JPH08271617A - Target tracking apparatus - Google Patents

Abstract

PURPOSE: To obtain a separated cluster hypothesis generation device when a cluster is separated by a method wherein a cluster establishment and integration device which integrates a cluster corresponding to the case where an observation vector exists, and an in-gate judgement-matrix computation device which computes an in-gate judgement indicating a possibility that the observation vector corresponds to an error signal, an existing track and a new target are installed. CONSTITUTION: An observation vector Z1, 1 at a time t1 is input. At this time, an observation vector selection part 1 sends the Z1, 1 to a cluster establishment and integration part 3 as an independent observation vector which has nothing to do with an existing cluster. Then, the cluster establishement and integration part 3 establishes a cluster 1 including the Z1, 1 so as to be defined in a in-gate cluster display, and it writes the Z1, 1 into an in-cluster observation vector table 4 for the cluster 1. At this time, only an observation vector at a present time is stated in the vector table 4. Then, an in-gate judgement matrix computation part 5 computes an in-gate judgment matrix indicating all observation vectors at this time inside the cluster and the correlation possibility of a track.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a target tracking device for estimating the tracks of a plurality of targets from information such as observation vectors obtained from sensors such as radar.

[0002]

2. Description of the Related Art In order to obtain a track from an observation vector obtained by a sensor, a tracking filter is applied to an existing track to calculate a predicted position of existence of a target at a current time, and a predicted position range (hereinafter, referred to as a predicted position range). This region is called a gate) and the target wake at the current time is estimated by the correlation processing between the observed vector and the actual observation vector.

Here, when a plurality of targets exist in a narrow area, there are cases where a plurality of targets exist in the gate of one track. In order to continue the correct tracking even in such a situation, it is necessary to perform the correlation between the track and the observation vector with higher accuracy than in the case of tracking one target.

Conventionally, as a device which meets this demand, FIG.
7, a multi-target tracking method as shown in FIG. 18 has been proposed. 17 and 18 show "DB Reid: ■ An Algori
thm for Tracking Multiple Targets ■, IEEE Transact
ions on Automatic Control, AC-24, p843-854, 197
9 is a diagram showing a flow chart showing an algorithm of the multiple target tracking method shown in FIG. 9 ”and a representation of a hypothesis matrix. In the figure, 66 indicates the relationship between the gate and the observation vector with respect to the existing track, 67 is the tree expression of the hypothesis, and 68 is the matrix expression of the hypothesis on the computer.

The operation of the conventional example will be described.

First, in addition to FIG. 17 and FIG. 18, FIG.
The basic concept is explained with reference to.

As shown in FIG. 3, it is assumed that two targets are moving in the space. When these targets are observed by the sensor, the sensor operates discretely, and the observation vector of the target is obtained discretely. In addition, an erroneous signal other than the target may be input, or conversely, the target may fail to be observed, and the observation vector from the target may not be obtained.
For example, the observation vector as shown in FIG. 3 is obtained.

The tracking algorithm operates as follows with respect to the observation vector group thus obtained.

In step 59, a new observation vector group is received from the sensor.

In step 60, the time is updated according to the observation time.

In step 61, the tracking filter is turned for each track, and in step 60 the gate at the updated time is calculated. The relationship between this gate and the observation vector is examined to determine the observation vector that can be correlated to each track. Also investigate cluster consolidation. Cluster integration occurs when multiple wakes contained in another cluster are correlated with one observation vector.

Further, a new cluster is generated by an observation vector which is not included in any gate. The two ellipses indicated by 66 in FIG. 18 indicate the gates of track 1 and track 2, respectively. The observation vector 11 is included in the gate of track 1, and the observation vector is included in the gate of track 2. It can be seen that the vectors 11, 12, and 13 are included. Thus, the observation vector contained in the gate is an observation vector that can be correlated with the track.

[0013] Further, if the observing time is one time before, the track 1
Even if the track and the track 2 belong to different clusters, since the observation vector 11 is included in the gate of both tracks here, the two clusters are integrated and the tracks 1 and 2 and the observation vectors 11 and 12 and 13 are combined. A new cluster containing is created.

In step 62, initialization processing is performed on the observation vector that is not included in the gate of any track.

In step 63, the hypothesis is reduced. Here we delete unlikely hypotheses and merge hypotheses that are estimating similar tracks.

There are the following four types of methods proposed in this conventional example. (1) Only the hypothesis with the highest reliability is left. (2) Hypotheses whose reliability is less than a certain reference value are available. (3) The hypotheses having the same contents for the past N times are integrated. (4) Integrate hypotheses that have the same number of tracks and almost the same content (position, speed, etc.) of each track.

In step 64, the hypothesis is updated, the reliability of each hypothesis is calculated, and the observation vector is updated for each hypothesis.

In FIG. 18, 3 for two provisional detection targets.
The update of the hypothesis when individual observation vectors are observed is explained. As described above, the relationship between the gate of the track of each tentative detection target and the observation vector is shown in 66 of FIG. 18, and from this figure, the tentative detection target 1 can be correlated with the observation vector 11, Goal 2 is observation vector 11,
It can be seen that correlation with 12 and 13 is possible.

Reference numeral 67 in FIG. 18 represents the hypothesis at this time in a tree diagram. Observation vector 11, 1
Although 2 and 13 were observed at the same time, the hypothesis building process proceeds in the order of 11, 12, and 13 here. The left column of this figure shows possible states of the observation vector 11. First, 0 at the top indicates that the observation vector 11 is an erroneous signal. The following 1 and 2 indicate that the observation vector 11 is the observation vector obtained from the provisional detection target 1 and the provisional detection target 2, respectively. Finally, the bottom 3 indicates that the observation vector 11 was obtained from the new tentative detection target 3. As the tentative detection target number, a number that is not used when the detection target appears is used. Here, the lowest number is assigned.

Next, in the center column, the possible states of the observation vector 12 are shown corresponding to the states of the observation vector 11. Here, as can be seen from 66 in FIG. 18, since the observation vector 12 cannot be obtained from the tentative detection target 1, the value 1 cannot be taken. Further, since no more than two observation vectors can be obtained from one provisional detection target at the same time, when it is assumed that the observation vector 11 is obtained from the provisional detection target 2,
The observation vector 12 cannot have the value 2. Moreover, the value 3 cannot be taken for the same reason. Further, when the observation vector 12 is set as a new tentative detection target, a value of 4 is given according to the above rule.

Finally, the right column shows possible states of the observation vector 13 corresponding to the states of the observation vectors 11 and 12.

Next, reference numeral 68 in FIG. 18 is a hypothesis matrix in which the content of the hypothesis shown in 67 in FIG. 18 is expressed as a matrix for holding in the computer. In this hypothesis, each row corresponds to the hypothesis and each column corresponds to the observation vector.

Here, as described above, the number of each element is 0 indicating an erroneous signal, and a value of 1 or more is an identification number given when each tentative detection target first appears, It should be noted that it is not the number that identifies the track. For example, in the hypothesis in the third row, the observation vector 11 correlates to the provisional detection target 2, and in the hypothesis in the fifth row, the observation vector 1
2 correlates to provisional detection target 2. Both have the same value 2
, But it is naturally a different track.

