JP3065822B2 - Moving object detection device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

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

[0002]

2. Description of the Related Art Conventionally, there has been known an apparatus which recognizes a preceding vehicle using radars and travels following the preceding vehicle. Generally, at the time of follow-up running, a situation may occur in which another vehicle is interrupted between the own vehicle and the preceding vehicle, or the preceding vehicle changes because the preceding vehicle changes lanes to the adjacent lane. Therefore, it is necessary to consider vehicles other than the preceding vehicle as objects to be recognized.

[0003] JP-A-2-36500, JP-A-1-36500
No. 213593, JP-A-61-20877,
And Japanese Patent Application Laid-Open No. 2-40800 disclose techniques for recognizing a preceding vehicle, but in these techniques, no consideration is given to recognition of a vehicle other than the preceding vehicle.

In the technology described in Japanese Patent Application Laid-Open No. 1-197133, although recognition of vehicles other than the preceding vehicle is also taken into consideration, a transmitting / receiving device is provided in each vehicle and information is obtained from other vehicles by radio waves. Therefore, it is not practical to obtain information on a vehicle that does not have a transmission / reception device.

Further, Japanese Patent Application Laid-Open No. 61-145474 discloses a technique of storing a plurality of past distance data, obtaining a relative speed by linear approximation, and separating a preceding vehicle from a roadside reflector. However, when trying to recognize a vehicle other than the preceding vehicle using this method, it is not possible to distinguish the vehicle in the adjacent lane from the preceding vehicle because only the distance information is considered and the horizontal position is not considered. Can not. Further, the relative speed is obtained by linear approximation. However, since the relative speeds of other vehicles including the preceding vehicle are generally not constant, the accuracy of linear approximation deteriorates. Further, as a criterion for grouping when linearly approximating the distance data, a process of determining the same group when the distance from the immediately preceding observation result is short is performed. However, in the situation shown in FIG. At t, L0 (t) is close to L0 (t-1), so that L0 (t)
(T) is close to L1 (t-1), so it belongs to G1 group,
Each will be misclassified.

Further, Japanese Patent Application Laid-Open No. 61-278775,
JP-A-62-36581 discloses a technique in which a preceding vehicle is recognized by a plurality of radars and a vehicle in an adjacent lane is distinguished from a preceding vehicle. However, the embodiment of this publication describes a case where the number of laser beams is three,
It states that "another number of beams, for example, 2, 4, 5,... May be selected, and the preceding vehicle detection capability can be expected in accordance with the number." ,
Considering the case of capturing an object with two or more beams,
The conditional branch of the preceding vehicle recognition unit becomes complicated for the number n of the beams, which is not practical. Further, the calculation of the relative velocity is based on the detection distance history 1c-9, 1c-
8,... 1c-1, 1c, and does not consider calculating the velocity of an object moving while straddling the beam. Therefore, the vehicle speed of the interrupted vehicle cannot be immediately recognized.

[0007] Further, since correspondence is made based on the position, there is a possibility that the same correspondence error as described above may occur.

[0008]

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above-mentioned problems, and when a moving object being tracked is switched, information of the switched moving object can be obtained immediately, and an interrupt is generated. It is an object of the present invention to provide a moving object detection device that can obtain effective information when controlling a speed or the like by predicting a situation to occur.

In order to achieve the above object, the present invention provides a position detecting means for detecting a position of a moving object , a speed detecting means for detecting a relative speed between the moving object and the own vehicle , Storage means for storing the history of information, and the relative information detected by the position information and speed detection means stored in the storage means
Prediction means for predicting a position of the object moves on the basis of the speed, the object position based on the predicted position detected position and predicting means by the position detecting means is moving is detected that the storage means The determination means for determining whether the storage object whose position information is stored corresponds to the storage object, and the storage object determined to be corresponding by the determination means and the determination means determine that the storage object does not correspond The position information of the storage object whose number of times is less than the predetermined number of times is updated, the position information of the storage object whose number of times determined that the storage object is not supported by the determination means is erased more than the predetermined number of times, and the determination means corresponds to the storage object Storage content changing means for storing the position information of the detected object determined not to have been stored.

