JPH06150195A - Object detector - Google Patents

Abstract

PURPOSE:To reduce an influence of erroneous recognition in the case that a noise or the like is erroneously recognized as a preceding vehicle by extending the holding time for missing of the preceding vehicle. CONSTITUTION:An object detecting means 10 detects the present position of a moving object like a running vehicle, and the past position of the object detected by the object detecting means 10 is stored in a storage means 12. A discriminating means 14 discriminates whether the detected object and the stored object correspond to each other or not based on the present position of the detected object and the position of the stored object stored in the storage means 12. An operation means 16 performs such operation that the degree of sureness is high in the case of the stored object judged to correspond to the detected object by the discriminating means 14 but is low in the case of the stored object judged to not correspond to it. A stored contents change means 18 changes stored contents for stored objects, whose degrees of sureness are equal to or higher than a prescribed value, basing on the detected present position and erases stored contents for stored objects whose degrees of sureness are lower than the prescribed value, and positions of detected objects which are judged to not correspond to stored objects by the discriminating means 14 are stored in the storage means 12.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an object detecting device, and more particularly to an object detecting device for detecting a moving object such as a moving vehicle.

[0002]

2. Description of the Related Art Conventionally, there is known a device which recognizes a preceding vehicle by using radars and travels following the vehicle. In the recognition of the preceding vehicle by these devices, there are problems such as a temporary detection error of the preceding vehicle due to the uncertainty of the sensor and a misrecognition of the preceding vehicle due to the mixing of noise.

Japanese Unexamined Patent Publication Nos. 2-36500 and 1-
No. 213593, JP-A No. 61-20877,
JP-A-61-145474, JP-A-61-278
Japanese Patent Laid-Open No. 775, JP-A-62-36581, and Japanese Patent Laid-Open No. 2-40800 disclose techniques for recognizing a preceding vehicle. However, these techniques take measures against the loss of sight of the preceding vehicle. Absent.

Further, in Japanese Unexamined Patent Publication No. 1-114550, when a preceding vehicle is lost at a doorway of a curve or the like, the control vehicle speed of the own vehicle is maintained for a certain time w1 as a countermeasure against the loss. As a method similar to this, a method of holding the preceding vehicle data for a certain period of time and a method of holding the inter-vehicle distance for a certain period of time are conceivable.

If the holding time is set to be long in order to cope with a long loss (about several seconds) of the preceding vehicle, the control is delayed by this holding time when the preceding vehicle is mistakenly recognized due to noise or the like. Causes of noise include the case where an obstacle other than the preceding vehicle is mistakenly recognized as the preceding vehicle and the noise is mixed into the sensor system.

Contrary to the above, if the holding time is shortened,
I can't cope with long lost sight. Causes of long-time loss of sight include operation at entrances and exits of curves, up and down slopes, adverse environments such as rainy weather, and radar malfunctions.

Further, Japanese Laid-Open Patent Publication No. 61-272673 discloses a technique for increasing the S / N ratio of a radar signal by accumulating a plurality of observation results in a memory. However, depending on the mechanism of the radar device, the preceding vehicle may temporarily go out of the radar measurement range, such as when the nose of the vehicle bounces or when the vehicle crosses an inflection point on a slope. In this case, since the radar signal itself cannot be obtained, even if the S / N ratio is increased by this method, the lost sight cannot be solved.

[0008]

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and is effective when a moving object such as a preceding vehicle or a vehicle traveling in another lane is lost. If the holding time is long and the noise etc. is mistaken for the preceding vehicle, the influence of the mistake will be reduced and the detected object will be
An object of the present invention is to provide an object detection device that can cope with the loss of sight when it is temporarily deviated from the measurement range of a laser or the like.