In step 65, the cluster separation judgment is performed,
If possible, separate clusters and establish tracking. Normally, when adding an observation vector at a new time, cluster integration only occurs and cluster separation never occurs, but when the hypothesis is reduced by the method of step 63, clutter separation occurs. there is a possibility. In this method, the cluster separation determination is that a cluster is separated when the identification result of an observation vector is the same for all hypotheses. However, this separation determination method is incomplete, and examples have been found in which those that should not be separated are separated or those that should be separated are not separated.

The hypothesis construction and updating method will be described again with reference to the example of FIG. The results are shown in FIG. 19 in the state 69 of FIG. In this example, it starts from the situation where there is no detected target. First, the observation vector Z1,1 was observed at the first observation time t1. This observation vector may be an erroneous signal and a detection target. Therefore, a value 0 and a value 1 are given according to the method described above.

Next, at time t2, two observation vectors Z2,
1 and Z2,2 were observed. Assuming that these two are in the gate of the track when Z1,1 is considered as the detection target, the following processing is performed. Here, as in the case of FIG. 18, the hypothesis construction work is advanced, but the time is from t1 to t2.
It should be noted that it can be correlated with detection target 1 because it has advanced to. Otherwise, the hypothesis is constructed for Z2,1 first and then Z2,2 as in the case of FIG.

As a result of the above work, the hypothetical matrix in the computer becomes as shown by 71 in FIG. In the example of FIG. 18, the hypothesis matrix includes only observation vectors at the same time, but generally, as in this example, observation vectors at a plurality of times are sequentially added to reconstruct the hypothesis for all of them. It

[0028]

The conventional target tracking device is configured as described above, and an element in the hypothesis matrix is a target identification number when an observation vector is recognized as a new target, and is a number for distinguishing a track. However, there was a problem that it was not easy to extract the wake. There is also a problem that the cluster separation method is incomplete and may not operate normally depending on the situation.

The present invention has been made to solve the above problems, and the target tracking device according to the first aspect of the present invention is to obtain a target tracking device in which track extraction is easy. Has an aim.

A target tracking device according to the second aspect of the present invention is intended to obtain a target tracking device in which track extraction is easy and the number of hypotheses can be reduced.

The hypothesis reducing apparatus according to the third aspect is intended to obtain a hypothesis reducing apparatus capable of appropriately selecting and deleting an unlikely hypothesis.

Further, the hypothesis reducing apparatus according to the fourth aspect is intended to obtain a hypothesis reducing apparatus capable of appropriately selecting and deleting an unlikely hypothesis.

A target tracking device according to the fifth aspect of the present invention aims to accurately determine the separability of clusters during hypothesis reduction, and obtain a target tracking device capable of performing cluster separation if possible. I am trying.

The cluster separating apparatus according to the sixth aspect of the present invention is intended to obtain a cluster separating apparatus capable of accurately determining the separability of clusters during hypothesis reduction, and performing cluster separation if possible. I am trying.

Further, the cluster separation determination device according to the seventh aspect is intended to accurately determine the separability of clusters when the hypothesis is reduced.

Further, the cluster separation judging device for a cluster consisting of only one track according to the eighth claim can obtain a cluster separation judging device which can accurately judge the separability of a cluster consisting of only one track when the hypothesis is reduced. It is an object.

The separated cluster hypothesis generation device according to the ninth aspect is intended to obtain a separated cluster hypothesis generation device which can regenerate the hypotheses of the respective separated clusters when the clusters are separated. .

The target tracking apparatus according to the tenth aspect of the present invention obtains a target tracking apparatus capable of simplifying the process and generating a hypothesis at high speed when the observation vector does not include an erroneous signal. It is an object.

The target tracking device according to the eleventh aspect can simplify the processing when the observation vector does not include an erroneous signal, and at the same time can reduce the number of hypotheses. The purpose is to get.

Further, the target tracking device according to the twelfth claim can simplify the processing when the observation vector does not include an erroneous signal, at the same time, can reduce the number of hypotheses, and at the same time, The objective is to accurately determine the separability of clusters during hypothesis reduction, and to obtain a target tracking device that can perform cluster separation if possible.

The cluster separating apparatus according to the thirteenth aspect of the present invention can easily and accurately determine the separability of a cluster when an observation vector does not include an erroneous signal, and if possible, a simple The purpose of the present invention is to obtain a cluster separation device capable of performing cluster separation.

The simple cluster separation determination device for a cluster consisting of only one track according to the fourteenth claim is capable of separating a cluster consisting of only one track when hypothesis reduction is performed when the observation vector does not include an erroneous signal. The purpose of the present invention is to obtain a cluster separation determination device that can determine the property easily and accurately.

Further, the simple separated cluster hypothesis generating device according to the fifteenth aspect is capable of regenerating the hypotheses of the respective separated clusters when the clusters are separated when the observation vector does not include an erroneous signal. The purpose is to obtain a separable cluster hypothesis generator.

[0044]

The target tracking device according to the first aspect of the present invention creates a new cluster by using an observation vector that does not correspond to a track in an existing cluster,
In addition, when there is an observation vector that is associated with a track in multiple clusters, a new cluster that integrates the corresponding clusters, an integrating device, and all the observation vectors corresponding to each cluster are false signals, existing tracks, and new targets. In-gate decision matrix calculation device for calculating an in-gate decision matrix showing all possibilities corresponding to each of the above, and a track for calculating a plurality of track correlation matrices each showing one extension method of the hypothesis from the in-gate decision matrix It is provided with a correlation matrix calculating device and a hypothesis updating device for creating a new hypothesis from the track correlation matrix and the existing hypothesis.

The target tracking device according to the second aspect comprises a hypothesis reducing device for reducing the number of hypotheses.

The target tracking device according to the third aspect of the present invention includes means for calculating an evaluation value for each track, means for selecting a certain number of tracks in descending order of evaluation value, and selected tracks. It is provided with means for deleting hypotheses not included and means for deleting tracks not included in the remaining hypotheses.

The target tracking device according to the fourth aspect of the present invention further comprises means for calculating an evaluation value for each track, means for selecting a fixed number of tracks in descending order of evaluation value, and selected tracks. A means for deleting and a means for deleting a hypothesis including the deleted track are provided.

The target tracking device according to the fifth aspect is provided with a cluster separating device for separating the clusters when possible when the hypothesis is reduced.

The target tracking device according to the sixth aspect of the invention corresponds to a cluster separation determination device that determines whether or not the clusters are separated when the hypothesis is reduced, and a cluster separation determination device when the clusters are separated. It is provided with a separated cluster hypothesis generating device for generating a hypothesis.

The target tracking device according to the seventh aspect of the present invention comprises means for investigating the similarity relationship of all tracks in the cluster,
It is provided with a means for judging the presence or absence of cluster separation and its content based on the state of grouping of tracks based on the similar relationship.

The target tracking device according to the eighth aspect of the present invention includes means for detecting whether or not a certain track is included in a certain hypothesis, and all observation vectors constituting a certain track as false signals in the certain hypothesis. It is equipped with a means to detect that it is being treated and a means to detect that a certain track satisfies one of the above two conditions in all hypotheses.

