD cameras are each mounted at a predetermined interval in front of the ceiling in the vehicle interior (see FIG. 1), and images the object outside the vehicle from different viewpoints. The stereo camera 3 performs A / D conversion, affine conversion, and the like on each image (reference image and comparison image) captured by the left and right CCD cameras, and outputs these image signals to the IPU 5.

  The millimeter wave radar 4 is attached to, for example, a front bumper structure material of the vehicle 1 (see FIG. 1). The millimeter wave radar 4 has a transmission / reception unit (not shown), and the transmission / reception unit transmits and receives millimeter waves in the horizontal direction of the vehicle 1 within a predetermined scanning range at regular intervals. The millimeter wave radar 4 is a radar comprising two-dimensional distribution information of a three-dimensional object in front of the host vehicle based on a measurement result of a time difference until the transmitted millimeter wave is reflected by a reflection object such as a three-dimensional object and returns. An image is generated and output to the IPU 5.

  The IPU 5 recognizes the environment outside the vehicle based on the image signals from the stereo camera 3 and the millimeter wave radar 4.

  More specifically, the IPU 5 uses a well-known calculation process based on the stereo image and the triangulation principle, etc., to obtain a white line on the road, a side wall such as a guardrail or curb along the road, and a three-dimensional vehicle or the like. Detect objects. Then, the IPU 5 assigns a different ID to each piece of information (for example, relative speed Vi, relative acceleration Ai, relative distance Zi, etc. with the own vehicle 1) related to the detected white line, side wall, and three-dimensional object. At this time, since a three-dimensional object such as a vehicle often has two or more planes detected continuously through a corner, the IPU 5 converts a three-dimensional object such as a vehicle into a corner-shaped three-dimensional object. Register separately.

  Further, the IPU 5 performs a three-dimensional object detection based on the radar image by extracting a portion where distance values on the radar image are continuous as one solid object. Then, the IPU 5 assigns a different ID for each piece of information (for example, relative speed Vm, relative acceleration Am, relative distance Zm, etc. with the host vehicle 1) related to the detected three-dimensional object.

  Then, the IPU 5 combines the three-dimensional object detected based on the stereo image (hereinafter referred to as an image three-dimensional object) and the three-dimensional object detected based on the radar image (hereinafter referred to as a radar three-dimensional object). 3D object recognition.

  That is, the IPU 5 determines the same probability for each combination of each image solid object and each radar solid object based on the position and moving speed of each image solid object and each radar solid object, and the same probability exceeds a predetermined value. Each combination of the image solid object and the radar solid object that most closely matches is recognized as a fusion solid object. Thereby, in the IPU 5, a solid object recognized by the image solid object alone (for example, a solid object indicated by a circle in FIG. 3), a solid object recognized by the radar solid object alone (for example, a square in FIG. 3) 3D objects that are recognized by a combination of an image 3D object and a radar 3D object (for example, a 3D object indicated by a circle and a square in FIG. 3). To recognize.

  Further, the IPU 5 estimates the own vehicle traveling lane based on the information such as the white line and the side wall recognized from the stereo image, the traveling state information of the own vehicle 1 obtained from the VDC 8, and the estimated own vehicle traveling lane. Carry out the preceding vehicle capture / departure judgment. That is, when there is a three-dimensional object on the estimated own vehicle travel lane, the IPU 5 captures (detects) the three-dimensional object that is present closest to the own vehicle 1 as a preceding vehicle.

  At that time, when the three-dimensional object captured as the preceding vehicle is a fusion three-dimensional object, the IPU 5 converts the preceding vehicle information based on the information of the radar three-dimensional object constituting the fusion three-dimensional object to the first preceding vehicle information (hereinafter, The preceding vehicle information based on the information of the image solid object is registered as second preceding vehicle information (hereinafter also referred to as preceding vehicle information B). Further, when the three-dimensional object captured as the preceding vehicle is a radar three-dimensional object, the IPU 5 registers the preceding vehicle information based on the information of the radar three-dimensional object as the first preceding vehicle information, and the second preceding vehicle information Register as invalid. Further, when the three-dimensional object captured as the preceding vehicle is an image three-dimensional object, the IPU 5 registers the preceding vehicle information based on the information of the three-dimensional object as the second preceding vehicle information, and the first preceding vehicle information is registered. Register as invalid. That is, the IPU 5 functions as a first preceding vehicle information detecting unit that detects first preceding vehicle information based on the measurement result of the millimeter wave radar 4 and the stereo image captured by the stereo camera 3. It has a function as a 2nd preceding vehicle information detection means which detects 2 preceding vehicle information.