[0009]

To achieve the above object, the present invention provides an object detection means for detecting the current position of an object, and a storage means for storing the past position of the detected object detected by the object detection means. And whether the detected object whose current position is detected based on the current position of the detected object and the position of the stored object stored in the storage means and the stored object whose position is stored in the storage means correspond to each other. Determination means for determining whether the storage object is present, a calculation means for calculating a certainty factor indicating the degree of existence of the storage object based on the determination result of the determination means, and the stored content of the storage object having the certainty factor of a predetermined value or more is detected. The stored content for the storage object whose confidence factor is less than a predetermined value is deleted, and the position for the detected object determined not to correspond to the storage object by the determination means is stored. Stored contents are configured to include a changing unit, and that.

[0010]

The object detecting means of the present invention detects the current position of a moving object such as a traveling vehicle or a stopped object such as a stopped vehicle, and the storage means detects the detected object detected by the object detecting means. Remember the past position of. The determination means determines whether the detected object whose current position is detected based on the current position of the object and the position of the storage object stored in the storage means and the storage object whose position is stored in the storage means correspond to each other. Determine whether or not. For example, if a detected object whose current position has been detected exists in a region within a predetermined range including the stored past position, the position is stored in the detected object whose current position has been detected and the storage means. It can be determined that the stored objects correspond to each other. The calculation means calculates a certainty factor indicating the degree of existence of the storage object based on the determination result of the determination means. At this time, a certain degree of confidence is calculated for a storage object determined to correspond to the detected object by the determination means, and a certainty is determined for the storage object determined to not correspond to the detected object by the determination means. It is calculated so that the degree becomes smaller.

Then, the storage content changing means changes the storage content of the storage object having a certainty factor of a predetermined value or more based on the detected current position. As a result, the storage content of the storage means is updated to the latest content for a storage object with a certainty factor equal to or higher than a predetermined value, that is, an object that has not been lost or has been lost within a predetermined time. Can be dealt with. Further, the storage content changing unit erases the storage content of the storage object having a certainty factor of less than a predetermined value. As a result, the content stored in the storage means is erased for an object whose certainty factor is less than a predetermined value, that is, an object whose loss is over a predetermined time. Furthermore, the memory content changing means is
The position of the detected object which is detected by the detection unit but is determined not to correspond to the storage object of the determination unit is stored in the storage unit. This makes it possible to deal with a case where a lost object is detected again after a long loss.

[0012]

EXAMPLES Examples of the present invention will be described below. First, a functional block of this embodiment is shown in FIG. As shown in the figure, the present embodiment includes an object detection unit 10 that detects the current position of a moving object and a storage unit 12 that stores the past position of the detected object detected by the object detection unit 10. I have it. The object detection means 10 and the storage means 12 are
The detected object whose current position is detected based on the current position of the detected object and the past position of the stored object stored in the storage unit 12 and the stored object whose position is stored in the storage unit 12 correspond to each other. It is connected to the judgment means 14 for judging whether or not there is. The judging means 14 is connected to the calculating means 16 for calculating the certainty factor indicating the degree of existence of the storage object based on the judgment result of the judging means 14. The calculating means 16 changes the stored content of a storage object having a certainty factor of a predetermined value or more based on the detected current position, and
It is connected to a storage content changing means 18 that erases the storage content of a storage object having a certainty factor of less than a predetermined value and stores the position of a detected object determined by the determination means 14 not to correspond to the storage object.

The object position detecting means 10 is a sensor capable of detecting the position of a moving object, and is a sensor capable of distinguishing a plurality of objects, for example, a two-dimensional coordinate of a scan type laser, an image type or the like can be obtained. A sensor that can obtain one-dimensional coordinates by using a sensor, a microwave, or the like can be used. Alternatively, a sensor that can obtain the relative velocity at the same time as the position may be used, and by selecting these sensors, an effect corresponding to the performance of the selected sensor can be expected. In the following, description will be made using a sensor that can obtain two-dimensional coordinates.

The object information storage means 12 uses, for example, a RAM, and the position of the detected object (preceding vehicle) (two-dimensional information according to the sensor), certainty factor, and other information (eg speed).
Are collectively stored as a storage object for each detected object, for example.

As a storage method, information may be collectively stored for each storage object as in Example 1 below, or each information may be stored in the form of an array as in Example 2. Since the number of objects to be detected, that is, the number of preceding vehicles, is generally about 5 during following traveling, it is sufficient to secure a storage area for about 10 to 20 vehicles with a margin.