Further, the target tracking device according to the ninth aspect is a means for generating a new hypothesis including a separation track from an old hypothesis when a cluster separation occurs, and a case where the old hypothesis does not include a separation track. In addition, it is provided with a means for generating a new hypothesis containing only false signals and a means for collecting the generated new hypotheses having the same contents into one new hypothesis.

The target tracking apparatus according to the tenth aspect of the present invention simplifies the processing when an erroneous signal presence / absence determining apparatus determines whether or not an erroneous signal is included in the input observation vector, and when there is no erroneous signal. It is provided with an in-gate decision matrix calculation device having a function and a track correlation matrix calculation device having a function of simplifying the process when there is no erroneous signal.

The target tracking device according to the eleventh aspect comprises a hypothesis reducing device for reducing the number of hypotheses.

A target tracking device according to a twelfth aspect of the present invention comprises a cluster separating device for separating clusters.

The target tracking apparatus according to the thirteenth aspect of the present invention further comprises a simple cluster separation / determination apparatus for easily determining whether or not the clusters are separated when hypotheses are reduced and there is no erroneous signal. The simple separation cluster hypothesis generation device for easily generating the hypothesis corresponding to the cluster of No.

The target tracking device according to the fourteenth aspect of the present invention includes means for detecting whether or not a certain track is included in a certain hypothesis, and detecting that a certain track satisfies this condition in all the hypotheses. It is equipped with means.

Further, the target tracking device according to the fifteenth aspect has the same contents in the means for generating a new hypothesis including the separation track from the old hypothesis and the new hypothesis generated when the cluster separation occurs. It is equipped with a means to put things into one new hypothesis.

[0059]

In the target tracking device according to the first aspect of the present invention, all the observation vectors corresponding to each cluster indicate all the possibilities of false signals, existing tracks and new targets. The inner decision matrix is calculated, and a plurality of track correlation matrices each showing one extension method of the hypothesis are calculated from the gate decision matrix, and a new hypothesis is created from the track correlation matrix and the existing hypothesis.

Further, in the target tracking device according to the second aspect, the number of hypotheses is reduced.

Further, in the target tracking device according to the third aspect, an evaluation value for each track is calculated, and a certain number of tracks are selected in descending order of evaluation value, and a hypothesis that does not include the selected track. , And the wakes not included in the remaining hypotheses.

Further, in the target tracking device according to the fourth aspect, the evaluation value for each track is calculated, a certain number of tracks are selected in order from the one with the lowest evaluation value, and the selected track is deleted. Delete the hypothesis that contains the deleted track.

Further, in the target tracking device according to the fifth aspect, clusters are separated if possible at the time of hypothesis reduction.

Further, in the target tracking device according to the sixth aspect, it is determined whether or not the clusters are separated when the hypotheses are reduced, and when the clusters are separated, the hypotheses corresponding to the respective clusters are generated. .

Further, in the target tracking device according to the seventh aspect, the similarity of all tracks in the cluster is investigated, and the presence or absence of cluster separation and its content are determined from the state of grouping of tracks by the similarity. To do.

Further, in the target tracking device according to the eighth aspect, it is detected whether or not a certain track is included in a certain hypothesis, and all the observation vectors constituting a certain track are treated as false signals in all the hypotheses. It is detected that a certain track satisfies one of the above two conditions in all the hypotheses.

Further, in the target tracking apparatus according to the ninth aspect, when the separation of the cluster occurs, a new hypothesis including the separation track is generated from the old hypothesis, and when the old hypothesis does not include the separation track. A new hypothesis containing only false signals is generated, and the new hypotheses that have the same content are combined into one new hypothesis.

Further, in the target tracking apparatus according to the tenth aspect, it is determined whether or not an erroneous signal is included in the input observation vector, and the number of hypotheses generated when there is no erroneous signal is reduced.

Further, in the target tracking apparatus according to the eleventh aspect, the number of hypotheses is reduced in the situation where there is no erroneous signal in the input observation vector.

Further, in the target tracking apparatus according to the twelfth aspect, the clusters are separated in the situation where there is no erroneous signal in the input observation vector.

Further, in the target tracking apparatus according to the thirteenth aspect, whether or not the clusters are separated when the hypothesis is reduced is simply determined when there is no erroneous signal, and each separated cluster is dealt with. A hypothesis is easily generated when there is no false signal.

Further, in the target tracking device according to the fourteenth claim, if there is no error signal in the input observation vector, it is detected whether or not a certain track is included in a certain hypothesis, and a certain track is included in all the hypotheses. In, it is detected that this condition is satisfied.

Further, in the target tracking device according to the fifteenth aspect, when there is no error signal in the input observation vector, when the cluster separation occurs, the new hypothesis including the separation track is generated from the old hypothesis. Then, among the generated new hypotheses, those having the same contents are combined into one new hypothesis.

[0074]

【Example】

Example 1. FIG. 1 is an overall configuration diagram showing an embodiment of a target tracking device according to the present invention. In FIG. 1, reference numeral 1 is an observation vector selection unit that selects an observation vector included in the gate of each track from all the observation vectors input to the device. Two
Is an in-system cluster table showing the state of the entire cluster in the target tracking device. 3 is to integrate an existing cluster from the relationship between the output of the observation vector selector and the existing cluster shown in the in-system cluster table, and to create a new cluster and create an in-cluster observation vector table. It is a department. Reference numeral 4 is an intra-cluster observation vector table showing all the observation vectors included in the cluster.
Reference numeral 5 denotes an in-gate matrix calculation unit that inputs an in-cluster observation vector table and a data group indicating the status of hypotheses in the cluster and calculates an in-gate decision matrix in the cluster. Reference numeral 6 denotes an intra-gate gate determination matrix showing the relationship between the observation vector in the cluster and the track. Reference numeral 7 denotes a track correlation matrix calculation unit that calculates the track correlation matrix in the cluster by using the intra-cluster gate determination matrix as an input. Reference numeral 8 is an intra-cluster wake correlation matrix showing the expandability of the hypothesis within the cluster. A hypothesis updating unit 9 updates the hypothesis corresponding to the situation of the hypothesis by the observation vector up to the previous time and the observation vector input at the current time from the intra-cluster track correlation matrix. Reference numeral 10 is an intra-cluster hypothetical situation data group. Reference numeral 11 is an intra-cluster hypothesis table showing all the hypotheses in the cluster. Reference numeral 12 is an intra-hypothesis track table showing all tracks in the hypothesis for each hypothesis. Reference numeral 13 is an intra-cluster track-observation vector table showing the observation vectors forming the tracks for all tracks in the cluster. Reference numeral 14 is a gate calculation unit that calculates a predicted existence position range at the next observation vector input time for all tracks in the cluster. When a plurality of hypotheses exist in the cluster, a track determination unit 15 selects one of the best hypotheses to determine the number of targets and their tracks. Reference numeral 16 is a target tracking device. Reference numeral 17 denotes a target observation device which is a sensor for observing a target in space and obtaining an observation vector. Reference numeral 18 denotes a target display device which displays a track on the display and shows the state of the target to the user.