[0010]

The position detecting means of the present invention detects the position of a moving object such as a traveling vehicle, and the speed detecting means detects the relative speed between the moving object and the own vehicle . As the speed detecting means, the relative speed of the object by calculating the change in position of a unit time from the history of the position detected by the speed sensor and position detecting means for detecting the relative velocity of a moving object directly Calculation means for detecting can be used. The storage unit stores a history of the position information. The storage means may store speed information and the like together. The prediction unit predicts a position at which the object moves based on the position information stored in the storage unit and the relative speed detected by the speed detection unit. Determination means, predicted position detected position and predicting means by the position detecting means, i.e. on the basis of the predicted position, the position is stored in the position information on the object storage means that is moving is detected It is determined whether or not the stored object corresponds. For example, if the detected position is present in an area within a predetermined range including the predicted position, the detected object whose position has been detected corresponds to the storage object whose position information is stored in the storage unit. Can be determined. The storage content changing means updates the position information of the storage object determined to be compatible by the determination means and the storage object whose number of times determined by the determination means to be incompatible is less than a predetermined number of times. As described above, since the position is predicted to determine whether the detected object and the storage object correspond to each other, it is possible to cope with an interruption of another moving object. Since the position information of the storage object that is determined to be incompatible is less than the predetermined number of times is also updated, the storage object can be treated as a virtual object even if the object is temporarily lost. . In addition, the storage content changing unit deletes information of the storage object whose number of times that the determination unit determines that the content is not supported is a predetermined number or more. As a result, the position information of the storage means is erased for a stored object whose number of times determined to be unsupported is equal to or more than a predetermined number of times, that is, for an object whose misplacement exceeds a predetermined time. In addition, the storage content changing means causes the storage means to store the position with respect to the detected object, which is detected by the position detecting means, but is determined not to correspond to the storage object by the determining means. Thus, it is possible to cope with a case where a lost object is detected again after a long loss or a case where a new object is detected.

[0011]

Embodiments of the present invention will be described below. First, this embodiment is represented by functional blocks as shown in FIG. As shown in the figure, the present embodiment includes a position detection unit 10 for detecting the current positions of a plurality of moving objects, and a storage unit 20 for storing a history of position information of the plurality of moving objects. ing. The storage means 20, the own multiple objects moving and the history of the position information stored in the storage means 20
It is connected to speed calculating means 12 as speed detecting means for calculating a relative speed with respect to the vehicle . The storage means 20 and the speed calculation means 12 determine whether a plurality of objects moving from the previous positions of the plurality of moving objects stored in the storage means 20 and the relative speeds calculated this time by the speed calculation means 12 are present. It is connected to a prediction means 14 for calculating a predicted position predicted to be located. The position detection means 10 and the prediction means 14 determine whether or not the positions of a plurality of moving objects detected within an area within a predetermined range including the predicted position are detected, and the positions are detected. It is connected to a judgment means 16 for judging whether or not a plurality of moving objects correspond to a storage object whose position information is stored in the storage means 20, and outputting position information together with the judgment result. The judgment means 16
The storage unit 20 is connected to a storage content change unit 18 that updates and deletes the storage content of the storage unit 20 based on the determination result of the determination unit 16.

The position detecting means 10 is a sensor capable of detecting the position of a moving object, and a sensor capable of distinguishing a plurality of objects, for example, a scanning laser, an image type, or the like.
A sensor that can obtain dimensional coordinates, a sensor that can obtain one-dimensional coordinates using millimeter waves, or the like can be used. Hereinafter, a description will be given using a sensor that can obtain two-dimensional coordinates.

The storage means 20 uses, for example, a RAM, and records the position information history of a plurality of moving objects detected by the position detection means 10, the relative speed history calculated by the speed calculation means 12, and the prediction by the prediction means 14. The position and other information are collectively stored for each vehicle.

The speed calculating means 12 calculates the relative speed of a plurality of moving objects from the position information stored in the storage means 20. The current time is t, and the time t of a certain object is
Is the detected position in Pm (t), and the predicted position is Pp
(T), the calculated relative speeds are Vm (t) and Vp (t). First, from the position Pm (t-1) detected in the previous measurement of a certain object and the position Pm (t-2) detected in the last two measurements, the relative speed at the time of the previous detection is stored. Is obtained by the following equation.