Example of storage method 1 Storage object 1: x-coordinate at the time of the previous measurement y-coordinate at the time of the previous measurement Confidence at the time of the previous measurement x-direction speed at the time of the previous measurement y-direction speed at the time of the previous measurement Storage object 2: last-time measurement X-coordinate of time y-coordinate of previous measurement Confidence of previous measurement x-direction speed of previous measurement y-direction speed of previous measurement Example of memory method 2 x-coordinate of storage object 1 x-coordinate of storage object 2 Y-coordinate of the memory object 1 y-coordinate of the memory object 2 Confidence of the memory object 1 Confidence of the memory object 2 The determination means 14 stores the detected object (for example, a car) and information as follows, for example. Stored objects (for example,
Car) and whether they correspond. First, it is assumed that the storage means 12 stores the positions of the storage objects 1 to 3 as shown in FIG. The sector 20 is the measurement range of the sensor, and the host vehicle is at the left end, which is the corner of the sector. Then, it is assumed that the detection objects 1 to 3 are detected at the positions shown in FIG. 3 in the next measurement. Detection objects 1-3 and storage objects 1-3
When it is determined whether and correspond to each other, ranges 1 to 3 are defined for each storage object as shown in FIG.
Within these ranges 1 to 3, the detected object closest to the memory object is associated with the memory object existing in this range. In this example, since the storage object 1 and the detection object 1 exist in the range 1, the storage object 1 and the detection object 1 correspond to each other, and the storage object 2 and the detection object 2 exist in the range 2. Since the storage object 2 and the detection object 2 correspond to each other, and the detection object does not exist in the range 3, there is no detection object corresponding to the storage object 3, that is, the storage object corresponding to the detection object 3 exists. Will not do. It should be noted that a storage area is provided in the storage means for the detected object for which the corresponding storage object does not exist.

The range in which the correspondence is made takes into consideration the distance at which the object may relatively move within one measurement cycle, the magnitude of the error included in the obtained measurement result, and the certainty factor of existence. To decide. Of course, it is possible to consider other factors, and it is also possible to arbitrarily determine the range to be associated. The shape of the range to be associated may be selected according to the actual method.

When the storage content updating means 12 calculates the relative speed, the position obtained by the current measurement is predicted, the difference between the predicted position and the detected position is calculated, and the difference is calculated according to this difference. The reliability can be improved by correcting the relative speed. Furthermore, by using a sensor that can obtain the relative velocity, it is possible to determine whether or not the detected object and the stored object correspond using the relative velocity in addition to the position. Further, the position obtained by this measurement can be predicted from the relative velocity and the calculated relative acceleration.

Calculation means 1 for calculating the certainty factor of the existence of an object
At 6, the confidence factor representing the degree of existence of the storage object is calculated based on the correspondence result determined by the determination means 14. Specifically, the confidence is increased or decreased as follows.

That is, for the storage object corresponding to the detected object, the value of the certainty factor in the stored information is increased. On the other hand, for a storage object that does not correspond to the detected object, the value of the certainty factor in the stored information is decreased. "Confidence"
Instead of, it is also possible to use "uncertainty" in which the increase or decrease in confidence is reversed.

As a method of increasing / decreasing the value of the certainty factor, for example, the probability that the sensor detects an object is experimentally obtained, and the probability is utilized (method 1), and the corresponding missing time or period is set. There is a method (method 2) of obtaining the increase / decrease amount of the certainty factor from the set losing time or period.

The certainty factor P (k + 1) in method 1 can be increased or decreased by the following formulas (1) and (2).

When there is a detected object corresponding to the memory object P (k + 1) = P (k) + (1-P (k)). Alpha. (1) There is no detected object corresponding to the memory object Case P (k + 1) = P (k) −P (k) · (1-α) = P (k) · α (2) where P (k) is a storage object at a certain point at time k. Confidence when present, α (0 << α <1) is the probability that the sensor detects an object at that point, and P (k + 1) is the confidence when there is a memory object at that point at time k + 1 .