Next, the operation of the first embodiment will be described. Similar to the description of the operation of the conventional example, the operation of this embodiment will be described in the situation of times t1 and t2 in FIG.

First, the observation vector Z1,1 at time t1 is input. In this situation, since there is no existing cluster, hypothesis or track, the observation vector selection unit 1 sends Z1,1 to the new cluster integration unit 3 as an independent observation vector unrelated to the existing cluster.

Next, the new cluster creation / integration unit 3 newly creates the cluster 1 including Z1,1 and defines it in the in-system cluster table 2 and writes Z1,1 in the in-cluster observation vector table 4 of the cluster 1. Here, in the intra-cluster observation vector table 4, only the observation vector at the current time is described.

Next, the in-gate decision matrix calculation unit 5 calculates an in-gate decision matrix showing the possibility of correlation between all the observation vectors of this time in the cluster and the track.

Generally, the in-gate decision matrix at the time tk is such that the number of observation vectors at tk is mk, the number of already tracked targets at tk (that is, the number of tracked targets at tk-1) is Nk-1, and tracking at tk is performed. When the target number is Nk = Nk-1 + mk, it is defined as follows.

[0080]

[Equation 1]

Here, the row is the observation vector Zk, j at tk.
Corresponding to (j = 1, 2, ..., Mk), the columns correspond to wakes. Also, each element indicates whether or not each observation vector is within the gate of each track.

Specifically, each element is set as follows.
First, the column of t = 0 shows the case where the observation vector is an erroneous signal. In fact, all observation vectors can be false signals, so

[0083]

[Equation 2]

It is assumed that

Next, the column of (1≤t≤Nk-mk) corresponds to the track Tt which is the tracked target. That is, when the observation vector Zk, j (j = 1, 2, ..., Mk) is included in the gate of the track Tt,

[0086]

(Equation 3)

If not included,

[0088]

[Equation 4]

It is assumed that

Next, the column (Nk-mk + 1≤t≤Nk) corresponds to the new target track Tt. This is for expressing the possibility that all the observation vectors are new targets, and one observation vector corresponds to one track. That is, in the case of (j = t-Nk + mk),

[0091]

(Equation 5)

On the contrary, when (j ≠ t-Nk + mk),

[0093]

(Equation 6)

It is assumed that

Applying the in-gate decision matrix defined as above to the example of FIG. 3 is as follows. here,
Since the observation vector mk is 1, the tracked track Nk-1 is 0, and the tracked track Nk is 1, the following 1-by-2 in-gate decision matrix is generated.

[0096]

(Equation 7)

This matrix representation shows the possibility that the observation vectors Z1,2 are erroneous signals and that they may correspond to the new target track T1.

Next, the track correlation matrix calculation unit 7 calculates all track correlation matrices from the in-gate determination matrix. The track correlation matrix shows the correlation between the observation vector and the track that can actually be assumed as a hypothesis.

Generally, the track correlation matrix at time tk is defined as follows from the in-gate decision matrix.

[0100]

(Equation 8)

Here, like the intra-gate correlation matrix, the row corresponds to the observation vector at tk, the column corresponds to the track, and each element indicates whether each observation vector is correlated with each track. .

Specifically, each element is set as follows.
That is, the observation vector Zk, j (j = 1, 2, ...,
mk) is correlated with the track Tt (t = 0, 1, ..., Nk),

[0103]

[Equation 9]

If there is no correlation,

[0105]

[Equation 10]

It is assumed that

When the track correlation matrix is created from the in-gate decision matrix, all combinations satisfying the three parties at the same time are expressed as different track correlation matrices according to the following three criteria. (A) Only the element of the track correlation matrix corresponding to the element that is 1 in the in-gate decision matrix can be 1 and the other elements can be 0. (A) In all columns of the track correlation matrix other than the column of t = 0,
Only at most one element is 1 and the other elements are 0. (C) In all the rows of the track correlation matrix, one element is always set to 1 and the other elements are set to 0.

The track correlation matrix defined as above is applied to the example of FIG. 3 as follows.

[0109]

[Equation 11]

By using these two matrix expressions, the observation vector Z
The hypothesis that 1 and 2 are false signals and the new target wake T1
It is shown that a hypothesis that corresponds to can be created.

Next, the hypothesis updating unit 9 updates the hypothesis to the one corresponding to the current situation by combining the previously calculated hypothesis with the track correlation matrix calculated previously. Here, if a tracked track already tracked in the track correlation matrix that is said to be correlated with the observation vector is not included in the hypothesis as a tracked track, the two cannot be combined. With all other combinations, the hypothesis is updated by adding a new observation vector to the tracked track and extending the track, adding a new track as a new target, and treating a certain observation vector as an erroneous signal. Here, in many cases, one hypothesis is combined with a plurality of track correlation matrices and updated to a plurality of hypotheses, so that the number of hypotheses increases each time the hypotheses are updated.

In the example of FIG. 3, there is no existing hypothesis to be combined, so a new hypothesis is created from the track correlation matrix. First, from Ω (H ^1,1 ), the observation vector Z ^1,1 is considered as an erroneous signal, and a hypothesis X ^1,1 with no track is generated. This is expressed as follows.

[0113]

(Equation 12)

Next, from Ω (H ^1,2 ), the observation vector Z 1,1
Is regarded as a signal from the new target, a hypothesis X ^1,2 that newly starts the track T1 is generated.

[0115]

(Equation 13)

Here, the track T1 is

[0117]

[Equation 14]

It is described as

Finally, when requested by the track determination unit 15, one of the hypotheses is selected by some method to uniquely determine the target number and the track.

Next, the operation of the apparatus when the time advances to t2 in the above-mentioned state and the observation vectors Z2,1 and Z2,2 are newly input will be described.

First, the gate calculation unit 14 calculates a gate, which is the predicted existence range at time t2, for all tracks in the cluster. In this case, the gate is calculated for T1 which is the only track existing in the cluster.

Next, the observation vector selection unit 1 investigates the relationship between the gate and the observation vector, and as a result, here, Z2,1
Both Z1 and Z2,2 are inside the gate of track T1.

Next, regarding the new cluster and integration unit 3,
No new clusters occur here, nor does cluster consolidation occur. As a result, it has been confirmed that the observation vectors Z2,1 and Z2,2 are present in the cluster to be explained. However, if another cluster exists,
If the gate of the track contained therein also contains Z2,1 or Z2,2, both clusters are merged.

Next, in the gate decision matrix calculation unit 5, time t2
The in-gate decision matrix in is calculated as follows.

[0125]

(Equation 15)

Here, the first line is the observation vector Z2,1 and the second line is
The row corresponds to Z2,2. In addition, the first row is a false signal, the second row is the existing track T1, the third row is the new track T2, and the fourth row is the new track T.
Corresponds to 3. As mentioned earlier, all observation vectors can be false signals, so both columns contain the value 1. In this example, both observation vectors are track T1.
Since it is in the gate of, the value of 1 is entered in the second column.

Next, the track correlation matrix calculating unit 7 calculates the track correlation matrix at time t2 as follows.

