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

Abstract

The present disclosure provides a directed target association method, device, electronic device, storage medium and program product. The directed target association method includes: receiving multiple target observation information obtained by multiple different observation loads for observing targets appearing in the same geographical area; for each observation load in the multiple different observation loads, according to the target observation information of each target observed by the observation load, determining the geometric description information of each target; determining multiple observation load pairs from the multiple different observation loads; for each observation load pair in the multiple observation load pairs, based on the geometric description information of each two targets, determining the consistency measure of the observation load pair; according to the consistency measure of the multiple observation load pairs, determining the association relationship between the targets observed by the multiple different observation loads. The method can realize target association and provide a basis for the joint observation of multiple different observation loads and multi-source information fusion.

Description

Technical Field

[0001] The present disclosure generally relates to the field of satellite positioning technology, and more specifically, to a directed 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 observation method. This method mounts different observation payloads on different satellite platforms, which are used to obtain ground target information from different dimensions, and then complete information aggregation through the inter-satellite Internet, thereby realizing high-precision detection and identification of ground targets based on multi-source and multi-system information fusion.

[0003] Commonly used observation payloads include AIS (Automatic Identification System), optics, infrared, SAR (Synthetic Aperture Radar), etc. AIS mainly detects AIS signals sent by ships, and after demodulation, gives the ship's MMSI (Maritime Mobile Service Identity) number (a 9-digit identifier used to identify ships, shore base stations and mobile devices at sea), IMO (International Maritime Organization) identification code, longitude and latitude, ship type, length, width, direction of movement, etc. Observation payloads such as optics, infrared, and SAR obtain target imaging data, perform target detection and identification through feature extraction and analysis, and achieve target positioning through on-orbit positioning technology. Observation payloads of different systems obtain different target features due to the different spectral bands or detection methods used. For example, the texture features of SAR, infrared, and visible light are very different, while non-imaging payloads such as electronic payloads do not have texture features. The geometric features such as length and width of ship targets that can be obtained by most observation payloads are easily affected by wakes, waves, resolution, etc., which leads to large differences between the geometric features obtained by different observation payloads.

[0004] In addition, due to the influence of satellite platform sensors and positioning algorithm accuracy differences, the target positioning obtained by different satellite platforms will have a certain offset from the actual position, and time-sharing observations will also lead to inconsistent target positions due to target movement. Especially for the sea surface, due to the lack of obvious ground reference, it is difficult to align the same target obtained by different observation payloads. In addition, affected by the detection capability, observation range, processing capability, etc. of the observation payload, the number of targets obtained by different observation payloads is different, and there may be certain false alarms, which brings great difficulties to the association of multi-source targets. Summary of the invention

[0005] The present disclosure provides a directed target association method, device, electronic device, storage medium and program product, which are used to solve at least one of the above problems.

[0006] According to a first aspect of an embodiment of the present disclosure, a directed target association method is provided, the directed target association method comprising: receiving a plurality of target observation information obtained by observing a plurality of different observation loads on targets appearing in the same geographical area, wherein the observation time difference of the plurality of different observation loads is less than a preset time difference, and one target observation information corresponds to one observation load and one target; for each observation load in the plurality of different observation loads, determining geometric description information of each target based on the target observation information of each target observed by the observation load, wherein the geometric description information is used to describe the relative position relationship between the corresponding target and other targets among the targets observed by the observation load except the corresponding target; determining a plurality of observation load pairs from the plurality of different observation loads, and for each observation load pair in the plurality of observation load pairs, determining a plurality of target pairs, Wherein, each observation load pair includes a first observation load and a second observation load, and each target pair includes a first target and a second target, the first target is a target observed by the first observation load, and the second target is a target observed by the second observation load; for each target pair in the multiple target pairs, the geometric description information of the first target is compared with the geometric description information of the second target to obtain a target pair similarity measure of the target pair, and the target pair similarity measures of the multiple target pairs are used as consistency measures of the observation load pairs, wherein the consistency measure is used to represent the degree of similarity of the observed targets of the corresponding observation load pairs; according to the consistency measures of the multiple observation load pairs, the association relationship between the targets observed by each of the multiple different observation loads is determined, wherein the association relationship represents the relationship that the targets observed by different observation loads belong to the same entity.

[0007] Optionally, the multiple different observation loads include one first observation load and multiple second observation loads, the first observation load is any one of the multiple different observation loads, wherein determining multiple observation load pairs from the multiple different observation loads includes: respectively forming an observation load pair with the first observation load and each of the second observation loads to obtain the multiple observation load pairs.

[0008] Optionally, the target observation information includes the corresponding target observed by the corresponding observation load. Location information and direction information , the direction information To describe the corresponding target direction, goal represents the target numbered j observed by the observation payload numbered i, wherein the geometric description information of each target is determined based on the target observation information of each target observed by the observation payload, including: for each target , except for the target Other goals Location information and direction information Convert to the reference coordinate system to get other targets Conversion position information and conversion direction information , where the origin of the reference coordinate system is the target The coordinate axis direction of the reference coordinate system is consistent with the target direction; according to other goals Conversion position information and conversion direction information , determine the target The geometric description information.

[0009] Optionally, the Conversion position information and conversion direction information , determine the target The geometric description information includes: when the observed load is the first observed load, the target For the first goal, other goals Conversion position information and conversion direction information , as the first goal Geometric description information ,in, Indicates that among the targets observed by the first observation payload, except target The set of all other targets except For the second goal, for each other goal , based on other goals Conversion position information , determine other goals Symmetrical position information of symmetrical points relative to the x-axis, y-axis and origin in the reference coordinate system , , , get other goals Four relative position information ,in, ; Other targets Each relative position information and conversion direction information , as the second goal A set of geometric description information , get the second goal Four sets of geometric description information, where the m values ​​of the same set of geometric description information are equal. Indicates that among the targets observed by the second observation payload, except target The set of all other targets except

[0010] Optionally, for each target pair in the multiple target pairs, comparing the geometric description information of the first target with the geometric description information of the second target to obtain a target pair similarity measure of the target pair, and using the target pair similarity measures of the multiple target pairs as the consistency measure of the observation load pair, including: for each target pair in the multiple target pairs, comparing the geometric description information of the first target with each set of geometric description information of the second target The four groups of target pair similarity measures of the target pairs are compared respectively to obtain four groups of target pair similarity measures, wherein the target pair similarity measures are constructed to be positively or negatively correlated with the possibility that the two targets in the corresponding target pair belong to the same entity; the four groups of target pair similarity measures of the multiple target pairs are summarized by group to obtain four groups of consistency measures of the observation load pairs; the association relationship between the targets observed by each of the multiple different observation loads is determined based on the consistency measures of the multiple observation load pairs, including: for each observation load pair in the multiple observation load pairs, the group with the highest similarity is determined from the four groups of consistency measures of the observation load pairs, recorded as the preferred consistency measure; based on the preferred consistency measure, the target pairs belonging to the same entity in each target pair of the observation load pairs are determined.

[0011] Optionally, the geometric description information of the first target is compared with each group of geometric description information of the second target respectively to obtain four groups of target pair similarity measures of the target pairs, including: determining multiple other target pairs, wherein each other target pair includes a first other target and a second other target, the first other target is a target other than the first target observed by the first observation load, and the second other target is a target other than the second target observed by the second observation load; for each group of geometric description information of the second target, determining a preset function value of each other target pair in the multiple other target pairs according to the geometric description information of the first target and the geometric description information of the second target, taking the sum of the preset function values ​​of the multiple other target pairs as a group of target pair similarity measures of the target pair, to obtain four groups of target pair similarity measures of the target pair.

[0012] According to a second aspect of an embodiment of the present disclosure, a directed target association device is provided, the directed target association device comprising: a receiving unit, configured to receive a plurality of target observation information obtained by observing a plurality of different observation loads on targets appearing in the same geographical area, wherein the observation time difference of the plurality of different observation loads is less than a preset time difference, and one target observation information corresponds to one observation load and one target; a description unit, configured to determine, for each observation load in the plurality of different observation loads, geometric description information of each target based on the target observation information of each target observed by the observation load, wherein the geometric description information is used to describe the relative position relationship between the corresponding target and other targets among the targets observed by the observation load except the corresponding target; a pairing unit, configured to determine a plurality of observation load pairs from the plurality of different observation loads, and for each observation load pair in the plurality of observation load pairs, determine a plurality of target pairs, wherein each observation load pair includes a first observation load and a second observation load, and each target pair includes a first target and a second target, wherein the first target is a target observed by the first observation load, and the second target is a target observed by the second observation load; a measurement unit is configured to compare the geometric description information of the first target with the geometric description information of the second target for each target pair in the multiple target pairs, to obtain a target pair similarity measure of the target pairs, and to use the target pair similarity measures of the multiple target pairs as consistency measures of the observation load pairs, wherein the consistency measure is used to represent the degree of similarity of the observed targets of the corresponding observation load pairs; a determination unit is configured to determine the association relationship between the targets observed by each of the multiple different observation loads based on the consistency measures of the multiple observation load pairs, wherein the association relationship represents the relationship that the targets observed by different observation loads belong to the same entity.

[0013] Optionally, the multiple different observation loads include one first observation load and multiple second observation loads, the first observation load is any one of the multiple different observation loads, wherein the determining of multiple observation load pairs from the multiple different observation loads performed by the pairing unit includes: respectively forming an observation load pair with the first observation load and each of the second observation loads to obtain the multiple observation load pairs.

[0014] Optionally, the target observation information includes the corresponding target observed by the corresponding observation load. Location information and direction information , the direction information To describe the corresponding target direction, goal represents a target numbered j observed by an observation payload numbered i, wherein the description unit determines the geometric description information of each target based on the target observation information of each target observed by the observation payload, including: for each target , except for the target Other goals Location information and direction information Convert to the reference coordinate system to get other targets Conversion position information and conversion direction information , where the origin of the reference coordinate system is the target The coordinate axis direction of the reference coordinate system is consistent with the target direction; according to other goals Conversion position information and conversion direction information , determine the target The geometric description information.

[0015] Optionally, the description unit performs the Conversion position information and conversion direction information , determine the target The geometric description information includes: when the observed load is the first observed load, the target For the first goal, other goals Conversion position information and conversion direction information , as the first goal Geometric description information ,in, Indicates that among the targets observed by the first observation payload, except target The set of all other targets except For the second goal, for each other goal , based on other goals Conversion position information , determine other goals Symmetrical position information of symmetrical points relative to the x-axis, y-axis and origin in the reference coordinate system , , , get other goals Four relative position information ,in, = ; Other targets Each relative position information and conversion direction information , as the second goal A set of geometric description information , get the second goal Four sets of geometric description information, where the m values ​​of the same set of geometric description information are equal. Indicates that among the targets observed by the second observation payload, except target The set of all other targets except

[0016] Optionally, the measurement unit is also configured to: for each target pair in the multiple target pairs, compare the geometric description information of the first target with each group of geometric description information of the second target, respectively, to obtain four groups of target pair similarity measures of the target pairs, wherein the target pair similarity measures are constructed to be positively correlated or negatively correlated with the possibility that the two targets in the corresponding target pair belong to the same entity; summarize the four groups of target pair similarity measures of the multiple target pairs by group, to obtain four groups of consistency measures of the observation load pairs; the determination unit is also configured to: for each observation load pair in the multiple observation load pairs, determine the group with the highest similarity from the four groups of consistency measures of the observation load pairs, recorded as the preferred consistency measure; based on the preferred consistency measure, determine the target pairs in each target pair of the observation load pairs that belong to the same entity.

[0017] Optionally, the measurement unit performs the comparison of the geometric description information of the first target with each group of geometric description information of the second target respectively to obtain four groups of target pair similarity measures of the target pairs, including: determining multiple other target pairs, wherein each other target pair includes a first other target and a second other target, the first other target is a target other than the first target observed by the first observation load, and the second other target is a target other than the second target observed by the second observation load; for each group of geometric description information of the second target, determining a preset function value of each other target pair in the multiple other target pairs according to the geometric description information of the first target and the geometric description information of the second target, taking the sum of the preset function values ​​of the multiple other target pairs as a group of target pair similarity measures of the target pair, to obtain four groups of target pair similarity measures of the target pair.

[0018] According to a third 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 a directed target association method according to an exemplary embodiment of the present disclosure.

[0019] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by at least one processor, the at least one processor is prompted to execute a directed target association method according to an exemplary embodiment of the present disclosure.

[0020] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising computer instructions, which, when executed by at least one processor, prompt the at least one processor to execute a directed target association method according to an exemplary embodiment of the present disclosure.

[0021] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: According to the directed target association method, device, electronic device, storage medium and program product of the present disclosure, considering that the positioning error of different observation loads to the target is often a systematic error, all the targets observed by one observation load should have similar differences as a whole compared with all the targets observed by another observation load. Based on this analysis, different observation loads are allowed to observe targets in the same geographical area within a preset time difference, and for each target, a complete and independent geometric description of the target is made with the help of other targets observed by the same observation load, and then an observation load pair is constructed, and based on the geometric description information of the two targets observed by the observation load pair, a consistency measure representing the similarity of the observed targets of the observation load pair is obtained, and the consistency measure information can be used to determine the targets observed by different observation loads and belonging to the same entity, thereby realizing target association, and providing a basis for the joint observation of multiple different observation loads and multi-source information fusion.

[0022] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0024] Figure 1 is a flowchart of a directed target associating method according to an exemplary embodiment of the present disclosure.

[0025] Figure 2It is a schematic diagram of a support domain and an influence domain of a ship target according to a directed target association method according to a specific embodiment of the present disclosure.

[0026] Figure 3 It is a schematic diagram of the support domain and influence domain of a ship target after coordinate transformation according to the directed target association method of a specific embodiment of the present disclosure.

[0027] Figure 4 is a block diagram of a directed target associating apparatus according to an exemplary embodiment of the present disclosure.

[0028] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0030] 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 implementation methods described in the following examples do not represent all implementation methods 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 attached claims.

[0031] 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.

[0032] Hereinafter, a directed target associating method, apparatus, electronic device, storage medium, and program product according to exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0033] Figure 1 is a flowchart of a directed target associating method according to an exemplary embodiment of the present disclosure.

[0034] Reference Figure 1In step S101, multiple target observation information obtained by observing targets appearing in the same geographical area through multiple different observation payloads is received.

[0035] Specifically, the observation time difference of multiple different observation payloads is less than the preset time difference, so that observations can be made at the same or similar time, so that the targets observed by different observation payloads are objectively the same or close, providing a basis for collaborative observation. As an example, for the scenario of multi-satellite joint earth observation, one or more satellites carrying observation payloads of different systems can coordinate observations of the same sea area simultaneously or in relays along their respective orbits through means such as side swing, so that the observation time difference is less than the preset time difference.

[0036] One target observation information corresponds to one observation payload and one target. In other words, the information of one target observed by one observation payload is one target observation information. To represent the target numbered j observed by the observed payload numbered i.

[0037] It should be understood that for the scenario of multi-satellite joint earth observation, these target observation information are what needs to be integrated during information fusion. The purpose of the exemplary embodiments of the present disclosure is to align the targets belonging to the same entity (such as a ship) observed by different observation payloads based on this information.

[0038] In step S102, for each observation load among a plurality of different observation loads, geometric description information of each target is determined according to target observation information of each target observed by the observation load.

[0039] Specifically, the geometric description information is used to describe the relative position relationship between the corresponding target and other targets observed by the observation payload except the corresponding target. By using the relative position relationship between each target and other targets one by one to describe the current target, each target can have complete and independent geometric description information, thereby achieving independent description of each target.

[0040] In step S103, a plurality of observed load pairs are determined from a plurality of different observed loads, and for each of the plurality of observed load pairs, a plurality of target pairs are determined.

[0041] Specifically, each observation load pair includes a first observation load and a second observation load, and each target pair includes a first target and a second target, wherein the first target is a target observed by the first observation load, and the second target is a target observed by the second observation load. By forming a plurality of observation load pairs with a plurality of different observation loads, a one-to-one comparison between two observation loads can be performed, thereby reducing the computational complexity. Specifically for each observation load pair, by taking one of the targets observed by the two observation loads to form a target pair, and then forming a plurality of target pairs, a one-to-one comparison between two specific targets can be performed in the subsequent step S104 to obtain a target pair similarity measure, which not only further reduces the computational complexity, but also obtains the comparison results of the two specific targets, providing easy-to-use basis information for the ultimate goal of determining the target association relationship.

[0042] In step S104, for each target pair among the multiple target pairs, the geometric description information of the first target is compared with the geometric description information of the second target to obtain a target pair similarity measure of the target pairs, and the target pair similarity measures of the multiple target pairs are used as consistency measures of the observed load pairs.

[0043] Specifically, the consistency measure obtained by summarizing the target pair similarity measures of multiple target pairs is used to represent the similarity degree of the observed targets of the corresponding observation payload pairs.

[0044] In step S105, the association relationship between the targets observed by the multiple different observation loads is determined based on the consistency measurement of the multiple observation load pairs.

[0045] Specifically, the association relationship indicates that the targets observed by different observation loads belong to the same entity, which represents the execution purpose of the directed target association method according to the exemplary embodiment of the present disclosure.

[0046] According to the directed target association method disclosed in the present invention, considering that the positioning errors of different observation loads for targets are often systematic errors, all targets observed by one observation load should have similar differences as a whole compared with all targets observed by another observation load. Based on this analysis, different observation loads are allowed to observe targets in the same geographical area within a preset time difference. For each target, a complete and independent geometric description of the target is performed with the help of other targets observed by the same observation load, and then an observation load pair is constructed. Based on the geometric description information of each pair of targets observed by the observation load pair, a consistency measure representing the similarity of the observed targets of the observation load pair is obtained. The consistency measure information can be used to determine the targets observed by different observation loads and belonging to the same entity, thereby achieving target association, and providing a basis for the joint observation of multiple different observation loads and multi-source information fusion.

[0047] Next, a directed target association method according to an exemplary embodiment of the present disclosure is further introduced.

[0048] Regarding the construction of observation load pairs in step S103, as an example, observation load pairs can be randomly constructed from multiple different observation loads until each observation load can directly or indirectly constitute an observation load pair with each other observation load. For example, observation load A and observation load B constitute an observation load pair, and observation load B also constitutes an observation load pair with observation load C. Then observation load A can indirectly constitute an observation load pair with observation load C, thereby ensuring that for each observation load, the correlation relationship between the target observed by the observation load and the targets observed by other observation loads can be directly or indirectly determined.

[0049] It is also possible to pair multiple different observation loads in pairs, that is, to make each observation load form an observation load pair with each other observation load. When the number of multiple different observation loads is I, the number of observation load pairs obtained is .

[0050] The multiple different observation loads can also be set to include a first observation load and multiple second observation loads, and the first observation load is any one of the multiple different observation loads. That is, any one of the multiple different observation loads is determined as the first observation load, and the other observation loads are used as the second observation load. Correspondingly, the operation of determining multiple observation load pairs from multiple different observation loads in step S103 includes: the first observation load and each second observation load are respectively formed into an observation load pair to obtain multiple observation load pairs. By specifying the same first observation load and forming an observation load pair with other observation loads (i.e., each second observation load), it is possible to directly or indirectly construct the association relationship between any two observation loads in all the observation loads, and to minimize the number of observation load pairs. In addition, since each observation load pair shares the first observation load, the construction process of the observation load pair can be simplified, thereby improving the overall calculation efficiency.

[0051] Of course, other methods may be used to construct observation load pairs, and the present disclosure does not limit this.

[0052] Next, in conjunction with a more specific example of target observation information, the corresponding geometric description information, target pair similarity measure, consistency measure and target association relationship determination method, that is, the execution method of step S102, step S104 and step S105 are introduced. It should be noted that mathematical symbols are used below to represent different concepts. It should be understood that these mathematical symbols are only examples to facilitate the distinction between different concepts, and are not limitations on the technical solutions protected by the present disclosure.

[0053] In this example, the target observation information includes the corresponding target observed by the corresponding observation payload. Location information and direction information Among them, the target Indicates the target number j observed by the observation payload number i. Position information Used to locate the corresponding target Geographic location, such as longitude and latitude. Direction information To describe the corresponding target For example, when the target entity is a ship, the direction information It describes the direction of the bow, so that the directional targets can be observed and described, and then the correlation relationship of the directional targets can be determined.

[0054] Accordingly, in step S102, according to the target observation information of each target observed by the observation payload, the target geometric description information of each target is determined, including: for each target , except for the target Other goals Location information and direction information Convert to the reference coordinate system to get other targets Conversion position information and conversion direction information , where the origin of the reference coordinate system is the target The position of the reference coordinate system and the direction of the coordinate axis of the target The direction of the x-axis is related to the target The same direction or the opposite direction as the target The direction has a certain angle in the clockwise or counterclockwise direction); according to other objectives Conversion position information and conversion direction information , determine the target The geometric description information of each target , build a reference coordinate system based on its position and orientation, and observe other targets Convert from a common coordinate system for all targets (such as longitude and latitude coordinate system) to a relative coordinate system, the reference coordinate system, and use the converted position information obtained after the conversion and conversion direction information , conveniently representing other goals With current target The relative position relationship.

[0055] How to use other goals Conversion position information and conversion direction information , determine the target As an example, this information can be directly used as the geometric description information of the corresponding target, or it can be further calculated to obtain other targets. With corresponding goals For the latter, the coordinate system can be not converted and the original position information can be directly used to calculate the spacing and relative angle.

[0056] Next, we will take the example of directly using this information as the geometric description information of the corresponding target for further introduction. The essential principles of other examples are the same, and you can refer to this example, and this disclosure will not describe them one by one.

[0057] Considering that the direction of the target obtained from visible light, infrared, SAR and other images is usually only the length direction of the target, there are two possibilities for the direction of the target, namely the two extension directions of the target length, plus the possibility of mirror imaging. Therefore, in order to associate the targets observed by different observation payloads, it is necessary to expand the converted coordinate information obtained after the coordinate system is converted based on these possibilities. It should be understood that since these possibilities do not affect the direction of other targets after the coordinate system is converted, the conversion direction information does not need to be expanded. Optionally, according to other targets Conversion position information and conversion direction information , determine the target The operations on target geometric description information include the following two categories.

[0058] Category 1: When the observed load is the first observed load, the target As the first goal, other goals Conversion position information and conversion direction information , as the first goal Geometric description information ,in, Indicates that among all the targets observed by the first observation load, except target In other words, for the first target, the converted position information and converted direction information of other targets are directly used as the target geometric description information of the corresponding target. It should be understood that the mathematical symbols of the first target and the corresponding other targets are changed at this time to facilitate the distinction from the second target observed by the second observation payload.

[0059] Category 2: When the observed load is the second observed load, the target For each other goal , based on other goals Conversion position information , determine other goals Symmetrical position information of the symmetrical points relative to the x-axis, y-axis, and origin in the reference coordinate system , , , get other goals Four relative position information ,in, = , that is, m=1 means that the relative position information is obtained by performing an axisymmetric transformation on the x-axis of the reference coordinate system based on the converted position information, m=2 means that the relative position information is obtained by performing an axisymmetric transformation on the y-axis of the reference coordinate system based on the converted position information, m=3 means that the relative position information is obtained by performing a centrosymmetric transformation on the origin of the reference coordinate system based on the converted position information, and m=4 means that the relative position information is the converted position information; other targets Each relative position information and conversion direction information , as the second goal A set of geometric description information , get the second goal There are four groups of geometric description information, among which the m values ​​of the same group of geometric description information are equal, which ensures the consistency of the relative position information of each other target in the same group of geometric description information of each second target, that is, they are all converted position information, or they are all obtained by symmetric transformation of the converted position information based on the same symmetry axis or symmetry center. Indicates that among the targets observed by the second observation payload, except target By determining the symmetric position of the point relative to the x-axis, y-axis, and origin in the reference coordinate system based on the point position of the converted position information in the reference coordinate system, four sets of geometric description information can be expanded to cover the possibility of different orientations and mirror imaging, and in the subsequent steps, a set of system influencing factors (i.e., target orientation, whether there is mirror imaging) that are consistent with the first observation load can be determined, reducing the interference of inconsistent orientation and mirror imaging on target association.

[0060] Further optionally, step S104 includes: for each target pair in the multiple target pairs, comparing the geometric description information of the first target with each group of geometric description information of the second target, respectively, to obtain four groups of target pair similarity measures of the target pairs, wherein the target pair similarity measures are constructed to be positively or negatively correlated with the possibility that the two targets in the corresponding target pair belong to the same entity; aggregating the four groups of target pair similarity measures of the multiple target pairs by group to obtain four groups of consistency measures of the observation load pairs.

[0061] Specifically, since the target geometric description information of each target includes the position and direction of each other target in its reference coordinate system, based on this, for a target pair, when comparing the first target and the second target, multiple other target pairs can be determined for each first other target corresponding to the first target and each second other target corresponding to the second target, and a preset function with position information and direction information as independent variables is constructed. For each other target pair, the position information and direction information of the corresponding other targets in the geometric description information of the first target and the second target are substituted, and the value of the preset function is solved, and the preset function values ​​of each other target pair are summed, and the sum value is used as the target pair similarity measure of the target pair. It should be understood that the goal of constructing the above function is to make the sum of the function values ​​of each other target pair positively or negatively correlated with the possibility that the two targets in the corresponding target pair belong to the same entity. In addition, since there are four sets of geometric description information for the second target, each set of geometric description information of the second target is calculated separately. Taking a set of geometric description information as an example, the relative position information and conversion direction information of the corresponding second other target in the set of geometric description information are substituted into the above-mentioned preset function with position information and direction information as independent variables to obtain the preset function value of the set of other target pairs, and the preset function values ​​of the set of multiple other target pairs of the target pair are summed, and the sum is used as a set of target pair similarity measures of the target pair. The four sets of target geometric description information are calculated separately to obtain four sets of target pair similarity measures of the target pair. For an observation load pair, the similarity measures of each set of target pairs can be summarized from the dimension of the target pair to obtain four sets of consistency measures of the observation load pair. As an example, each target pair and its corresponding target pair similarity measure can be directly recorded during the summary, and the target pair similarity measures of each target pair can also be preprocessed first, for example, combining the target pair similarity measures, deleting the target pairs that obviously do not belong to the same entity, and then recording the target pair similarity measures of the remaining target pairs.

[0062] On this basis, step S105 includes: for each observation load pair among the multiple observation load pairs, determining the group with the highest similarity from the four groups of consistency metrics of the observation load pairs, recorded as the preferred consistency metric, which is equivalent to realizing the screening of four groups of geometric description information; based on the preferred consistency metric, determining the target pairs belonging to the same entity among each target pair of the observation load pairs.

[0063] Based on the previous introduction to the four sets of geometric description information, it can be known that the set of similarity information with the highest degree of similarity corresponds to a set of geometric description information in which the system influencing factors are consistent with the first observation load, and the correlation between the targets observed by different observation loads can be determined accordingly. As an example, the sum of the similarity measures of multiple target pairs in each set of consistency measures can be calculated. Specifically, only the sum of the similarity measures of the target pairs retained after preprocessing can be calculated, and the correlation between the target pair similarity measures and the possibility that the two targets in the corresponding target pairs belong to the same entity is combined, and the set of consistency measures with the largest or smallest sum is determined as the preferred consistency measure.

[0064] In addition, regarding how to determine the target pairs belonging to the same entity based on the preferred consistency measure, for an observation load pair, since the same first target will constitute a target pair with multiple different second targets, and the target pair similarity measure is constructed to be positively or negatively correlated with the possibility that the two targets in the corresponding target pair belong to the same entity, therefore, on the one hand, with the help of the specific value of the single target pair similarity measure, it is possible to roughly determine whether the first target and the second target in the corresponding target pair may belong to the same entity. On the other hand, for several second targets that are roughly determined to belong to the same entity as the same first target, the one that is most likely to belong to the same entity as the first target can be determined by comparing the target pair similarity measures corresponding to these second targets, thereby realizing the determination of the association relationship. Specifically, if the number of second targets that are roughly determined to belong to the same entity as the same first target is one, then the second target can be directly determined to be the second target that belongs to the same entity as the first target. If the number of second targets that are roughly determined to belong to the same entity as the same first target is multiple, then based on the correlation represented by the target pair similarity measure, the one with the largest (positive correlation) or smallest (negative correlation) corresponding to the target pair similarity measure among these second targets is determined to be the second target that belongs to the same entity as the first target.

[0065] It should be understood that the above embodiment expands four sets of geometric description information for the second target, and finally selects one set for the scene where some observation payloads cannot distinguish the target orientation. Therefore, for the case where the target orientation can be clearly distinguished, such as the case where the target entity is a ship and the bow and stern can be clearly distinguished, there is no need to expand the geometric description information, and only one set of geometric description information needs to be determined based on the conversion position information and the conversion direction information.

[0066] Accordingly, at this time, step S104 may include: for each target pair in the multiple target pairs, comparing the geometric description information of the first target with the geometric description information of the second target to obtain a target pair similarity measure of the target pair, wherein the target pair similarity measure is constructed to be positively or negatively correlated with the possibility that the two targets in the corresponding target pair belong to the same entity; aggregating the target pair similarity measures of the multiple target pairs to obtain a consistency measure of the observation load pairs.

[0067] On this basis, step S105 includes: for each of the multiple observed load pairs, based on the consistency metric of the observed load pair, determining the target pairs belonging to the same entity in each target pair of the observed load pair. That is, it is equivalent to taking the unique consistency metric of the observed load pair as the preferred consistency metric in the previous embodiment, and determining the association relationship of the targets observed by the observed load pair in the manner of the previous embodiment.

[0068] Next, the directed target association method disclosed in the present invention is introduced in conjunction with a specific embodiment.

[0069] This specific embodiment provides a method for associating sea surface ship targets based on collaborative observation of heterogeneous payloads, which is oriented to the target association of collaborative observation tasks of multi-system payloads. Its application background is that one or more satellites carrying different system observation payloads simultaneously or relay collaborative observations on the same sea area along their respective orbits through means such as side swing, and the observation time is not much different; the relative position of the target is basically stable in the collaborative observation time domain and sea area; after different observation payloads obtain data, the ship target detection, identification and positioning are completed based on the computing platform of the satellite where they are located, and target information products including longitude, latitude and direction, i.e., target description information, are generated; after the data processing of each observation payload is completed, the target information product is transmitted to the same satellite computing platform, which collects and aggregates the target information products of each observation payload for association and fusion. This specific embodiment focuses on the ship target association measurement between heterogeneous payloads, i.e., the target association after the information is aggregated on the satellite, so it is set that all the work before the aggregation has been completed. The target association of this specific embodiment is to construct a similarity measurement based on direction and longitude and latitude to achieve target association between different observation payloads, which generally includes the following steps.

[0070] Step 1: Group the received target description information including latitude, longitude and direction according to the observation payload, and the target description information of each observation payload constitutes a group.

[0071] Step 2: Set the number of targets in each group to be greater than 1, and use the target's direction, longitude and latitude and other information to build the geometric description information of each target. Specifically, within each group of targets, the geometric description information of each target is built using the relative relationship between the targets.

[0072] Step 3: Use geometric description information to measure the topological consistency of targets between different observation payloads.

[0073] Step 4: Based on the consistency metric, establish the association relationship between targets of different observation payloads.

[0074] This specific embodiment is aimed at the coordinated sea surface observation tasks of multiple-system observation payloads. Different satellites or the same satellite are equipped with observation payloads of different detection systems, such as AIS, visible light, infrared, SAR, etc., which observe simultaneously or relay observations at short time intervals. In the observed time domain and sea area, the target position of the ship may change due to movement, but the relative position does not change much.

[0075] The number of targets acquired by different observation payloads is greater than one, and the target description information includes longitude, latitude and target direction. The position and direction of the same target obtained by different observation payloads may have certain deviations due to platform positioning system errors or short-term movement.

[0076] The following takes the topological consistency measurement of the target between two observation payloads as an example to explain this method in detail.

[0077] Step 1: Set the observation load The target set , , is the number of targets found by observation load i, is the jth target discovered by the observed payload i. Recorded as the first observation load, Recorded as the second observation load. For any target , let its direction and position be , ,in is the direction angle, , is the longitude, is the latitude. First, some definitions are given.

[0078] Impact area: is the center and the radius is The circular domain is defined as the target The impact domain of is the observed load positioning accuracy.

[0079] Support domain: Centered on The smallest circular region of influence of all other targets is defined as the target The support domain, the radius of the support domain is .like Figure 2 As shown, the external is the center and the radius is The target is the large circle The support domain is is the center and the radius is The small circle is One of the goals domain of influence.

[0080] Support set: Defined as a goal The support set of , that is, the target set Target A collection of targets other than .

[0081] Step 2: Target any target , and construct its geometric description information through the following method.

[0082] (21) Target , which supports all goals , do the following coordinate transformation to get the new coordinates:

[0083] .

[0084] Where R is the rotation matrix, that is, Supporting various goals in the concentration Transform to based on In the determined reference coordinate system, the reference coordinate system is is the origin O , with the goal The direction is the positive direction of the x-axis, and the y-axis is determined accordingly, such as Figure 3 As shown. It can be understood that in the reference coordinate system, The direction becomes .

[0085] (22) Target The description vector is denoted as .

[0086] (23) For the first observation load Any target observed , let i = 1, and use the methods (21) and (22) to get the target Geometric description information .

[0087] (24) For the second observation load Any target observed , let i = 2, first use (21) and (22) to get the target Any target in the support set The position and direction obtained after coordinate transformation In addition, considering that the ship target direction obtained from visible light, infrared, SAR and other images is usually only the hull direction, there are two possibilities for the bow direction, plus there may be mirror imaging, so for the second observation payload , in order to align its target with the first observed payload, based on , determine the target Four relative position information: ; ; ; .

[0088] In summary, the second observation load Any target Four sets of target geometry description information can be obtained: ;

[0089] ;

[0090] ;

[0091] .

[0092] Step 3: Construct the first observation load based on the target geometry description information To the second observation load Any two targets The topological consistency measure is defined as follows: , m=1,2,3,4, as the target pair Similarity measure for target pairs:

[0093] = ;

[0094] = ;

[0095] = ;

[0096] = .

[0097] in,

[0098] .

[0099] is the adjustment parameter that takes into account the small changes in relative position caused by short-term motion. It is easy to see that , ,and The bigger, and The stronger the similarity.

[0100] Step 4: Get the first observation load in step 3 To the second observation load Any two targets form a target pair The four target pair similarity measures are four distance values Dist m , represents the second observation load Relative first observation load There are four possible relative transformations. Since all targets uniformly follow one of the relative transformations, the most likely transformation can be determined by the association strength, thereby determining the final association result.

[0101] In practice, the first observed load under each transformation can be obtained by nearest neighbor search or bipartite graph matching. With the second observation load The association result of a target pair. But this is not the focus of this disclosure. Here, taking the nearest neighbor search as an example, the following specific processing flow is given.

[0102] (41) Loop through the second observation load For the four sets of geometric description vectors, perform (42)~(46) to obtain four sets of consistency measures for the observed load pairs.

[0103] (42) First observation load The first goal of each and the second observation load Each secondary goal in Can be formed For any set of geometric description vectors, calculate The target pair similarity measure of target pairs is constructed to construct the measurement matrix H m :

[0104] .

[0105] (43) Execute (44) repeatedly until H m Until there is no element greater than 0.

[0106] (44) Select The maximum value v in the middle, record the row and column where it is located, and get a matching target pair (row number, column number), where the row number represents the second observation load The target number, column number represents the first observed load The target sequence number is, and v is the associated value of the matching target pair. The matching target pair and the associated value are recorded in the association result In The value of v in is changed to -1.

[0107] (45) When If there is no element greater than 0 in All elements in that are greater than 0. The target pairs corresponding to the elements less than 0 in must not belong to the same entity and will not be recorded. The rows and columns with all zeros in the table correspond to the second observed loads. and the first observed load The unassociated targets have a corresponding association value of 0. They are recorded as independent targets in the association result. In. Related results as a set of consistency measures for pairs of observed loadings.

[0108] (46) Calculate the correlation results The sum of all the association values ​​in is recorded as the association strength .

[0109] (47) In the four correlation strengths Select the largest , and its corresponding association results As the preferred consistency measure, it is also the final association result. Specifically, in this association result In the first goal , find the first target For all matching target pairs, if there is only one matching target pair, the second target in the matching target pair is the same as the first target. The second target belonging to the same entity. If there are multiple matching target pairs, the one with the largest correlation value is determined and the second target is determined as the first target. A second target belonging to the same entity.

[0110] This specific embodiment belongs to the field of target detection and recognition, remote sensing multi-source target association, and multi-source information fusion. For the sea surface ship targets under the collaborative observation of heterogeneous observation payloads, due to the few common features and positioning deviations, the association difficulty is great. A method for measuring the association of simultaneous and near-phase ship targets under the collaborative observation of heterogeneous observation payloads is provided. This method is based on the satellite platform on-orbit positioning system error and target motion considerations. According to the common properties of heterogeneous payloads, a method for measuring association based on topological consistency is designed. Considering that the positioning errors of on-orbit targets located on different satellite platforms are mostly system errors, that is, there is a difference of rotation and translation between the two groups of targets output by two satellite platforms (or payloads), the two common properties of target position and direction are used to construct a geometric description of the relative position relationship of the target, and based on this description, a topological similarity measurement of targets between different observation payloads is established, realizing the multi-target association of heterogeneous payloads such as AIS, optical, SAR, and infrared, and establishing a unified data foundation for subsequent multi-source information fusion. This method is simple and effective, with low computational complexity, and can meet the real-time processing requirements under limited computing resources on-orbit.

[0111] Figure 4 is a block diagram of a directional target association device according to an exemplary embodiment of the present disclosure. Figure 4 The device includes a target event receiving unit 401, a description unit 402, a pairing unit 403, a measurement unit 404, and a determination unit 405.

[0112] The receiving unit 401 can receive multiple target observation information obtained by multiple different observation payloads observing targets appearing in the same geographical area, wherein the observation time difference of the multiple different observation payloads is less than the preset time difference, and one target observation information corresponds to one observation payload and one target.

[0113] The description unit 402 can determine the geometric description information of each target for each observation load among multiple different observation loads based on the target observation information of each target observed by the observation load, wherein the geometric description information is used to describe the relative position relationship between the corresponding target and other targets among the targets observed by the observation load except the corresponding target.

[0114] The pairing unit 403 can determine multiple observation load pairs from multiple different observation loads, and for each observation load pair in the multiple observation load pairs, determine multiple target pairs, wherein each observation load pair includes a first observation load and a second observation load, and each target pair includes a first target and a second target, the first target is a target observed by the first observation load, and the second target is a target observed by the second observation load.

[0115] The measurement unit 404 can compare the geometric description information of the first target with the geometric description information of the second target for each target pair in the multiple target pairs to obtain a target pair similarity measure of the target pairs, and use the target pair similarity measures of the multiple target pairs as a consistency measure of the observation load pairs, wherein the consistency measure is used to represent the degree of similarity of the observed targets of the corresponding observation load pairs.

[0116] The determination unit 405 may determine the association relationship between the targets observed by the multiple different observation loads according to the consistency measurement of the multiple observation load pairs, wherein the association relationship indicates that the targets observed by the different observation loads belong to the same entity.

[0117] Optionally, the multiple different observation loads include a first observation load and multiple second observation loads, the first observation load is any one of the multiple different observation loads, wherein the pairing unit 403 determines multiple observation load pairs from the multiple different observation loads, including: the first observation load and each second observation load are respectively formed into an observation load pair to obtain multiple observation load pairs.

[0118] Optionally, the target observation information includes the corresponding target observed by the corresponding observation payload Location information and direction information , direction information To describe the corresponding target direction, goal represents the target numbered j observed by the observation payload numbered i, wherein the description unit 402 determines the geometric description information of each target based on the target observation information of each target observed by the observation payload, including: for each target , except for the target Other goals Location information and direction information Convert to the reference coordinate system to get other targets Conversion position information and conversion direction information , where the origin of the reference coordinate system is the target The position of the reference coordinate system and the direction of the coordinate axis of the target direction; according to other goals Conversion position information and conversion direction information , determine the target The geometric description information.

[0119] Optionally, the description unit 402 performs the following operations according to other objectives: Conversion position information and conversion direction information , determine the target The geometric description information includes: when the observation load is the first observation load, the target As the first goal, other goals Conversion position information and conversion direction information , as the first goal Target geometry description information ,in, Indicates that among all the targets observed by the first observation load, except target The set of all other targets except For each other goal , based on other goals Conversion position information , determine other goals Symmetrical position information of the symmetrical points relative to the x-axis, y-axis, and origin in the reference coordinate system , , , get other goals Four relative position information ,in, = ; Other targets Each relative position information and conversion direction information , as the second goal A set of geometric description information , get the second goal Four sets of geometric description information, where the m values ​​of the same set of geometric description information are equal. Indicates that among the targets observed by the second observation payload, except target The set of all other targets except

[0120] Optionally, the measurement unit 404 may also: for each target pair in the multiple target pairs, compare the geometric description information of the first target with each group of geometric description information of the second target, respectively, to obtain four groups of target pair similarity measures of the target pairs, wherein the target pair similarity measures are constructed to be positively or negatively correlated with the possibility that the two targets in the corresponding target pair belong to the same entity; summarize the four groups of target pair similarity measures of the multiple target pairs by group, to obtain four groups of consistency measures of the observation load pairs; the determination unit 405 may also: for each observation load pair in the multiple observation load pairs, determine the group with the highest similarity from the four groups of consistency measures of the observation load pairs, recorded as the preferred consistency measure; based on the preferred consistency measure, determine the target pairs in each target pair of the observation load pairs that belong to the same entity.

[0121] Optionally, the measurement unit 404 compares the geometric description information of the first target with each group of geometric description information of the second target respectively to obtain four groups of target pair similarity measures for the target pairs, including: determining multiple other target pairs, wherein each other target pair includes a first other target and a second other target, the first other target is a target other than the first target observed by the first observation load, and the second other target is a target other than the second target observed by the second observation load; for each group of geometric description information of the second target, determining a preset function value for each other target pair in the multiple other target pairs based on the geometric description information of the first target and the geometric description information of the second target, taking the sum of the preset function values ​​of the multiple other target pairs as a group of target pair similarity measures for the target pair, and obtaining four groups of target pair similarity measures for the target pairs.

[0122] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0123] Figure 5 A structural block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown.

[0124] Reference Figure 5 The electronic device includes: at least one memory 501 and at least one processor 502, wherein the at least one memory 501 stores computer executable instructions, and when the computer executable instructions are executed by the at least one processor 502, the at least one processor is prompted to execute the directed target association method as described in the above exemplary embodiment.

[0125] 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.

[0126] In an electronic device, the processor 502 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 502 may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0127] The processor 502 may execute instructions or codes stored in the memory 501, wherein the memory 501 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.

[0128] The memory 501 may be integrated with the processor 502, for example, by placing RAM or flash memory within an integrated circuit microprocessor or the like. In addition, the memory 501 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 501 and the processor 502 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 502 can read files stored in the memory.

[0129] 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.

[0130] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing instructions may also be provided, wherein the instructions, when executed by at least one processor, cause the at least one processor to execute the directed target association method as described in the above exemplary embodiment. Examples of computer-readable storage media 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.

[0131] According to an exemplary embodiment of the present disclosure, a computer program product may also be provided, including computer instructions. When the computer instructions are executed by at least one processor, the directed target association method as described in the above exemplary embodiment is executed.

[0132] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which 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 description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

[0133] 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 directed target association method, characterized in that: The directed target association method comprises: Receiving a plurality of target observation information obtained by observing a plurality of different observation payloads on a target appearing in the same geographical area, wherein the observation time difference of the plurality of different observation payloads is less than a preset time difference, and one target observation information corresponds to one observation payload and one target; For each observation load among the multiple different observation loads, determining geometric description information of each target according to target observation information of each target observed by the observation load, wherein the geometric description information is used to describe the relative position relationship between the corresponding target and other targets among the targets observed by the observation load except the corresponding target; Determine a plurality of observation load pairs from the plurality of different observation loads, and for each observation load pair in the plurality of observation load pairs, determine a plurality of target pairs, wherein each observation load pair includes a first observation load and a second observation load, and each target pair includes a first target and a second target, wherein the first target is a target observed by the first observation load, and the second target is a target observed by the second observation load; For each target pair of the multiple target pairs, the geometric description information of the first target is compared with the geometric description information of the second target to obtain a target pair similarity measure of the target pair, and the target pair similarity measures of the multiple target pairs are used as consistency measures of the observation load pairs, wherein the consistency measure is used to represent the similarity degree of the observation targets of the corresponding observation load pairs; Determine, according to the consistency measure of the plurality of observation load pairs, an association relationship between the targets respectively observed by the plurality of different observation loads, wherein the association relationship indicates that the targets observed by the different observation loads belong to the same entity; The target observation information includes the corresponding target observed by the corresponding observation load. Location information and direction information , the direction information To describe the corresponding target direction, goal represents a target numbered j observed by an observation payload numbered i, wherein the step of determining geometric description information of each target based on target observation information of each target observed by the observation payload includes: For each goal , except for the target Other goals Location information and direction information Convert to the reference coordinate system to get other targets Conversion position information and conversion direction information , where the origin of the reference coordinate system is the target The coordinate axis direction of the reference coordinate system is consistent with the target The orientation of According to other goals Conversion position information and conversion direction information , determine the target The geometric description information.

2. The directed target association method according to claim 1, characterized in that: The multiple different observation loads include one first observation load and multiple second observation loads, the first observation load is any one of the multiple different observation loads, wherein determining multiple observation load pairs from the multiple different observation loads includes: The first observation load and each of the second observation loads respectively constitute an observation load pair to obtain the multiple observation load pairs.

3. The directed target association method according to claim 1, characterized in that: Other objectives Conversion position information and conversion direction information , determine the target The geometric description information includes: When the observed load is the first observed load, the target For the first goal, other goals Conversion position information and conversion direction information , as the first goal Geometric description information ,in, Indicates that among the targets observed by the first observation payload, except target The set of all other targets except When the observed load is the second observed load, the target For the second goal, for each other goal , based on other goals Conversion position information , determine other goals Symmetrical position information of symmetrical points relative to the x-axis, y-axis and origin in the reference coordinate system , , , get other goals Four relative position information ,in, = ; Other goals Each relative position information and conversion direction information , as the second goal A set of geometric description information , get the second goal Four sets of geometric description information, where the m values ​​of the same set of geometric description information are equal. Indicates that among the targets observed by the second observation payload, except target The set of all other targets except 4. The directed target association method according to claim 3, characterized in that: For each target pair of the multiple target pairs, the geometric description information of the first target is compared with the geometric description information of the second target to obtain a target pair similarity measure of the target pair, and the target pair similarity measures of the multiple target pairs are used as consistency measures of the observation load pairs, including: For each target pair of the plurality of target pairs, respectively comparing the geometric description information of the first target with each set of geometric description information of the second target, to obtain four sets of target pair similarity measures of the target pair, wherein the target pair similarity measures are constructed to be positively correlated or negatively correlated with the likelihood that the two targets in the corresponding target pair belong to the same entity; Aggregating the four groups of target pair similarity measures of the plurality of target pairs by group to obtain four groups of consistency measures of the observation load pairs; The determining, based on the consistency metrics of the plurality of observation load pairs, the association relationship between the targets respectively observed by the plurality of different observation loads comprises: For each of the plurality of observed load pairs, determine a group with the highest similarity from the four groups of consistency metrics of the observed load pair, and record it as a preferred consistency metric; Based on the preferred consistency metric, target pairs belonging to the same entity among the target pairs of the observed load pairs are determined.

5. The directed target association method according to claim 4, characterized in that: The geometric description information of the first target is compared with each group of geometric description information of the second target to obtain four groups of target pair similarity measures of the target pairs, including: determining a plurality of other target pairs, wherein each other target pair comprises a first other target and a second other target, wherein the first other target is a target other than the first target observed by the first observation payload, and the second other target is a target other than the second target observed by the second observation payload; For each set of geometric description information of the second target, determine the preset function value of each other target pair in the multiple other target pairs according to the geometric description information of the first target and the geometric description information of the second target, and take the sum of the preset function values ​​of the multiple other target pairs as a set of target pair similarity measures of the target pairs, to obtain four sets of target pair similarity measures of the target pairs.

6. A directed target association device, characterized in that: The directed target associating device comprises: A receiving unit is configured to receive a plurality of target observation information obtained by observing a plurality of different observation payloads on a target appearing in a same geographical area, wherein the observation time difference of the plurality of different observation payloads is less than a preset time difference, and one target observation information corresponds to one observation payload and one target; a description unit configured to determine, for each observation load among the multiple different observation loads, geometric description information of each target according to target observation information of each target observed by the observation load, wherein the geometric description information is used to describe a relative position relationship between the corresponding target and other targets among the targets observed by the observation load except the corresponding target; a pairing unit configured to determine a plurality of observation load pairs from the plurality of different observation loads, and for each of the plurality of observation load pairs, determine a plurality of target pairs, wherein each observation load pair includes a first observation load and a second observation load, and each target pair includes a first target and a second target, wherein the first target is a target observed by the first observation load, and the second target is a target observed by the second observation load; a measurement unit configured to compare the geometric description information of the first target with the geometric description information of the second target for each target pair of the plurality of target pairs, obtain a target pair similarity measure of the target pair, and use the target pair similarity measures of the plurality of target pairs as consistency measures of the observation load pairs, wherein the consistency measure is used to represent the similarity degree of the observation targets of the corresponding observation load pairs; A determining unit is configured to determine, based on the consistency measure of the plurality of observation load pairs, an association relationship between the targets respectively observed by the plurality of different observation loads, wherein the association relationship indicates that the targets observed by the different observation loads belong to the same entity; The target observation information includes the corresponding target observed by the corresponding observation load. Location information and direction information , the direction information To describe the corresponding target direction, goal The target numbered j observed by the observation payload numbered i, wherein the description unit determines the geometric description information of each target according to the target observation information of each target observed by the observation payload, including: For each goal , except for the target Other goals Location information and direction information Convert to the reference coordinate system to get other targets Conversion position information and conversion direction information , where the origin of the reference coordinate system is the target The coordinate axis direction of the reference coordinate system is consistent with the target The orientation of According to other goals Conversion position information and conversion direction information , determine the target The geometric description information.

7. An electronic device, characterized in that: include: 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 directed target association method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by at least one processor, the at least one processor is prompted to perform the directed target association method according to any one of claims 1 to 5.

9. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by at least one processor, the at least one processor is prompted to perform the directed target association method according to any one of claims 1 to 5.

Images