  Further, the IPU 5 selects either the first preceding vehicle information or the second preceding vehicle information based on a preset condition, and obtains the final preceding vehicle information C based on the selected preceding vehicle information. recognize. That is, the IPU 5 functions as a preceding vehicle information selection unit and a preceding vehicle information recognition unit.

  The PCU 6 supervises each function of the driving support device 2 and determines whether or not an alarm or acceleration / deceleration control is necessary based on various information obtained from the IPU 5 or the VDC 8. Then, according to these determination results, the PCU 6 outputs a display signal to the center display 10 and the combination meter 11, and outputs a buzzer (or sound) signal to the speakers 11a and 12a connected to the combination meter 11 and the audio device 12. Various driving support functions are realized by appropriately performing output, outputting control signals to the ECU 7 and the VDC 8, and the like.

  For example, when the preceding vehicle is captured on the own vehicle traveling lane, the PCU 6 displays the warning light of the combination meter 11 when the inter-vehicle distance with the preceding vehicle is equal to or less than a predetermined warning inter-vehicle distance, A buzzer is output from the speaker 11a (inter-vehicle distance warning function).

  Further, the PCU 6 determines that the distance between the white line and the extension line of the outer side wall of the own vehicle 1 is approximately “0” within a preset front distance from the positional relationship between the white line of the own vehicle traveling lane and the own vehicle 1. When it is determined, the warning light of the combination meter 11 is turned on and a buzzer is output from the speaker 11a (lane departure warning function).

  Further, the PCU 6 performs follow-up driving control for the preceding vehicle when the preceding vehicle is captured on the own vehicle traveling lane by acceleration / deceleration control through the ECU 7 and the VDC 8, and determines whether the preceding vehicle has left the own vehicle traveling lane. At this time, the vehicle shifts to constant speed traveling control at the set vehicle speed (ACC function; inter-vehicle distance control cruise control function).

  Further, the PCU 6 measures the wobbling on the driving lane based on the relationship between the own vehicle 1 and the white line, and when detecting the wandering deeply related to looking away or falling asleep from the frequency analysis, Advance timing. Further, when a lane departure is detected, a warning is given by voice from the speaker 12a (stagger warning function).

  Further, the PCU 6 detects the wheel speed difference between the front and rear wheels when the driver depresses the brake. When this value exceeds a predetermined value, the PCU 6 determines that the tire is likely to slip, and this is indicated through the center display 10. Display (grip prediction function).

  Further, the PCU 6 displays information on the distance between the preceding vehicle traveling on the vehicle traveling lane and the oncoming vehicle through the center display 10. Further, when the host vehicle approaches the preceding vehicle at a speed equal to or higher than a certain speed, a buzzer is output from the speaker 12a (visual field support function).

  Here, the center display 10 is provided with a touch switch function, and the PCU 6 executes / cancels each driving support function and switches the display of the center display 10 in accordance with the operation of the touch switch by the driver.

  Next, the preceding vehicle information C recognition process executed by the IPU 5 will be described in detail according to the preceding vehicle information recognition routine shown in FIGS. Here, in this embodiment, for example, the preceding vehicle speed V and the inter-vehicle distance Z with respect to the host vehicle 1 are recognized as the preceding vehicle information C.

  This routine is repeatedly executed every set time (for example, every 100 mmsec). When the routine starts, the IPU 5 first determines whether a preceding vehicle is currently detected on the own vehicle traveling lane in step S101. Check for no. If it is determined in step S101 that the preceding vehicle is not detected on the own vehicle traveling lane, the IPU 5 proceeds to step S102 and recognizes that the preceding vehicle information C is invalid, and then exits the routine.

  On the other hand, if it is determined in step S101 that a preceding vehicle has been detected on the own vehicle traveling lane, the IPU 5 proceeds to step S103, and whether or not the detected preceding vehicle is based on a radar three-dimensional object or a fusion three-dimensional object. (That is, whether or not a preceding vehicle is detected by at least the millimeter wave radar 4).