[0128]

[Equation 16]

Next, the hypothesis updating section 9 updates the hypothesis. First, the hypothesis X ^1,1 is updated. Here, since the track correlation matrix assuming the existence of the tracked track T1 cannot be used, 4
The hypothesis will be updated by the track correlation matrix. The results are shown below.

[0130]

[Equation 17]

Next, the hypothesis X ^1,2 is updated. 8 here
All the track correlation matrices will be used to update the hypothesis. The results are shown below.

[0132]

(Equation 18)

In summary, the two hypotheses at t1 were updated and 12 hypotheses were generated at t2. As a result, there are 5 tracks in this cluster.

Thereafter, the time advances, and the above work is repeated each time a new observation vector is input.

Example 2. FIG. 2 is an overall configuration diagram showing an embodiment of a target tracking device according to the present invention. In FIG.
Reference numeral 19 is a hypothesis reduction unit that reduces the number of hypotheses by performing some evaluation on the hypotheses and deleting some of the hypotheses according to the results. Other configurations are the same as those of the target tracking device of FIG. 1 described in the first embodiment.

Next, the operation of the second embodiment will be described. When the hypothesis construction is repeated by performing the same operation as in the first embodiment, the number of hypotheses increases rapidly. For example, t1 in the previous example
The number of hypotheses, which was 2 at t2, has increased to 12 at t2.
As described above, if the hypothesis construction is continued with the basic configuration of the first embodiment, the processing amount and the data amount associated with the hypothesis construction become very large, and the performance limit of the device may be exceeded.

The hypothesis reduction unit 19 inputs the intra-cluster hypothesis situation data group at an arbitrary time point, evaluates the plausibility of the hypothesis by some method, and the hypothesis with a low evaluation, that is,
It removes the unlikely hypothesis and returns the result. As a concrete method, for example, the one shown in the conventional example can be used. As described above, by reducing the hypothesis at an arbitrary time, it is possible to continue the tracking processing such as hypothesis construction without exceeding the performance limit of the device.

Example 3. FIG. 4 is a flow chart showing the operation of an embodiment of the hypothesis reduction device according to the present invention.
Here, the hypothesis reduction device performs steps 20 to 23 shown in FIG.
Comprising means for performing.

Next, the operation will be described. As described in the second embodiment, the hypothesis reduction unit 19 receives the intra-cluster hypothesis situation data group as input data, uses this data to delete some hypotheses, and returns the result.

First, in step 20, an evaluation value indicating the plausibility of a track is calculated for all tracks in the cluster.

Next, at step 21, a certain number of tracks are selected in order from the one having the highest evaluation value.

Next, in step 22, all the hypotheses in the cluster are examined, and the hypotheses that do not include any of the hypotheses selected in step c2 are deleted.

Finally, in step 23, the tracks included in the remaining hypotheses are investigated, and all the tracks in the cluster that are not included are deleted. This completes the hypothesis reduction process and returns the result.

Example 4. FIG. 5 is a flowchart showing the operation of another embodiment of the hypothesis reduction device according to the present invention. Here, the hypothesis reduction apparatus comprises means for executing steps 24 to 27 shown in FIG.

Next, the operation of the fourth embodiment will be described. As described in the second embodiment, the hypothesis reduction unit 19 receives the intra-cluster hypothesis situation data group as input data, uses this data to delete some hypotheses, and returns the result.

First, at step 24, an evaluation value indicating the plausibility of the track is calculated for all tracks in the cluster.

Next, in step 25, a fixed number of tracks are selected in order from the one having the lowest evaluation value.

Next, at step 26, the track selected at step 25 is deleted.

Finally, in step 27, the hypothesis containing the deleted track is deleted. This is the end of the hypothesis reduction process,
Returns the result.

Example 5. FIG. 6 is an overall configuration diagram showing an embodiment of a target tracking device according to the present invention. In FIG.
Reference numeral 28 denotes a cluster separation unit that evaluates whether or not the cluster can be separated when the hypothesis is reduced, and reconstructs the hypothesis of each cluster when the cluster can be separated. Other configurations are the same as those of the target tracking device of FIG. 2 described in the second embodiment.

Next, the operation of the fifth embodiment will be described. When the hypothesis construction is repeated by performing the same operation as that of the first embodiment, two clusters may be integrated by having a common observation vector in the process.
However, as long as the basic operation of hypothesis building is repeated,
In principle, cluster separation does not occur.

However, when the hypothesis reduction described in the second embodiment is performed, cluster separation may occur. When the clusters are separated, the scale of each hypothesis is reduced, and the processing amount required for updating the hypothesis can be reduced for the entire device. Therefore, in the present invention, at any time after the hypothesis reduction, the cluster separation unit 28 performs the cluster separation determination and the actual cluster separation processing. The cluster separation unit 28 defines a cluster as follows using the relationship of all tracks in the device, and performs the cluster separation process on the condition.

That is, the tracks Ti and Tj are called similar tracks only when the tracks Ti and Tj share at least one observation vector.

[0154]

[Formula 19]

Write as At wakes Ti and Tj,

[0156]

(Equation 20)

[0157] to become Ti _1, Ti _2, ···, only if the Ti _n exists,

[0158]

[Equation 21]

It is defined as This relation satisfies the reflection temperament, the symmetry temperament, and the transition temperament, that is, the equivalence relation.
At any given time, all tracks can be classified according to the equivalence relation and can be divided into a plurality of disjoint classes. This kind of thing is called a cluster.

As described in the first embodiment, the present target tracking device carries out the hypothesis building process by displaying the track in front, and the intra-cluster hypothesis situation data group contains the information necessary for the above condition determination. . The cluster separation unit 28 determines the separation of the cluster from this information, then separates the cluster and reconstructs the hypothesis, and updates the intra-cluster hypothesis situation data group.

Example 6. FIG. 7 is an overall configuration diagram of an embodiment of the cluster separation device according to the present invention. In the figure, 29 is a cluster separation determination unit that determines the cluster separation based on the equivalence relation of the tracks described in the fifth embodiment, and 30 is a separated cluster hypothesis generation unit that separates the clusters and reconstructs the hypotheses of the separated clusters.

Next, the operation of the sixth embodiment will be described. The cluster separation device inputs the intra-cluster hypothesis situation data group,
First, it is given to the cluster separation determination unit 29. The cluster separation determination unit 29 performs cluster separation determination by the method described in the fifth embodiment, and passes the result to the separated cluster hypothesis generation unit 30. The separated cluster hypothesis generation unit 30 reconstructs a hypothesis that has a new cluster configuration from the determination result and the intra-cluster hypothesis situation data group, and outputs the changed intra-cluster hypothesis situation data group.

Example 7. FIG. 8 is a flow chart showing the operation of an embodiment of the cluster separation determination device according to the present invention. Here, the cluster separation determination device is the same as that shown in FIG.
1 to 36 are provided.

Next, the operation of the seventh embodiment will be described. The cluster separation determination device starts the separation determination process when it receives the intra-cluster hypothesis situation data group.

First, in step 31, one track out of all tracks in the cluster is focused and all similar tracks of the track are extracted.

Next, in step 32, it is judged whether or not a similar track has been extracted. The fact that there is no similar track here means that one cluster is formed only by the first track of interest. If there is a similar track, the process proceeds to a step for extracting a similar track for the extracted similar track.

