CN116012629A - Cube characterization method based on target group identification and morphology judgment - Google Patents
Cube characterization method based on target group identification and morphology judgment Download PDFInfo
- Publication number
- CN116012629A CN116012629A CN202211635620.3A CN202211635620A CN116012629A CN 116012629 A CN116012629 A CN 116012629A CN 202211635620 A CN202211635620 A CN 202211635620A CN 116012629 A CN116012629 A CN 116012629A
- Authority
- CN
- China
- Prior art keywords
- target
- targets
- target group
- group
- cube
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012512 characterization method Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims abstract description 11
- 239000003086 colorant Substances 0.000 claims abstract description 7
- 238000009432 framing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000007123 defense Effects 0.000 description 2
- 238000005755 formation reaction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The application relates to the technical field of electric digital data processing, in particular to a cube characterization method based on target group identification and morphology judgment. The method comprises the following steps: s100, acquiring a feature matrix of a target; s200, obtaining d n,i The method comprises the steps of carrying out a first treatment on the surface of the S300, clustering targets with the same appearance time; s400, obtaining c j Corresponding minimum target group c j,min The method comprises the steps of carrying out a first treatment on the surface of the S500, obtaining c r j,min A corresponding target group morphology type; s600, constructing a target cube on the user interface, and representing the target in the target cube, comprising: using a first colorThe bounding boxes of colors frame each minimum target group, and the bounding boxes of a second color frame each maximum target group. The invention quantitatively represents the difference between the targets, intelligently identifies the range and the form of the target group, improves the relation between the targets and the representation mode of the relation between the targets and the target group, and improves the experience of the user.
Description
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to a cube characterization method based on target group identification and morphological judgment.
Background
The number of targets encountered under a specific space-time scene is large, the types of targets are complex, a cooperative relationship exists among the targets, a plurality of targets jointly form a target group, and the tasks are completed in a group mode; in large tasks, the target groups often have cooperative forms such as mutual cooperation and shielding. How to improve the representation modes of the relation between targets and target groups on a user interface and improve the experience of users is a problem to be solved urgently.
Disclosure of Invention
The invention aims to provide a cube representation method based on target group identification and form judgment, which improves the representation modes of the relation between targets and target groups on a user interface and improves the experience feeling of a user.
According to the invention, a cube characterization method based on target group identification and morphology judgment is provided, which comprises the following steps:
s100, obtaining a feature matrix A= (a) of the target 1 ,a 2 ,…,a N )，a n For the characteristic value of the nth object, the value range of N is 1 to N, N is the number of objects, a n ＝(a n,1 ,a n,2 ,…,a n,M )，a n,m The value of M is 1 to M, and M is the number of the features corresponding to the object; the features corresponding to the targets include x-coordinate features corresponding to the positions, y-coordinate features corresponding to the positions, time features appearing and affiliated camping features.
S200, traversing A according to mu and a n And a i Acquisition of d n,i ，d n,i A is the difference between the nth target and the ith target i For the eigenvalue of the ith target, i=1, 2, …, N, i+.n, μ is a diagonal matrix of mxm, the p-th row of μ is the element μ of the p-th column p,p P=1, 2, …, M, the weight of the p-th feature of the target.
S300, traversing A, according to d n,i Clustering targets with the same appearance time with a DBSCAN algorithm to obtain a target cluster C= (C) 1 ,c 2 ,…,c J )，c j The value range of J is 1 to J for the J-th target cluster obtained by clustering, and J is the number of target clusters obtained by clustering; each target cluster is a maximum target cluster.
S400, traversing C to obtain C j Corresponding minimum target group c j,min ＝{c 1 j,min ,c 2 j,min ,…,c R j,min }，c r j,min C is j The corresponding R minimum target group has the value range of R from 1 to R, and R is c j The number of corresponding minimum target groups; c j,min Any minimum target group comprises targets which are core point targets, c j,min Any one of the smallest target group and c j,min The distance between any one of the other minimum target groups is larger than eps, which is a distance threshold set when using the DBSCAN algorithm.
