JP2004198323A - Object recognition device for vehicle - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an object recognition device for a vehicle for accurately recognizing an object existing forward of the vehicle. <P>SOLUTION: A plurality of laser lights are irradiated in a prescribed angular range forward of the vehicle from a laser radar sensor 5. Distance measuring data consisting of a time interval ΔT until reflective light is detected and an irradiation angle are acquired, makes a vehicle width direction an X axis and is converted into an XZ coordinate for making the forward a Z axis. In the XZ coordinate, since each reflective light is point data indicating a reflective object as a point, the positions of the point data are adjacent, and the point data satisfying a condition that a difference between the intensities of reflective waves is a prescribed value or less are collected to be integrated. Thereby a weak part (for instance, a vehicular body part) of reflective intensity of the laser light and a high part (for instance, a reflector part) of reflective intensity can be discriminated. Thus, a distance and a shape of the reflective object can be exactly calculated on the basis of the high part of the reflective intensity. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a vehicle object recognition device that irradiates a plurality of transmission waves over a predetermined angle range in front of a vehicle and recognizes an object such as a preceding vehicle in front of the host vehicle based on the reflected waves.
[0002]
[Prior art]
Conventionally, an object recognition device that recognizes an object in front of a vehicle by irradiating a transmission wave such as a light wave or millimeter wave over a predetermined angle in front of the vehicle and detecting the reflected wave has been considered. This type of device is applied, for example, to a device that generates an alarm by detecting that the distance from a preceding vehicle or the like has become short, or a device that controls the vehicle speed so as to maintain a predetermined distance from the preceding vehicle. And used for recognition of preceding vehicles as control objects thereof.
[0003]
For example, in Patent Document 1, a laser radar sensor irradiates a plurality of laser beams in front of a vehicle over a predetermined angle range in the vehicle width direction and the vehicle height direction, and an object such as a preceding vehicle based on the reflected light. A vehicle object recognition device for recognizing a vehicle is disclosed. In a specific laser beam irradiation method in the vehicle object recognition device, first, a plurality of laser beams are irradiated at predetermined angles over a predetermined angle range in the vehicle width direction (line irradiation). And when this line irradiation is complete | finished, the irradiation angle in a vehicle height direction is changed, and line irradiation is performed again. As described above, by executing the line irradiation a plurality of times, a predetermined two-dimensional area in the vehicle width direction and the vehicle height direction is scanned using the laser beam.
[0004]
[Patent Document 1]
JP-A-11-38141
[0005]
[Problems to be solved by the invention]
When a predetermined two-dimensional area is scanned with a plurality of laser beams by the above-described method, for example, when a relatively large object such as a preceding vehicle is present ahead, the plurality of laser beams are reflected by the object. The reflected light is detected by a laser radar sensor. Thus, when the laser radar sensor detects a plurality of reflected lights, it is necessary to determine whether the reflected lights are reflected by the same object or reflected by different objects. That is, in order to correctly recognize each object, it is necessary to classify the reflected light for each object.
[0006]
For this reason, in the conventional vehicle object recognition device, first, the position of the reflector in the vehicle width direction and the distance to the reflector are calculated from the reflected light data obtained by performing the line irradiation. Then, when the position of the reflecting object in the vehicle width direction and the distance to the reflecting object are close to each irradiation line, it is estimated as an integrated reflecting object, and pre-segment data in which they are integrated is created. . Furthermore, the pre-segment data obtained by irradiation of each line is compared, and when the positions and distances in the vehicle height direction are close to each other, the main segment data in which they are integrated is created.
[0007]
However, in the conventional vehicle object recognition device, since it is determined whether or not it is an integral reflecting object based only on the position of the reflecting object (vehicle width direction position, vehicle height direction position, distance), Problems as described below arise.
[0008]
For example, even when a plurality of reflected lights from one preceding vehicle are detected, the intensity of the reflected light from the vehicle body part may not be sufficient. For this reason, the reflected light from the vehicle body part may or may not be detected. In this case, the distance measurement data regarding the preceding vehicle becomes unstable.
[0009]
In addition, when it is determined whether or not the object is integrated based only on the position of the reflecting object, even if it is actually a separate object, it may be regarded as an integrated object. For example, when there is a stationary object such as a signboard at a position close to or above the side of the preceding vehicle, the preceding vehicle is recognized as being integral with the stationary object. In such a case, the preceding vehicle that should be recognized originally has a different size and may not be correctly recognized as the preceding vehicle.
[0010]
The present invention has been made in view of the above points, and an object of the present invention is to provide a vehicle object recognition device that can more accurately recognize an object existing in front of a vehicle.
[0011]
[Means for Solving the Problems]
In order to achieve the above object, the vehicle object recognition device according to claim 1 irradiates a plurality of transmission waves over a predetermined angle range forward of the vehicle, and each transmission wave is reflected by a reflector, Radar means for outputting a received signal corresponding to the intensity of the reflected wave when the reflected wave is received;
A vehicle object recognition device comprising a recognition means for recognizing an object present in front of the vehicle based on a transmission / reception result by a radar means,
The radar means, based on a time interval from irradiation of the transmission wave to reception of the reflected wave, distance calculation means for calculating the distance to the reflector in the irradiation direction of the transmission wave;
Intensity calculating means for obtaining the intensity of the reflected wave from the received signal,
The recognizing means, when the radar means receives a plurality of reflected waves, the difference in distance calculated by the distance calculating means based on the plurality of reflected waves is not more than a predetermined distance, and the plurality of reflected waves Is caused by a transmission wave irradiated in the vicinity of the radar means, and all the conditions that the difference in intensity calculated by the intensity calculation means for the plurality of reflected waves is equal to or less than a predetermined value are satisfied. In this case, there is provided a first integrating means for recognizing the same reflecting object by integrating the reflecting objects that generate the plurality of reflected waves.
[0012]
A vehicle as a recognition target in the vehicle object recognition device includes reflectors attached to the rear surface thereof in a symmetrical manner. This reflector has a higher reflection strength than the vehicle body portion of the vehicle with respect to the transmitted wave. Therefore, the reflected wave from the reflector does not become unstable like the reflected wave from the vehicle body part, and can be stably received by the radar means.
[0013]
In the present invention, the intensity of the reflected wave is used in order to stably detect the vehicle as the recognition target. That is, in addition to the condition that the positions of the reflecting objects are adjacent to each other, the difference in intensity of the reflected waves is a predetermined value or less as a condition for integrating the reflecting objects recognized as points by each reflected wave. And the conditions are adopted.
[0014]
As described above, when the difference in the intensity of the reflected waves is equal to or less than a predetermined value, the reflecting object is recognized as an integrated reflecting object, thereby allowing a portion having a low reflection intensity (for example, a vehicle body) and a portion having a high reflection intensity (for example, a reflector) Part). As a result, it is possible to calculate the distance to the reflecting object and the shape based on the reflecting object having a high reflected wave intensity among the integrated reflecting objects. It is possible to accurately grasp the shape and the like.
[0015]
As described in claim 2, the intensity calculating means divides the reflected waves into a plurality of groups according to the intensity of the reflected waves, and the first integrating means is a group in which the reflected waves are the same by the intensity calculating means. It is preferable to determine that the difference in intensity is equal to or less than a predetermined value. In this way, the intensity of each reflected wave and the intensity difference can be easily distinguished.
[0016]
As described in claim 3, when the distance calculated by the distance calculating unit is equal to or less than a predetermined distance, the recognizing unit may exclude a reflecting object that is not integrated with another reflecting object from the recognition target. preferable. A reflected wave from an object existing below a predetermined distance generally tends to increase in intensity. For this reason, when an object actually exists, a plurality of reflected waves having the same intensity should be received by the radar means. Considering this from the opposite viewpoint, when a reflector by one reflected wave is not integrated with another reflector, the reflected wave can be regarded as noise generated for some reason. Therefore, in such a case, it is preferable to exclude the reflection object due to the reflected wave from the recognition target.
[0017]
According to a fourth aspect of the present invention, when the intensity of the reflected wave calculated by the intensity calculating unit is equal to or lower than a predetermined level and the number of integrated reflectors is equal to or lower than the predetermined number, the recognizing unit reflects the reflected wave. It is preferable to exclude objects from recognition targets. Even when the intensity of the reflected wave is low and the number of integrated reflectors is equal to or less than the predetermined number (including zero), the reflected wave can be regarded as noise generated for some reason. It is.
[0018]
According to a fifth aspect of the present invention, the first integration means is a predetermined condition that is a condition relating to a difference in distance calculated by the distance calculation means based on a plurality of reflected waves as the distance calculated by the distance calculation means increases. It is preferable to increase the distance. This is because the intensity of the reflected wave tends to decrease as the distance to the reflector increases, and the decrease in the intensity of the reflected wave and the measurement accuracy of the distance have a correlation. That is, since the measurement accuracy of the distance tends to decrease as the distance to the reflecting object becomes shorter, it is preferable to relax the distance condition for determining the integration.
[0019]
As described in claim 6, when the number of transmission waves interposed between two transmission waves is equal to or less than a predetermined number, the first integration means determines that the transmission waves are irradiated in proximity It is preferable to decrease the number as the distance calculated by the distance calculating means becomes longer. Since a plurality of transmission waves are emitted from the radar means over a predetermined angular range, when an object is present at a short distance from the host vehicle, more transmission waves are reflected by the object, and The interval between transmitted waves when reaching the object is short. Then, as the distance between the object and the host vehicle becomes longer, the interval between the transmission waves becomes longer. Therefore, as described above, when the number of transmission waves intervening between two transmission waves is equal to or less than a predetermined number, when determining a transmission wave irradiated in proximity, the longer the distance to the reflective object, It is preferable to reduce the number.
[0020]
According to a seventh aspect of the present invention, the radar means irradiates the plurality of transmission waves along the vehicle width direction of the vehicle, and the recognition means is integrated by the first integration means. When there are a plurality of reflected objects, and the distance in the vehicle width direction and the distance in the irradiation direction of the transmission wave between the plurality of reflected objects are each equal to or less than a predetermined integration determination distance, the plurality of reflected objects And a second integrated means for recognizing the same integrated reflective object.
[0021]
As described above, in the vehicle object recognition device according to the seventh aspect, the reflection object made of the reflection object having the same intensity of the reflected wave is obtained, and thereafter, the reflection object is the same from the positional relationship between the reflection objects. If it can be regarded as an object, it is further recognized as an integrated reflective object. As a result, the intensity of the reflected wave is required for the reflecting object constituting the integrated reflecting object. For example, for the distance to the integrated reflecting object, the reflecting object whose reflected wave intensity is equal to or higher than a predetermined level. If the size of the integrated reflective object deviates from the normal range, the size of the integrated reflective object may be calculated by excluding reflective objects with low reflected wave intensity. It becomes possible. Thereby, it becomes possible to recognize objects, such as a preceding vehicle, more correctly.
[0022]
For the same reason as described in claim 5, as described in claim 8, the second integration unit determines the integration as the distance to the reflecting object in the transmission wave irradiation direction becomes longer. It is preferable to set the distance long.
[0023]
According to a ninth aspect of the present invention, the recognition means includes a distance / shape calculation means for obtaining a distance to the integrated reflective object integrated by the second integrated means and a width of the integrated reflective object, This distance / shape calculating means is integrated by the second integrating means based on the distance to the reflecting object in which the first integrating means integrates the reflecting object whose reflected wave intensity is a predetermined level or more. It is preferable to obtain the distance to the integrated reflective object. A reflected wave having an intensity of a predetermined level or higher can be stably received by the radar means, and the measurement accuracy of the distance to the reflecting object in which the reflected wave whose intensity is higher than the predetermined level is integrated is very high. Very expensive. For this reason, the accuracy of the distance can be improved by obtaining the distance to the integrated reflecting object based on the distance to the reflecting object integrated with the reflecting object whose reflected wave intensity is a predetermined level or more.
[0024]
According to the tenth aspect of the present invention, when the second integration unit obtains an integrated reflection object obtained by integrating the plurality of reflection objects, the distance / shape calculation unit calculates the reflected wave of the plurality of reflection objects. When the intensities are different and the width of the integrated reflecting object exceeds a predetermined length, it is preferable to obtain the width of the integrated reflecting object except for the reflecting object having the weakest reflected wave intensity. The object to be recognized by the vehicle object recognition device is a vehicle, and it is extremely unlikely that an object having a width that exceeds the width of the vehicle in the region where the vehicle should be originally exists. This is because a reflective object having a relatively low intensity can be assumed to be caused by noise or the like.
[0025]
In the vehicle object recognition device according to claim 11, the radar unit performs irradiation of the transmission wave over a predetermined angle range in the vehicle width direction of the vehicle a plurality of times by changing the irradiation angle in the vehicle height direction. Is,
For each transmission wave irradiation line in the vehicle width direction of the vehicle, the first integrating means and the second integrating means respectively integrate the reflecting objects, and further integrate the reflecting objects to form an integrated reflecting object. Is what we want,
The recognizing means detects the integrated reflection object when the integrated reflection object obtained for each irradiation line is present at a close position and the difference between the moving speeds is less than a predetermined speed difference. It is further characterized by comprising target marking means for further integrating the objects and recognizing them as targets.
[0026]
As described above, when a plurality of transmission wave irradiation lines are set in the vehicle height direction, it is necessary to determine whether or not the integrated reflection objects obtained for each adjacent irradiation line are the same object. In this case, as in the prior art, if it is determined whether or not the objects are the same by only the positional relationship between the integrated reflecting objects, it may not be possible to accurately recognize an object such as a preceding vehicle. . That is, as described above, when there is a stationary object such as a signboard above or ahead of the preceding vehicle, it may be recognized that the preceding vehicle is integrated with the stationary object.
[0027]
Therefore, in the vehicle object recognition device according to claim 11, only when the condition that the difference in moving speed of the integrated reflecting object obtained for each irradiation line is equal to or less than the predetermined speed difference is satisfied, the same object is detected. Recognized as an integrated target. Thereby, the problem as described above, that is, a situation where a moving object and a stationary object are erroneously recognized as the same object can be avoided.
[0028]
As described in claim 12, the moving speed of the integrated reflecting object is calculated as a relative speed in the vehicle width direction with respect to the own vehicle and a relative speed in the irradiation direction of the transmission wave, When both relative velocities of the integrated reflective object are equal to or less than a predetermined speed difference, it is preferable that the plurality of integrated reflective objects are integrated into a target. Thus, by using both relative velocities in the vehicle width direction and the irradiation direction of the transmission wave, it is possible to correctly grasp the moving state of the moving object existing in front of the host vehicle. Therefore, it is possible to prevent a moving object and a stationary object as well as moving objects from being recognized as being the same object.
[0029]
According to a thirteenth aspect of the present invention, the target unit calculates the radar based on the distance to the integrated reflecting object calculated by the distance / shape calculating unit, the width of the integrated reflecting object, and the relative velocity of the integrated reflecting object. When an estimated area where the integrated reflective object exists is calculated at each detection time interval of the means, and other integrated reflective objects belong to the estimated area, the integrated reflective objects are present at close positions. Judgment can be made.
[0030]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an inter-vehicle distance control apparatus according to an embodiment of the present invention will be described. In the present embodiment, the vehicle object recognition device is applied to the inter-vehicle distance control device 1, and the inter-vehicle distance control device 1 also has a function of outputting an alarm when there is an obstacle in the area to be alarmed. Is.
[0031]
FIG. 1 is a system block diagram of the inter-vehicle distance control device 1. The inter-vehicle control device 1 is configured around a recognition / inter-vehicle control ECU 3. The recognition / vehicle distance control ECU 3 mainly includes a microcomputer and includes an input / output interface (I / O) and the like. Since these hardware configurations are general, detailed description thereof is omitted.
[0032]
The recognition / vehicle distance control ECU 3 receives detection signals from the laser radar sensor 5, the vehicle speed sensor 7, the brake switch 9, and the throttle opening sensor 11, and outputs an alarm sound generator 13, a distance indicator 15, and a sensor abnormality indicator. 17. Drive signals are output to the brake driver 19, the throttle driver 21 and the automatic transmission controller 23. The recognition / vehicle distance control ECU 3 includes an alarm volume setting unit 24 for setting an alarm volume, an alarm sensitivity setting unit 25 for setting sensitivity in alarm determination processing, a cruise control switch 26, and a steering wheel for detecting an operation amount of a steering wheel (not shown). A sensor 27 and a yaw rate sensor 28 for detecting the yaw rate generated in the automobile are connected. The recognition / vehicle distance control ECU 3 includes a power switch 29. When the power switch 29 is turned on, the recognition / vehicle distance control ECU 3 starts a predetermined process.
[0033]
As shown in FIG. 2A, the laser radar sensor 5 includes a light emitting unit, a light receiving unit, a laser radar CPU 70, and the like as main parts. The light emitting unit includes a semiconductor laser diode (hereinafter simply referred to as a laser diode) 75 that emits pulsed laser light through a light emitting lens 71, a scanner 72, and a glass plate 77. The laser diode 75 is connected to the laser radar CPU 70 via the laser diode drive circuit 76, and emits (emits) laser light by a drive signal from the laser radar CPU 70. In addition, a polygon mirror 73 is provided in the scanner 72 so as to be rotatable around a vertical axis, and when a drive signal from the laser radar CPU 70 is input via a motor drive unit 74, the polygon mirror 73 is connected to a motor (not shown). It is rotated by the driving force. The rotational position of the motor is detected by a motor rotational position sensor 78 and output to the laser radar CPU 70.
[0034]
Since the polygon mirror 73 of the present embodiment includes six mirrors having different plane tilt angles, the laser beam is swept and irradiated (scanned) discontinuously within a predetermined angle range in the vehicle width direction and the vehicle height direction. Output. The laser beam is scanned two-dimensionally in this way, and the scanning pattern will be described with reference to FIG. In FIG. 3, the emitted laser beam pattern 92 is shown only when emitted to the right end and the left end in the measurement area 91, and is omitted in the middle. In addition, the outgoing laser beam pattern 92 is illustrated as an elliptical shape as an example in FIG. 3, but is not limited to this shape, and may be a rectangular shape or the like. Furthermore, in addition to those using laser light, radio waves such as millimeter waves, ultrasonic waves, or the like may be used. Moreover, it is not necessary to stick to the scanning method, and any method that can measure two directions other than the distance may be used.
[0035]
As shown in FIG. 3, when the central direction of the measurement area is the Z axis, the laser beam sequentially scans a predetermined area in the XY plane perpendicular to the Z axis. In the present embodiment, the Y axis that is the height direction is the reference direction, the X axis that is the vehicle width direction is the scanning direction, and the scan area is 0.08 deg × 450 points = 20 deg in the X axis direction. In the direction, 1.4 deg × 3 lines = 4 deg. The scanning direction is from left to right in FIG. 3 for the X-axis direction, and from top to bottom in FIG. 3 for the Y-axis direction. Specifically, first, 450 laser beams are irradiated at intervals of 0.08 ° in the X-axis direction with respect to the first scanning line located at the uppermost portion when viewed in the Y-axis direction. Since one scan line is detected in this way, 450 laser beams are similarly applied to the second scan line at the next position viewed in the Y-axis direction at intervals of 0.08 ° in the X-axis direction. Irradiate. In this way, the same laser light irradiation is repeated up to the third scanning line. Accordingly, laser light is scanned for each scanning line from the upper left to the lower right, and data for 450 points × 3 lines = 1350 points is obtained.
[0036]
By such a two-dimensional scan, for each scanning line, a scan angle θx indicating the scanning direction and a time difference from laser light irradiation to light reception corresponding to the distance to the reflector are obtained. The distance scan angle θx is defined as an angle between a line obtained by projecting the emitted laser light on the XZ plane and the Z axis.
[0037]
The light receiving unit of the laser radar sensor 5 includes a light receiving element 83 that receives laser light reflected by an object (not shown) through a light receiving lens 81 and outputs a voltage corresponding to the intensity. The output voltage of the light receiving element 83 is amplified by the amplifier 85 and then output to the comparator 87. The comparator 87 compares the output voltage of the amplifier 85 with a reference voltage, and outputs a predetermined light receiving signal to the time measuring circuit 89 when the output voltage> the reference voltage.
[0038]
The time measurement circuit 89 also receives a drive signal output from the laser radar CPU 70 to the laser diode drive circuit 76. As shown in FIG. 2B, the drive signal is the start pulse PA, the light reception signal is the stop pulse PB, and the phase difference between the two pulses PA and PB (ie, the time T0 when the laser beam is emitted and the reflection is reflected). The time difference ΔT from the time T1 when the light is received is encoded into a binary digital signal. Further, the time during which the stop pulse PB is equal to or higher than the reference voltage is measured as the pulse width of the stop pulse PB. These values are encoded into binary digital signals and output to the laser radar CPU 70. The laser radar CPU 70 measures the input time difference ΔT between the two pulses PA and PB input from the time measuring circuit 89, the laser beam scan angle θx, and the received light intensity data (corresponding to the pulse width of the stop pulse PB). The data is output to the recognition / vehicle distance control ECU 3 as data.
[0039]
Here, the received light intensity data will be described. FIG. 2C shows two reflected light stop pulses PB having different received light intensities. In FIG. 2C, a curve L1 corresponds to a stop pulse PB of reflected light having a relatively high light reception intensity, and a curve L2 corresponds to a stop pulse PB of reflected light having a relatively low light reception intensity.
[0040]
The time at which the reference voltage V0 input to the comparator 87 crosses the reference voltage V0 in the rising process of the curve L1 in the figure is t11, the time at which the curve L1 crosses the reference voltage V0 is t12, and the time t11 and the time t12 Let the time difference be Δt1. Further, a time when the curve L2 rises with the reference voltage V0 is t21, a time when the curve L2 falls with the reference voltage V0 is t22, and a time difference between the time t21 and the time t22 is Δt2. The reference voltage V0 is set to a magnitude that can avoid the influence of noise components.
[0041]
As apparent from FIG. 2C, the time difference Δt1 which is the pulse width of the stop pulse PB of the reflected light having a strong light reception intensity and the time difference which is the pulse width of the stop pulse PB of the reflected light having a weak light reception intensity. When comparing with Δt2, the relationship Δt1> Δt2 is established. That is, the pulse width of the stop pulse PB of the reflected light corresponds to the received light intensity. When the received light intensity is small, the pulse width is shortened, and when the received light intensity is large, the pulse width is increased. Therefore, the time difference (Δt1, Δt2) which is the pulse width is an index characterizing the intensity of the received reflected light.
[0042]
The received light intensity varies depending on the reflection intensity of the reflecting object and the distance to the reflecting object. That is, when the reflection intensity of the reflection object is high or the distance to the reflection object is short, the received light intensity of the reflected light increases, and when the reflection intensity is low or the distance to the reflection object is long, the reflection The light receiving intensity is reduced.
[0043]
The recognition / vehicle distance control ECU 3 recognizes an object based on the distance measurement data from the laser radar sensor 5, and adjusts the brake driver 19, the throttle driver 21, and the automatic according to the situation of the preceding vehicle obtained from the recognized object. A so-called inter-vehicle distance control is performed in which the vehicle speed is controlled by outputting a drive signal to the transmission controller 23. In addition, an alarm determination process for alarming when a recognized object exists in a predetermined alarm area for a predetermined time is also performed at the same time. As the object in this case, a front vehicle traveling in front of the own vehicle, a front vehicle stopped, or the like is applicable.
[0044]
Next, the internal configuration of the recognition / vehicle distance control ECU 3 will be described as a control block. The distance measurement data output from the laser radar sensor 5 is sent to the object recognition block 43. In the object recognition block 43, for each scanning line, the time difference ΔT and the scanning angle θx obtained as distance measurement data are set with the laser radar sensor 5 center as the origin (0, 0), the vehicle width direction is the X axis, and the vehicle forward direction is Convert to XZ Cartesian coordinates for Z axis. Then, the ranging data converted into XZ rectangular coordinates is subjected to three types of integration processing, which will be described later, pre-segment data, main segment data, and target, and is aggregated for each object existing in front of the vehicle. Is done.
[0045]
Then, based on the distance measurement data collected for each object, the center position (X, Z) and size (W, D) of the object are obtained. Further, a relative speed (Vx, Vz) of an object such as a preceding vehicle based on the vehicle position is obtained based on a temporal change in the center position (X, Z) of the object. Further, in the object recognition block 43, whether the object is a stop object from the vehicle speed (own vehicle speed) output from the vehicle speed calculation block 47 based on the detection value of the vehicle speed sensor 7 and the relative speed (Vx, Vz) obtained above. Identification of whether it is a moving object is performed. Note that (X, D) indicating the size of the object is (lateral width, depth), respectively. An object model having such data is called a “target model”.
[0046]
Whether or not the data obtained in the object recognition block 43 is an abnormal range value is detected by the sensor abnormality detection block 44. If the data is an abnormal range value, the sensor abnormality indicator 17 displays that fact. Is made.
[0047]
Further, the steering angle is calculated by the steering angle calculation block 49 based on the signal from the steering sensor 27, and the yaw rate is calculated by the yaw rate calculation block 51 based on the signal from the yaw rate sensor 28. A curve radius (curvature radius) calculation block 57 calculates a curve radius (curvature radius) R based on the vehicle speed from the vehicle speed calculation block 47, the steering angle from the steering angle calculation block 49, and the yaw rate from the yaw rate calculation block 51. calculate. In the preceding vehicle determination block 53, the curve radius R, the center position coordinates (X, Z) obtained in the object recognition block 43, the object size (W, D), and the relative speed (Vx, Vz). Based on the above, the preceding vehicle having the shortest distance from the host vehicle is selected, and the distance Z and the relative speed Vz from the preceding vehicle are obtained.
[0048]
Then, the inter-vehicle distance control unit and the alarm determination unit block 55 include the distance Z to the preceding vehicle, the relative speed Vz, the setting state of the cruise control switch 26, the depression state of the brake switch 9, the opening degree from the throttle opening sensor 11, and Based on the sensitivity set value by the alarm sensitivity setting unit 25, it is determined whether or not an alarm is issued if the alarm is determined, and the content of the vehicle speed control is determined if the cruise is determined. As a result, if an alarm is required, an alarm generation signal is output to the alarm sound generator 13. If the cruise is determined, a control signal is output to the automatic transmission controller 23, the brake driver 19 and the throttle driver 21 to perform necessary control. When these controls are executed, necessary display signals are output to the distance indicator 15 to notify the driver of the situation.
[0049]
In such inter-vehicle distance control and warning determination, it is important that object recognition as a premise thereof, more specifically, recognition of a vehicle that is a recognition target object here is appropriately performed. Therefore, in order to appropriately perform the vehicle recognition, processing related to object recognition executed in the object recognition block 43 of the recognition / vehicle distance control ECU 3 will be described.
[0050]
FIG. 4 is a flowchart showing main processing related to object recognition. First, in step S10 of FIG. 4, distance measurement data is read from the laser radar sensor 5 for each scanning line. Note that the measurement period of the entire three scanning lines in the laser radar sensor 5 is 100 msec.
[0051]
In step S20, data with low received light intensity is deleted from the read distance measurement data. That is, the distance measurement data includes the pulse width of the stop pulse PB indicating the received light intensity of the reflected wave. By comparing the pulse width with the deletion reference value, the measurement data having a pulse width less than or equal to a predetermined value is obtained. Delete the distance data. Further, in this step S20, the distance measurement data is grouped into a group with a large received light intensity, a group with a light received intensity, and a group with a small received light intensity based on the pulse width of the stop pulse PB. Specifically, three types of reference values to be compared with the length of the pulse width are prepared, and ranging data having a pulse width greater than or equal to the largest first reference value is grouped into a group with a large received light intensity. Then, distance measurement data having a pulse width between the first reference value and a second reference value smaller than the first reference value are grouped into groups of received light intensity, and the second reference value is grouped. Ranging data belonging to the value and the third reference value (<second reference value) are grouped into groups with low received light intensity. The third reference value corresponds to the above-described deletion reference value, and distance measurement data having a pulse width equal to or smaller than the third reference value is deleted.
[0052]
In step S30, distance data is pre-segmented, and in step S40, the pre-segmented distance data is segmented. This pre-segmentation process and this segmentation process will be described in detail below. The pre-segmentation process corresponds to the first integration unit in the present invention, and the segmentation process corresponds to the second integration unit.
[0053]
FIG. 5 is an explanatory diagram showing the flow of the pre-segmentation processing and the main segmentation processing and the outline thereof. First, the flow of pre-segmentation processing and main segmentation processing will be described. As shown in FIG. 5, the pre-segmentation process is performed on the distance measurement data of the first scanning line. That is, ranging data that satisfies a predetermined pre-segmentation condition (integration condition) is collected to form a pre-segment. Next, this segmentation processing is performed on the distance measurement data of the first segmented scan line. In this main segmentation process, when the presegments formed by the presegmentation process satisfy a predetermined main segmentation condition (integration condition), the presegments are connected to form the main segment. The pre-segmentation condition and the present segmentation condition will be described later.
[0054]
Subsequently, pre-segmentation processing and main segmentation processing are performed on the distance measurement data of the second scan line, and finally, pre-segmentation processing and main segmentation are performed on the distance measurement data of the third scan line. Perform processing. As described above, the pre-segmentation process and the main segmentation process are sequentially executed for each scan line.
[0055]
Next, the pre-segmentation process, particularly the pre-segmentation condition will be described in detail based on FIGS. 6A shows distance measurement data converted into XZ rectangular coordinates, and FIG. 6B shows pre-segmented data.
[0056]
As shown in FIG. 6A, when ranging data for one scanning line is converted into XZ orthogonal coordinates, each ranging data indicates a reflector in front of the vehicle as a point. When the point data indicating these reflecting objects as points satisfies the following three conditions (pre-segmentation conditions), the point data is integrated to create a pre-segment.
(1) The distance difference ΔZ in the Z-axis direction is not more than a predetermined distance.
(2) The distance difference ΔX in the X-axis direction is not more than a predetermined distance.
(3) The received light intensity is grouped into the same group.
[0057]
Of the above conditions (1) to (3), the conditions (1) and (2) are basic requirements for integrating a plurality of point data. That is, when the laser light is reflected by the same reflecting object, particularly the same preceding vehicle, the distance measurement data obtained by the reflected light shows substantially the same distance in the Z-axis direction, and in the X-axis direction. Exists within a distance range corresponding to the vehicle width.
[0058]
However, the predetermined distance compared with the above-described distance difference ΔZ in the Z-axis direction is changed so as to increase as the distance Z to the reflector increases. For example, the predetermined processing is set to 1.5 m in the distance range up to 70 m, and the predetermined distance is set to 2.0 m in the distance range exceeding 70 m. This is because the measurement accuracy of the distance tends to decrease as the distance Z to the reflector increases.
[0059]
Further, the predetermined distance compared with the distance difference ΔX in the X-axis direction is also changed so as to increase as the distance Z to the reflector increases. For example, when the distance to the reflector is up to 10 m, the predetermined distance is about 2 cm, and the predetermined distance is gradually increased to about 20 cm as the distance Z to the reflector increases. When a plurality of laser beams are irradiated from the laser radar sensor 5 over a predetermined angle range, when a reflecting object exists at a short distance from the host vehicle, more laser beams are reflected by the reflecting object. In addition, the interval between the laser beams when reaching the reflector becomes short. As the distance Z to the reflector increases, the interval between the laser beams increases. Therefore, from the viewpoint of the resolution of such laser light, as described above, the distance condition in the X-axis direction under the pre-segmentation condition is relaxed as the distance Z to the reflector increases.
[0060]
Note that the distance in the X-axis direction may be compared with a predetermined distance after the distance measurement data is converted into XZ rectangular coordinates, and the difference ΔX in the X-axis direction of each point data may be compared with a predetermined distance. The distance difference ΔX in the X-axis direction may be indirectly determined from the number of laser beams existing between the laser beams corresponding to the distance measurement data. That is, it is determined that the distance condition in the X-axis direction is satisfied when the number of laser beams interposed between the two laser beams is equal to or less than the predetermined number. In this way, there is an advantage that the processing load for determining the distance condition of the X axis can be reduced.
[0061]
As described above, when determining the distance condition in the X-axis direction based on the number of laser beams interposed between the two laser beams, the number for determining the integration decreases as the distance Z to the reflector increases. Let This is because the distance in the X-axis direction of the laser light increases as the distance Z to the reflector increases.
[0062]
In the present embodiment, in addition to the above-described conditions (1) and (2), a condition relating to the received light intensity of each distance measurement data is also determined. In other words, in order to collect distance measurement data with a small difference in received light intensity and create a pre-segment, one condition for pre-segmentation is that the received light intensity is grouped into the same group (high received light intensity, medium, small) It was.
[0063]
The main recognition target in the vehicle object recognition device is a preceding vehicle in front of the host vehicle, and the preceding vehicle includes reflectors attached symmetrically on the rear surface. This reflector has a higher reflection intensity than the vehicle body portion with respect to the laser light. Accordingly, the reflected light from the reflector does not become unstable like the reflected light from the vehicle body portion, and can be received by the laser radar sensor 5 stably.
[0064]
Then, by collecting the distance measurement data grouped into the same group of received light intensity and creating a pre-segment, a portion having a low reflection intensity (for example, a vehicle body portion) and a portion having a high reflection intensity (for example, a reflector portion) are obtained. Can be distinguished. As a result, when creating the main segment by integrating the pre-segments, it is possible to calculate the distance and shape of the main segment with reference to the pre-segment having high reflected light intensity. Thereby, the distance, shape, etc. of this segment can be grasped correctly.
[0065]
Further, in the pre-segmentation processing, in order to eliminate the influence of noise such as extraneous light, if any of the following two conditions (4) and (5) is satisfied, the distance measurement data is It was decided not to treat it as a pre-segment.
[0066]
(4) When the distance to the reflecting object is a predetermined distance (for example, 100 m) or less, the distance measurement data is not integrated with other distance measurement data, that is, only one laser beam can be reflected alone. If
[0067]
In the predetermined distance range, the vehicle that is the object to be recognized has a size that allows a plurality of laser beams to hit, and only one laser beam satisfies the conditions (1) and (2) described above. It is usually impossible to exist independently at a predetermined distance or more, or to have a received light intensity different from that of other reflected light. Therefore, when the distance measurement data is not integrated with other distance measurement data, the reflected light can be regarded as noise generated for some reason. For this reason, ranging data regarded as noise is not handled as a pre-segment by the ranging data alone.
[0068]
(5) The number of distance measurement data to be integrated is a predetermined number (for example, 2) or less, and the received light intensity is grouped into groups with a small received light intensity.
[0069]
Even when the intensity of the reflected light is low and the number of distance measurement data to be integrated is equal to or less than a predetermined number (including zero), the reflected light can be regarded as noise generated for some reason. Because.
[0070]
When the distance measurement data shown in FIG. 6A is pre-segmented according to the pre-segmentation conditions described above, five pre-segments are formed as shown in FIG. 6B. Then, for each pre-segment, the position (X, Z) of each distance measurement data is averaged to obtain the center position (Xc, Zc), and the minimum value and maximum value of the position (X, Z) of each distance measurement data are obtained. The width W and the depth D are obtained based on the values.
[0071]
Next, in step S30, the segmentation process is performed, and when the pre-segments formed from the distance measurement data of one scanning line satisfy the segmentation conditions, they are integrated into the segment. Note that a pre-segment that is not integrated with another pre-segment is the main segment as it is.
[0072]
This segmentation condition is that the difference (ΔXc, ΔZc) between the pre-segment center positions (Xc, Zc) is equal to or less than the integration determination distance (ΔX, ΔZ). This integration determination distance (ΔX, ΔZ) is changed according to the distance Z to the pre-segment. For example, when the distance Z is 35 m or less, the X-axis direction difference ΔX is 15 cm or less, the Z-axis direction difference ΔZ is 1.5 m or less, and when the distance Z is 35 m to 70 m, ΔX is 20 cm or less. In the range where ΔZ is 1.5 m or less and 70 m or more, ΔX is set to 25 cm or less and ΔZ is set to 2 m or less. Thus, the reason why the integration determination distance (ΔX, ΔZ) is changed according to the distance Z to the pre-segment is because the measurement accuracy and resolution of the laser beam are taken into consideration.
[0073]
Accordingly, as illustrated in FIG. 7, areas corresponding to the integration determination distances (ΔX, ΔZ) are set in the X-axis and Z-axis directions, respectively, according to the distance Z to the pre-segments PS1, PS2, PS3. Is done. For example, when the center position (Xc, Zc) of another pre-segment PS2 belongs to an area set for the pre-segment PS1, the pre-segment PS1 and the pre-segment PS2 are integrated to form this segment. Is done. Note that, since the pre-segment PS3 is out of the region, it is not integrated with the pre-segments PS1 and PS2, and becomes the main segment alone.
[0074]
However, in this segmentation process, in order to correctly grasp the distance and shape to the reflective object recognized as the main segment, if this segment is formed by integrating multiple pre-segments, the distance to the main segment Calculation and width calculation are performed as follows.
[0075]
First, a pre-segment for calculating the distance Z to this segment is extracted based on the received light intensity. Specifically, a pre-segment having a medium received light intensity or higher is extracted. However, if there is only one pre-segment having a light reception intensity of medium or higher and the number of distance measurement data constituting the pre-segment is one, a pre-segment having a low light reception intensity is also extracted. . This is because the depth and the like of this segment cannot be calculated with a single distance measurement data. Further, even when there is no pre-segment having a light reception intensity of medium or higher, a pre-segment having a low light reception intensity is extracted.
[0076]
Based on the pre-segment extracted in this way, the distance Z to the main segment is calculated. Specifically, the distance Z to this segment is calculated as an average value of the distances Z of the extracted pre-segments. Further, the minimum distance Zmin in the extracted pre-segment distance Z and the maximum distance Zmax in the extracted pre-segment distance Z are obtained, and the depth D of this segment is obtained from the difference between the minimum distance Zmin and the maximum distance Zmax. Note that the minimum distance Zmin and the maximum distance Zmax are obtained from the minimum value and the maximum value of each distance measurement data constituting the extraction pre-segment.
[0077]
Thus, in principle, by extracting a pre-segment having a light reception intensity of medium or higher and obtaining the distance Z to the present segment by the extracted pre-segment, the accuracy of the distance can be improved. That is, the reflected light having high intensity can be stably received by the laser radar sensor 5, and the accuracy of the distance to the reflecting object calculated based on the received light signal by such reflected light is very high. For this reason, the distance Z etc. to this segment can be calculated | required with high precision by calculating the distance Z etc. based only on the pre-segment whose light reception intensity is medium or more.
[0078]
Next, a method for calculating the width W of this segment will be described. The horizontal width W of this segment is first calculated using all pre-segments. That is, the horizontal width W is calculated from the position of the distance measurement data located at the right end and the left end of all the pre-segments. If the calculated lateral width W is smaller than the maximum lateral width W0 normally possessed by the vehicle (for example, 2.7 m in consideration of errors), the lateral width W is used as it is.
[0079]
However, when the calculated horizontal width is larger than the maximum value W0 and this segment is composed of a plurality of pre-segments having different received light intensities, the horizontal width of the present segment is reduced except for the pre-segments with low received light intensity. calculate. It is very unlikely that an object having a width that greatly exceeds the width of the vehicle exists in an area where the vehicle to be recognized should be present. Therefore, in this case, since it can be estimated that the pre-segment with a small received light intensity is caused by noise or the like, the lateral width W is calculated excluding the pre-segment.
[0080]
However, when the pre-segment having a low light receiving intensity is excluded and the width W is too small (for example, less than 1 m), the pre-segment is not excluded. Similarly, even when the lateral width W exceeds the maximum value W0, the pre-segment is not deleted even when the received light intensity of all the pre-segments is the same. Then, after calculating the horizontal width W of this segment, based on the horizontal width W, the center position of the present segment on the X axis is calculated.
[0081]
Thus, when this segment is formed for each scanning line, the target processing is then performed as shown in step S50. In the target processing, as shown in FIG. 8, it is determined whether or not the present segments in each scanning line should be integrated. Then, the segments determined to be integrated are connected to form an integrated target model.
[0082]
Hereinafter, the target processing will be described based on the explanatory diagram of FIG. 9 and the flowchart of FIG. In the target processing, first, in step S110, an estimated position of each main segment is calculated. That is, as shown in FIG. 9, when it is assumed that this segment has moved from the position at the time of the previous process at the relative speed at the time of the previous process, the estimated position where the present segment will exist is calculated. Subsequently, in step S120, an estimated movement range having a predetermined amount of width in each of the X-axis and Z-axis directions is set around the estimated position. In step S130, a segment that includes at least part of the estimated movement range is selected. Note that the above-described minimum distance Zmin, maximum distance Zmax, and the right end position and the left end position of the corrected lateral width W are used to calculate the position of this segment compared with the estimated movement range.
In step S140, when there are a plurality of main segments selected in step S130, the relative speed differences (ΔVx, ΔVz) of the main segments in the X-axis and Z-axis directions are respectively predetermined speed differences (ΔVx0, ΔVz0). Judge whether or not it is less than In step S150, if it is determined in step S140 that the relative speed difference (ΔVx, ΔVz) is less than the predetermined speed difference (ΔVx0, ΔVz0), the plurality of main segments are regarded as one. These target segments are integrated to form a target model. That is, the horizontal width Wm and the depth Dm are obtained from the minimum and maximum values in the X-axis and Z-axis directions of ranging data belonging to a plurality of main segments, and the distance to each main segment is averaged to obtain a target model. The distance Zm is obtained. The predetermined speed difference (ΔVx0, ΔVz0) may be a constant value or may be changed so as to increase as the traveling speed of the host vehicle increases.
[0083]
On the other hand, when there is one main segment included in the estimated movement range, the target model is configured by the single segment alone.
[0084]
When the present segment corresponding to the present segment obtained last time is specified, the data update process of the present segment is executed in order to calculate the next estimated position and the like. The updated data includes the past coordinates of the center coordinates (Xc, Zc), width W, depth D, relative speeds (Vx, Vz) in the X-axis direction and Z-axis direction, and center coordinates (Xc, Zc) of each segment. For example, batch data. In addition, this segment that does not belong to any estimated range is registered as a new actual segment.
[0085]
As described above, according to the target processing in the present embodiment, the X-axis and Z-axis directions of each segment are determined when determining whether the segments obtained for each scanning line are the same object. The relative speed difference is used. For this reason, even when a moving object such as a preceding vehicle and a stationary object such as a signboard approach, or even when preceding vehicles approach each other, they are reliably distinguished and recognized as separate objects. Can do.
[0086]
In addition, this invention is not limited to such embodiment at all, and can be implemented with various forms in the range which does not deviate from the main point of this invention.
[0087]
In the above embodiment, the pulse width of the stop pulse PB is adopted as an index indicating the received light intensity, but other indexes may be used. For example, a peak value detection circuit for detecting the peak value of the stop pulse PB can be provided, and this peak value can be used as an index indicating the received light intensity. Further, the rising angle of the stop pulse PB, that is, the time from the start of rising of the stop pulse PB to the predetermined reference voltage may be adopted as an index indicating the received light intensity.
[0088]
In the above embodiment, the polygon mirror 73 having a different surface tilt angle is used to perform two-dimensional scanning of laser light. However, for example, a galvanometer mirror that can scan in the vehicle width direction can be used, and the tilt angle of the mirror surface can be changed. This can be realized in the same manner even if a simple mechanism is used. However, the polygon mirror 73 has an advantage that a two-dimensional scan can be realized only by rotational driving.
[0089]
In the above embodiment, the object recognition block 43 converts the distance and the corresponding scan angle θx from the polar coordinate system to the XZ orthogonal coordinate system, but the processing may be performed by the laser radar sensor 5.
[0090]
In the above embodiment, the laser radar sensor 5 using laser light is employed, but radio waves such as millimeter waves, ultrasonic waves, and the like may be used. Moreover, it is not necessary to stick to the scanning method, and any method that can measure the direction other than the distance may be used. For example, when FMCW radar or Doppler radar is used with a millimeter wave, the distance information from the reflected wave (received wave) to the preceding vehicle and the relative speed information of the preceding vehicle can be obtained at one time. The process of calculating the relative speed based on the distance information as in the case of the case becomes unnecessary.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of an inter-vehicle distance control device to which the present invention is applied.
2A is a configuration diagram showing a configuration of a laser radar sensor, FIG. 2B is an explanatory diagram for explaining a distance detection method in the laser radar sensor, and FIG. 2C is an index showing received light intensity; It is explanatory drawing explaining the pulse width of the stop pulse as.
FIG. 3 is a perspective view showing an irradiable area of the laser radar sensor.
FIG. 4 is a flowchart illustrating processing related to object recognition.
FIG. 5 is an explanatory diagram for explaining the order of pre-segmentation processing and main segmentation processing;
6A shows distance measurement data converted into XZ orthogonal coordinates, and FIG. 6B is an explanatory diagram showing pre-segmented data.
FIG. 7 is an explanatory diagram for explaining the contents of the segmentation process;
FIG. 8 is an explanatory diagram for explaining a targetization process.
FIG. 9 is an explanatory diagram for explaining integration conditions in the target processing.
FIG. 10 is a flowchart showing target processing.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Vehicle control apparatus, 3 ... Recognition / vehicle distance control ECU, 5 ... Laser radar sensor, 7 ... Vehicle speed sensor, 9 ... Brake switch, 11 ... Throttle opening sensor, 13 ... Alarm sound generator, 15 ... Distance indicator, DESCRIPTION OF SYMBOLS 17 ... Sensor abnormality indicator, 19 ... Brake drive, 21 ... Throttle drive, 23 ... Automatic transmission controller, 24 ... Alarm volume setting device, 25 ... Alarm sensitivity setting device, 26 ... Cruise control switch, 27 ... Steering Sensor: 28 ... Yaw rate sensor, 29 ... Power switch, 30 ... Wiper switch, 43 ... Object recognition block, 44 ... Sensor abnormality detection block, 47 ... Vehicle speed calculation block, 49 ... Steering angle calculation block, 51 ... Yaw rate calculation block, 53 ... preceding vehicle determination block, 55 ... inter-vehicle distance control unit and alarm determination unit block, 57 ... curve radius calculation block DESCRIPTION OF SYMBOLS 70 ... Laser radar CPU, 71 ... Light emitting lens, 72 ... Scanner, 73 ... Mirror, 74 ... Motor drive circuit, 75 ... Semiconductor laser diode, 76 ... Laser diode drive circuit, 77 ... Glass plate, 81 ... Light receiving lens, 83 ... Light receiving element, 85 ... Amplifier, 87 ... Comparator, 89 ... Time measuring circuit

Claims (13)

A plurality of transmission waves are irradiated in front of the vehicle over a predetermined angle range, and when each transmission wave is reflected by a reflector and the reflected wave is received, a reception signal corresponding to the intensity of the reflected wave is output. Radar means;
Recognizing means for recognizing an object existing in front of the vehicle based on a transmission / reception result by the radar means,
The radar means, based on a time interval from irradiation of the transmission wave to reception of the reflected wave, distance calculation means for calculating a distance to the reflector in the irradiation direction of the transmission wave;
Intensity calculating means for obtaining the intensity of the reflected wave from the received signal,
The recognizing means, when the radar means receives a plurality of reflected waves, a difference in distance calculated by the distance calculating means based on the plurality of reflected waves is a predetermined distance or less, and the plurality of the plurality of reflected waves The reflected wave is generated by a transmission wave irradiated in the vicinity from the radar unit, and the difference in intensity calculated by the intensity calculating unit with respect to the plurality of reflected waves is not more than a predetermined value. An object recognition apparatus for a vehicle, comprising: first integrated means for recognizing a reflection object that generates a plurality of reflected waves as a single reflection object when all the conditions are satisfied. The intensity calculation means divides the reflected wave into a plurality of groups according to the intensity of the reflected wave,
The said 1st integration means judges that the difference in intensity | strength is below a predetermined value, when the several reflected wave is divided into the same group by the said intensity | strength calculation means. The object recognition apparatus for vehicles as described. 2. The recognition unit according to claim 1, wherein when the distance calculated by the distance calculation unit is equal to or less than a predetermined distance, the recognition unit excludes a reflection object that is not integrated with another reflection object from the recognition target. The vehicle object recognition device according to claim 2. The recognizing means excludes the reflected object from the recognition target when the intensity of the reflected wave calculated by the intensity calculating means is not more than a predetermined level and the number of integrated reflecting objects is not more than a predetermined number. The object recognition apparatus for vehicles according to claim 1 or 2 characterized by things. The first integration unit increases the predetermined distance, which is a condition regarding the difference in distance calculated by the distance calculation unit based on a plurality of reflected waves, as the distance calculated by the distance calculation unit increases. The vehicle object recognition device according to claim 1, wherein the vehicle object recognition device is a vehicle object recognition device. The first integration means determines that the transmission wave is irradiated in proximity when the number of transmission waves interposed between two transmission waves is equal to or less than a predetermined number, and the distance calculation means The vehicle object recognition device according to any one of claims 1 to 4, wherein the number decreases as the calculated distance increases. The radar means irradiates a plurality of transmission waves along the vehicle width direction of the vehicle, and the recognition means has a plurality of reflecting objects integrated by the first integration means. When the distance in the vehicle width direction between the plurality of reflecting objects and the distance in the irradiation direction of the transmission wave are equal to or less than a predetermined integration determination distance, the plurality of reflecting objects are integrated to form the same integrated reflection. The vehicle object recognition device according to any one of claims 1 to 6, further comprising second integration means for recognizing an object. The vehicle object recognition according to claim 7, wherein the second integration unit sets the integration determination distance to be longer as the distance to the reflection object in the irradiation direction of the transmission wave is longer. apparatus. The recognizing means includes distance / shape calculating means for obtaining a distance to the integrated reflecting object integrated by the second integrating means, and a width of the integrated reflecting object,
The distance / shape calculating means is based on the distance to the reflecting object obtained by integrating the reflecting object whose reflected wave intensity is equal to or higher than a predetermined level by the first integrating means. 9. The vehicle object recognition device according to claim 7, wherein a distance to the integrated reflective object is obtained. The distance / shape calculating means, when the second integrating means obtains an integrated reflecting object obtained by integrating a plurality of reflecting objects, the reflected waves of the plurality of reflecting objects have different intensities, and The width of the integrated reflective object is obtained when the width of the integrated reflective object exceeds a predetermined length, except for the reflective object having the weakest reflected wave intensity. The vehicle object recognition device according to claim 9. The radar means performs the irradiation of the transmission wave over a predetermined angle range in the vehicle width direction of the vehicle a plurality of times by changing the irradiation angle in the vehicle height direction of the vehicle,
For each transmission wave irradiation line in the vehicle width direction of the vehicle, the first integration means and the second integration means are integrated by integrating the reflecting objects and the reflecting objects, respectively. To find a reflective object,
The recognizing means is integrated when the integrated reflecting object obtained for each irradiation line is present at a close position and the condition that the difference between the moving speeds is a predetermined speed difference or less is satisfied. The vehicle object recognition apparatus according to claim 7, further comprising a target converting unit that further recognizes the reflective object as a target. The moving speed of the integrated reflecting object is calculated as a relative speed in the vehicle width direction with respect to the host vehicle and a relative speed in the irradiation direction of the transmission wave, and the target means is configured to detect both relatives of the plurality of integrated reflecting objects. The vehicle object recognition device according to claim 11, wherein when both speeds are equal to or less than a predetermined speed difference, the plurality of integrated reflective objects are integrated into a target. The target unit is configured to calculate the distance from the distance to the integrated reflecting object calculated by the distance / shape calculating unit, the width of the integrated reflecting object, and the relative speed of the integrated reflecting object for each detection time interval of the radar unit. Calculating an estimated area where the integrated reflective object is present, and determining that the integrated reflective object exists in a close position when other integrated reflective objects belong to the estimated area. The vehicle object recognition device according to claim 11 or 12.

Images