  When it is determined in step S103 that the preceding vehicle is detected by the millimeter wave radar 4, the IPU 5 proceeds to step S104, and the preceding vehicle speed Va = Vm as the preceding vehicle information A based on the information of the radar three-dimensional object. After the inter-vehicle distance Za = Zm and the preceding vehicle acceleration Aa = Am are registered, the process proceeds to step S106.

  On the other hand, if it is determined in step S103 that the preceding vehicle is not detected by the millimeter wave radar 4, the IPU 5 proceeds to step S105, and after registering that the preceding vehicle information A based on the information of the radar three-dimensional object is invalid, Proceed to step S106.

  When the process proceeds from step S104 or step S105 to step S106, the IPU 5 determines whether or not the detected preceding vehicle is based on an image solid object or a fusion solid object (that is, at least the stereo camera 3 detects the preceding vehicle). Whether or not).

  If it is determined in step S106 that the preceding vehicle is not detected by the stereo camera 3, the IPU 5 proceeds to step S107, registers that the preceding vehicle information B based on the image solid object is invalid, and then proceeds to step S121. move on.

  On the other hand, if it is determined in step S106 that the preceding vehicle has been detected by the stereo camera 3, the IPU 5 proceeds to step S108, and the processing up to step S120 below is performed to obtain information about the image solid object captured as the preceding vehicle. Based on the preceding vehicle information B is registered. Specifically, the preceding vehicle speed Vb and the inter-vehicle distance Zb are registered as the preceding vehicle information B. At this time, in order to prevent the preceding vehicle information B from fluctuating unstable due to image fluctuation or the like, the IPU 5 determines the relative speed Vi of the past predetermined time (predetermined number of samples) including the current relative speed Vi. The average value (moving average value) is registered as the preceding vehicle speed Vb, and the value (moving average value) obtained by averaging the relative distance Zi of the past predetermined time (predetermined number of samples) including the current relative distance Zi is the inter-vehicle distance. Register as distance Zb.

  That is, first, in step S108, the IPU 5 increments a counter Ti indicating the number of times that the preceding vehicle has been continuously detected by the stereo camera 3 (Ti ← Ti + 1), and then proceeds to step S109.

In subsequent step S109, the IPU 5 checks whether the preceding vehicle information A is invalid or whether the preceding vehicle acceleration Aa of the preceding vehicle information A is outside the range of −2 km / h ^{2 to 2} km / h ² .

In step S109, when it is determined that the preceding vehicle information A is invalid, or when it is determined that the preceding vehicle acceleration Aa of the preceding vehicle information A is outside the range of −2 km / h ^{2 to 2} km / h ^2. In step S110, the IPU 5 decrements the sample counter S (S ← S-1), and then proceeds to step S112. Here, the sample counter S is a count value for defining the number of samples when the preceding vehicle information B is averaged.

On the other hand, if it is determined in step S109 that the preceding vehicle information A is valid and the preceding vehicle acceleration Aa of the preceding vehicle information A is within the range of −2 km / h ^{2 to 2} km / h ² , the IPU 5 Proceeds to step S111, increments the sample counter S (S ← S + 1), and then proceeds to step S112.

  When the process proceeds from step S110 or step S111 to step S112, the IPU 5 checks whether or not the sample counter S is larger than a preset upper limit value (for example, S = 50).

  If it is determined in step S112 that the sample counter S> 50, the IPU 5 proceeds to step S113, corrects the sample counter S to the upper limit (S ← 50), and then proceeds to step S116.

  On the other hand, if it is determined in step S112 that the sample counter S ≦ 50, the IPU 5 proceeds to step S114, and checks whether the sample counter S is smaller than a preset lower limit value (for example, S = 20). .

  If it is determined in step S114 that the sample counter S <20, the IPU 5 proceeds to step S115, corrects the sample counter S to the lower limit (S ← 20), and then proceeds to step S116.

  On the other hand, if it is determined in step S114 that the sample counter S ≧ 20, the IPU 5 directly proceeds to step S116.

  When the process proceeds from step S113, step S115, or step S114 to step S116, the IPU 5 checks whether or not the same preceding vehicle as the current frame has been detected by the stereo camera 3 in the previous frame. Here, the case where the same preceding vehicle as the previous frame is not detected means that, for example, the preceding vehicle detected this time is not detected in the previous frame and the preceding vehicle detected this time is newly detected by the stereo camera 3. Or a case where a preceding vehicle different from the previous frame is newly detected due to a lane change or the like of the preceding vehicle.