[0015] Vm (t-1) = ( Pm (t-1) - P m
(T−2)) / Δt Δt: Measurement time interval Since the speed fluctuation due to the error in the position detected by the position detection means is large in this state, Vp () obtained from the past relative speed history using an appropriate filter is used. t-1) is the relative speed at the time of the previous detection. For example, when using an N-order moving average filter,

[0016]

(Equation 1)

When an Nth-order Butterworth filter is used,

[0018]

(Equation 2)

An, Bn: constants In the predicting means 14, the previous position of the storage object stored in the storage means 20 as a result of the previous measurement and the previous relative speed calculated by the speed calculating means 12 are used. , Predict the position of the object that will be moving in the current measurement. The current predicted position Pp (t) of a certain object is the position P detected in the previous measurement stored in the storage means 20.
From m (t-1) and the previous relative speed Vp (t- 1 ) calculated by the speed calculating means, it can be obtained by the following equation.

Pp (t) = Pm (t−1) + Vp (t−1) × Δt Δt: Measurement Time Interval The determination unit 16 detects, for example, an object detected by the position detection unit 10 as follows. It is determined whether or not (for example, a car) corresponds to a storage object (for example, a car) stored in the storage unit 20. First, it is assumed that the storage unit 20 stores the position information of the storage objects a to c as shown in FIG. The fan shape 20 is the measurement range of the sensor, and the vehicle is located at the left end, which is the corner of the fan shape. Then, it is assumed that the detected objects x to z are detected at the positions shown in FIG. 3 in the next measurement (time t). When determining whether the detected objects x to z correspond to the storage objects a to c, the predicted positions Ppa (t) to Ppc (t) are obtained for each storage object as shown in FIG.
As shown in FIG. 5, ranges a to c for association are defined around Ppa (t) to Ppc (t). These ranges a to
Within c, the detected object closest to the stored object is associated with the stored object in this range. In this example, since the detected object x exists within the range a of the storage object a, the storage object a corresponds to the detected object x, and the detected object y exists within the range b of the storage object b. The storage object b and the detection object y correspond to each other, and there is no detection object in the range c of the storage object c, so that there is no detection object corresponding to the storage object c, and as a result, the detection object z corresponds. There will be no memory objects. It should be noted that a storage area is provided in the storage means for a detected object having no corresponding storage object.

The range to be associated can be determined in consideration of the magnitude of the error included in the detected position and the distance that the object may move in one measurement. Of course, other factors can be considered, and the range to be associated can be arbitrarily determined. The shape of the range to be associated may be selected according to the method of actually performing the operation, such as an ellipse or a rectangle.

In the storage content updating means 18, the judgment means 16
The following processing is performed based on the result of the determination. That is, for a storage object that is associated with the detected object, the detected position Pm (t) is stored, and the other storage contents are updated. If the storage object that does not correspond to the detected object satisfies the criterion for deleting the storage object from the storage means 20, the information of the storage object is stored in the storage means 20.
Erase from Otherwise, the predicted position Pp
(T) is stored as the detected position Pm (t), and the other stored contents are updated. For a detected object that has not been associated with a stored object, a new stored content having a predetermined initial value is created in the information storage means 20, and the detected position Pm
(T) is stored.

A specific example for realizing an embodiment of the present invention will be described below with reference to the drawings. FIG. 7 is a block diagram illustrating a vehicle detection device in which the moving object detection device according to the present embodiment is implemented using a computer. 7, the vehicle detection device includes a detection device 21 that detects distance information, angle information, and the like of another vehicle based on the own vehicle, and a computer 3 that performs data processing on an output signal of the detection device 21. . As the detection device 21, for example, a scan-type laser radar described in the embodiment of Japanese Patent Application Laid-Open No. 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 calculates information such as the distance to another vehicle by taking in the signal output from the detecting device 21. The computer 3 is a CPU 3 that performs arithmetic processing.
1, an input / output interface 33 for converting an external signal into a digital signal which can be processed internally, and converting an internal digital signal into an external signal, a RAM 35 as a temporary storage means, ROM 37 storing control programs and data of the above, and a bus such as a data bus and a control bus for connecting these.

