JP2003014844A - Object type determination device and object type determination method - Google Patents

Abstract

(57) [Summary] [PROBLEMS] To determine the type of an object existing in front of a host vehicle. A laser radar that generates a plurality of detection points based on reflected waves from an object existing in front of a host vehicle,
Performs grouping processing based on the object position of each detection point, and the relative speed of each detection point, detects an object consisting of a plurality of detection point detection points, and based on the relative speed of the detection point group indicating the object. It is determined whether the object is a traveling vehicle or a stationary object, and if the object is determined to be a stationary object, and the traveling vehicle is present between the stationary object and the own vehicle, the stationary object is marked as an overhead sign. Is determined, the maximum number of detection points for each object, the data filling rate indicating the ratio of the number of detection points detected by the laser radar 1 is calculated, it is determined that the object is a stationary object, the stationary object, When there is no running vehicle between the host vehicle and the host vehicle, the calculation unit 3 that determines the type of the stationary object based on the data filling rate is provided.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is mounted on a vehicle, emits invisible laser light, radio waves, etc., detects the presence or absence of an object from a reflected wave from an object in front of the vehicle, and travels from the detected object. The present invention relates to an object type determination device and an object type determination method for determining a vehicle, a sign, and the like.

[0002]

2. Description of the Related Art Conventionally, for example, Japanese Patent Application Laid-Open No. 2000-1 has been known as a target determination device for determining the type of an object using a radar.
There is a controlled object selection device disclosed in Japanese Patent No. 32799.

This controlled object selecting device is provided with distance measuring means, and first, a detection group is generated by collecting the distance groups according to the data measured by the distance measuring means.

The controlled object selection device generates a detection group for each distance measurement, further groups the detection groups according to the position and movement of each detection group, and recognizes them as one object.

Then, the controlled object selection device determines whether the object is a preceding vehicle, a delineator, or a sign depending on the movement of the recognized object and the width of the object.

[0006]

A conventional controlled object selection device, which is a target object determination device for determining the type of an object, determines the type of the object based on information such as the position and movement of the detected object and the width of the object. There is.

However, in the determination of the type of the object by such a method, for example, when there is no vehicle traveling ahead of the own vehicle, a guide sign indicating a destination or the like is displayed overhead on a highway. Since it is obviously larger than the vehicle, it is not judged as a stopped vehicle, but it is very difficult to judge whether a sign equivalent to a normal vehicle or a heavy truck is a stopped vehicle or a sign.

Therefore, the conventional method has a problem that it is not possible to distinguish a stationary object in front of the own lane into a vehicle and a sign.

The present invention has been proposed in view of the above-mentioned circumstances, and provides an object type determination device and an object type determination method capable of accurately distinguishing a detected object into a traveling vehicle and a stopped object. It is a thing.

[0010]

In order to solve the above-mentioned problems, the invention according to claim 1 is an object type determination device for determining the type of an object mounted on a vehicle and existing in front of the vehicle. Then, the transmitted wave is scanned on the object existing in front of the own vehicle, the reflected wave reflected from the object is detected, and based on the detected reflected wave, a plurality of detection points indicating the object position with respect to the own vehicle are detected. An object position detecting means for generating, a relative speed detecting means for detecting a relative speed of the object existing in front of the own vehicle with respect to the own vehicle at each detection point detected by the object position detecting means, and the object position detecting means. An object for detecting the object consisting of a detection point group of a plurality of detection points by performing grouping processing based on the object position of each detection point generated by the above and the relative speed of each detection point detected by the relative speed detection means. Detecting means; first determining means for determining whether the object is a traveling vehicle or a stationary object based on the relative speed of a detection point group indicating the object detected by the object detecting means; Second determining means for determining that the stopped object is an overhead sign when the first determining means determines that the object is a stopped object and there is a traveling vehicle between the stopped object and the own vehicle; A calculating means for calculating a data filling rate indicating a ratio between the maximum number of detection points for each object and the number of detection points detected by the object position detecting means; and the object is a stopped object by the first determining means. When there is no traveling vehicle between the stationary object and the own vehicle, a third determining means is provided for determining the type of the stationary object based on the data filling rate calculated by the calculating means. .