  If it is determined in step S116 that the same preceding vehicle as the previous frame is detected by the stereo camera 3, the IPU 5 proceeds to step S117 and checks whether the counter Ti is equal to or smaller than the sample counter S.

If it is determined in step S117 that the counter Ti> sample counter S, the IPU 5 proceeds to step S118, where the preceding vehicle information B based on the information of the image solid object is as follows.
Prior vehicle speed Vb = (average value of Vi detected in past S frames including current frame)
Inter-vehicle distance Zb = (average value of Zi detected in past S frames including current frame)
Is registered, the process proceeds to step S121.

On the other hand, if it is determined in step S117 that the counter Ti ≦ sample counter S, the IPU 5 proceeds to step S119, and as the preceding vehicle information B based on the information of the image solid object,
Prior vehicle speed Vb = (average value of Vi detected in past Ti frames including current frame)
Inter-vehicle distance Zb = (average value of Zi detected in past Ti frames including the current frame)
Register. In step S119, the IPU 5 corrects the sample counter S to the lower limit (S ← 20), and then proceeds to step S121.

  If it is determined in step S116 that the same preceding vehicle as the previous frame is not detected by the stereo camera 3, the IPU 5 proceeds to step S120, and the preceding vehicle speed B is set as the preceding vehicle information B based on the information of the image solid object. Vb = Vi and inter-vehicle distance Zb = Zi are registered. In step S120, the IPU 5 corrects the counter Ti to an initial value (Ti ← 0), corrects the sample counter S to a lower limit (S ← 20), and then proceeds to step S121.

  When the process proceeds from step S118, step S119, or step S120 to step S121, the IPU 5 selectively recognizes the preceding preceding vehicle information C by selectively using the preceding vehicle information A or the preceding vehicle information B through the processing up to step S139. I do. Specifically, the preceding vehicle speed V and the inter-vehicle distance Z are recognized as the final preceding vehicle information C. At this time, when the preceding vehicle information A is valid, the IPU 5 preferentially selects the preceding vehicle information A as the preceding vehicle information that is a basis for recognizing the preceding vehicle information C. Further, when switching from the preceding vehicle information A to the preceding vehicle information B, or at the time of switching from the preceding vehicle information B to the preceding vehicle information A, the IPU 5 switches in order to suppress rapid fluctuations in the preceding vehicle information C. The preceding vehicle information C recognized immediately before is gradually converged to the newly selected preceding vehicle information (A or B) over a preset transition time.

  First, when the IPU 5 proceeds from step S118, step S119, or step S120 to step S121, it checks whether the preceding vehicle information A is valid.

  If it is determined in step S121 that the preceding vehicle information A is valid, the IPU 5 proceeds to step S122, and the preceding vehicle that is the same as the current frame in the previous frame is at least one of the stereo camera 3 and the millimeter wave radar 4. Check if it was detected in. Here, the case where the same preceding vehicle as the previous frame has not been detected means, for example, that no preceding vehicle has been detected in the previous frame from any of the stereo camera 3 and the millimeter wave radar 4, and a new preceding vehicle has been detected this time. When it is detected, or when a preceding vehicle different from the previous frame is newly detected due to a lane change or the like of the preceding vehicle.

  When it is determined in step S122 that the same preceding vehicle as the current frame has been detected in the previous frame, the IPU 5 proceeds to step S125 and checks whether the preceding vehicle information A in the previous frame is invalid. That is, in step S122, the IPU 5 checks whether or not the preceding vehicle information A in the previous frame is invalid, so that the preceding vehicle information that is currently the basis of the preceding vehicle information C is changed from the preceding vehicle information B to the preceding vehicle information. It is checked whether or not it is immediately after switching to A.

  If it is determined in step S125 that the preceding vehicle information A is invalid in the previous frame and is immediately after switching from the preceding vehicle information B to the preceding vehicle information A, the IPU 5 proceeds to step S126, and the counter CT Is set to an initial value (for example, CT ← 19), and then the process proceeds to step S127. Here, the counter CT is a counter for defining the remaining time of the transition time when switching the preceding vehicle information that is the basis of the final preceding vehicle information, and at the time of switching from the preceding vehicle information B to the preceding vehicle information A. For example, when the counter CT is initialized to “19”, the transient time is set to 2 seconds.