The computer 3 executes processing according to the flowcharts shown in FIGS. First, in step 100 of FIG. 9, the current position of the vehicle detected from the detection signal obtained from the detection device 21 is obtained. For the position of the vehicle, for example, a method described in Japanese Patent Application Laid-Open No. 1-213593 can be used. At this time, as shown in FIG. 8, the detected positions of the other vehicles are designated as car 1, car 2,.
..., car N On the other hand, a car in which the position information and the like are detected and stored in the RAM, that is, a stored object is called a model, and this model is referred to as a model 1, a model 2,..., A model i as shown in FIG. , ..., Model M
And

In the next step 200, the relative speeds of the models 1 to M stored in the RAM are calculated, and the positions of the models are predicted. The processing of the speed calculation and the position prediction will be described in detail with reference to the flowchart of FIG.

First, in order to start execution of a loop for sequentially examining models, the model number i is set to 1, which is an expected value (step 202).

In step 204, the model positions Pm (t-1), Pm (t-2),.
・ Pm (t−n) and the measurement time interval Δt are taken in. The value of n is determined by the order of the filter used in the speed calculation in the next step 206.

In step 206, the speed of the model is calculated. This is performed in the following procedure. First, from the position Pm (t-1) detected in the previous measurement and the position Pm (t-2) detected in the previous measurement, the relative speed at the previous measurement is obtained by the following equation.

Vm (t-1) = (Pm (t-1) -Pm
(T−2)) / Δt Δt: Measurement time interval Since the influence of the speed fluctuation due to the error of the position detected by the position detection means is large in this state, it was obtained from the past relative speed history using an appropriate filter. Let Vp (t-1) be the relative speed at the time of the previous detection. For example, when using a third-order moving average filter,

[0031]

(Equation 3)

When a fifth-order Butterworth filter is used,

[0033]

(Equation 4)

Here, An and Bn are constants.

In the above equation, Vm (t-2),..., Vp
(T-2),... Can be calculated from the past position of the model fetched in step 204, but it is not necessary to calculate each time by storing the speed calculation result in the RAM. In that case, Vm (t-2),..., Vp (t-
2),... As a filter for speed calculation, in addition to these filters, for example, a method using a Kalman filter can be considered.

[0036] make a prediction of the position of the model in step 208. This can be calculated by the following equation.

Pp (t) = Pp (t−1) + Vp (t−1) × Δt Δt: Measurement Time Period In step 210, to check the next model,
Let i = i + 1. In step 212, the end of the model loop is determined. If the model loop has ended, the process ends. If the model loop has not ended, the process proceeds to step 204.

In the next step 300 of FIG. 9, it is determined whether or not the detected vehicle corresponds to the model stored in the RAM. The details of this determination are executed by the routine shown in the flowchart of FIG. To explain this routine, first, in order to execute a loop for examining the car detected in step 302, the number j of the car is set to 1, which is the initial value. Next, in step 304, the model number i is set to 1, which is an initial value, to execute a loop for sequentially examining the models. Next, step 30
It is determined in step 6 whether the corresponding flag of the car with the number j (vehicle j) has been reset.
Since the model corresponding to the vehicle j has not been found yet, the process goes to step 308 to check the correspondence between the vehicle j and the model i. If the model has not been reset, the model corresponding to the vehicle j has already been found and the process goes to step 330 to execute the vehicle loop. Advance.

In step 308, the correspondence between the car j and the model i is checked, and in step 310, it is determined whether or not the car j and the model i correspond. This determination is made as follows. That is, a search range for determining whether or not the model i is supported is determined, and the car j having the highest evaluation value within the range is determined to be the one that has been handled. If no car exists within the range, it is determined that the corresponding car could not be measured. As a search range for determining whether or not the model is compatible, a range centered on the predicted position Pp (t) obtained in step 200 may be used. It is also possible to automatically change the search range for judging whether or not. As a method of determining the evaluation value, a method of giving a higher evaluation value as the distance between the model i and the car j is shorter, a stochastic matching degree from the variance of the position error between the model i and the car j, A method of setting an evaluation value is conceivable. Further, in this embodiment, the evaluation value is determined only by the position information, but information other than the position,
For example, it is also possible to determine whether or not the vehicle is supported by adding the speed, the color and the shape of the vehicle, etc. to the evaluation value.

At step 308 and step 310, the vehicle j
And the model i is determined. If the vehicle j corresponds to the model i, the process proceeds to step 312. If not, the process proceeds to step 326.

In step 312, it is determined whether or not the corresponding flag of the model i has been reset.
It is determined whether a car corresponding to the model i has already been found. If the corresponding flag of the model i has been reset and no car corresponding to the model i has been found, the process proceeds to step 322. On the other hand, if a corresponding car has already been found, the process proceeds to step 314.