Next, in steps 33 and 34, the process is repeated until all the similar tracks are extracted, and when there are no more similar tracks, one equivalence relation, that is, the tracks forming one cluster. The group has been extracted.

Next, at step 35, one cluster is defined by the tracks extracted by the above processing, and the remaining tracks are sorted for the next processing.

Finally, in step 36, it is judged whether or not there is a residual track not included in the cluster by the above processing, and if there is, a similar processing is repeated to carry out further cluster separation processing. finish.

Example 8. Next, a description will be given of an embodiment of a cluster separation determination device for a cluster including only one track according to the present invention. This cluster separating device is particularly intended to easily separate a cluster including only one track, and does not separate a cluster including a plurality of tracks. Figure 9
Is a flow chart showing the operation of the embodiment of the cluster separation determination device according to the present invention. Here, the cluster separation determination device comprises means for executing steps 37 to 48 shown in FIG.

Next, the operation of the above eighth embodiment will be described. The cluster separation determination device starts the separation determination process when it receives the intra-cluster hypothesis situation data group.

First, at step 37, one track is selected as a target for separation determination. In the following steps, we investigate whether this track is treated as if it were in each hypothesis in the cluster. Here, if the track is included in all the hypotheses or all the observation vectors forming the track are treated as erroneous signals, it can be determined that the track of interest is separated.

Next, at step 38, a hypothesis to be investigated is selected.

Next, at 39, it is checked whether the track of interest is included in the hypothesis of interest.

Next, at 40, determination processing is performed. If the track of interest is included in the hypothesis of interest, there is a possibility of separation of this track at this point, so the process moves to the next hypothesis. If it is not included, the next condition is determined.

Next, at 41, it is checked whether all the observation vectors forming the track of interest are treated as false signals by the hypothesis of interest.

Next, at 42, the determination process of the result is performed, and if all are included as an erroneous signal, this track may be separated, so that the determination process is moved to the next hypothesis. If it is not included, it is determined that this track is not separated, and the process is moved to.

Next, in step 43, it is recorded that the track of interest is not a separation track.

Next, in step 44, since the track of interest may be a separated track, the next hypothesis to be investigated is selected for the determination process.

Next, in step 45, a judgment process is performed, and if there is a hypothesis to be investigated, the hypothesis is investigated. Also, if the hypothesis to be surveyed has disappeared, it is determined that the track of interest is a separated track.

Next, in step 46, it is recorded that the track of interest is a separated track and forms a new cluster.

Next, at step 47, a process of selecting a track is performed in order to perform the determination process for the next track.

Finally, in step 48, it is judged whether or not there is a residual track. If yes, the separation judgment process is continued, and if not, the separation judgment process is ended.

Example 9. Next, an embodiment of the separated cluster hypothesis generation device according to the present invention will be described. FIG. 10 is a flow chart showing the operation of the embodiment of the separated cluster hypothesis generation device according to the present invention. Here, the separated cluster hypothesis generation device comprises means for executing steps 49 to 51 shown in FIG.

Next, the operation of the ninth embodiment will be described. Here, the old cluster may be separated into a plurality of new clusters, each containing one or more tracks. The procedure for reconstructing one hypothesis of a plurality of new clusters will be described below.

First, in step 49, it is checked whether all the hypotheses contained in the old cluster include the track of the new cluster, and if they include the new cluster, the new hypothesis consisting of only the new track contained therein is checked. To generate.

Next, in step 50, a new hypothesis consisting only of erroneous signals is generated only when there is an old hypothesis that does not include any new track in step 49.

Finally, in step 51, the new hypotheses created in the above steps and having the same contents are integrated.

Example 10. FIG. 11 is an overall configuration diagram showing an embodiment of a target tracking device according to the present invention. In FIG. 11, reference numeral 52 denotes an erroneous signal presence / absence determining unit that determines whether or not an erroneous signal is included in the observation vector based on signals from the target control device and the operation instruction device. An in-gate decision matrix calculation unit 53 has a function of simplifying the processing when there is no erroneous signal. Reference numeral 54 is also a track matrix calculation device having a function of simplifying the processing when there is no erroneous signal. Reference numeral 55 is an operation instructing device for the user to instruct the erroneous signal presence / absence determining unit to perform an operation. Other parts are the same as those in FIG. 1 of the first embodiment.

Next, the operation of the tenth embodiment will be described. Many parts of the target tracking apparatus in this embodiment are the same as those in the first embodiment.
The target tracking device operates in the same manner, but the calculation of the in-gate determination matrix and the calculation of the track correlation matrix are simplified when there is no erroneous signal.

In the following description, in the same situation as in the first embodiment, the operation of the apparatus when there is no erroneous signal will be described with an emphasis on the difference.

First, the operation up to the in-gate decision matrix calculating section is the same as in the first embodiment.

Next, the in-gate decision matrix calculation section 53 changes the processing contents in response to the decision result of the erroneous signal presence / absence decision section 52. The definition of the configuration of the in-gate decision matrix is the same as that in the first embodiment even when there is no erroneous signal, but the column indicating the possibility of the erroneous signal in the first column is always set to 1 in the first embodiment. hand,
On the contrary, if there is no erroneous signal, be sure to set it to 0.

When the in-gate decision matrix defined as above is applied to the example of FIG. 3, it becomes as follows.

[0195]

[Equation 22]

This matrix representation shows that the observation vector Z1,2 may correspond to the wake T1, which is a new target. Unlike the first embodiment, the possibility of an erroneous signal disappears.

Next, the track correlation matrix calculation unit 54. Here too, the process is simplified if there is no error signal, but if the method of forcibly setting the error column of the in-gate decision matrix to 0 as shown in the present embodiment is adopted, structurally Is exactly the same as in the first embodiment.

When the track correlation matrix defined as above is applied to the example of FIG. 3, it becomes as follows.

[0199]

(Equation 23)

It is shown from this matrix expression that it is possible to create a hypothesis that the observation vector Z1,2 corresponds to the new target track T1.

The following structure of the hypothesis updating unit 9 is similar to that of the first embodiment, and the observation vector Z ^1,1 is regarded as a signal from the new target from Ω (H ^1,1 ), and the hypothesis X for newly starting the track T 1 is assumed. ^1,1 is generated.

[0202]

[Equation 24]

Here, the track T1 is

[0204]

(Equation 25)

It is described as follows.

Finally, the track determination unit 15 is also the same as in the first embodiment.

Next, the operation of the apparatus when the time advances to t2 and new observation vectors Z2,1 and Z2,2 are input in the above state will be described.

First, in the same way as in the first embodiment, the gate calculator 14 calculates a gate for T1, which is the only track existing in the cluster.

Next, the observation vector selection unit 1 and the new cluster / integration unit 3 are the same as in the first embodiment.

Next, the in-gate decision matrix calculation unit 53 performs time t.
The in-gate decision matrix in 2 is calculated as follows.