  On the other hand, if it is determined in step S125 that the preceding vehicle information A in the previous frame is valid, the IPU 5 proceeds directly to step S127.

  When the process proceeds from step S125 or step S126 to step S127, the IPU 5 checks whether or not the counter CT is “0”. That is, the IPU 5 checks whether or not the transition time due to switching to the preceding vehicle information A has expired by determining whether or not the counter CT is “0”.

If it is determined in step S127 that the counter CT ≠ 0 and the transition time has not yet expired, the IPU 5 proceeds to step S128, and the preceding vehicle information A (preceding vehicle speed Va, inter-vehicle distance Za) of the current frame. Correction coefficients ΔV and ΔZ for defining the correction amount with respect to
ΔV = (preceding vehicle speed V-Va of previous frame) / (CT + 1)
ΔZ = (distance between previous frames Z−Za) / (CT + 1)
Calculated by

  Then, when the process proceeds from step S128 to step S129, the IPU 5 decrements the counter CT (CT ← CT-1), and then proceeds to step S130.

  On the other hand, if it is determined in step S127 that the counter CT = 0 and the transition time has expired, the IPU 5 proceeds to step S124, sets the correction coefficients ΔV and ΔZ to “0”, and then proceeds to step S130. move on.

  If it is determined in step S122 that the same preceding vehicle as the current frame is not detected in the previous frame, the IPU 5 proceeds to step S123, sets the counter CT to “0”, and in step S124, the correction coefficient ΔV , ΔZ are set to “0”, respectively, and the process proceeds to step S130.

When the process proceeds from step S124 or step S129 to step S130, the IPU 5 obtains final preceding vehicle information C (preceding vehicle speed V, inter-vehicle distance Z) recognized based on the preceding vehicle information A,
Leading vehicle speed V = Va + (ΔV · CT)
Inter-vehicle distance Z = Za + (ΔV · CT)
After calculating, the routine is exited.

  As a result, the preceding vehicle information C is gradually obtained over a predetermined transition time (for example, 2 seconds) after the preceding vehicle information that is the basis of recognition is switched from the preceding vehicle information B to the preceding vehicle information A. It is converged to information A. That is, for example, as shown in FIG. 6, when the preceding vehicle speed that is the basis for the preceding vehicle speed V is switched from the preceding vehicle speed Vb to the preceding vehicle speed Va, the preceding vehicle speed V has a transition time of 2 seconds. Gradually, the vehicle speed is converged to the preceding vehicle speed Va. Similarly, although not shown, when the intervehicular distance that is the basis for the intervehicular distance Z is switched from the intervehicular distance Zb to the intervehicular distance Za, the intervehicular distance Z gradually converges to the intervehicular distance Za through a transition time of 2 seconds. Is done. Further, when the transition time expires or when a new preceding vehicle is detected, ΔV and ΔZ are both set to “0”, so that the preceding vehicle speed Va and the inter-vehicle distance Za remain unchanged. Recognized as speed V and inter-vehicle distance Z.

  On the other hand, if it is determined in step S121 that the preceding vehicle information A is invalid, the IPU 5 proceeds to step S131, and the preceding vehicle that is the same as the current frame in the previous frame is at least one of the stereo camera 3 and the millimeter wave radar 4. Check if it was detected in.

  If it is determined in step S134 that the same preceding vehicle as the current frame has been detected in the previous frame, the IPU 5 proceeds to step S134 and checks whether the preceding vehicle information A in the previous frame is valid. That is, in step S134, the IPU 5 checks whether or not the preceding vehicle information A in the previous frame is valid, so that the preceding vehicle information that is currently the basis of the preceding vehicle information C is changed from the preceding vehicle information A to the preceding vehicle information. It is checked whether or not it is immediately after switching to B.

  If it is determined in step S134 that the preceding vehicle information A is valid in the previous frame and is immediately after switching from the preceding vehicle information A to the preceding vehicle information B, the IPU 5 proceeds to step S135, and the counter CT Is set to an initial value (for example, CT ← 49), and the process proceeds to step S136. Here, when switching from the preceding vehicle information A to the preceding vehicle information B, for example, the transient time is set to 5 seconds by setting the counter CT to “49”.

  On the other hand, if it is determined in step S134 that the preceding vehicle information A in the previous frame is invalid, the IPU 5 directly proceeds to step S136.