S500, traversing C, according to C r j,min Difference between any two targets and c r j,min Position acquisition of target c r j,min The corresponding target group morphology type.
S600, constructing a target cube on a user interface, and representing a target in the target cube, wherein x, y and z axes corresponding to the target cube respectively correspond to x coordinates corresponding to the position of the target, y coordinates corresponding to the position of the target and the time when the target appears; the representation of the object in the object cube comprises: respectively framing each minimum target group in the target cube by using a surrounding frame with a first color, and respectively framing each maximum target group in the target cube by using a surrounding frame with a second color; representing the targets in the minimum target group by using colors corresponding to the corresponding target group morphology types, wherein the colors corresponding to different target group morphology types are different; the difference between any two targets in the same minimum target group is represented in a target cube by using lines with different widths, and the width of the lines is inversely related to the difference.
Compared with the prior art, the method provided by the invention has obvious beneficial effects, can achieve quite technical progress and practicality by virtue of the technical scheme, has wide industrial utilization value, and has at least the following beneficial effects:
the invention quantitatively represents the difference between the targets, and obtains the difference between any two targets according to the characteristic value corresponding to each target; according to the obtained difference between any two targets, the target cluster appearing at the same time is clustered by using a DBSCAN algorithm to obtain a plurality of target clusters, each target cluster is a maximum target cluster, and the minimum target cluster in each target cluster is further obtained. Constructing a target cube, wherein targets are represented, and the difference between two targets corresponding to a connecting line is represented through the width of the connecting line between the two targets in a minimum target group, wherein the larger the difference is, the smaller the relevance is; the difference between the targets in the minimum target group is smaller, and the relevance is tight, so that each minimum target group is used as a minimum unit to perform characterization (frame selection by a first color) in a constructed target cube space; certain relativity exists between each minimum target group in the maximum target groups and between targets which do not belong to any minimum target group and the minimum target groups, and the method is suitable for global relation control, so that each maximum target group is used as an integral unit to be characterized (selected by a second color frame) in a constructed target cube space; therefore, a user can quickly see which targets are likely to be a cooperative unit and the relevance between the targets in the constructed target cube, so that the user experience is improved, and the interpretability of fusion analysis such as subsequent intention judgment, dynamic prediction and the like is also improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a cube identification method based on object group identification and morphology judgment according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a minimum target group of the type of the central target group configuration according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a minimum target group of the edge type target group configuration according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a minimum target group of a distributed target group configuration according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
According to the present invention, there is provided a cube characterization method based on object group identification and morphology judgment, as shown in fig. 1, comprising the steps of:
s100, obtaining a feature matrix A= (a) of the target 1 ,a 2 ,…,a N )，a n For the characteristic value of the nth object, the value range of N is 1 to N, N is the number of objects, a n ＝(a n,1 ,a n,2 ,…,a n,M )，a n,m The value of M is 1 to M, and M is the number of the features corresponding to the object; the target-corresponding features include position-corresponding x-seatsThe standard feature, the y coordinate feature corresponding to the position, the time feature of appearance and the affiliated camping feature.
It should be noted that, in the present invention, the types and the number of features included in each object are not limited, but the number of features included in each object is the same, and the arrangement order of features corresponding to each object is the same, that is, the mth feature corresponding to different objects is the same feature.
As one example, each of the objects of the present invention further includes a type feature and/or a performance feature including at least one of weight, average speed, maximum speed, fire range, and attack intensity, among others. Wherein the types are classified into reconnaissance, hit, replenishment, command, defense, etc., the characteristic values of the corresponding type features of each type are different, for example, the types are respectively e according to the sequence of hit, reconnaissance, command, defense, replenishment -2 、e -1 、e 0 、e 1 、e 2 . When the camping of the target is a cubic camping, a my camping or a friend camping respectively, the characteristic values corresponding to the characteristics of the target are e respectively 1 、e 3 、e 5 。
Those skilled in the art will appreciate that any method of obtaining the feature values corresponding to the above features in the prior art falls within the scope of the present invention.