The certainty factor of Method 1 will be described with a specific example. It is assumed that the probability α is set for each range as shown in FIG. 5 (here, the probability α is set for each range separated by the distance, but the range α is set according to the detection characteristics of the sensor. It is also possible to set the probability α for each, or to express the probability α as a function of position). Moreover, the certainty factors P1 (k), P2 (k), and P of the memory objects 1 to 3 at time k
3 (k) are respectively set as a memory object 1: a certainty factor P1 (k) = 0.95, a memory object 2: a certainty factor P2 (k) = 0.80, and a memory object 3: a certainty factor P3 (k) = 0.60. , The confidence threshold for deleting the stored contents of the storage object is θ
= 0.5, the certainty factors P1 (k + 1) and P2 (k + at time k + 1 are obtained from the correspondence result of FIG. 4 described above.
1) and P3 (k + 1) are updated as follows.

Memory object 1: Certainty factor P1 (k + 1) = P1 (k) + (1
-P1 (k))-α1 = 0.95 + (1-0.95)-
0.95 = 0.9975 Memory object 2: Certainty factor P2 (k + 1) = P2 (k) + (1
-P1 (k))-α2 = 0.80 + (1-0.80)-
0.90 = 0.98 Memory object 3: Certainty factor P3 (k + 1) = P3 (k) · α3
= 0.60 · 0.80 = 0.48 The confidence level P (k + 1) in Method 2 is a loss-of-miss period, for example, an object with a confidence level of 1 is present for at least n times of loss. If there is a request to handle it, α in equations (1) and (2) above should be ⁿ √
It can be obtained as (1-θ). Here, θ is a certainty threshold that serves as a reference for deleting a memory object.

[0026] In this case, since there is no probabilistic sense the detection result given by the following equation (3), simply α = (1-θ) / n (≒ n √ (1-θ in (4) )), The expected effect can be obtained even with the simplified calculation.

When there is a detected object corresponding to the memory object P (k + 1) = P (k) + α (3) When there is no detected object corresponding to the memory object P (k + 1) = P (k) -Α (4) The storage content changing means 18 performs the following processing. First, as a result of changing the certainty factor by the calculation unit 16 that calculates the certainty factor of the existence of the storage object, the stored content stored in the storage unit 12 is deleted for the storage object whose certainty factor becomes smaller than the threshold value. . For example, in the above specific example, the certainty factor P3 (k + 1) of the storage object 3 is 0.48, and the threshold value θ = 0.5.
Because of the following, the stored contents of the storage object 3 are deleted.

Next, for a storage object having a certainty factor equal to or higher than the threshold value, the stored contents such as the position coordinates and relative speed of the storage object are updated. Finally, for the detected object that cannot be associated with the stored object, an area for storing the information of the new stored object is created in the storage means 12, and the initial value of the certainty factor, the position coordinate, and the relative value are stored in this area. Memorize initial values such as speed.

Next, the operation of this embodiment will be described.
FIG. 6 shows how the degree of certainty changes when the object is lost due to the actual existence of the object. Since the probability of correctly recognizing an object is much higher than the probability of being missed, the confidence factor comes to a value close to 1 during a long observation. If the person loses sight of the object in that state and cannot detect it, the confidence level decreases, but the probability of correctly recognizing the object is much higher than the probability of losing sight, so the object is detected again before it falls below the threshold. , Confidence increases again. On the other hand, when the object is erroneously recognized by noise as shown in FIG. 7, the erroneous recognition period is temporary, so the certainty factor does not increase so much and the certainty factor quickly falls below the threshold value. The memory contents are quickly erased from.

In this way, cars that have been observed many times
Even if the user loses sight of the time (number of times) to some extent, the existence thereof can be determined, and the misrecognition time becomes short for misidentification due to noise or the like. Further, as already shown in FIG. 6, the confidence factor fluctuates greatly when the missing point occurs, and when it is detected correctly, the confidence factor becomes approximately 1 and has a constant value. From this, the rate at which the sensor system can detect the object can be confirmed.