  When the process proceeds from step S134 or step S135 to step S136, the IPU 5 checks whether or not the counter CT is “0”. That is, the IPU 5 checks whether or not the transition time due to switching to the preceding vehicle information B has expired by determining whether or not the counter CT is “0”.

If it is determined in step S136 that the counter CT ≠ 0 and the transition time has not yet expired, the IPU 5 proceeds to step S137, and the preceding vehicle information B (the preceding vehicle speed Vb, the inter-vehicle distance Zb) of the current frame. Correction coefficients ΔV and ΔZ for defining the correction amount with respect to
ΔV = (preceding vehicle speed of previous frame V−Vb) / (CT + 1)
ΔZ = (distance between front frames Z−Zb) / (CT + 1)
Calculated by

  Then, when the process proceeds from step S137 to step S138, the IPU 5 decrements the counter CT (CT ← CT-1), and then proceeds to step S139.

  On the other hand, if it is determined in step S136 that the counter CT = 0 and the transition time has expired, the IPU 5 proceeds to step S133, sets the correction coefficients ΔV and ΔZ to “0”, and then proceeds to step S139. move on.

  If it is determined in step S131 that the same preceding vehicle as the current frame is not detected in the previous frame, the IPU 5 proceeds to step S132, sets the counter CT to “0”, and in step S133, the correction coefficient ΔV , ΔZ are respectively set to “0”, and the process proceeds to step S139.

When the process proceeds from step S133 or step S137 to step S139, the IPU 5 determines the final preceding vehicle information C (preceding vehicle speed V, inter-vehicle distance Z) recognized based on the preceding vehicle information B.
Leading vehicle speed V = Vb + ΔV · CT
Distance between vehicles Z = Zb + ΔV · CT
After calculating, the routine is exited.

  As a result, the preceding vehicle information C is gradually updated over a predetermined transition time (for example, 5 seconds) after the preceding vehicle information as the basis of recognition is switched from the preceding vehicle information A to the preceding vehicle information B. It is converged to information B. That is, when the preceding vehicle speed, which is the basis for recognition of the preceding vehicle speed V, is switched from the preceding vehicle speed Va to the preceding vehicle speed Vb, the preceding vehicle speed V is gradually increased through the transition time of 5 seconds. To converge. Similarly, when the inter-vehicle distance that becomes the basis of the inter-vehicle distance Z is switched from the inter-vehicle distance Za to the inter-vehicle distance Zb, the inter-vehicle distance Z gradually converges to the inter-vehicle distance Zb after a transition time of 5 seconds. Further, when the transition time expires or when a new preceding vehicle is detected, ΔV and ΔZ are both set to “0”, so that the preceding vehicle speed Vb and the inter-vehicle distance Zb remain unchanged. Recognized as speed V and inter-vehicle distance Z.

  According to such a form, the preceding vehicle information A detected based on the measurement result of the millimeter wave radar 4 and the preceding vehicle information B detected based on the stereo image captured by the stereo camera 3 are selectively selected. In the process of recognizing the final preceding vehicle information C used in the above, it is preset at the time of switching from the preceding vehicle information A to the preceding vehicle information B, or at the time of switching from the preceding vehicle information B to the preceding vehicle information A. When there is an error between the preceding vehicle information A and the preceding vehicle information B because the preceding vehicle information C is gradually converged to the newly selected preceding vehicle information over a transition time. In addition, rapid fluctuations in the preceding vehicle information C can be suppressed, and the stable preceding vehicle information C can be recognized. Accordingly, it is possible to realize ACC control or the like without a sense of incongruity.

  At this time, in the recognition of the preceding vehicle information C, when both the preceding vehicle information A and B are detected, the millimeter wave radar 4 having better distance measurement than the preceding vehicle information B based on the stereo camera 3. By preferentially selecting the preceding vehicle information A based on this, it is possible to recognize the preceding vehicle information C with high accuracy.

  Further, by setting the transition time at the time of switching from the preceding vehicle information A to the preceding vehicle information B longer than the transition time at the time of switching from the preceding vehicle information B to the preceding vehicle information A, the highly accurate preceding vehicle information A The specific gravity used for the recognition of the preceding vehicle information C can be increased, and the recognition accuracy of the preceding vehicle information C can be further improved.