S200, traversing A according to mu and a n And a i Acquisition of d n,i ，d n,i A is the difference between the nth target and the ith target i For the eigenvalue of the ith target, i=1, 2, …, N, i+.n, μ is a diagonal matrix of mxm, the p-th row of μ is the element μ of the p-th column p,p P=1, 2, …, M, the weight of the p-th feature of the target.
According to the invention, the importance of different features to the judgment target group is different, the weight corresponding to the feature with larger importance is larger, and the weight corresponding to the feature with smaller importance is smaller. The weights corresponding to the features can be preset manually according to the experience values, the range of the weights corresponding to the features is (0, 1), and the sum of the weights corresponding to all the features is 1.
Alternatively, the present invention obtains d based on the mahalanobis distance n,i ，d n,i The following relationship is satisfied:
wherein T is the transpose, Σ A Is the covariance matrix of A, Σ -1 A Is sigma (sigma) A Is a matrix of inverse of (a).
According to the formula, the difference between any two targets can be obtained, and the larger the difference is, the smaller the relevance between the two targets is; the smaller the difference, the greater the correlation between the two targets. Those skilled in the art will appreciate that any method of obtaining the magnitude of the difference between two vectors falls within the scope of the present invention.
S300, traversing A, according to d n,i Clustering targets with the same appearance time with a DBSCAN algorithm to obtain a target cluster C= (C) 1 ,c 2 ,…,c J )，c j The value range of J is 1 to J for the J-th target cluster obtained by clustering, and J is the number of target clusters obtained by clustering; each target cluster is a maximum target cluster.
According to the invention, the time of occurrence of different targets may be the same or different; in order to study the association relation between different targets which appear at the same time, the invention takes the same appearance time as a screening condition for clustering. If the time of the occurrence of the targets corresponding to A is the same, clustering all the targets corresponding to A; if the target corresponding to A appears in a plurality of times, the invention clusters the targets corresponding to A in batches, and the appearance time of each batch of clustered targets is the same.
It should be appreciated that the basic idea of the DBSCAN algorithm is: for each target, a circle with radius as a distance threshold eps is used as a correlation range, and targets with the number of threshold MinPts (not including the target point) more than or equal to the number of threshold MinPts exist in the correlation range as core points; other targets exist in the association range, and the targets with the quantity smaller than MinPts are boundary points; the noise point is the point where no other object exists within the range. Where MinPts and eps are parameters that need to be set in advance when clustering using the DBSCAN algorithm. In order to improve the clustering effect of the invention on the targets with the same occurrence time and improve the accuracy of judging the minimum unit range, preferably, the clustering method for the targets with the same occurrence time by using a DBSCAN algorithm comprises the following steps:
setting MinPts in DBSCAN algorithm: setting k to be [1, M-1]]Acquiring the average difference between each object in the objects with the same appearance time and the corresponding k objects with the smallest difference, and acquiring the sum dis of the average differences corresponding to all objects in the objects with the same appearance time k The method comprises the steps of carrying out a first treatment on the surface of the For k to [1, M-2]]Acquiring slope
Setting k corresponding to the maximum slope as MinPts; dis (dis) k+1 And (3) adding the first average differences corresponding to all the targets in the targets with the same appearance time, wherein the first average differences are the average differences between the targets and the targets with the smallest corresponding k+1 differences.
It should be understood that the setting k belongs to [1, M-1], i.e. k=1, 2, …, M-1; k belongs to [1, M-2], i.e. k=1, 2, …, M-2. And for the b-th target in the targets with the same appearance time, the average difference between the b-th target and the corresponding k targets with the smallest difference is the average value of the differences between the first k targets with the smallest difference with the b-th target in the targets with the same appearance time. And for the b-th target in the targets with the same appearance time, the average difference between the b-th target and the corresponding k+1-th target with the smallest difference is the average value of the differences between the k+1-th target and the b-th target with the smallest difference in the targets with the same appearance time.