Specific examples for implementing the embodiments of the present invention will be described below with reference to the drawings. FIG. 8 is a block diagram showing a vehicle detection device in which the object detection device of this embodiment is realized by using a computer. As shown in FIG. 8, the vehicle detection device includes a detection device 21 that detects distance information, angle information, and the like of another vehicle with respect to the own vehicle, and a computer 3 that processes the output signal of the detection device 21. Has been done. As the detection device 21, for example, a scan type laser radar described in the embodiment of JP-A 1-213593 can be used. The detection device 21 outputs a detection signal including a distance signal, a scan signal, and an angle signal.

The computer 3 takes in the detection signal output from the detection device 21 and calculates information such as the distance to another vehicle. The computer 3 is a CP that performs arithmetic processing.
U31, an input / output interface 33 that converts an external signal into a digital signal that can be processed internally, and also converts an internal digital signal into an external signal, a RAM 35 as a temporary storage unit, and various types. The control program and data are stored in the ROM 37, and a bus such as a data bus and a control bus for connecting them is used.

The computer 3 executes the processing according to the flowcharts shown in FIGS. First, FIG.
In step 100, the vehicle position measured from the detection signal obtained from the detection device 21 is obtained. The position of the vehicle can be obtained, for example, by using the method described in Japanese Patent Laid-Open No. 1-213593. At this time, as shown in FIG. 9, the measured positions of the other vehicles are set as vehicle 1, vehicle 2, ..., Vehicle j ,. On the other hand, the RA measured by then
A car in which position information and the like are stored in M is referred to as a model, and this model is referred to as model 1, model 2, ..., Model j, ..., Model M as shown in FIG.

In the next step 200, the measured vehicle and
It is determined whether or not the vehicle (model) stored in the RAM corresponds. The details of this determination are executed by the routine shown in the flowchart of FIG. Explaining this routine, first, in order to execute the loop for checking the car measured in step 202, the car number j is set to 1 which is an initial value. Next, in step 204, the model number i is set to 1 which is an initial value in order to execute a loop for sequentially examining the model. Then, step 206
It is determined whether or not the corresponding flag of the car with the number j (car j) is reset with. Since there is no car corresponding to the model i (i-th model) when it is reset,
In step 208, the correspondence between the vehicle j and the model i is checked, and in step 210, it is determined whether or not the vehicle j and the model i correspond. Whether or not they correspond is determined by whether or not the vehicle j and the model i can be regarded as the same. This determination is made as follows.

That is, the range of the search for determining whether or not the model i is supported is determined, and the vehicle j having the highest evaluation value within the range is determined to be the corresponding vehicle. When there is no vehicle within the range, it is determined that the corresponding vehicle j cannot be measured. The range of the search for determining whether or not it is compatible takes into consideration the distance in which the vehicle may relatively move within one measurement cycle, the positional error of the model, the positional error of the vehicle, and the like. It is only necessary to decide, and it is also possible to automatically change the search range for determining whether or not there is a correspondence according to the error calculation result.

As a method of determining the evaluation value, model i and car j
A method of giving a higher evaluation value the shorter the distance between
A method of using the degree of coincidence as an evaluation value may be considered. Also,
In this embodiment, the evaluation value is determined only by the position information,
It is also possible to add information other than the position, for example, speed, color / shape of the vehicle, etc., to the evaluation value to determine whether or not they correspond.

In step 208 and step 210, the vehicle j
And the model i are determined to correspond to each other. If the vehicle j and the model i correspond to each other, the process proceeds to step 212, and if not, the process proceeds to step 226.

In step 212, it is judged whether the corresponding flag of the model i is reset,
It is determined whether a car corresponding to the model i has previously existed. If the corresponding flag of the model i is reset and there is no vehicle corresponding to the model i, step 2
In step 22, the model number i corresponding to the corresponding flag of the vehicle j is set. On the other hand, if the corresponding vehicle already exists, the process proceeds to step 214.

In step 214, the model i and the car judged to have already corresponded are examined. Here, it is assumed that it corresponds to the car j '.

