Observation target association method, device, electronic device, storage medium and program product

Abstract

The present disclosure provides an observation target association method, device, electronic device, storage medium and program product. The observation target association method includes: obtaining positioning information of targets observed by observation payloads mounted on multiple satellite platforms; determining the target positioning deviation between any two satellite platforms where the observation payloads are located based on the obtained target positioning information; determining the target association matrix between any two observation payloads based on the target positioning deviation between the satellite platforms where the observation payloads are located; constructing an undirected weighted graph based on the target association matrix between any two observation payloads; identifying at least one group of interrelated targets based on the undirected weighted graph, wherein multiple targets in each group of interrelated targets are respectively observed by different observation payloads and correspond to the same actual object.

Description

Technical Field

[0001] The present disclosure generally relates to the field of multi-source information processing technology, and more specifically, to an observation target association method, device, electronic device, storage medium and program product. Background Art

[0002] With the continuous development of space Internet technology and satellite remote sensing technology, multi-satellite joint earth observation has become an emerging means of observation. Different satellite platforms can mount different sensors to obtain ground target information from different dimensions, and complete information aggregation through the intersatellite Internet, so as to achieve high-precision detection and identification of ground targets based on multi-source and multi-system information fusion. Commonly used payloads include AIS, optical, infrared, SAR and other types of payloads. AIS mainly detects AIS signals sent by ships. After demodulation, it can obtain the ship's unique number (MMSI number), International Maritime Organization (IMO) identification code, longitude and latitude, ship type, length, width and other information. Ship target detection and identification can be carried out based on the imaging data obtained by optical, infrared, SAR and other types of payloads, and target positioning can be achieved through on-orbit positioning technology. Although through some fine processing, the length, width and other geometric information of the target can also be obtained from the optical, infrared and SAR payload data, but its accuracy depends on the algorithm, and is easily affected by the wake, waves, resolution, etc., and there are large differences between payloads.

[0003] Due to the influence of satellite platform sensors and positioning algorithm accuracy, there will be a certain offset between the target positioning of the satellite platform and the actual position of the actual object corresponding to the target. Especially when detecting and identifying ships on the sea surface, due to the lack of obvious ground reference, it is difficult to align multiple targets corresponding to the same actual object observed by different payloads. In addition, due to the influence of payload detection capability, observation range, processing capability, etc., the number of targets observed by different payloads in the same sea area may be different, and there may be certain false alarms, which brings great difficulties to the association of multi-source targets. Summary of the invention

[0004] The exemplary embodiments of the present disclosure provide an observation target association method, device, electronic device, storage medium and program product, which can conveniently and effectively realize target association based on multi-satellite and multi-system collaborative observation.

[0005] According to a first aspect of an embodiment of the present disclosure, an observation target association method is provided, the observation target association method comprising: obtaining positioning information of targets observed by observation payloads mounted on multiple satellite platforms; determining the target positioning deviation between any two satellite platforms where the observation payloads are located based on the obtained target positioning information; determining a target association matrix between any two observation payloads based on the target positioning deviation between the satellite platforms where the observation payloads are located; constructing an undirected weighted graph based on the target association matrix between any two observation payloads; and identifying at least one group of interrelated targets based on the undirected weighted graph, wherein multiple targets in each group of interrelated targets are respectively observed by different observation payloads and correspond to the same actual object.

[0006] Optionally, the step of determining the target positioning deviation between the satellite platforms where any two observation payloads are located based on the acquired target positioning information includes: dividing the targets observed by each observation payload into a group of targets, and obtaining groups of targets corresponding to each observation payload one-to-one; dividing the positioning information of each group of targets into a group of positioning information, and obtaining groups of positioning information corresponding to each observation payload one-to-one; for any two observation payloads, based on the two groups of positioning information corresponding to the any two observation payloads, determining the deviation information in the overall positioning between the two groups of targets corresponding to the any two observation payloads, and determining the deviation information as the target positioning deviation between the satellite platforms where the any two observation payloads are located.

[0007] Optionally, the step of determining the target association matrix between any two observation payloads based on the target positioning deviation between the satellite platforms where any two observation payloads are located includes: converting the positioning information of each target observed by one of the any two observation payloads into positioning information on the satellite platform where the other of the any two observation payloads is located, according to the target positioning deviation between the satellite platforms where the any two observation payloads are located; determining the target association matrix between the any two observation payloads based on the gap between the converted positioning information and the positioning information of each target observed by the other observation payload; wherein the element in the kth row and sth column of the target association matrix between the any two observation payloads represents the possibility of mutual association between the kth target observed by the one observation payload and the sth target observed by the other observation payload.

[0008] Optionally, the step of constructing an undirected weighted graph based on the target association matrix between the two observed loads includes: constructing a first point set and a second point set, wherein each point included in the first point set corresponds one-to-one to each target observed by each observed load, and the second point set includes multiple virtual terminal points; if it is determined based on the target association matrix between the two observed loads that the possibility of any two targets being correlated is higher than a preset threshold, then constructing an edge between two points representing the two targets, and setting the weight of the edge based on the possibility of the two targets being correlated; for each point in the first point set , respectively at this point and each point in the second point set Build an edge between them and determine the weight of the edge, where if i=j, or and If they are not observed by the same observation load, the weight of the edge is set to the first weight, otherwise the weight of the edge is set to the second weight.

[0009] Optionally, the step of identifying at least one group of interconnected targets based on the undirected weighted graph includes: constructing an energy function about the cost of marking points in the first point set as points in the second point set based on the undirected weighted graph; and determining multiple observation targets corresponding to multiple points with the same mark when the energy function takes the minimum value as a group of interconnected targets.

[0010] Optionally, the energy function is:

[0011] ,

[0012] Wherein, V represents the first point set, E represents the edge set of the undirected weighted graph, represents a point in the first point set Mark as point The price, , represents the second point set, Indicate point and Point The edge between Indicate point and Point Marked as and The price, and The method is determined based on the weights of the edges in the undirected weighted graph.

[0013] According to a second aspect of an embodiment of the present disclosure, an observation target association device is provided, and the observation target association device includes: a position information acquisition unit, configured to acquire positioning information of targets observed by observation payloads mounted thereon from multiple satellite platforms; a positioning deviation determination unit, configured to determine the target positioning deviation between any two satellite platforms where the observation payloads are located based on the acquired target positioning information; an association matrix determination unit, configured to determine the target association matrix between any two observation payloads based on the target positioning deviation between the satellite platforms where the observation payloads are located; a graph construction unit, configured to construct an undirected weighted graph based on the target association matrix between any two observation payloads; and an association identification unit, configured to identify at least one group of interrelated targets based on the undirected weighted graph, wherein multiple targets in each group of interrelated targets are respectively observed by different observation payloads and correspond to the same actual object.

[0014] According to a third aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium storing instructions, which, when executed by a processor of an electronic device, enables the electronic device to execute the observation target association method as described above.

[0015] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: at least one processor; and at least one memory storing computer executable instructions, wherein the computer executable instructions, when executed by the at least one processor, prompt the at least one processor to execute the observation target association method as described above.

[0016] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product, comprising computer executable instructions, which, when executed by at least one processor, implement the observation target association method as described above.

[0017] According to the exemplary embodiments of the present disclosure, the observation target association method, device, electronic device, storage medium and program product can effectively realize target association based on multi-satellite and multi-system collaborative observation, and the calculation complexity is low, which is suitable for rapid processing on orbit.

[0018] In the following description, some aspects and / or advantages of the general inventive concept will be set forth, and some other aspects and / or advantages will be known through the following description or the implementation of the general inventive concept. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] These and / or other aspects and advantages of the present application will become clearer and easier to understand from the following detailed description of the embodiments of the present application in conjunction with the accompanying drawings, in which:

[0020] Figure 1A flowchart showing an observation target association method according to an exemplary embodiment of the present disclosure;

[0021] Figure 2 A flow chart showing a method for determining a target positioning deviation between satellite platforms where any two observation payloads are located according to an exemplary embodiment of the present disclosure;

[0022] Figure 3 A flowchart showing a method for determining a target correlation matrix between any two observed loads according to an exemplary embodiment of the present disclosure;

[0023] Figure 4 A flowchart showing a method for constructing an undirected weighted graph based on a target association matrix between two observed loads according to an exemplary embodiment of the present disclosure;

[0024] Figure 5 A flowchart showing a method for identifying at least one group of interrelated targets based on an undirected weighted graph according to an exemplary embodiment of the present disclosure;

[0025] Figure 6 A structural block diagram showing an observation target association device according to an exemplary embodiment of the present disclosure is shown;

[0026] Figure 7 A structural block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0027] Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like parts throughout. The embodiments will be described below with reference to the drawings in order to explain the present disclosure.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0029] It should be noted that the phrase "at least one of the items" in the present disclosure includes three types of parallel situations: "any one of the items", "a combination of any number of the items", and "all of the items". For example, "including at least one of A and B" includes the following three types of parallel situations: (1) including A; (2) including B; (3) including A and B. Another example is "executing at least one of step 1 and step 2" which means the following three types of parallel situations: (1) executing step 1; (2) executing step 2; (3) executing step 1 and step 2.

[0030] The present application belongs to the field of target detection, remote sensing multi-source target association, and multi-source information fusion, and in particular, it relates to a target association method based on multi-satellite and multi-system collaborative observation. As an example, the application background can be that multiple satellites carrying observation payloads of different systems simultaneously or in relay along their respective orbits through means such as side swing to coordinate observation of the same field (for example, sea area), and the observation time is not much different; the relative positions between multiple actual objects in the collaborative observation time domain and sea area are basically stable; after different payloads obtain data, the actual object (for example, ship) is detected, identified and positioned based on the computing platform of the satellite, and target information including longitude and latitude is generated; after the data processing of each payload is completed, the target information can be transmitted to the same computing platform through the intersatellite Internet. The satellite platform collects and aggregates the target information processed by each satellite, and establishes the target correspondence relationship (that is, the mutual correlation relationship) between different payloads based on the existing target information. For example, for the same actual object (vessel A), payload 1 observes the actual object and marks it as target B, and payload 2 also observes the actual object and marks it as target C. Since there is a certain offset between the positioning of the target by the satellite platform and the actual position of the actual object corresponding to the target (i.e., there is a certain positioning error in the satellite platform (e.g., the on-orbit positioning system)), the positioning information of target B given by satellite platform 1 where payload 1 is located and the positioning information of target C given by satellite platform 2 where payload 2 is located may be different. Therefore, it is difficult to directly align multiple targets (i.e., target B and target C) corresponding to the same actual object observed by different payloads through positioning information. This requires accurately identifying targets B and C as being mutually correlated with each other corresponding to the same actual object based on the positioning information of target B and the positioning information of target C. This application focuses on how to establish multi-source target association after the information on each satellite is gathered in the context of multi-satellite collaborative observation and distributed processing. In order to achieve this goal, based on the positioning error of satellites (for example, on-orbit positioning systems), a correlation technology based on position topology is designed for the load characteristic target information obtained by multi-satellite distributed processing. It can realize cross-system multi-target association such as AIS, optical, SAR, infrared, etc., and establish a unified data foundation for subsequent multi-source fusion identification. This technology is simple and effective, with low computational complexity, and is suitable for rapid on-orbit processing. The following will be combined with Figures 1 to 7 Provide detailed explanation.

[0031] Figure 1 A flow chart of an observation target association method according to an exemplary embodiment of the present disclosure is shown. As an exemplary embodiment, the observation target association method can be implemented by a computer program, for example, the observation target association method can be executed by application software installed in an electronic device (eg, a computing platform).

[0032] Reference Figure 1 In step S100, positioning information of targets observed by observation payloads mounted thereon is obtained from multiple satellite platforms.

[0033] As an exemplary embodiment, step S100 may include: receiving positioning information of targets observed by observation payloads mounted on the satellite platforms and sent by the satellite platforms from the multiple satellite platforms.

[0034] As an exemplary embodiment, the type of observation payload may include, but is not limited to, at least one of the following: AIS, optical, infrared, SAR.

[0035] As an exemplary embodiment, the positioning information of the target may include but is not limited to the geographic coordinate information of the target. As an example, the geographic coordinate information of the target may specifically be the latitude and longitude coordinates of the target.

[0036] In step S200, based on the acquired positioning information of the target, the target positioning deviation between any two satellite platforms where the observation payloads are located is determined.

[0037] The target positioning deviation between any two satellite platforms where observation payloads are located (for example, the positioning systems of satellite platforms) can be understood as: for the same actual object, the deviation between the positioning of the actual object by the satellite platforms where the two observation payloads are located. For example, for the same actual object (vessel A), payload 1 observes the actual object and marks it as target B, and payload 2 also observes the actual object and marks it as target C. The deviation between the positioning information of target B given by satellite platform 1 where payload 1 is located and the positioning information of target C given by satellite platform 2 where payload 2 is located, that is, the target positioning deviation between satellite platform 1 and satellite platform 2 where payload 1 and payload 2 are located.

[0038] As an exemplary embodiment, the target positioning deviation between the satellite platforms where the i-th observation payload and the j-th observation payload are located may include: the rotation matrix and translation vector .

[0039] As an exemplary embodiment, step S200 may include: grouping the positioning information of the target obtained from multiple satellite platforms according to the payload to obtain multiple groups of positioning information; then, based on the obtained multiple groups of positioning information, determining the target positioning deviation between any two satellite platforms where the observation payloads are located.

[0040] As an example, ,in, represents the i-th group of positioning information, m represents the total number of payloads participating in information aggregation, (e.g., greater than or equal to 2) represents the total number of targets observed by load i, Represents the positioning information of the jth target observed by payload i.

[0041] The following will be combined Figure 2 A specific exemplary embodiment of step S200 is described below, which will not be expanded here.

[0042] In step S300, a target correlation matrix between any two observation payloads is determined according to the target positioning deviation between the satellite platforms where any two observation payloads are located.

[0043] As an exemplary embodiment, the element in the kth row and sth column of the target correlation matrix between any two observation loads represents the possibility that the kth target observed by one observation load is correlated with the sth target observed by the other observation load.

[0044] The following will be combined Figure 3 A specific exemplary embodiment of step S300 is described below, which will not be expanded here.

[0045] In step S400, an undirected weighted graph is constructed based on the target association matrix between the two observed loads.

[0046] As an exemplary embodiment, step S400 may include: integrating the target association matrix between the two observed loads to establish the target association matrix of all loads; and then constructing an undirected weighted graph based on the target association matrix of all loads.

[0047] The following will be combined Figure 4 A specific exemplary embodiment of step S400 is described below, which will not be expanded here.

[0048] In step S500, at least one group of interrelated targets is identified based on the undirected weighted graph.

[0049] The multiple targets in each group of interrelated targets are respectively observed by different observation payloads and correspond to the same actual object. In other words, the multiple targets corresponding to the same actual object observed by different payloads constitute a group of interrelated targets.

[0050] As an exemplary embodiment, step S500 may include: constructing an energy function based on an undirected weighted graph, and determining the at least one set of interrelated targets by solving the minimum value of the energy function. As an example, the minimum value of the energy function may be solved by a multi-way graph cut algorithm (e.g., a minimum multi-way graph cut algorithm).

[0051] The following will be combined Figure 5 A specific exemplary embodiment of step S500 is described below, which will not be expanded here.

[0052] Figure 2 A flow chart showing a method for determining a target positioning deviation between satellite platforms where any two observation payloads are located according to an exemplary embodiment of the present disclosure.

[0053] Reference Figure 2 In step S201, the targets observed by each observation load are divided into a group of targets to obtain groups of targets corresponding to each observation load.

[0054] In step S202, the positioning information of each group of targets is divided into a group of positioning information, and each group of positioning information corresponding to each observation payload is obtained.

[0055] In step S203, for any two observation payloads, based on the two sets of positioning information corresponding to the any two observation payloads, the deviation information in the overall positioning between the two sets of targets corresponding to the any two observation payloads is determined, and the deviation information is determined as the target positioning deviation between the satellite platforms where the any two observation payloads are located.

[0056] The present application takes into account that the positioning information of the target observed by any observation payload will change due to the motion of the actual object to which it corresponds, but usually the relative positions of multiple targets observed by the observation payload do not change much (it can be understood that the overall shape of the multiple targets observed does not change much), and most of the target positioning errors of the satellite platform belong to systematic errors, that is, when each satellite observes simultaneously or relays at short time intervals, the two groups of targets given by the two satellite platforms differ by a basically consistent rotation and translation within the observed time domain and field. Therefore, based on this characteristic, the present application proposes to use the overall position relative deviation between the two groups of targets as the target positioning deviation between the corresponding satellite platforms where the two observation payloads are located. For example, the overall position relative deviation between the two groups of targets can be represented by a rotation matrix and a translation vector, that is, the overall position of one group of targets can basically match the overall position of the other group of targets after corresponding rotation and translation.

[0057] As an exemplary embodiment, Ransac may be used to estimate the overall relative position deviation between two groups of targets.

[0058] Figure 3A flow chart showing a method for determining a target correlation matrix between any two observed loads according to an exemplary embodiment of the present disclosure.

[0059] Reference Figure 3 In step S301, the positioning information of each target observed by one observation payload (hereinafter also referred to as the first observation payload) of any two observation payloads is converted into the positioning information under the satellite platform where the other observation payload (hereinafter also referred to as the second observation payload) of the any two observation payloads is located according to the target positioning deviation between the satellite platforms where the any two observation payloads are located.

[0060] In other words, based on the positioning information of each target observed by the first observation payload (that is, the positioning information given by the satellite platform where the second observation payload is located for the target) and the target positioning deviation between the satellite platforms where the first observation payload and the second observation payload are located, the positioning information that the satellite platform where the second observation payload is located will give for each of the above targets is estimated.

[0061] As an example, you can use Transform the longitude and latitude coordinates of each target observed by payload i to the positioning system coordinate system corresponding to payload j. yes The matrix composed of the latitude and longitude coordinates of the target in, where yes The corresponding longitude and latitude coordinate column vector is transformed into the coordinates of the positioning system coordinate system corresponding to the load j through the following transformation :

[0062] .

[0063] In step S302, based on the difference between the converted positioning information and the positioning information of each target observed by the second observation payload, a target correlation matrix between any two observation payloads (ie, the first observation payload and the second observation payload) is determined.

[0064] As an exemplary embodiment, the element of the kth row and sth column in the target association matrix between any two observation payloads represents the possibility of correlation between the kth target observed by the first observation payload and the sth target observed by the second observation payload. As an example, the value of the element of the kth row and sth column in the target association matrix can be obtained based on the following difference: the difference (e.g., Euclidean distance) between the positioning information of the kth target observed by the first observation payload converted into the positioning information under the satellite platform where the second observation payload is located and the positioning information of the sth target observed by the second observation payload.

[0065] As an example, , The target correlation matrix corresponding to the two groups The value of the element in row k and column s Target-based and The specific calculation is as follows:

[0066] ,

[0067] in, It represents the positioning information of the kth target observed by the observation payload i converted into the positioning information of the satellite platform where the observation payload j is located. It represents the positioning information of the sth target observed by the observation payload j. d is the error threshold, which can be set according to the actual situation. Two targets whose distance is less than d can be considered to have potential association.

[0068] According to an exemplary embodiment of the present disclosure, coordinate transformation is performed according to the target positioning deviations corresponding to the two observation payloads to align the two groups of targets, and then the distance between the two groups of targets after alignment is calculated, thereby obtaining a target association matrix between the two observation payloads.

[0069] In addition, it can be seen from the calculation process of the target association matrix that .

[0070] As an example, let , .

[0071] As an exemplary embodiment, the target correlation matrix between the two observed loads can be integrated to establish the target correlation matrix of all loads. The target correlation matrix P of all loads is constructed as follows:

[0072] P= .

[0073] Figure 4 The following illustrates an exemplary embodiment of the present disclosure, wherein an undirected weighted graph G is constructed based on a target correlation matrix between two observation loads. , E) Flowchart of the method.

[0074] Reference Figure 4 , in step S401, a first point set V and a second point set L are constructed.

[0075] Each point included in the first point set corresponds one-to-one to each target observed by each observation payload, and the second point set includes multiple virtual terminal points.

[0076] As an example, the first point set V = { , , }, the second point set L={ , , , , } is a set of virtual terminal points, where is the total number of points in V; E is the edge set of graph G, that is, , is the edge connecting point s and point t.

[0077] In step S402, if it is determined that the possibility of mutual correlation between any two targets is higher than a preset threshold based on the target correlation matrix between the pairwise observed loads, an edge is constructed between two points representing the any two targets, and the weight of the edge is set based on the possibility of mutual correlation between the any two targets.

[0078] As an exemplary embodiment, any , if the corresponding elements in the target correlation matrix P of all loads >0, then the edge can be constructed , with weights .

[0079] In step S403, for each point in the first point set , respectively at this point and each point in the second point set Build an edge between them and determine the weight of the edge.

[0080] As an exemplary embodiment, if i=j, or and If the edge is observed by different observation loads (i.e., not in the same group), the weight of the edge is set to the first weight; otherwise, the weight of the edge is set to the second weight.

[0081] As an example, connect each point in V to all points in L to construct edges , weight The settings are as follows:

[0082] ,

[0083] in, It can be set to a smaller weight, such as 1; It can be set to a larger weight, such as 1000.

[0084] Figure 5 A flowchart of a method for identifying at least one group of interrelated targets based on an undirected weighted graph according to an exemplary embodiment of the present disclosure is shown.

[0085] Reference Figure 5In step S501, based on the undirected weighted graph, an energy function of the cost of marking points in the first point set as points in the second point set is constructed.

[0086] In step S502, multiple observation targets corresponding to multiple points of the same mark when the energy function takes a minimum value are determined as a group of interrelated targets.

[0087] As an exemplary embodiment, the energy function = ,

[0088] in, represents the sum of the independent marking costs of all points in V, represents the sum of the constraint marking costs of adjacent points in V, Represents the points in the first point set Mark as point The price, , Indicate point and Point The edges between (i.e., points and Point are two adjacent nodes). Indicate point and Point Marked as and The cost (i.e., is the constraint marking cost of two adjacent points in G), and Determined based on the weights of the edges in an undirected weighted graph.

[0089] As an example, Can be a point With point The weight of the edge between

[0090] ,

[0091] in, Can be a point With point The weight of the edge between It is a tuning parameter used to balance the data item and the smooth item. A fixed value such as 100 can be selected. It is used to distinguish the cost difference between adjacent points with different labels and those with the same label. It can be set to a fixed value, such as 2.

[0092] As an example, the minimum value of the energy function is Assign a tag , so that the sum of data energy term and smooth energy term is minimized.

[0093] As an example, you can use The algorithm solves the minimum solution of E and obtains the optimal target association of all loads, that is, the targets corresponding to a group of points with the same mark constitute the inter-correlated targets.

[0094] According to an exemplary embodiment of the present disclosure, an undirected weighted graph is constructed based on the target association matrix, and the optimal target association is modeled as an energy minimization problem based on the weighted graph, and the minimum solution of the energy function corresponds to the minimum multi-way cut of the weighted graph; the optimal target association of all loads is achieved by solving the minimum cut.

[0095] According to an exemplary embodiment of the present disclosure, based on the observation background of multi-satellite and multi-system collaborative area (for example, sea surface), multi-satellite distributed processing is used to obtain target information of multi-system payload characteristics, and multi-source target information is aggregated through the intersatellite network. Considering the satellite positioning system error, a multi-source target association technology based on position topology is designed, which can realize cross-system multi-target association such as AIS, optical, SAR, infrared, etc., and establish a unified data foundation for subsequent multi-source information fusion. Specifically, two groups of targets can be aligned by estimating the corresponding target positioning deviations between payloads, and the target association matrix between payloads can be constructed based on the Euclidean distance; then, the target association matrix of all payloads is constructed based on the target association matrix between two payloads, and a weighted graph is constructed based on the target association matrix of all payloads; the optimal target association is modeled as an energy minimization problem on the weighted graph, and the minimum solution of the energy function corresponds to the minimum multi-path cut of the weighted graph, and the optimal target association of all payloads is achieved by solving the minimum cut. The technology is simple and effective, with low computational complexity, and can meet the real-time processing requirements under limited computing resources on orbit.

[0096] Figure 6 A structural block diagram of an observation target associating device according to an exemplary embodiment of the present disclosure is shown.

[0097] like Figure 6 As shown, the observation target association device according to the exemplary embodiment of the present disclosure includes: a position information acquisition unit 100, a positioning deviation determination unit 200, an association matrix determination unit 300, a graph construction unit 400, and an association identification unit 500.

[0098] Specifically, the position information acquisition unit 100 is configured to acquire, from multiple satellite platforms, the positioning information of targets observed by the observation payloads mounted thereon.

[0099] The positioning deviation determining unit 200 is configured to determine the target positioning deviation between any two satellite platforms where the observation payloads are located based on the acquired positioning information of the target.

[0100] The correlation matrix determination unit 300 is configured to determine the target correlation matrix between any two observation payloads according to the target positioning deviation between the satellite platforms where any two observation payloads are located.

[0101] The graph construction unit 400 is configured to construct an undirected weighted graph based on a target association matrix between two observation loads.

[0102] The association identification unit 500 is configured to identify at least one group of interrelated targets based on the undirected weighted graph, wherein multiple targets in each group of interrelated targets are respectively observed by different observation loads and correspond to the same actual object.

[0103] As an example, the positioning deviation determination unit 200 can be configured to: divide the targets observed by each observation payload into a group of targets, and obtain groups of targets corresponding to each observation payload; divide the positioning information of each group of targets into a group of positioning information, and obtain groups of positioning information corresponding to each observation payload; for any two observation payloads, based on the two groups of positioning information corresponding to the any two observation payloads, determine the deviation information in the overall positioning between the two groups of targets corresponding to the any two observation payloads, and determine the deviation information as the target positioning deviation between the satellite platforms where the any two observation payloads are located.

[0104] As an example, the association matrix determination unit 300 can be configured to: convert the positioning information of each target observed by one of any two observation payloads into positioning information on the satellite platform where the other of the any two observation payloads is located, according to the target positioning deviation between the satellite platforms where the any two observation payloads are located; determine the target association matrix between the any two observation payloads based on the gap between the converted positioning information and the positioning information of each target observed by the other observation payload; wherein the element in the kth row and sth column of the target association matrix between the any two observation payloads represents: the possibility of mutual correlation between the kth target observed by the one observation payload and the sth target observed by the other observation payload.

[0105] As an example, the graph construction unit 400 may be configured to: construct a first point set and a second point set, wherein each point included in the first point set corresponds one-to-one to each target observed by each observation load, and the second point set includes multiple virtual terminal points; if it is determined based on the target association matrix between the two observation loads that the possibility of any two targets being correlated is higher than a preset threshold, then an edge is constructed between two points representing the any two targets, and the weight of the edge is set based on the possibility of the any two targets being correlated; for each point in the first point set , respectively at this point and each point in the second point set Build an edge between them and determine the weight of the edge, where if i=j, or and If they are not observed by the same observation load, the weight of the edge is set to the first weight, otherwise the weight of the edge is set to the second weight.

[0106] As an example, the association identification unit 500 can be configured to: construct an energy function about the cost of marking a point in the first point set as a point in the second point set based on the undirected weighted graph; and determine multiple observation targets corresponding to multiple points with the same mark when the energy function takes the minimum value as a group of mutually correlated targets.

[0107] As an example, the energy function may be:

[0108] ,

[0109] Wherein, V represents the first point set, E represents the edge set of the undirected weighted graph, represents a point in the first point set Mark as point The price, , represents the second point set, Indicate point and Point The edge between Indicate point and Point Marked as and The price, and The method is determined based on the weights of the edges in the undirected weighted graph.

[0110] It should be understood that the specific processing performed by the observation target associating device according to the exemplary embodiment of the present disclosure has been referred to. Figures 1 to 5 The details have been described in detail and will not be repeated here.

[0111] It should be understood that the various units and modules in the observation target associating device according to the exemplary embodiment of the present disclosure may be implemented as hardware components and / or software components.

[0112] Figure 7 A structural block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0113] Reference Figure 7The electronic device includes: at least one memory 600 and at least one processor 700, wherein the at least one memory 600 stores a set of computer executable instructions, and when the computer executable instruction set is executed by the at least one processor 700, the observed target association method described in the above exemplary embodiment is executed.

[0114] As an example, the electronic device may be a PC, a tablet device, a personal digital assistant, a smart phone, or other device capable of executing the above instruction set. Here, the electronic device is not necessarily a single electronic device, but may also be any device or circuit collection capable of executing the above instructions (or instruction sets) individually or in combination. The electronic device may also be part of an integrated control system or system manager, or may be configured as a portable electronic device interconnected with a local or remote (e.g., via wireless transmission) interface.

[0115] In an electronic device, the processor 700 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. As an example and not limitation, the processor 700 may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0116] The processor 700 may execute instructions or codes stored in the memory 600, wherein the memory 600 may also store data. Instructions and data may also be sent and received over a network via a network interface device, wherein the network interface device may employ any known transmission protocol.

[0117] The memory 600 may be integrated with the processor 700, for example, by placing RAM or flash memory within an integrated circuit microprocessor or the like. In addition, the memory 600 may include a separate device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system. The memory 600 and the processor 700 may be operatively coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the processor 700 can read files stored in the memory.

[0118] In addition, the electronic device may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the electronic device may be connected to each other via a bus and / or a network.

[0119] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing instructions may also be provided, wherein when the instructions are executed by at least one processor, the at least one processor is prompted to execute the observed target association method as described in the above exemplary embodiment. Examples of computer-readable storage media here include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disk storage, hard disk drive (HDD), solid state drive (SSD), card storage (such as, multimedia card, secure digital (SD) card or extreme digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other device, any other device is configured to store computer programs and any associated data, data files and data structures in a non-transitory manner and provide the computer programs and any associated data, data files and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the above-mentioned computer-readable storage medium can be run in an environment deployed in a computer device such as a client, a host, an agent device, a server, etc. In addition, in one example, the computer program and any associated data, data files and data structures are distributed on a networked computer system, so that the computer program and any associated data, data files and data structures are stored, accessed and executed in a distributed manner by one or more processors or computers.

[0120] According to an exemplary embodiment of the present disclosure, a computer program product may also be provided, and instructions in the computer program product may be executed by at least one processor to complete the observed target association method as described in the above exemplary embodiment.

[0121] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0122] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for associating an observed object, characterized in that: The observed target association method comprises: Obtain positioning information of targets observed by observation payloads mounted on multiple satellite platforms; Based on the acquired target positioning information, determine the target positioning deviation between any two satellite platforms where the observation payloads are located; Determining a target correlation matrix between any two observation payloads according to a target positioning deviation between satellite platforms where any two observation payloads are located; Based on the target correlation matrix between two observation loads, an undirected weighted graph is constructed; Based on the undirected weighted graph, identifying at least one group of interrelated targets, wherein multiple targets in each group of interrelated targets are respectively observed by different observation loads and correspond to the same actual object; The step of determining the target correlation matrix between any two observation payloads according to the target positioning deviation between the satellite platforms where any two observation payloads are located comprises: The positioning information of each target observed by one of the two observation payloads is converted into the positioning information of the satellite platform where the other of the two observation payloads is located according to the target positioning deviation between the satellite platforms where the two observation payloads are located; Based on the difference between the converted positioning information and the positioning information of each target observed by the other observation payload, determine the target association matrix between the two arbitrary observation payloads, wherein the element in the kth row and sth column of the target association matrix between the two arbitrary observation payloads represents: the possibility of mutual association between the kth target observed by the one observation payload and the sth target observed by the other observation payload; The step of constructing an undirected weighted graph based on the target association matrix between two observation loads comprises: Constructing a first point set and a second point set, wherein each point included in the first point set corresponds one-to-one to each target observed by each observation payload, and the second point set includes a plurality of virtual terminal points; If it is determined that the possibility of any two targets being correlated with each other is higher than a preset threshold based on the target correlation matrix between the pairwise observed loads, an edge is constructed between two points representing the any two targets, and a weight of the edge is set based on the possibility of the any two targets being correlated with each other; For each point in the first point set , respectively at this point and each point in the second point set Build an edge between them and determine the weight of the edge, where if i=j, or and If they are not observed by the same observation load, the weight of the edge is set to the first weight, otherwise the weight of the edge is set to the second weight.

2. The observation target association method according to claim 1, characterized in that: The step of determining the target positioning deviation between any two satellite platforms where the observation payloads are located based on the acquired target positioning information comprises: The targets observed by each observation load are divided into a group of targets, and each group of targets corresponding to each observation load is obtained; The positioning information of each group of targets is divided into a group of positioning information, and each group of positioning information corresponding to each observation payload is obtained; For any two observation payloads, based on the two sets of positioning information corresponding to the any two observation payloads, the deviation information in the overall positioning between the two sets of targets corresponding to the any two observation payloads is determined, and the deviation information is determined as the target positioning deviation between the satellite platforms where the any two observation payloads are located.

3. The observation target association method according to claim 1, characterized in that: The step of identifying at least one set of interrelated targets based on the undirected weighted graph comprises: Based on the undirected weighted graph, construct an energy function of the cost of marking points in the first point set as points in the second point set; The multiple observation targets corresponding to the multiple points corresponding to the same mark when the energy function takes the minimum value are determined as a group of interrelated targets.

4. The observation target association method according to claim 3, characterized in that: The energy function is: ， Wherein, V represents the first point set, E represents the edge set of the undirected weighted graph, represents a point in the first point set Mark as point The price, , represents the second point set, Indicate point and Point The edge between Indicate point and Point Marked as and The price, and The method is determined based on the weights of the edges in the undirected weighted graph.

5. An observation target association device, characterized in that: The observed target associating device comprises: A position information acquisition unit is configured to acquire, from multiple satellite platforms, positioning information of targets observed by observation payloads mounted thereon; A positioning deviation determination unit is configured to determine a target positioning deviation between any two satellite platforms where the observation payloads are located based on the acquired positioning information of the target; A correlation matrix determination unit is configured to determine a target correlation matrix between any two observation payloads according to a target positioning deviation between satellite platforms where any two observation payloads are located; A graph construction unit is configured to construct an undirected weighted graph based on a target correlation matrix between two pairs of observed loads; an association identification unit configured to identify at least one group of interrelated targets based on the undirected weighted graph, wherein a plurality of targets in each group of interrelated targets are respectively observed by different observation loads and correspond to the same actual object; Wherein, the association matrix determination unit is specifically configured as follows: The positioning information of each target observed by one of the two observation payloads is converted into the positioning information of the satellite platform where the other of the two observation payloads is located according to the target positioning deviation between the satellite platforms where the two observation payloads are located; Based on the difference between the converted positioning information and the positioning information of each target observed by the other observation payload, determine the target association matrix between the two arbitrary observation payloads, wherein the element in the kth row and sth column of the target association matrix between the two arbitrary observation payloads represents: the possibility of mutual association between the kth target observed by the one observation payload and the sth target observed by the other observation payload; Wherein, the graph construction unit is specifically configured as follows: Constructing a first point set and a second point set, wherein each point included in the first point set corresponds one-to-one to each target observed by each observation payload, and the second point set includes a plurality of virtual terminal points; If it is determined that the possibility of any two targets being correlated with each other is higher than a preset threshold based on the target correlation matrix between the pairwise observed loads, an edge is constructed between two points representing the any two targets, and a weight of the edge is set based on the possibility of the any two targets being correlated with each other; For each point in the first point set , respectively at this point and each point in the second point set Build an edge between them and determine the weight of the edge, where if i=j, or and If they are not observed by the same observation load, the weight of the edge is set to the first weight, otherwise the weight of the edge is set to the second weight.

6. A computer-readable storage medium storing instructions, characterized in that: When the instructions are executed by a processor of an electronic device, the electronic device is enabled to execute the observation target association method as claimed in any one of claims 1 to 4.

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; at least one memory storing computer executable instructions, Wherein, when the computer executable instructions are executed by the at least one processor, the at least one processor is prompted to execute the observation target association method as described in any one of claims 1 to 4.

8. A computer program product comprising computer executable instructions, characterized in that: When the computer executable instructions are executed by at least one processor, the observation target association method according to any one of claims 1 to 4 is implemented.

Images