Setting eps in DBSCAN algorithm: acquiring the differential change s of each of the targets having the same appearance time b ＝(d b,MinPts+1 -d b,MinPts )/d b,MinPts ，d b,MinPts+1 D, for the average difference between the b-th target and the corresponding MinPts+1 least-different target b,MinPts Average variability for the b-th target and the corresponding min pts least-different targets; the average difference between the target corresponding to the greatest differential variation and the target with the smallest differential of the corresponding MinPts is set as eps.
After MinPts and eps are determined, clustering can be performed by taking the difference between any two targets as the distance between the two targets in a DBSCAN algorithm. The clustering process using the DBSCAN algorithm is a prior art, and will not be described in detail here.
S400, traversing C to obtain C j Corresponding minimum target group c j,min ＝{c 1 j,min ,c 2 j,min ,…,c R j,min }，c r j,min C is j The corresponding R minimum target group has the value range of R from 1 to R, and R is c j The number of corresponding minimum target groups; c j,min Any minimum target group comprises targets which are core point targets, c j,min Any one of the smallest target group and c j,min The distance between any one of the other minimum target groups is larger than eps, which is a distance threshold set when using the DBSCAN algorithm.
The core point target is a target determined to be a core point in the DBSCAN algorithm. The number of the minimum target groups included in one target cluster may not be unique, and if a certain core point target is in the association range of another core point target, the two core point targets belong to the same minimum target group; otherwise, the two core point targets do not belong to the same minimum target group; traversing all core point targets in the maximum target group to obtain the minimum target group in the maximum target group.
S500, traversing C, according to C r j,min Difference between any two targets and c r j,min Position acquisition of target c r j,min The corresponding target group morphology type.
Preferably, the purpose isThe target group morphology type is a central target group morphology, an edge target group morphology or a distributed target group morphology. Important targets in the minimum target group with the type of the central target group form are positioned in the center of the target group and are commonly found in guard formations; important targets in the minimum target group with the edge type target group form are located at edges and are commonly found in cooperative attack; the correlation among the targets in the minimum target group with the type of the distributed target group morphology does not have significant difference, and is commonly found in daily formations, as shown in fig. 2-4, circles in the figures represent targets, and the width of a connecting line between the targets represents the difference between the targets. The said method according to c r j,min Difference between any two targets and c r j,min Position acquisition of target c r j,min The corresponding target group morphology type comprises:
s510 according to c r j,min Differential acquisition between any two targets c r j,min Average of the differences between each target and the other targets.
S520, for c r j,min The average value of the differences between each target and other targets is obtained by using a quartile drawing box type graph, the upper quartile and the lower quartile are obtained, the lower edge is the lower quartile minus 1.5 times of the box length, and the box length is the upper quartile minus the lower quartile.
It should be understood that c r j,min The average value of the differences between all targets and other targets is arranged from small to large and divided into four equal parts, wherein the average value of the differences at three dividing point positions is quartile, the upper quartile refers to the average value of the larger differences in the three dividing point positions, and the lower quartile refers to the average value of the smaller differences in the three dividing point positions.
S530, if there is no object outside the lower edge, determining c r j,min Is a distributed target group form; otherwise, S540 is entered.
S540, taking the target with the minimum average value as a center target, taking c as the center target r j,min Any other than a central targetThree targets form a target group, a triangle formed by connecting lines among the targets in each target group is obtained, and if the central target is positioned in the triangle formed by any target group, c is determined r j,min Is in a central target group form; otherwise, judge c r j,min Is in the form of an edge type target group.
S600, constructing a target cube on a user interface, and representing a target in the target cube, wherein x, y and z axes corresponding to the target cube respectively correspond to x coordinates corresponding to the position of the target, y coordinates corresponding to the position of the target and the time when the target appears; the representation of the object in the object cube comprises: respectively framing each minimum target group in the target cube by using a surrounding frame with a first color, and respectively framing each maximum target group in the target cube by using a surrounding frame with a second color; representing the targets in the minimum target group by using colors corresponding to the corresponding target group morphology types, wherein the colors corresponding to different target group morphology types are different; the difference between any two targets in the same minimum target group is represented in a target cube by using lines with different widths, and the width of the lines is inversely related to the difference.