In step 314, the model i and the car determined to have already corresponded are checked. Here, it is assumed that it corresponds to the car j '.

In step 316, based on the current position and the predicted position, the distance L (i, j), which is the evaluation value of the correspondence between the car j and the model i, and the evaluation value of the correspondence between the car j 'and the model i And the distance L (i, j ′).

In step 318, the evaluation values are compared.
If the distance L (i, j) is equal to or less than the distance L (i, j '), the process proceeds to step 320. On the other hand, if the distance L (i, j) is larger than the distance L (i, j ′), the process proceeds to step 326. In step 320, the distance L is calculated in step 318.
Since it is determined that (i, j) is smaller than the distance L (i, j '), the car j better corresponds to the model i than the car j' (the distance is shorter). 'Corresponding flag is reset.

At step 322, the corresponding model number i is set in the corresponding flag of the car j. Then, in the next step 224, the number j of the corresponding car is set in the corresponding flag of the model i.

In step 326, i = i + 1 is set to check the next model. And step 328
Then, it is determined whether or not the model loop has ended. If the model loop has been completed, the process proceeds to step 330. If the model loop has not been completed, the process proceeds to step 306 to repeat the above processing.

In step 330, j = j + 1 is set in order to check the next detected vehicle. In step 332, it is determined whether or not the vehicle loop has been completed. If the car loop has ended, the process is ended. If the car loop has not ended, the process proceeds to step 304 to repeat the above process.

In the next step 400 of FIG. 9, the model of the car in the RAM is updated. This model update routine will be described with reference to FIG. In this routine, unnecessary models are deleted from the storage area, and a storage area for a new model is created. In order to smoothly delete and create in this routine, for example, the entire model may be linked by a bidirectional list. This is because each model has a pointer to the previous model in the storage area and a pointer to the subsequent model. By following the pointer, all models can be accessed. Come back to the model.

In step 402, i = 1 is set to start a model loop, and in step 404, step 2 is executed.
At 00, it is checked whether a car corresponding to the model i has been found. If a corresponding car has been found, the process proceeds to step 406. If a corresponding car has not been found, the process proceeds to step 410.

At step 406, a non-correspondence flag F (i) indicating that a car corresponding to the model i has not been found.
Is set to 0.

In step 408, the current position Pm of the model i is determined based on the detected position of the car corresponding to the model i.
i (t) is stored in the RAM, and the flow advances to step 418.

On the other hand, at step 410, a non-corresponding flag F indicating that no car corresponding to the model i has been found.
Add 1 to (i).

As a result of the operations in steps 406 and 410, the uncorrespondence flag F (i) is a number indicating the number of consecutive unsuccessful responses so far.

In step 412, it is checked whether the unsupported flag is larger than a predetermined threshold. If it is larger than the threshold value, the process proceeds to step 414 to delete the model i, and if not, the process proceeds to step 416.

In step 414, the model is deleted.
In step 416, since the vehicle corresponding to the model i was not found, the predicted position Pp is set as the current position of the model.
Using i (t), Pmi (t) = Ppi (t).

In step 418, i = i + 1 is set to check the next model. In step 420, it is determined whether or not the model loop has ended. When the model loop ends, the process proceeds to step 422. If the loop has not ended, the process proceeds to step 404.

In step 422, a car loop is started and j
= 1. In step 424, it is checked whether or not there is a model corresponding to the car j. If there is no corresponding model, the corresponding flag of the car j is set to 0. In that case, the process proceeds to step 426. If there is a corresponding model, the corresponding flag contains a model number other than 0. In that case, the process proceeds to step 430.

In step 426, the new model k is
In the storage area of the AM, in step 428, the current position Pmk (t) of the newly created model based on the detected position of the vehicle j is stored in the RAM.

In step 430, j = j + 1 is set to check the next vehicle. In step 432, it is determined whether or not the vehicle loop has ended. If the loop has not ended yet, the process proceeds to step 424, and if the loop has not ended, the process ends.

FIG. 6 shows a comparison between the case where the car model is used as described above and the case where the car model is not used. If the car model is not used, it is difficult to associate the position of the previously observed car with the position of the car observed this time, but if the car model is used as in this embodiment, Prediction of the position facilitates association.