  Further, by detecting the preceding vehicle information B by averaging the information of the three-dimensional image object of a predetermined number of samples, it is possible to suppress unnecessary fluctuations in the preceding vehicle information B caused by fluctuations on the image of the preceding vehicle. Can do.

  At that time, if the preceding vehicle information A is invalid, or if it is confirmed that the preceding vehicle is accelerating / decelerating at a predetermined acceleration or more based on the preceding vehicle information A (preceding vehicle acceleration Aa) By decrementing the counter S, the preceding vehicle speed Vb and the inter-vehicle distance Zb can be varied with good response according to the actual traveling state of the preceding vehicle. When it is confirmed that the preceding vehicle is traveling at a substantially constant speed based on the preceding vehicle information A (preceding vehicle acceleration Aa), the sample counter S is incremented to increase the preceding vehicle speed Vb and the inter-vehicle distance. Unnecessary fluctuations in Zb can be more effectively suppressed.

  In the above-described embodiment, an example in which the stereo camera 3 is used as the imaging unit and the millimeter wave radar 4 is used as the radar unit has been described. However, the present invention is not limited to this example. Of course, a monocular camera or the like may be used, and an infrared laser radar or the like may be used as the radar means.

  In the above-described embodiment, since the millimeter wave radar 4 is generally superior in distance measurement performance than the stereo camera 3, the preceding vehicle information A is given priority when recognizing the final preceding vehicle information C. In addition, an example in which the transition time at the time of switching from the preceding vehicle information B to the preceding vehicle information A is set shorter than the transition time at the time of switching from the preceding vehicle information A to the preceding vehicle information B has been described. However, the present invention is not limited to this. For example, when the imaging unit is more excellent in distance measurement than the radar unit, it is needless to say that the reverse setting may be used.

Schematic configuration diagram of a vehicle equipped with a driving support device Functional block diagram showing a schematic configuration of a vehicle driving support device Illustration of three-dimensional object in each detection form Flowchart showing a preceding vehicle information recognition routine Flowchart showing a preceding vehicle information recognition routine Chart showing the state when the preceding vehicle information is switched

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Vehicle 2 ... Driving assistance apparatus 3 ... Stereo camera (imaging means)
4 ... Millimeter wave radar (radar means)
5. Image processing unit (first preceding vehicle information detecting means, second preceding vehicle information detecting means, preceding vehicle information recognizing means, preceding vehicle information selecting means)
A ... Preceding car information (first preceding car information)
B ... Preceding car information (second preceding car information)
C ... Preceding car information (final preceding car information)
Agent Patent Attorney Susumu Ito

Claims (5)

In a vehicle driving support device that recognizes preceding vehicle information using a radar unit and an imaging unit in combination,
First preceding vehicle information detecting means for detecting first preceding vehicle information based on the measurement result of the radar means;
Second preceding vehicle information detection means for detecting second preceding vehicle information based on the image captured by the imaging means;
Preceding vehicle information recognition means for recognizing final preceding vehicle information based on either the first preceding vehicle information or the second preceding vehicle information;
A preceding vehicle that selectively switches the preceding vehicle information that becomes the basis for recognizing the final preceding vehicle information to either the first preceding vehicle information or the second preceding vehicle information based on a preset condition. Information switching means,
The preceding vehicle information recognition means is configured to switch from the first preceding vehicle information to the second preceding vehicle information and when switching from the second preceding vehicle information to the first preceding vehicle information. A vehicle driving support apparatus characterized in that the final preceding vehicle information is gradually converged to the newly selected preceding vehicle information over a preset transition time.   The preceding vehicle information selection means preferentially selects the first preceding vehicle information when both the first preceding vehicle information and the second preceding vehicle information are detected. The vehicle driving support device according to claim 1.   The transition time at the time of switching from the first preceding vehicle information to the second preceding vehicle information is set longer than the transition time at the time of switching from the second preceding vehicle information to the first preceding vehicle information. The vehicle driving support device according to claim 1, wherein the vehicle driving support device is a vehicle driving support device.   2. The second preceding vehicle information detecting means obtains the second preceding vehicle information by averaging the preceding vehicle information of a predetermined number of samples continuously detected for each image. The vehicle driving support device according to claim 3.   5. The vehicle driving support apparatus according to claim 4, wherein the second preceding vehicle information detecting means variably sets the number of samples based on the first preceding vehicle information.

Images