The z axis of the target cube is the time when the target appears, so that the target cube characterizes the minimum target group and the maximum target group corresponding to different time, and a user can know the evolution rule of the minimum target group and the maximum target group along with time based on the target cube.
Preferably, the expressing the target in the target cube further includes: setting the color of a central target in the smallest target group with the target group morphology type being the central target group morphology or the edge target group morphology to be different from the color of a non-central target in the smallest target group. Therefore, the user rapidly identifies the important target in the smallest target group with the target group form type being the central target group form or the edge target group form.
Preferably, the expressing the target in the target cube further includes: any two targets which do not belong to the same minimum target group are connected through a line, and the width of the line is in negative correlation with the difference between the two corresponding targets. Thus, the user can also quickly acquire the magnitude of the association between targets appearing at different times.
The invention quantitatively represents the difference between the targets, and obtains the difference between any two targets according to the characteristic value corresponding to each target; according to the obtained difference between any two targets, the target cluster appearing at the same time is clustered by using a DBSCAN algorithm to obtain a plurality of target clusters, each target cluster is a maximum target cluster, and the minimum target cluster in each target cluster is further obtained. Constructing a target cube, wherein targets are represented, and the difference between two targets corresponding to a connecting line is represented through the width of the connecting line between the two targets in a minimum target group, wherein the larger the difference is, the smaller the relevance is; the difference between the targets in the minimum target group is smaller, and the relevance is tight, so that each minimum target group is used as a minimum unit to perform characterization (frame selection by a first color) in a constructed target cube space; certain relativity exists between each minimum target group in the maximum target groups and between targets which do not belong to any minimum target group and the minimum target groups, and the method is suitable for global relation control, so that each maximum target group is used as an integral unit to be characterized (selected by a second color frame) in a constructed target cube space; therefore, a user can quickly see which targets are likely to be a cooperative unit and the relevance between the targets in the constructed target cube, so that the user experience is improved, and the interpretability of fusion analysis such as subsequent intention judgment, dynamic prediction and the like is also improved.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (7)
1. The cube identification method based on target group identification and morphology judgment is characterized by comprising the following steps of:
s100, obtaining a feature matrix A= (a) of the target 1 ,a 2 ,…,a N )，a n For the characteristic value of the nth object, the value range of N is 1 to N, N is the number of objects, a n ＝(a n,1 ,a n,2 ,…,a n,M )，a n,m The value of M is 1 to M, and M is the number of the features corresponding to the object; the features corresponding to the targets comprise x-coordinate features corresponding to the positions, y-coordinate features corresponding to the positions, time features appearing and affiliated array features;
s200, traversing A according to mu and a n And a i Acquisition of d n,i ，d n,i A is the difference between the nth target and the ith target i For the eigenvalue of the ith target, i=1, 2, …, N, i+.n, μ is a diagonal matrix of mxm, the p-th row of μ is the element μ of the p-th column p,p The weight of the p-th feature of the target, p=1, 2, …, M;
s300, traversing A, according to d n,i Clustering targets with the same appearance time with a DBSCAN algorithm to obtain a target cluster C= (C) 1 ,c 2 ,…,c J )，c j The value range of J is 1 to J for the J-th target cluster obtained by clustering, and J is the number of target clusters obtained by clustering; each target cluster is a maximum target cluster;
s400, traversing C to obtain C j Corresponding minimum target group c j,min ＝{c 1 j,min ,c 2 j,min ,…,c R j,min }，c r j,min C is j The corresponding R minimum target group has the value range of R from 1 to R, and R is c j The number of corresponding minimum target groups; c j,min Any minimum target group comprises targets which are core point targets, c j,min Any one of the smallest target group and c j,min The distance between any one of the other minimum target groups is larger than eps, and eps is a distance threshold value set when the DBSCAN algorithm is used;
s500, traversing C, according to C r j,min Difference between any two targets and c r j,min Position acquisition of target c r j,min A corresponding target group morphology type;
s600, constructing a target cube on a user interface, and representing a target in the target cube, wherein x, y and z axes corresponding to the target cube respectively correspond to x coordinates corresponding to the position of the target, y coordinates corresponding to the position of the target and the time when the target appears; the representation of the object in the object cube comprises: respectively framing each minimum target group in the target cube by using a surrounding frame with a first color, and respectively framing each maximum target group in the target cube by using a surrounding frame with a second color; representing the targets in the minimum target group by using colors corresponding to the corresponding target group morphology types, wherein the colors corresponding to different target group morphology types are different; the difference between any two targets in the same minimum target group is represented in a target cube by using lines with different widths, and the width of the lines is inversely related to the difference.