In step 216, the distance L (i, j) which is the evaluation value of the correspondence between the car j and the model i, and the distance L (i, j ') which is the evaluation value of the correspondence between the car j'and the model i. And calculate. In step 218, evaluation values are compared. if,
If the distance L (i, j ') is less than or equal to the distance L (i, j), the process proceeds to step 226. On the other hand, the distance L (i, j ') is the distance L
If it is larger than (i, j), the process proceeds to step 220.

In step 220, since it is determined in step 218 that the distance L (i, j ') is larger than the distance L (i, j), the vehicle j is better suited to the model i than the vehicle j'. Since they correspond (the distance is short), the correspondence flag of the car j ′ is reset, and in step 222, the model number i corresponding to the correspondence flag of the car j is set. Then, in the next step 224, the corresponding vehicle number j is set in the corresponding flag of the model i.

In step 226, i = i + 1 is set to investigate the next model. In step 228, it is determined whether or not the model loop has ended. If the model loop is completed, the process proceeds to step 230. If the model loop is not completed yet, the process proceeds to step 206 and the above process is repeated.

In step 230, j = j + 1 is set in order to check the next measured vehicle, and in step 232, it is determined whether or not the vehicle loop has ended. If the car loop is completed, the process is terminated, and if the car loop is not yet completed, the process proceeds to step 204 and the above process is repeated.

After determining the correspondence between the vehicle and the model as described above in step 200 of FIG. 10, in step 300 the certainty factor is calculated according to the correspondence state. This confidence factor calculation process will be described in detail with reference to the flowchart of FIG.

First, the model number is set to i = 1 in order to start execution of a loop for sequentially examining the model (step 302). Next, in step 304, it is determined whether or not the corresponding flag of the model i is reset, and thus it is determined in step 200 whether or not the vehicle corresponding to the model i is present. When it is determined that the corresponding flag of the model i is reset, that is, when it is determined that the corresponding vehicle does not exist, the process proceeds to step 306 to reduce the certainty factor, and the corresponding flag of the model i is set. If it is determined that the vehicle is present, that is, if the corresponding vehicle is present, the process proceeds to step 308 to increase the certainty factor.

The increase / decrease of the certainty factor will be described with an example. As shown in FIG. 17, the measurement range 20 of the detection device 21,
It is assumed that the detection probability α is set. Here, the probability α is set by dividing the range by the distance, but it is also possible to divide the range according to the detection characteristics of the sensor or express α as a function of position. Further, as shown in FIG. 14, the certainty factor at time t of each model is set as follows.

Model 1: Confidence P1 (t) = 0.95 Model 2: Confidence P2 (t) = 0.80 Model 3: Confidence P3 (t) = 0.60 Further, the vehicle position of step 100 The position of the vehicle obtained by the calculation is as shown in FIG. From the correspondence result of FIG. 16, the certainty factor at time t + 1 is updated as follows.

Model 1: Confidence increase P1 (t + 1) = P1 (t) + (1-P1 (t)). Alpha.
1 = 0.95 + (1-0.95) .0.95 = 0.9975 Model 2: Increased confidence level P2 (t + 1) = P2 (t) + (1-P1 (t)). Alpha.
2 = 0.80 + (1-0.80) · 0.90 = 0.98 Model 3: Confidence reduction P3 (k + t) = P3 (t) · α3 = 0.60 · 0.80 = 0.48 step In 310, to find out about the next model,
Let i = i + 1. In step 312, it is determined whether or not the model loop has ended. If the model loop is completed, the process is terminated, and if the model loop is not yet completed, the process proceeds to step 304.

In the next step 400, the car model in RAM is updated. This model updating routine will be described with reference to FIG. In this routine, an unnecessary model is deleted from the storage area and a new model storage area is created. In order to delete and create smoothly with this routine, for example, the entire model may be linked by a bidirectional list.

In step 402, i = 1 is set in order to start the model loop, and in step 404, it is judged whether or not the certainty factor of the model is less than or equal to a threshold value. If the certainty factor of the model is less than or equal to the threshold value, the process proceeds to step 406 to delete the stored contents of the corresponding model. On the other hand, if the model certainty factor is larger than the threshold value, the process proceeds to step 408. In step 408, i = i to determine the next model.
Set to +1.

At the next step 410, it is determined whether or not the model loop is completed. If the model loop is completed, the procedure proceeds to step 412, and if the loop is not yet completed, the procedure proceeds to step 404 and the above processing is repeated.

In step 412, j = 1 is set to start the vehicle loop. In step 414, it is determined whether or not the model corresponding to the vehicle j exists by determining whether or not the corresponding flag of the vehicle j is reset. If the corresponding model does not exist, the corresponding flag is 0, so the process proceeds to step 416, and the position of the vehicle in which the corresponding model does not exist is stored, and the new model is stored in the RAM. Create in. On the other hand, if the corresponding model exists, the corresponding flag is set to a model number other than 0. Therefore, the process proceeds to step 418, and in order to judge the next car, j =
Let j + 1.

In step 420, it is determined whether or not the vehicle loop has ended. If the loop has not ended, the process proceeds to step 414, and if the loop has ended, the process ends.

[0054]

As described above, according to the present invention, the certainty factor representing the degree of existence of a memory object is calculated, and the stored contents are changed, erased, and newly stored according to the certainty factor. Since the contents are stored, it is possible to deal with a long loss of sight of an object and to reduce the influence of erroneous detection due to noise or the like.

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of the present invention.

FIG. 2 is a diagram showing a position of a storage object.

FIG. 3 is a diagram showing a position of a detected object.

FIG. 4 is a diagram showing a range for determining whether or not a stored object and a detected object correspond to each other.

FIG. 5 is a diagram showing an existence probability in a detection range.

FIG. 6 is a diagram showing a change in the certainty factor of the existence of a moving object with respect to the loss of sight of the moving object.

FIG. 7 is a diagram showing a change in the certainty factor of the presence of a moving object when it is erroneously detected by noise.

FIG. 8 is a block diagram showing a specific example of the present embodiment.

FIG. 9 is a diagram showing a model and a vehicle storage area stored in a RAM.

FIG. 10 is a flowchart showing a vehicle detection processing routine of this embodiment.

FIG. 11 is a flowchart showing details of step 200 of FIG.

FIG. 12 is a flow chart showing details of step 300 of FIG.

13 is a flow chart showing details of step 400 of FIG.

FIG. 14 is a diagram showing the position of a model.

FIG. 15 is a diagram showing a detected vehicle position.

FIG. 16 is a diagram showing a range for determining whether or not a model corresponds to a detected vehicle.

FIG. 17 is a diagram showing the existence probability in the detection range.

[Explanation of symbols]

 3 Computer 21 Detection device

Front Page Continuation (72) Inventor Yoshiki Ninomiya, Nagakute-cho, Aichi-gun, Aichi Prefecture 1-41 Yokomichi, Yokosuka Central Research Institute Co., Ltd. (72) Inventor Takero Hongo, Aichi-gun, Nagakute-machi, Aichi-gun No. 41 1 Toyota Central Research Institute Co., Ltd. (72) Inventor Tokuwa No. 1 Toyota-cho, Toyota City, Aichi Prefecture Toyota Automobile Co., Ltd. (72) Inventor Yuichi Kubota No. 1 Toyota-cho, Aichi Prefecture Toyota Automobile Within the corporation

Claims (1)

[Claims] 1. An object detection means for detecting a current position of an object, a storage means for storing a past position of the detected object detected by the object detection means, and a current position of the detected object and the storage means. Based on the position of the storage object, a determination unit that determines whether the detected object whose current position has been detected corresponds to the storage object whose position is stored in the storage unit, and based on the determination result of the determination unit Calculating means for calculating the degree of certainty indicating the degree of existence of the storage object, and changing the stored content for the storage object having the certainty value equal to or greater than a predetermined value based on the detected current position and the certainty degree less than the predetermined value. And a storage content changing unit that erases the storage content of the storage object and stores the position of the detection object determined not to correspond to the storage object by the determination unit.