As described above, according to the present embodiment, the following effects can be obtained. (1) Since the position of the other vehicle is predicted on the basis of the speed, as shown in FIG. In addition, the measurement cycle can be made longer than in the case of associating only the position, which is useful for simplifying the apparatus.

(2) Since the speed of the storage object is calculated, that is, each of the storage objects already has speed information, it is not necessary to calculate a new relative speed when the preceding vehicle changes, and a new relative speed is required. The relative speed of the preceding vehicle is immediately obtained.

(3) In order to predict the position, for example, if there is an object approaching from the left or right in front of the own vehicle, it can be determined that there is an interruption, and control can be performed in such a situation.

(4) Since the stored object is treated as being present even when the detection of the object fails, it can be treated as a virtual preceding vehicle when it is lost. In this case, even if the relative position of the preceding vehicle is lost in the approaching situation, the relative speed of the stored object indicates that the preceding vehicle is approaching. , Safe control.

[0065]

As described above, according to the present invention, the position of a storage object is predicted, and the storage contents are changed, deleted, and new storage contents are stored in accordance with the predicted position.
It is possible to predict that the moving object being tracked is switched to another moving object, to cope with it, and to obtain information immediately when the moving object is switched.

[Brief description of the drawings]

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

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

FIG. 3 is a diagram illustrating a position of a detection object.

FIG. 4 is a diagram showing a predicted position.

FIG. 5 is a diagram showing a range for determining whether a storage object and a detected object correspond to each other.

FIG. 6 is a diagram showing a comparison between a case where a car model is used and a case where a car model is not used.

FIG. 7 is a block diagram showing a specific example of the embodiment.

FIG. 8 is a diagram showing a model stored in a RAM and a storage area of a vehicle.

FIG. 9 is a flowchart illustrating a vehicle detection processing routine according to the present embodiment.

FIG. 10 is a flowchart showing details of step 200 in FIG. 9;

FIG. 11 is a flowchart showing details of step 300 in FIG. 9;

FIG. 12 is a flowchart showing details of step 400 in FIG. 9;

FIG. 13 is a diagram for explaining a conventional technique.

[Explanation of symbols]

 3 Computer 21 Detector

Continued on the front page (72) Inventor Takero Hongo 41-41, Yokomichi, Nagakute-machi, Aichi-gun Inside (72) Inventor Yuichi Kubota 1 Toyota Town, Toyota City, Aichi Prefecture Inside Toyota Motor Corporation (56) References JP-A-4-261000 (JP, A) JP-A-62-36581 (JP, A) JP-A-61-278775 (JP, A) (58) Fields investigated (Int. Cl. ⁷ , DB name) G08G 1/16 G08G 1/017

Claims (4)

(57) [Claims] 1. A position detecting means for detecting a position of a moving object , a speed detecting means for detecting a relative speed between the moving object and the own vehicle, and a storage means for storing a history of position information. and predicting means for the object based on the detected relative speed stored position information and the speed detecting means in the storage means to predict the location of the mobile, which is predicted by the prediction means and the detected position by the position detecting means A determination unit configured to determine whether a moving object whose position is detected based on the position and a storage object whose position information is stored in the storage unit correspond to the determination unit; The position information of the storage object determined to be unsuitable by the determination means and the number of times determined to be incompatible by the determination means is updated less than a predetermined number of times, and the number of times determined to be unsupported by the determination means is greater than or equal to the predetermined number Erase location information of stored objects And, and the moving object detection apparatus comprising: a storage content changing means for storing the position information of the detected object is determined not to correspond to the stored object in the determination means. 2. The apparatus according to claim 1, wherein said speed detecting means detects a speed obtained from a previously measured position, a position measured two times before, and a measuring time interval stored in said storage means, and a speed obtained by using a filter. 2. The moving object detecting device according to claim 1, wherein the moving speed is a relative speed. 3. The apparatus according to claim 1, wherein said predicting means predicts a position to which the object moves based on a previously measured position stored in said storage means and a previous relative speed detected by said speed detecting means. Or the moving object detection device according to 2. 4. If the detected position is present in an area within a predetermined range including the predicted position, the determining means stores the detected object and the position information in the storage means. 4. A method according to claim 1, wherein the storage object is determined to correspond to the storage object.
The moving object detection device according to any one of claims 1 to 7.