According to a second aspect of the present invention, the calculation means has the number of detection points as n, an average value of the distances between the detection points and the vehicle as Z, an end width of the detection points indicating an object as W, and When the angle at which the object position detecting means scans the object is θ, the data filling rate is calculated using an expression represented by (n × Z × tan θ) / W 2.

In a third aspect of the present invention, the second determination means is provided only when the detected point group indicating the traveling vehicle between the stopped object to be determined and the own vehicle has a large variation. The stationary object is determined to be an overhead sign.

According to a fourth aspect of the present invention, the third determining means determines the stopped vehicle, the large sign, and the small sign based on the relative speed, width, the reflection intensity, and the data filling rate of the detection point group indicating the stopped object. Determine to classify into any type of sign / delineator.

According to a fifth aspect of the present invention, the third determining means determines that the stopped object is a stopped vehicle when there is no other object within the scanning range of the object position detecting means, and the third vehicle is within the scanning range. When there is another object, the stationary object is determined to be a large sign.

In the invention according to claim 6, when it is determined that the stopped object is a small sign / delineator, the third determination means continues the determination processing until the number of determination processing reaches a predetermined number.

In order to solve the above-mentioned problems, the invention according to claim 7 is an object type determination device which is mounted on a vehicle and determines the type of an object existing in front of the vehicle. The transmitted wave is scanned by the existing object, the reflected wave reflected from the object is detected, and a plurality of detection points indicating the object position with respect to the own vehicle are generated based on the detected reflected wave, and the own vehicle is also generated. The relative speed of the object existing in front of the own vehicle is detected for each detection point, the object position of each detection point, and the grouping process based on the relative speed of each detection point is performed, Detecting the object consisting of the detection point group, based on the relative speed of the detection point group indicating the object, it is determined whether the object is a traveling vehicle or a stationary object, the object is a stationary object. Determined to be above When there is a traveling vehicle between the stationary object and the own vehicle, the stationary object is determined to be an overhead sign, and the maximum detection score for each object and the data filling rate indicating the ratio of the detection score. If it is determined that the object is a stopped object based on the relative speed, and there is no traveling vehicle between the stopped object and the host vehicle, the stop based on at least the calculated data filling rate. Determine the object as one of the following types: stop vehicle, large sign, small sign / delineator.

[0017]

According to the first aspect of the present invention, even if a traveling vehicle exists with the scan range angles overlapping between the stopped object and the vehicle, the vehicle is stopped based on the data filling rate. The type of the object can be determined, and the detected object can be accurately identified as a traveling vehicle or a stopped object.

According to the second aspect of the invention, the number of detection points n, the average value Z of the distances between the detection points and the vehicle, the edge width W of the detection points indicating the object, and the angle θ for scanning the object are used. It is possible to calculate the data filling rate using an arithmetic expression to determine the type of the stationary object, and to accurately identify the detected object as a traveling vehicle or a stationary object as in the case of the invention according to claim 1. Can be realized.

According to the third aspect of the present invention, the stopped object is detected only when there is a large variation in the detection point group indicating the traveling vehicle between the stopped object which is the object to be judged by the second judging means and the own vehicle. Since it is determined to be an overhead sign, it is possible to prevent an erroneous determination when the stopped object and the traveling vehicle angularly overlap in the scanning range.

According to the fourth aspect of the invention, the stopped vehicle, the large sign, the small sign / the small sign / based on the relative speed, width, reflection intensity, and data filling rate of the detection point group indicating the stopped object by the third judging means. Since it is determined that the delineator is classified into one of the types, it is possible to reliably distinguish the sign and the vehicle even if the stop ahead is a sign equivalent to the width of an ordinary car or a large truck.

According to the fifth aspect of the present invention, the third determining means determines that the stopped object is a stopped vehicle when no other object exists within the scanning range, and the other object exists within the scanning range. Since a stopped object is determined to be a large sign, if there is an object in front of the vehicle of the sign, some detection points of the sign may not be detected by the object in front, and the data filling rate is It is possible to deal with the case where the determination condition of the stopped vehicle is met. Therefore, an erroneous determination of a stopped vehicle can be prevented by using a large sign for a stopped object having an object in front.