[0211]

(Equation 26)

Here, the first row is the observation vector Z2,1 and the second row is
The row corresponds to Z2,2. In addition, the first row is a false signal, the second row is the existing track T1, the third row is the new track T2, and the fourth row is the new track T.
Corresponds to 3. As described above, since all the observation vectors are not considered to be erroneous signals, the value 0 is put in the first column together. In this example, both observation vectors are track T1.
Since it is in the gate of, the value of 1 is entered in the second column.

Next, the track correlation matrix calculating section 54 calculates the track correlation matrix at time t2 as follows.

[0214]

[Equation 27]

Next, the hypothesis updating section 9 updates the hypothesis X ^1,1 . Here, the hypothesis will be updated using all three track correlation matrices. The results are shown below.

[0216]

[Equation 28]

In summary, one hypothesis at t1 was updated and three hypotheses were generated at t2.
As a result, there are 5 tracks in this cluster. Comparing this with the case of Example 1, 5
Although the book does not change, it can be seen that the number of hypotheses is reduced from 12 to 3, and the processing amount and the data amount are greatly reduced by coping with the situation where there is no erroneous signal.

Thereafter, the time advances, and the above work is repeated each time a new observation vector is input.

Example 11. FIG. 12 is an overall configuration diagram of an embodiment of a target tracking device according to the present invention. In this configuration, the hypothesis reducing unit 19 is added to the target tracking device shown in the tenth embodiment as in the second embodiment.

Next, the operation of the 11th embodiment will be described. The present embodiment operates in the same manner as the tenth embodiment, and at the arbitrary time after updating the hypothesis, the hypothesis is reduced as in the second embodiment.

Example 12. FIG. 13 is an overall configuration diagram of an embodiment of a target tracking device according to the present invention. In this configuration, a cluster separating device is added to the target tracking device shown in the eleventh embodiment as in the fifth embodiment. However,
The cluster separation unit 56 is different from the cluster separation unit 28 in that it can cope with a state where there is no erroneous signal.

Next, the operation of the twelfth embodiment will be described. The present embodiment operates in the same manner as the eleventh embodiment, in which the cluster separation unit 56 performs the cluster separation determination operation and the separation cluster hypothesis reconstructing operation at an arbitrary time after the hypothesis is reduced. Is what you do. However, the cluster separation unit 56 has a processing content selection function for simplifying the processing when there is no erroneous signal.

Example 13 FIG. 14 is an overall configuration diagram of an embodiment of a cluster separation device according to the present invention. In FIG. 14, reference numeral 57 denotes a simple cluster separation determination unit that simply determines the cluster separation when there is no erroneous signal. Also, 58
Is a simple separated cluster hypothesis generator that easily creates a separated cluster hypothesis when there is no error signal.

Next, the operation of the thirteenth embodiment will be described. The present embodiment has a function of changing the processing content depending on the presence or absence of an erroneous signal. When there is an erroneous signal, the same operation as the cluster separating apparatus of the sixth embodiment is performed, and when there is no erroneous signal, the simple cluster separation determination is made. Both the cluster separation determination in the unit 57 and the separation cluster hypothesis generation in the simple separation cluster hypothesis generation unit 58 operate in a simplified manner.

Example 14 FIG. 15 is a flowchart showing the operation of an embodiment of the simple cluster separation / determination device according to the present invention. Here, the simple cluster separation determination device comprises means for executing steps 37 to 48 shown in FIG.

Next, the operation of the 14th embodiment will be described. The operation of the simple cluster separation / determination device of this embodiment is the same as that of the eighth embodiment.
Step 41 from the processing flow of the cluster separation determination device
And the operation of step 42 is excluded.

Example 15. FIG. 16 is a flow chart showing the operation of one embodiment of the simple separation cluster hypothesis generation device according to the present invention. Here, the simple separation cluster hypothesis generation device comprises means for executing steps 49 to 51 shown in FIG.

Next, the operation of the fifteenth embodiment will be described. The operation of the simple separation cluster hypothesis generation device 58 of this embodiment is as follows.
The operation of step 50 is removed from the processing flow of the separated cluster hypothesis generation device of the ninth embodiment.

[0229]

As described above, since the target tracking device according to the first aspect of the present invention is configured to express the hypothesis by the track, the track extraction can be easily performed.

Since the target tracking device according to the second aspect of the present invention is provided with the hypothesis reducing device, it is possible to easily extract the track and reduce the number of hypotheses.

Further, the target tracking device according to the third aspect is configured to evaluate the plausibility of the track and select the hypothesis to be deleted according to the result, so that an unlikely hypothesis is appropriately selected. Can be deleted.

Further, the target tracking device according to the fourth claim is configured to evaluate the plausibility of the track and select the hypothesis to be deleted according to the result, so that the unlikely hypothesis is appropriately selected. Can be deleted.

Further, since the target tracking device according to the fifth aspect is provided with the cluster separating device, it is possible to easily extract the track, reduce the number of hypotheses, and separate the clusters when reducing the hypotheses. The possibility can be accurately determined and cluster separation can be performed if possible.

Since the target tracking device according to the sixth aspect comprises the cluster separation determination device and the separated cluster hypothesis generation device, the separability of the cluster is accurately determined when the hypothesis is reduced, and if possible. Cluster separation can be performed.

Further, the target tracking device according to the seventh aspect of the present invention is provided with the means for investigating the similarity relationship of the wakes, so that the separability of clusters can be accurately determined when the hypothesis is reduced.

Further, the target tracking device according to the eighth claim comprises means for detecting that the track in the hypothesis or all the observation vectors forming the track are included as an erroneous signal. It is possible to accurately determine the separability of a cluster consisting of only one track when reducing.

Further, since the target tracking device according to the ninth aspect comprises means for constructing a new hypothesis corresponding to a separated track from the old hypothesis, when the clusters are separated, the hypotheses of the separated clusters are regenerated. can do.

Since the target tracking device according to the tenth claim comprises means for instructing that the observation vector does not include an erroneous signal and means for reducing the number of hypotheses in that case, extraction of the track is easy. Thus, the hypothesis generation can be executed at high speed.

Since the target tracking device according to the eleventh claim is provided with the means for reducing the number of hypotheses, it is possible to easily extract the track and perform the hypothesis generation at a high speed. The number can be reduced.

The target tracking device according to the twelfth claim is provided with means for accurately determining the separability of the clusters when the hypothesis is reduced, and performing the cluster separation if possible. The extraction is easy, the hypothesis generation can be executed at high speed, the number of hypotheses can be reduced, and the total processing amount can be further reduced.

Since the target tracking device according to the thirteenth claim comprises the simple cluster separation determination device and the simple separation cluster hypothesis generation device, when the observation vector does not include an erroneous signal, the cluster separation is performed. Simple possibilities, and
It is possible to make an accurate determination and easily perform cluster separation if possible.

Further, the target tracking device according to the fourteenth claim simplifies the processing in response to the case where there is no erroneous signal. The separability of clusters consisting only of wakes can be determined easily and accurately.

Further, the target tracking device according to the fifteenth aspect simplifies the processing in response to the case where there is no erroneous signal, so that the cluster is separated when the observing vector does not include an erroneous signal. At this time, the hypotheses of each separated cluster can be easily regenerated.

[Brief description of drawings]

FIG. 1 is an overall configuration diagram of an embodiment of a target tracking device of the present invention.