2. The method according to claim 1, wherein in S500, the target group morphology type is a center target group morphology, an edge target group morphology, or a distributed target group morphology, and the method is based on c r j,min Difference between any two targets and c r j,min Position acquisition of target c r j,min The corresponding target group morphology type comprises:
s510 according to c r j,min Differential acquisition between any two targets c r j,min An average of the differences between each target and the other targets;
s520, for c r j,min Drawing a box graph by using quartiles to obtain an upper quartile and a lower quartile, wherein the lower edge is the lower quartile minus 1.5 times of the box length, and the box length is the upper quartile minus the lower quartile;
s530, if there is no object outside the lower edge, determining c r j,min Is a distributed target group form; otherwise, enter S540;
s540, taking the target with the minimum average value as a center target, taking c as the center target r j,min Any three targets except the central target form a target group, a triangle formed by connecting lines among the targets in each target group is obtained, and if the central target is positioned in the triangle formed by any target group, c is determined r j,min Is in a central target group form; otherwise, judge c r j,min Is in the form of an edge type target group.
3. The method of cubic identification based on object group identification and morphology judgment according to claim 1, wherein in S300, according to d n,i Clustering targets with the same appearance time by using a DBSCAN algorithm, wherein the clustering method comprises the following steps:
setting MinPts in DBSCAN algorithm: setting k to be [1, M-1]]Acquiring the average difference between each object in the objects with the same appearance time and the corresponding k objects with the smallest difference, and acquiring the sum dis of the average differences corresponding to all objects in the objects with the same appearance time k The method comprises the steps of carrying out a first treatment on the surface of the For k to [1, M-2]]Acquiring slope
Setting k corresponding to the maximum slope as MinPts; dis (dis) k+1 The first average difference corresponding to all targets in the targets with the same appearance time is the sum of the first average differences between the targets and the targets with the smallest corresponding k+1 differences;
setting eps in DBSCAN algorithm: acquiring the differential change s of each of the targets having the same appearance time b ＝(d b,MinPts+1 -d b,MinPts )/d b,MinPts ，d b,MinPts+1 D, for the average difference between the b-th target and the corresponding MinPts+1 least-different target b,MinPts Average variability for the b-th target and the corresponding min pts least-different targets; the average difference between the target corresponding to the greatest differential variation and the target with the smallest differential of the corresponding MinPts is set as eps.
4. The method of cubic characterization based on object group identification and morphology judgment according to claim 1, wherein in S100, the characteristics corresponding to the object further include performance characteristics including at least one of weight, average speed, maximum speed, fire range, and attack intensity.
5. The method for identifying and determining a cube based on object group identification and morphology according to claim 1, wherein in S600, the identifying the object in the object cube further comprises: any two targets which do not belong to the same minimum target group are connected through a line, and the width of the line is in negative correlation with the difference between the two corresponding targets.
6. The method for identifying and determining a cube based on object group as claimed in claim 2, wherein in S600, the identifying the object in the object cube further comprises: the color of the center target in the smallest target group whose target group morphology type is the center target group morphology or the edge target group morphology is set to a different color from the non-center target color.