According to the invention of claim 6, when the third determining means determines that the stopped object is a small sign / delineator, the determination processing is continuously performed until the number of determination processing reaches a predetermined number. The result can be reviewed, and if part of the object is within the scan range, the object width is narrow and it is determined as a small sign / delineator, but over time, the object is completely within the scan range. In this case, it is possible to prevent an erroneous determination. Therefore, it is possible to prevent erroneous determination by re-examining the determination of the classification of the object determined to be the small sign / delineator.

According to the seventh aspect of the present invention, even when the traveling vehicle exists with the scan range angles overlapping between the stopped object and the own vehicle, the stopped object is detected based on the data filling rate. The type can be determined, and the detected object can be accurately identified as a traveling vehicle or a stopped object.

[0024]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings.

The present invention is applied to, for example, the object type determination device shown in FIG.

[Arrangement of Object Type Judging Device] FIG. 1 is a block diagram showing the functional arrangement of an object type judging device mounted on a vehicle. This object type determination device includes a laser radar 1 provided in front of a vehicle, a vehicle behavior detection unit 2 for detecting behavior when the vehicle is traveling, and a front side of a host vehicle according to information from the laser radar 1 and the vehicle behavior detection unit 2. It is configured to include an object detection process for detecting an existing object and an arithmetic unit 3 for performing an object type determination process for determining the type of the detected object.

The object type determination processing determines, for example, a preceding vehicle traveling ahead of the host vehicle and a stationary object,
Further, it is a process of determining whether or not the stopped object is an overhead sign in front of the host vehicle. By performing this object type determination processing, the driver of the own vehicle is presented with the preceding traveling vehicle and the stopped object existing in front of the own vehicle.

As shown in the side view of FIG. 2 (a) and the top view of FIG. 2 (b), the laser radar 1 is arranged in the front portion 11a of the host vehicle 11 and the optical axis of the laser light L emitted therefrom. Is perpendicular to the vehicle 11, and the laser light L is set so that the scanning surface is parallel to the road surface.

The laser radar 1 scans the laser light L within a predetermined scan range by changing the optical axis at a predetermined angle on the scanning surface. As a result, the laser radar 1 irradiates the object existing in the scan range with the laser light L.

This laser radar 1 obtains a reflection signal based on the light intensity of the reflected laser light by detecting the reflected laser light which is emitted from the object and is reflected by the emitted laser light. The laser radar 1 performs distance measurement processing using the acquired reflection signal to generate distance measurement information indicating the distance between the object and the vehicle, and outputs the distance measurement information to the calculation unit 3.

The vehicle behavior detecting section 2 includes a shift position sensor for detecting a shift position of the vehicle and a wheel speed sensor for detecting wheel speeds of the left and right rear wheels of the vehicle. Furthermore,
The vehicle behavior detection unit 2 includes a calculation device that calculates a vehicle position, a vehicle traveling direction, a vehicle direction, and a moving distance by using sensor signals from a shift position sensor and a wheel speed sensor.

The vehicle behavior detecting section 2 outputs the vehicle position, the traveling direction, the vehicle direction, and the moving distance from each sensor to the calculating section 3 as vehicle traveling information.

The calculation unit 3 is a CPU mounted inside the vehicle.
(Central Processing Unit), RAM (Random Access
Memory), ROM (Read Only Memory), input / output I /
It is composed of a microcomputer such as F.

The calculation unit 3 performs an object detection process for detecting an object existing in front of the host vehicle 11 based on the information from the laser radar 1 and the vehicle behavior detection unit 2, and the detected object further travels ahead. Object type determination processing is performed to determine whether the vehicle is a stationary object such as a sign. The details of this object type determination processing will be described later.

[Operation of Computing Unit 3] [Detection of Overhead Marker] Using FIG. 3, an object in front is detected, and the computing unit 3 judges whether the detected object is an overhead sign.
A method for making a determination will be described. In this example, a case where the traveling vehicle 12 is located in front of the host vehicle 11 and the overhead sign 13 is located further in front of the host vehicle 11 will be described.

First, the laser radar 1 outputs a laser beam to scan an object in front, the traveling vehicle 12, and the overhead sign 13 one-dimensionally (x direction). Laser radar 1
Acquires a reflection signal based on the light intensity of the reflected laser light reflected from the object, performs distance measurement processing based on the acquired reflection signal, and sends distance measurement information to the calculation unit 3.

The point sequence consisting of a plurality of detection points shown on the traveling vehicle 12 and the overhead sign 13 is scanned by the laser radar 1 and the detection points calculated by performing the distance measurement processing are plotted at the distance positions. It is a thing.

The calculation unit 3 groups a plurality of detection points based on the distance measurement information and the vehicle traveling information output from the laser radar 1 and the vehicle behavior detection unit 2, respectively, to generate a detection point group indicating an object. Then, the object detection process is performed.

If the distance difference between the adjacent detection points among the detection points included in the detection point group is about 1 m, the calculation unit 3 groups the detection points as the same reflector. Arithmetic unit 3
Calculates the relative speed of the grouped detection points from the vehicle travel information output from the vehicle behavior detection unit 2. If the positions and relative speeds are the same in time series, the detection points are further grouped. And the detection point group is detected as an object.

After recognizing the detected point group as an object, the calculation unit 3 determines whether the object is a traveling vehicle or a stopped object based on the relative speed of the detected point group with respect to the host vehicle 11. At this time, the calculation unit 3 determines that the vehicle is a traveling vehicle if the relative speed of the object with respect to the own vehicle 11 is a predetermined threshold value Vt1 or more, and the stopped object if the relative speed of the object with respect to the own vehicle 11 is less than or equal to the threshold value Vt2. And The threshold values Vt1 and Vt2
Is a value set in advance and stored in a memory (not shown) in the arithmetic unit 3. As a result, the traveling vehicle 12 in FIG. 3 is recognized by the arithmetic unit 3 as a traveling vehicle, and the overhead sign 13 is recognized as a stationary object.

Further, if any one of the left end point θl, the middle point θc, and the right end point θr, which are the measurement points of the object recognized as the stationary object, is within the detection range (angle) of the traveling vehicle, the arithmetic unit 3 moves overhead. It will be a candidate for a sign. This is because when a one-dimensional scan is performed by the laser radar 1, the stopped object and the traveling vehicle do not angularly overlap each other unless they are located at a position higher than the traveling vehicle. As a result, a stopped object that overlaps at a position higher than the traveling vehicle is discriminated as a candidate for an overhead sign.

In FIG. 3, since the right end detection point θr of the detection points of the overhead sign 13 recognized as a stationary object is within the detection range of the traveling vehicle 12, the overhead sign 13 is calculated as an overhead sign candidate. Recognized by 3.

However, there is a case where the traveling vehicle and the stopped vehicle overlap due to the measurement error of the distance measurement. In this case, in order to prevent the stopped vehicle from being erroneously determined as an overhead sign, the dispersion of the detection points of the traveling vehicle may be prevented. Only when the degree is the threshold value Nt1 or more, the stopped object is set as the overhead marker candidate.

This is because when the traveling vehicle and the overhead sign overlap, the detection points indicating the sign distance and the detection points indicating the vehicle distance coexist in the overlapping area (scan range). The accuracy deteriorates, and the variation of the detection points in the traveling vehicle detection area increases. For this reason, if the detection points of the traveling vehicle have a large variation (the detection point dispersion is equal to or more than the threshold value Nt1), the overlapping stopped objects are set as the overhead marker candidates.

[Distance Data Filling Ratio R] Next, referring to FIG. 4, the maximum number of detection points for each object used when determining the object type and the number of detection points detected by the object position detecting means are described. The distance data filling rate R indicating the ratio will be described.

For the distance data filling rate R, n is the number of detection points, and Z is
Is a distance, W is an object width, and θ is a scan angle. Note that the distance Z indicates the distance between the vehicle 11 and the object composed of the detection points obtained as a result of the grouping, but since there are a plurality of detection points for the object, the distances to the respective detection points may be slightly different. Contains. Therefore, the distance Z used here is the average value or the median value of the detected distances.

R = (n × Z × tan θ) / W Equation (1) The distance data filling rate R is calculated by the arithmetic unit 3 using the above equation (1) and takes a numerical value of 0 to 1.0. For example, the detection points (distance data) are included in the entire detection range corresponding to the object width W.
Is 1.0 if there is any, and 1.0 or less if no detection points are obtained from all. In the case of a label, since the detection points can be obtained from most of the detection range even from a distance, the distance data filling rate R shown as the equation (1) shows a value close to 1.0. On the other hand, in a distant vehicle, the detection point is obtained only from the reflector provided in the vehicle, so the distance data filling rate R has a small value.

In the object 14 having the object width W shown in FIG. 4, for example, if the maximum number of detection points obtained is 8 and the number of detection points n of the object 14 is 7, the distance data filling rate R is It becomes 0.875, which is close to 1.0. In this case, the calculation unit 3 determines that the object 14 is a sign. If the number of detection points n of the object 14 is 2, the distance data filling rate R becomes a small value such as 0.25, and in this case, the calculation unit 3 determines that the object 14 is a vehicle.

[Classification of Stopped Objects] Next, a method of classifying an object recognized as a stopped object into any of a stopped vehicle, a large sign, and a small sign / delineator will be described with reference to FIG.

The computing unit 3 classifies a stationary object into any of a stationary vehicle, a large sign, and a small sign / delineator. The relative speed V (for example, the average relative speed) of the group of detection points and the grouped detection points. Object width W consisting of a group, reflection intensity P consisting of a group of detection points
(For example, average reflection intensity) and distance data filling rate R are used.

The calculation unit 3 determines that the relative velocity of the object is the threshold value V.
When it is recognized as a stopped object at time t2 or less, the stopped object is classified into one of a stopped vehicle, a large sign, and a small sign / delineator based on the following first to fourth conditions.

First condition: The condition for classifying as a stopped vehicle is that a vehicle having a wide object width W and a small distance data filling rate R is classified as a stopped vehicle. Note that the stopped object 16 in FIG. 5 meets this condition, and the stopped object 16 is classified as a stopped vehicle.

Second condition: If there is an overlapping object in front of the classification target, it is classified as a large sign. It should be noted that there is a stopped object 18 in front of the stopped object 17 in FIG. 5, and since this condition is met, it is classified as a large sign.

Third condition: If the object width W is wide and the distance data filling rate R is large, it is classified as a large sign.

Fourth condition: When the object width W is narrow, a small sign /
Classify as a delineator. In FIG. 5, the stationary object 1
5 and the stopped object 18 correspond to this condition, and are classified as a small sign / delineator. However, objects having a wide object width W and weak reflection intensity P are also considered as small markers / delineators. In addition, those having a low reflection intensity P are classified into small markers / delineators that allow the judgment result to be re-examined even after the judgment is made because the judgment system is deteriorated.

Next, if the number of detection points classified by the above-mentioned first to fourth conditions is N or more, the arithmetic unit 3 selects the most classification as the object type from the total of the classification results of each detection point. The judgment result. If the number of detection points classified by the first condition to the fourth condition is less than N, the measurement is continued until it becomes N or more. Specifically, in the case shown in FIG. 5, among the detection points forming the stationary object 17, five detection points are the second detection points.
When the object is classified as a large sign by the condition or the third condition, the object type of the stationary object 17 is set as the large sign.

The calculation unit 3 continues the measurement for the stationary object classified into the small sign / Derniator, and re-examines the determination result in a timely manner. The judgment results will not be reviewed for stationary objects classified as other.

"Review of Discrimination of Small Signs / Derniators" FIG. 6 shows a process for reviewing the determination result of the detection points where the stopped objects are classified into the small signs / delineators when classifying the stopped objects as described above. The figure for demonstrating is shown.

For example, in the case of a wide object such as the stopped object 19 shown in FIG. 6, when the vehicle travels and the distance between the stopped object 19 and the stopped object 19 becomes gradually smaller, the stopped object 1 is earlier in time.
Since only a part of 9 exists in the scan range of the laser radar 1, even if the object is classified as a small sign / delineator, the whole object exists in the scan range as the distance approaches, and therefore the object is classified as a small sign / delineator. There is a stationary object that can not be.

In such a case, it is an erroneous determination that the stationary object 19 is not completely within the scanning range and is classified as a small sign / delineator at a temporally previous stage. Therefore, the calculation unit 3 executes the work of revising the determination result in order to prevent such an erroneous determination with respect to the object discriminated as the small sign / delineator. The determination result by the calculation unit 3 is reviewed when the number of detected data is N times or more, similarly to the first determination, and when the determined result is the same, the number of detected data is reset.

"Procedure for Object Type Determination Processing by Computing Unit 3"
Next, the procedure of the object type determination processing by the object type determination device will be described using the flowchart shown in FIG. 7.

In step S1, the laser radar 1 scans the front of the vehicle 11 to receive the signal from the front reflector, calculates a detection point including the distance Z and the reflection intensity P, and processes it in step S2. Proceed.

In step S2, among the detection points obtained in step S1, those having a small distance difference among the adjacent detection points are grouped by the arithmetic unit 3, and the grouped detection points are arranged in position or relative in time series. If the speeds are the same, further grouping is performed. By performing the grouping process a plurality of times by the calculation unit 3, the presence of an object in front of the vehicle 11 composed of the detection point group is detected, and the process proceeds to step S3.

In step S3, the running unit existence determination is performed by the calculation unit 3 from the relative speed of each object detected in step S2. The relative speed is set to the threshold value Vt by the calculation unit 3.
If it is determined to be 1 or more, the process proceeds to step S4, and if it is determined that the relative speed is less than the threshold value Vt1, the process proceeds to step S5.

In step S4, for the detection point group forming the object detected in step S2 by the calculation unit 3, a traveling vehicle flag indicating that the object is a detection point forming a traveling vehicle is set, and the object type determination processing is performed. finish.

On the other hand, in step S5, the computing unit 3 determines the stationary object from the relative speed of the detection point groups grouped in step S2. If the relative speed is equal to or lower than the threshold value Vt2, the calculation unit 3 determines that the object is a stationary object in step S6
If the relative speed is greater than the threshold value Vt2, the object determination is not performed and the process returns to step S1.

In step S6, the operation unit 3 extracts the overhead marker candidates. Of the detection points forming the object determined to be the stationary object in step S5, any one of the detection point located at the right end, the detection point located at the center, and the detection point located at the left end is in front of the host vehicle 11. If it exists within the scan range of the traveling vehicle traveling in the above, the process proceeds to step S7 with the detection point group forming the object as an overhead marker candidate. That is, the calculation unit 3 causes the own vehicle 11
There is a traveling vehicle in front of the stopped object when viewed from the viewpoint, and it is determined whether or not the scanning range in which the stationary object is detected and the scanning range in which the traveling vehicle is detected overlap with each other when viewed from the host vehicle 11, and they overlap. If so, the process proceeds to step S7. If they do not overlap, the process proceeds to step S8.

In step S7, the computing unit 3 determines the overhead marker. If the variance of the detection point group indicating the object as the overhead sign candidate in step S6 and the detection point group indicating the traveling vehicle angularly overlapping the scan range is equal to or more than the threshold value Nt1, the process proceeds to step S8, and the dispersion is performed. When is less than Nt1, the process proceeds to step S9 without determining as an overhead sign.

In step S8, the arithmetic unit 3
In step S6, it is determined that the detection point group indicating the stopped object that is overlapped with the traveling vehicle is an overhead sign,
A flag indicating that it is an overhead sign is set at each of the detection points that form the stationary object, and the object type determination process ends.

In step S9, the calculation unit 3 calculates the characteristic amount necessary for determining the type of the stationary object. The feature amount for determining the type of the stationary object is the relative velocity of the detection point group, the object width W, the reflection intensity P, and the distance data filling rate R. The reflection intensity P is the maximum intensity P in the detection point group forming the object, and the distance data filling rate R is obtained from the above-mentioned formula (1). After calculating the characteristic amount, the calculation unit 3 advances the process to step S10.

In step S10, the operation unit 3 classifies the stopped object into one of a stopped vehicle, a large sign, and a small sign / deriniator based on the feature amount obtained by applying the first to fourth conditions. The process proceeds to step S11.

In step S11, step S10
Then, it is determined whether or not the total number of detection points classified by the calculation unit 3 has reached the number of detection points required for object determination. If the total number of detection points is N or more by the calculation unit 3, the process proceeds to the next step S12, and if the required number of detection points has not been reached, the process returns to step S1.

In step S12, the computing unit 3 determines an object. From the detection points classified into the stopped vehicle, the large sign, and the small sign / delineator, the one with the largest number is set as the determination result, and the process proceeds to the next step S13. However, when the number of detected points is the same, the process proceeds to the next process after step S1. Further, when it is determined that the stopped object is the small sign / delineator and the determination is performed again for the above-mentioned reason, the calculation unit 3 resets the accumulated classified result.

In step S13, the calculation section 3 determines the end of the object determination. When it is determined in step S12 that the stopped object is other than the small sign / delineator, the calculation unit 3 ends the object determination, and the object determined to be the small sign / delineator returns to step S1 again to perform the re-determination.

In this way, the object type determination device detects an object in front of the host vehicle 11 and further determines whether the detected object is a traveling vehicle, an overhead sign, or a small sign / deliniator. The type of the object can be determined.

[Effects of the Embodiment] As described in detail above, according to the object type determining apparatus of the present embodiment,
Even when the traveling vehicle exists with the scan range angles overlapping between the stopped object and the own vehicle 11, the type of the stopped object can be determined based on the distance data filling rate R and detected. The object can be accurately discriminated as a traveling vehicle or a stationary object.

Further, according to the object type determination device, the stop object is an overhead sign only when the detected point group indicating the traveling vehicle between the stop object to be determined and the own vehicle has a large variation. Since the determination is made, erroneous determination can be prevented even when the stationary object and the traveling vehicle angularly overlap the scanning range of the laser radar 1.

Further, according to the object type determination device, any one of the stopped vehicle, the large sign, and the small sign / delineator is determined based on the relative speed, width, reflection intensity, and distance data filling rate R of the detection point group indicating the stopped object. Since it is determined to classify the vehicle into one of these types, it is possible to reliably distinguish between the sign and the vehicle even if the stop ahead is a sign equivalent to the width of a normal car or a large truck.

Furthermore, according to the object type determination device, a stopped object is determined as a stopped vehicle when no other object exists in the scan range, and a stopped object is determined when another object exists in the scan range. Since it is determined to be a large sign, if an object is present in front of the own vehicle 11 of the sign, some detection points of the sign may not be detected by the object in front, and the distance data filling rate R stops. It is possible to deal with the case where the vehicle judgment conditions are met. Therefore,
According to this object type determination device, an erroneous determination of a stopped vehicle can be prevented by setting a large sign for a stopped object having an object in front.

Furthermore, according to the object type determination device, when the stop object is determined to be a small sign / delicinator, the determination process is continued until the number of determination processes reaches a predetermined number, and the determination result is reviewed. , If a part of the object exists in the scan range, the object width is narrow and it is determined to be a small sign / delineator. Can be prevented. Therefore, according to this object type determination device, it is possible to prevent erroneous determination by reviewing the classification determination again for the object determined to be the small sign / delineator.

The above-described embodiment is an example of the present invention. For this reason, the present invention is not limited to the above-described embodiment, and other than this embodiment, as long as it does not deviate from the technical idea of the present invention, various types according to the design etc. Of course, it is possible to change.

[Brief description of drawings]

FIG. 1 is a block diagram showing a functional configuration of an object type determination device to which the present invention has been applied.

FIG. 2 is a side view (a) and a top view (b) for explaining an optical axis of laser light when a laser radar is mounted on a front portion of a vehicle.

FIG. 3 is a diagram for explaining processing contents when an overhead marker is detected by a calculation unit.

FIG. 4 is a diagram for explaining a distance data filling rate calculated by a calculation unit.

FIG. 5 is a diagram for explaining processing contents when classifying a stationary object detected by a calculation unit into three types.

FIG. 6 is a diagram for explaining processing contents for re-determining a stopped object classified as a small sign / delineator by a calculation unit.

FIG. 7 is a flowchart for explaining a processing procedure when determining the type of an object in front of the own vehicle by the object type determination device to which the present invention is applied.

[Explanation of symbols]

1 laser radar 2 Vehicle behavior detector 3 Calculation unit 11 Own vehicle

   ─────────────────────────────────────────────────── ─── Continued front page    F-term (reference) 5H180 AA01 CC03 CC14 LL01 LL02                       LL09                 5J070 AC01 AC06 AE01 AF03 AK22                       BF11                 5J084 AA04 AA05 AA07 AA09 AB01                       AC02 BA03 BA11 EA04 EA22

Claims (7)

[Claims] 1. An object type determination device mounted on a vehicle for determining the type of an object existing in front of the vehicle, wherein the object existing in front of the vehicle is caused to scan a transmitted wave and reflected from the object. An object position detecting means for detecting a reflected wave that is generated and generating a plurality of detection points indicating an object position with respect to the own vehicle based on the detected reflected wave; and a relative position of the object existing in front of the own vehicle with respect to the own vehicle. Relative speed detecting means for detecting the speed for each detection point detected by the object position detecting means, object position of each detection point generated by the object position detecting means, and each detection detected by the relative speed detecting means The object detection means for performing the grouping process based on the relative speed of the points to detect the object composed of the detection point groups of the plurality of detection points, and the phase of the detection point group indicating the object detected by the object detection means First determining means for determining whether the object is a traveling vehicle or a stopped object based on the speed; and the first determining means determines that the object is the stopped object, If a traveling vehicle is present between the host vehicle and the host vehicle, second determining means for determining the stopped object as an overhead sign, the maximum number of detection points for each object, and the object position detecting means are detected. A calculating unit that calculates a data filling rate indicating a ratio with the number of detection points and the first determining unit determine that the object is a stopped object, and there is no traveling vehicle between the stopped object and the own vehicle. In this case, the type of the stationary object is determined based on the data filling rate calculated by the calculating means.
An object type determination device comprising: determination means. 2. The calculation means is n, the average value of the distance between the detection points and the vehicle is Z, the end width of the detection points indicating an object is W, and the object position detection means is 2. The object type determining apparatus according to claim 1, wherein the data filling rate is calculated using an expression expressed by (n × Z × tan θ) / W, where θ is an angle for scanning the object. . 3. The second determination means uses the overhead sign to indicate the stop object only when there is a large variation in the detection point group indicating the traveling vehicle between the stop object to be determined and the own vehicle. The object type determination device according to claim 1, wherein it is determined that there is an object type determination device. 4. The third determination means is any one of a stopped vehicle, a large sign, and a small sign / delineator based on the relative speed and width of the detection point group indicating the stopped object, the reflection intensity, and the data filling rate. The object type determination device according to claim 1, wherein the object type determination device according to claim 1 determines. 5. The third determining means determines the stopped object as a stopped vehicle when no other object exists within the scanning range of the object position detecting means, and the other object exists within the scanning range. The object type determination device according to claim 4, wherein the stopped object is determined to be a large sign in this case. 6. The third determination means, when the stop object is determined to be a small sign / deliciter, continues the determination processing until the number of determination processing reaches a predetermined number. 4. The object type determination device described in 4. 7. An object type determination device mounted on a vehicle for determining the type of an object existing in front of the vehicle, wherein the object existing in front of the vehicle is caused to scan a transmitted wave and reflected from the object. The detected reflected wave is detected, and based on the detected reflected wave, a plurality of detection points indicating the object position with respect to the own vehicle are generated, and the relative speeds of the object existing in front of the own vehicle with respect to the own vehicle are detected. Each point is detected, the grouping process based on the object position of each detection point and the relative velocity of each detection point is performed, and the object composed of the detection point group of a plurality of detection points is detected to indicate the object. Based on the relative speed of the detection point group, it is determined whether the object is a traveling vehicle or a stationary object, and it is determined that the object is a stationary object, and between the stationary object and the host vehicle. If there are moving vehicles in , The stationary object is determined to be an overhead sign, the maximum detection score for each object, and a data filling rate indicating the ratio of the detection score is calculated, and the object is a stationary object based on the relative speed. When there is no traveling vehicle between the stopped object and the host vehicle, the stopped object is determined to be one of a stopped vehicle, a large sign, and a small sign / delineator based on at least the calculated data filling rate. A method for determining an object type, which comprises determining the type.