FIG. 2 is an overall configuration diagram of an embodiment of a target tracking device of the present invention.

FIG. 3 is a diagram showing a generation state of an observation vector input to a target tracking device.

FIG. 4 is a flow chart showing the operation of the embodiment of the hypothesis reduction device according to the present invention.

FIG. 5 is a flow chart showing the operation of the embodiment of the hypothesis reduction device according to the present invention.

FIG. 6 is an overall configuration diagram of an embodiment of a target tracking device of the present invention.

FIG. 7 is an overall configuration diagram of an embodiment of a cluster separation device according to the present invention.

FIG. 8 is a flow chart showing the operation of the embodiment of the cluster separation determination device according to the present invention.

FIG. 9 is a flowchart showing the operation of an embodiment of a cluster separation determination device for a cluster consisting of only one track according to the present invention.

FIG. 10 is a flowchart showing the operation of the embodiment of the separated cluster hypothesis generation device according to the present invention.

FIG. 11 is an overall configuration diagram of an embodiment of a target tracking device of the present invention.

FIG. 12 is an overall configuration diagram of an embodiment of a target tracking device of the present invention.

FIG. 13 is an overall configuration diagram of an embodiment of a target tracking device of the present invention.

FIG. 14 is an overall configuration diagram of an embodiment of a cluster separation device of the present invention.

FIG. 15 is a flowchart showing the operation of an embodiment of a simple cluster separation / determination apparatus for a cluster consisting of only one track according to the present invention.

FIG. 16 is a flowchart showing the operation of the embodiment of the simple separation cluster hypothesis generation device of the present invention.

FIG. 17 is a flowchart showing an operation of a conventional target tracking device.

FIG. 18 is a diagram illustrating a hypothesis generation procedure of a conventional target tracking device.

FIG. 19 is a diagram illustrating a hypothesis generation procedure of a conventional target tracking device.

[Explanation of symbols]

1 Observation vector selection unit, 3 clusters newly installed, integration unit,
5 Gate judgment matrix calculation unit, 7 Track correlation matrix calculation unit, 9 Hypothesis update unit, 14 Gate calculation unit, 15 Track determination unit, 19 Hypothesis reduction unit, 28 Cluster separation unit, 2
9 cluster separation determination unit, 30 separation cluster hypothesis generation unit, 52 incorrect signal presence / absence determination unit, 53 in-gate determination matrix calculation unit, 54 wake correlation matrix calculation unit, 56 cluster separation unit, 57 simple cluster separation determination unit, 58 simple separation Cluster hypothesis generator.

Claims (15)

[Claims] 1. A target tracking device, a gate calculation device for calculating an existence possible region of an observation vector from an existing track included in each cluster, and an observation corresponding to a track for each cluster from the existence possible region and the entire observation vector. A new cluster is created by an observation vector selection device that selects a vector and an observation vector that does not correspond to a track in an existing cluster. Also, it corresponds to the case where there is an observation vector that can be associated with a track in multiple clusters. A new cluster that integrates the cluster, an integrated device, and all observation vectors that correspond to each cluster indicate the possibility of false signals, existing tracks, and new targets. From the decision matrix calculation device and the in-gate decision matrix, calculate a plurality of track correlation matrices, each of which represents one extension method of Target tracking device including a track correlation matrix calculation device that outputs a hypothesis update device that creates a new hypothesis from the track correlation matrix and existing hypotheses, and a track determination device that selects one of a plurality of hypotheses to determine a track . 2. The target tracking device according to claim 1, further comprising a hypothesis reduction device that reduces the number of hypotheses. 3. The hypothesis reduction apparatus according to claim 2, wherein the means for calculating the evaluation value for each track, the means for selecting a certain number of tracks in descending order of evaluation value, and the selected track are not included. The target tracking device according to claim 2, further comprising: a hypothesis deleting unit and a track not included in the remaining hypotheses. 4. The hypothesis reduction device according to claim 2, wherein the means for calculating the evaluation value for each track, the means for selecting a certain number of tracks in order from the one with the lowest evaluation value, and the selected track are deleted. 3. The target tracking device according to claim 2, further comprising means and means for deleting a hypothesis including the deleted track. 5. The target tracking device according to claim 2, further comprising a cluster separating device that separates the clusters if possible when the hypothesis is reduced. 6. The cluster separation device according to claim 5 determines a cluster separation judgment device for judging whether a cluster is separated when hypotheses are reduced, and a hypothesis corresponding to each cluster when the cluster is separated. The target tracking device according to claim 5, further comprising: a separated cluster hypothesis generating device for generating the separated cluster hypothesis. 7. The cluster separation determination device according to claim 6, and means for investigating the similarity relationship of all tracks in the cluster,
7. The target tracking device according to claim 6, further comprising means for determining the presence / absence of cluster separation and its content based on the state of grouping of the tracks based on the similar relationship. 8. The cluster separation / determination device according to claim 6 treats as means for detecting whether or not a certain track is included in a certain hypothesis and all observation vectors constituting a certain track as false signals in the certain hypothesis. A cluster of clusters consisting of only one track, including means for detecting that the track is broken and means for detecting that a track satisfies one of the above two conditions in all hypotheses The target tracking device according to claim 6, wherein the target tracking device is a separation determination device. 9. The separation cluster hypothesis generation device according to claim 6, when the separation of the cluster occurs, means for generating a new hypothesis including a separation track from the old hypothesis, and a case where the old hypothesis does not include a separation track. 7. The target tracking device according to claim 6, further comprising means for generating a new hypothesis containing only an erroneous signal, and means for collecting the generated new hypotheses having the same content into one new hypothesis. 10. An erroneous signal presence / absence determining device for determining whether or not an erroneous signal is included in an input observation vector,
Claims provided with an in-gate decision matrix calculation device having a function of simplifying processing when there is no erroneous signal, and a track correlation matrix calculation device similarly having a function of simplifying processing when there is no erroneous signal. 1. The target tracking device according to 1. 11. The target tracking device according to claim 10, further comprising a hypothesis reduction device for reducing the number of hypotheses. 12. The target tracking device according to claim 10, further comprising a cluster separating device that separates clusters. 13. The cluster separation device according to claim 12, wherein a simple cluster separation judgment device for easily judging whether or not the clusters are separated when hypotheses are reduced and there is no erroneous signal, and each of the separated clusters. 13. A simple separation cluster hypothesis generation device for easily generating the hypothesis corresponding to the above when there is no erroneous signal.
Target tracking device described. 14. The simple cluster separation / determination device according to claim 13 detects means for detecting whether or not a certain track is included in a certain hypothesis, and detects that a certain track satisfies this condition in all the hypotheses. 14. The target tracking device according to claim 13, wherein the target tracking device is a simple cluster separation determination device for a cluster consisting of only one track. 15. The simple separation cluster hypothesis generation device according to claim 13 is the same as the means for generating a new hypothesis including a separation track from the old hypothesis when the separation of the cluster occurs and the new hypothesis generated. 14. The target tracking device according to claim 13, wherein the target tracking device is a simple separation cluster hypothesis generating device having means for collecting contents into one new hypothesis.