7. The method of cubic identification based on object group identification and morphology judgment according to claim 1, wherein in S200, the target group identification and morphology judgment is based on μ, a n And a i Acquisition of d n,i Comprising: d, d n,i The following relationship is satisfied:
wherein T is the transpose, Σ A Is the covariance matrix of A, Σ -1 A Is sigma (sigma) A Is a matrix of inverse of (a).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211635620.3A CN116012629B (en) | 2022-12-19 | 2022-12-19 | Cube characterization method based on target group identification and morphology judgment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211635620.3A CN116012629B (en) | 2022-12-19 | 2022-12-19 | Cube characterization method based on target group identification and morphology judgment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116012629A true CN116012629A (en) | 2023-04-25 |
| CN116012629B CN116012629B (en) | 2023-06-13 |
Family
ID=86034718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211635620.3A Active CN116012629B (en) | 2022-12-19 | 2022-12-19 | Cube characterization method based on target group identification and morphology judgment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116012629B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6483940B1 (en) * | 1999-02-12 | 2002-11-19 | Institute For Information Industry | Method for dividing image |
| CN111783020A (en) * | 2020-07-22 | 2020-10-16 | 中国人民解放军海军航空大学 | Multidimensional characteristic battlefield entity target grouping method and system |
| CN114625943A (en) * | 2020-12-10 | 2022-06-14 | 中国人民解放军93216部队 | Group relation identification method and system |
-
2022
- 2022-12-19 CN CN202211635620.3A patent/CN116012629B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6483940B1 (en) * | 1999-02-12 | 2002-11-19 | Institute For Information Industry | Method for dividing image |
| CN111783020A (en) * | 2020-07-22 | 2020-10-16 | 中国人民解放军海军航空大学 | Multidimensional characteristic battlefield entity target grouping method and system |
| CN114625943A (en) * | 2020-12-10 | 2022-06-14 | 中国人民解放军93216部队 | Group relation identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 张松良;王付明;鲁柯;谢永生;: "城市战场目标分群的组合聚类方法", 指挥控制与仿真, no. 05 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116012629B (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993748B (en) | Three-dimensional grid object segmentation method based on point cloud processing network | |
| Lin et al. | Ship detection with superpixel-level Fisher vector in high-resolution SAR images | |
| CN104834922B (en) | Gesture identification method based on hybrid neural networks | |
| Sanguinetti et al. | Automatic determination of the number of clusters using spectral algorithms | |
| CN108363970A (en) | A kind of recognition methods of fingerling class and system | |
| CN104778242A (en) | Hand-drawn sketch image retrieval method and system on basis of image dynamic partitioning | |
| CN110232390B (en) | Method for extracting image features under changed illumination | |
| CN107341813A (en) | SAR image segmentation method based on structure learning and sketch characteristic inference network | |
| CN117690030B (en) | Multi-face flower identification method and system based on image processing | |
| CN111860359B (en) | Point cloud classification method based on improved random forest algorithm | |
| CN111709426B (en) | Diatom recognition method based on contour and texture | |
| CN116503575A (en) | Method for graphically generating high-quality building model and electronic equipment | |
| Naeini et al. | Improving the dynamic clustering of hyperspectral data based on the integration of swarm optimization and decision analysis | |
| CN109271544B (en) | Method and device for automatically selecting painter representatives | |
| CN116012629B (en) | Cube characterization method based on target group identification and morphology judgment | |
| CN112232181B (en) | Eagle eye color cognitive antagonism mechanism-simulated unmanned aerial vehicle marine target detection method | |
| CN110955809B (en) | High-dimensional data visualization method supporting topology structure maintenance | |
| CN105844299B (en) | A kind of image classification method based on bag of words | |
| EP1032918A1 (en) | Data decomposition/reduction method for visualizing data clusters/sub-clusters | |
| Pandey et al. | A hierarchical clustering approach for image datasets | |
| CN105069475B (en) | The image processing method of view-based access control model attention mechanism model | |
| CN110414379A (en) | In conjunction with the building extraction algorithm of elevation map Gabor textural characteristics and LiDAR point cloud feature | |
| CN115049828A (en) | Underwater sonar image target segmentation method based on self-adjusting spectral clustering and entropy weight method | |
| CN114092486A (en) | Automatic segmentation method and device for image texture background | |
| CN113963178A (en) | Method, device, equipment and medium for detecting infrared dim and small target under ground-air background |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |