Multi-aircraft target collaborative allocation method, device and equipment based on image detection

Abstract

The invention provides a multi-aircraft target collaborative allocation method, device and equipment based on image detection, and the method comprises the steps: obtaining a region image of a working region, and recognizing a plurality of targets and reference points from the region image; calculating the position relationship between each target and the reference point, and sorting each target based on the position relationship between each target and the reference point; dividing the sorted targets into a plurality of groups with the same number as the aircrafts, and distributing a corresponding group for each aircraft; and each aircraft selects one target from the corresponding group as a cooperative collision target, and collides the target. According to the method and the device, the overlapping problem of selecting cooperative collision targets can be effectively avoided through data chains and information interaction which are not needed among the aircrafts, and the cooperative distribution efficiency of the multiple aircraft targets is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of design and manufacturing of multiple aircraft, and in particular to a method, device and equipment for collaborative allocation of multiple aircraft targets based on image detection. Background Art

[0002] With the rapid development of guidance technology and target image intelligent recognition technology, collaborative operations on multiple isomorphic fixed targets by multiple aircraft have gradually become a new operation mode in the future. When performing collaborative operations on multiple isomorphic fixed targets, if the distance between the targets is small and the total number of targets is much larger than the total number of aircraft in the multi-aircraft, it is generally necessary to group the multiple targets first, and then select the collision targets corresponding to each aircraft in the group for collision operations. However, in the absence of data links and information exchange between the aircraft, it is difficult to ensure that the targets selected by each aircraft do not overlap, thereby reducing the collaborative efficiency. Therefore, how to ensure that the targets selected by each aircraft are not repeated during the collaborative operation, and then improve the efficiency of collaborative allocation of multi-aircraft targets is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0003] In view of this, the present disclosure proposes a method, device and equipment for collaborative allocation of multiple aircraft targets based on image detection, which can improve the efficiency of collaborative allocation of multiple aircraft targets.

[0004] According to a first aspect of the present disclosure, a method for collaboratively allocating multiple aircraft targets based on image detection is provided, comprising: Acquire a regional image of the working area, and identify multiple targets and reference points constituting a group target from the regional image; Calculating the positional relationship between each of the targets and the reference point, and sorting each of the targets based on the positional relationship between each of the targets and the reference point; Divide the sorted targets into a plurality of groups equal to the number of the aircraft, and assign a corresponding group to each of the aircraft according to the number of each of the aircraft; Each of the aircraft selects a target from the corresponding group as a cooperative collision target; Wherein, the reference point selected by each of the aircraft is the same designated reference object.

[0005] In a possible implementation manner, when a reference point is identified from the regional image, the method includes: Obtaining a bounding box of each of the objects; Calculating a bounding box of the group of objects based on the boundaries of each of the objects; Based on the bounding box of the group object, the reference point is identified.

[0006] In a possible implementation manner, when calculating the positional relationship between each of the targets and the reference point, the method includes: Selecting a target closest to the reference point from among the targets as a reference target; constructing an initial vector based on the reference target and the reference point; Calculating the line vector between each of the targets and the reference point; Based on the line vector between each of the targets and the reference point and the initial vector, the positional relationship between each of the targets and the reference point is calculated.

[0007] In a possible implementation, when the sorted targets are divided into a plurality of groups equal in number to the number of aircraft, the method includes: Acquire the total number of the aircraft and the total number of the targets; Calculating the number of targets in each formation based on the total number of the aircraft and the total number of the targets; According to the number of targets in each group, the sorted targets are divided into a number of groups equal to the number of aircraft.

[0008] In a possible implementation, when a target is selected from a corresponding group as a cooperative collision target, it is implemented based on the distance between each target in the group and the reference point.

[0009] According to a second aspect of the present disclosure, a multi-aircraft target collaborative allocation device based on image detection is provided, comprising: An image recognition module, used for acquiring a regional image of the operation area, and identifying a plurality of targets and reference points constituting a group target from the regional image; A sorting module, used for calculating the positional relationship between each of the targets and the reference point, and sorting each of the targets based on the positional relationship between each of the targets and the reference point; A grouping module, used to divide the sorted targets into a plurality of groups equal to the number of the aircraft, and assign a corresponding group to each of the aircraft according to the number of each of the aircraft; An allocation module, used to enable each of the aircraft to select a target from a corresponding group as a cooperative collision target; Wherein, the reference point selected by each of the aircraft is the same designated reference object.

[0010] In a possible implementation manner, the sorting module, when calculating the positional relationship between each of the targets and the reference point, is specifically configured to: Selecting a target closest to the reference point from among the targets as a reference target; constructing an initial vector based on the reference target and the reference point; Calculating the line vector between each of the targets and the reference point; Based on the line vector between each of the targets and the reference point and the initial vector, the positional relationship between each of the targets and the reference point is calculated.

[0011] In a possible implementation, the grouping module, when dividing the sorted targets into a plurality of groups equal in number to the number of aircraft, is specifically configured to: Acquire the total number of the aircraft and the total number of the targets; Calculating the number of targets in each formation based on the total number of the aircraft and the total number of the targets; According to the number of targets in each group, the sorted targets are divided into a number of groups equal to the number of aircraft.

[0012] According to a third aspect of the present disclosure, a multi-aircraft target collaborative allocation device based on image detection is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute the method described in the first aspect of the present disclosure.

[0013] According to a fourth aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions, when executed by a processor, implement the method described in the first aspect of the present disclosure.

[0014] The present disclosure provides a method, device and equipment for cooperative allocation of multiple aircraft targets based on image detection, the method comprising: obtaining a regional image of an operation area, and identifying multiple targets and reference points from the regional image; calculating the positional relationship between each target and the reference point, and sorting each target based on the positional relationship between each target and the reference point; dividing each sorted target into a plurality of groups equal to the number of aircraft, and assigning a corresponding group to each aircraft; each aircraft selects a target from the corresponding group as a cooperative collision target. In the present disclosure, unnecessary data links and information interactions between aircraft can also effectively avoid the overlapping problem of selecting cooperative collision targets, thereby improving the efficiency of cooperative allocation of multiple aircraft targets.

[0015] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0017] Figure 1 A flowchart showing a method for cooperative allocation of multiple aircraft targets based on image detection according to an embodiment of the present disclosure is shown; Figure 2 A schematic diagram showing a target recognition result according to an embodiment of the present disclosure is shown; Figure 3 A flowchart showing an example of a method for cooperative allocation of multiple aircraft targets based on image detection according to an embodiment of the present disclosure; Figure 4 An example diagram showing a group target grouping result according to an embodiment of the present disclosure; Figure 5 An example diagram showing an aircraft selecting a collision target within a formation according to an embodiment of the present disclosure; Figure 6 A schematic block diagram of a device for cooperatively allocating multiple aircraft targets based on image detection according to an embodiment of the present disclosure is shown; Figure 7 A schematic block diagram of a multi-aircraft target cooperative allocation device based on image detection according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0018] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0019] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0020] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0021] <Method Example> Figure 1 The flowchart of the method for coordinated allocation of multiple aircraft according to an embodiment of the present disclosure is shown. The method is completed by independent calculations by the seekers on each independent aircraft in the multi-aircraft. The target coordinated allocation method performed by the seekers on each aircraft is the same. Therefore, the method for coordinated allocation of multiple aircraft targets based on image detection in the present disclosure is described below by taking one seeker as an example. Figure 1 As shown, the method includes steps S1100-S1400.

[0022] S1100, obtaining a regional image of an operation area, and identifying a plurality of targets and reference points from the regional image, wherein the operation area refers to an area where a homogeneous fixed group of targets is located.

[0023] Specifically, during the collaborative allocation process, the regional image of the work area is acquired through the image acquisition device, and the acquired regional image is subjected to target recognition, thereby identifying multiple targets constituting a homogeneous fixed group target from the regional image. For each identified target, its bounding box and label are marked in the regional image. The label is used to uniquely identify a target object. In a specific example, the target recognition result of the homogeneous fixed group target can be as follows: Figure 2 shown.

[0024] After identifying each target in the regional image, reference points required for collaborative allocation can be further identified from the regional image according to each identified target. Specifically, the following steps can be included: First, obtain the bounding box of each object.

[0025] Second, based on the bounding boxes of each target, the bounding box of the group target is calculated. The bounding box of the group target includes the outer bounding boxes of all targets. In a specific example, the bounding box of the group target can be as follows: Figure 2 Shown in black frame.

[0026] Third, based on the bounding box of the group target, identify the reference point. Specifically, Figure 2 As shown, the bounding box of the group target may include at least one of a front bounding box, a rear bounding box, a left bounding box and a right bounding box. Among them, the front bounding box is a bounding box far away from the launch position of the aircraft, the rear bounding box is a bounding box close to the launch position of the aircraft, the left bounding box is a bounding box located to the left of the launch position of the aircraft, and the right bounding box is a bounding box located to the right of the launch position of the aircraft. When identifying reference points based on the bounding box of the group target, a designated reference object can be selected in front of the front bounding box as a reference point, a designated reference object can be selected behind the rear bounding box as a reference point, a designated reference object can be selected on the left side of the left bounding box as a reference point, and a designated reference object can be selected on the right side of the rear bounding box as a reference point. Among them, the reference point selected by each aircraft is the same designated reference object, and the designated reference object refers to a reference object with significant image features, which can be quickly identified and is closest to the reference bounding box. In a specific example, the designated reference object can be an object with significant features and can be quickly identified that is pre-projected near the reference bounding box.

[0027] It should be noted here that the positions of each independent aircraft are different, and the fields of view may be different. In order to ensure that each aircraft can identify the designated target, when identifying the reference target, the camera device can be adjusted up, down, left, and right respectively to accurately capture the designated reference object.

[0028] S1200, calculating the positional relationship between each target and the reference point, and sorting each target based on the positional relationship between each target and the reference point.

[0029] In a possible implementation, when calculating the positional relationship between each target and the reference point, the following steps may be included: First, select the target closest to the reference point from among the targets as the reference target.

[0030] It should be noted here that in order to ensure that the reference targets selected by each aircraft after independent calculation are the same, it is necessary to ensure that there is only one target closest to the reference point. Therefore, after obtaining the reference target, it is necessary to further determine whether the reference target closest to the reference point is unique: if the reference point is unique, then perform the operation of constructing the initial vector based on the reference point and the reference target; if the reference point is not unique, it is necessary to select a unique reference target as the final reference target based on the preset selection strategy, and then construct the initial vector based on the final reference target and the reference point. Among them, the preset selection strategy in each aircraft is consistent to ensure that each aircraft can select the same reference target when calculating independently. In one possible implementation, the preset selection strategy can be to select the reference target located on the far left from multiple reference targets with equal distances from the reference point as the final reference target. In another possible implementation, the preset selection strategy can be to select the reference target located on the far right from multiple reference targets with equal distances from the reference point as the final reference target.

[0031] Second, based on the reference target and the reference point, an initial vector is constructed. Specifically, the initial vector is constructed with the reference point as the starting point and the reference target as the end point.

[0032] Third, calculate the line vector between each target and the reference point. Specifically, with the reference point as the starting point and each target as the end point, construct the line vector between each target and the reference point, that is, the line vector between each target and the reference point is from the reference point to the target.

[0033] Fourth, based on the line vector and the initial vector between each target and the reference point, the positional relationship between each target and the reference point is calculated. Specifically, the cosine distance between the line vector and the initial vector between each target and the reference point is calculated, and the positional relationship between each target and the reference point is characterized by the calculated cosine distance. The calculation formula of the cosine distance is as follows: Where D i ( X, Y i ) is the i The cosine distance between the line vector between the target and the reference point and the initial vector, X is the initial vector, Y i for i The line vector between the target and the reference point, n is the total number of targets in the group.

[0034] After calculating the positional relationship between each target and the reference point, each target will be sorted according to the positional relationship between each target and the reference point. In an embodiment where the positional relationship is characterized by the cosine distance between the line vector between each target and the reference point and the initial vector, each target will be sorted in descending order of the cosine distance.

[0035] S1300: Divide the sorted targets into a number of groups equal to the number of aircraft, and assign a corresponding group to each aircraft.

[0036] In a possible implementation, when the sorted targets are divided into a plurality of groups equal to the number of aircraft, the following steps may be included: First, the total number of aircraft and the total number of targets are obtained. In the collaborative allocation method disclosed in the present invention, the total number of independent aircraft included in the multi-aircraft is less than the total number of targets included in the group target, that is, the number of targets to be operated is greater than or equal to the total number of independent aircraft in the multi-aircraft.

[0037] Second, based on the total number of aircraft and the total number of targets, the number of targets in each group is calculated. Specifically, the ratio of the total number of targets to the total number of aircraft is calculated, and the calculated ratio is the number of targets in each group.

[0038] Third, according to the number of targets in each group, the sorted targets are divided into multiple groups equal to the number of aircraft. For example, if the total number of targets is 30, the total number of aircraft is 6, and the ratio of the total number of targets to the total number of aircraft is 5, then the targets sorted 1-5 are divided into the first group; the targets sorted 6-10 are divided into the second group; the targets sorted 11-15 are divided into the third group, the targets sorted 16-20 are divided into the fourth group, the targets sorted 11-25 are divided into the fifth group, and the targets sorted 26-30 are divided into the sixth group.

[0039] After completing the grouping of the group targets, a corresponding group will be assigned to each aircraft. Specifically, each aircraft has its own number, and the aircraft are sorted in descending order according to their numbers. The first group is assigned to the first-ranked aircraft, the second group is assigned to the second-ranked aircraft, the third group is assigned to the third-ranked aircraft, and so on, so that each aircraft is assigned a corresponding group.

[0040] It should be noted that after performing independent calculations according to the above scheme, the grouping results of each aircraft on the target are the same, the sorting results of each aircraft number are also the same, and the number of groups is the same as the number of aircraft. Therefore, a corresponding group is assigned to each aircraft according to the sorting of each aircraft number, which can achieve unique and non-overlapping grouping of aircraft pairs. This effectively avoids the overlap of collision targets of each aircraft.

[0041] S1400, each aircraft selects a target from the corresponding group as a cooperative collision target.

[0042] In a possible implementation, when a target is selected from a corresponding group as a cooperative collision target, it is implemented based on the distance between each target in the group and a reference point.

[0043] Specifically, for the assigned group, the Euclidean distance between each target in the group and the reference point is calculated. The calculation formula of the Euclidean distance is as follows: Where, T c (x c , z c ) is the position coordinate of the reference point, T i (x i , z i ) is the position coordinate of the i-th target in the group, Si (T i , T c ) is the Euclidean distance between the i-th target in the group and the reference point.

[0044] After calculating the Euclidean distance between each target in the group and the reference point, the final collision target is screened out in combination with the reference point selection method, and the collision operation is performed on it. Specifically, when the reference point is in front of the front boundary, the target in the group with the smallest Euclidean distance is selected as the collaborative collision target. When the reference point is behind the rear boundary, the target in the group with the largest Euclidean distance is selected as the collaborative collision target. When the reference point is to the left of the left boundary or to the right of the right boundary, the target in the group with the smallest Euclidean distance is selected as the collaborative collision target.

[0045] When there are more than two targets in the group with the same Euclidean distance to the reference point, the target in the group closest to the center of the field of view can be selected as the final cooperative collision target.

[0046] It should be noted here that the method strategy for independent calculation of each aircraft is completely consistent, thereby ensuring that each aircraft can achieve the purpose of non-overlapping collaborative collision target selection when calculating completely independently.

[0047] The present disclosure provides a method for cooperative allocation of multi-aircraft targets based on image detection, including: obtaining a regional image of an operation area, and identifying multiple targets and reference points from the regional image; calculating the positional relationship between each target and the reference point, and sorting each target based on the positional relationship between each target and the reference point; dividing each sorted target into multiple groups with the same number of aircraft, and assigning a corresponding group to each aircraft; each aircraft selects a target from the corresponding group as a cooperative collision target. After adopting the method of the present disclosure, the reference points identified by each aircraft in the multi-aircraft are all the same designated reference objects, and although the positional relationship between each target and the same reference point calculated by different aircraft has deviations, the results of sorting based on the calculated positional relationship are consistent. That is to say, the sorting results of each target obtained by each aircraft in the independent calculation process are the same, and then the sorting results can be further divided into the same multiple groups based on the same total number of aircraft. Finally, a corresponding group is assigned to each aircraft according to the number of each aircraft, so as to ensure that the group assigned to each aircraft is also unique and non-overlapping, and then ensure that the cooperative collision targets selected by each aircraft will not overlap. It can be seen that in the present disclosure, each aircraft performs independent calculations based on the above rules, and no longer requires data links and information interactions between aircraft. This can also effectively avoid overlapping problems in selecting collaborative collision targets and improve the efficiency of collaborative allocation of multi-aircraft targets.

[0048] <Method Example> In order to clearly explain the method of the present invention, the method of the present invention is further explained below with reference to a specific example. In this example, the group target includes 60 homogeneous fixed targets, and 15 independent aircraft are launched at a time to perform collaborative operations on all targets. After each aircraft obtains the regional image of the operation area and identifies 60 targets from the regional image, it will simultaneously execute the following operations: Figure 3 The multi-aircraft target cooperative allocation method shown in FIG. Figure 3 As shown, the method may include steps S2110-S2022.

[0049] S2011, select a reference point. Specifically, calculate the front bounding box of the group target, and select a designated reference object in front of the front bounding box as a reference point.

[0050] S2012, selecting the target closest to the reference point from among the targets as the reference target.

[0051] S2013, determine whether the target closest to the reference point is unique, and execute step S2014 if it is not unique, and execute step S2015 if it is unique.

[0052] S2014: Select a reference target located at the far left (or far right) from a plurality of reference targets that are at equal distances from the reference point as the final reference target. The selection strategy of each aircraft is consistent.

[0053] S2015, construct an initial vector based on the reference target and the reference point.

[0054] S2016, calculating the line vector between each target and the reference point, and calculating the cosine distance between the line vector between each target and the reference point and the initial vector.

[0055] S2017, sort the targets in descending order of cosine distance.

[0056] S2018, according to the result of sorting by cosine distance, the targets are grouped according to the number of aircraft, and the number of targets in each group is the ratio of the total number of targets to the total number of aircraft. In this embodiment, the number of targets in each group = 60 / 15 = 4, so that the four targets with the largest cosine distance (i.e. Figure 4 1, 2, 9 and 10) in the first group, and then select the four targets with the largest cosine distance to form the second group, and so on, and finally select the four targets with the smallest cosine distance (i.e. Figure 4 6, 16, 26 and 27) are divided into the fifteenth group.

[0057] S2019, matching the group numbers with the aircraft numbers. Specifically, sort the aircraft numbers from large to small, and match the first group (i.e. Figure 4 1, 2, 9, and 10) are assigned to the first ranked aircraft, the second group is assigned to the second ranked aircraft, and so on. Figure 4 6, 16, 26 and 27) are assigned to the fifteenth aircraft.

[0058] S2020, calculating the Euclidean distance between the target in the corresponding group and the reference point.

[0059] S2021, select the target in the group closest to the reference point as the collision target. Figure 5 As shown, for the aircraft ranked fifteenth, its corresponding group includes targets 6, 16, 26 and 27, among which, target 6 is closest to the reference point, so target 6 is used as the collision target of the aircraft ranked fifteenth. For the aircraft ranked first, its corresponding group includes targets 1, 2, 9 and 10, among which, target 9 is closest to the reference point, so target 9 is used as the collision target of the aircraft ranked first.

[0060] S2022, determining whether the collision target is unique; if not unique, selecting the collision target closest to the center of the field of view from the multiple collision targets as the final collision target, and subjecting it to a collision operation.

[0061] When the above method is used to perform multiple rounds of continuous wave collisions on group targets, not only can the overlapping rate of the collision targets be reduced, but also the targets close to the reference point can be gradually cleared, which can minimize the interference of the explosion smoke screen on the image guidance head.

[0062] <Device Example> Figure 6 FIG. 1 is a schematic block diagram of a device for cooperatively allocating multiple aircraft targets based on image detection according to an embodiment of the present disclosure. Figure 6 As shown, the device 100 includes: An image recognition module 110 is used to obtain a regional image of the work area and recognize multiple targets and reference points constituting a group target from the regional image; A sorting module 120, used to calculate the positional relationship between each target and the reference point, and sort each target based on the positional relationship between each target and the reference point; A grouping module 130 is used to divide the sorted targets into a plurality of groups having the same number as the number of aircraft in the multi-aircraft, and assign a corresponding group to each aircraft according to the number of each aircraft; The allocation module 140 is used to enable each aircraft to select a target from the corresponding group as a cooperative collision target.

[0063] In a possible implementation, the sorting module, when calculating the positional relationship between each target and the reference point, is specifically configured to: Select the target closest to the reference point from among the targets as the reference target; Based on the reference target and the reference point, an initial vector is constructed; Calculate the line vector between each target and the reference point; Based on the line vector between each target and the reference point and the initial vector, the positional relationship between each target and the reference point is calculated.

[0064] In a possible implementation, when the grouping module divides the sorted targets into a plurality of groups having the same number as the number of aircraft in the multi-aircraft, it is specifically configured to: Get the total number of aircraft and targets in multiple aircraft; Calculate the number of targets in each formation based on the total number of aircraft and the total number of targets; According to the number of targets in each group, the sorted targets are divided into multiple groups equal to the number of aircraft.

[0065] <Equipment Embodiment> Figure 7 FIG. 1 is a schematic block diagram of a multi-aircraft target cooperative allocation device based on image detection according to an embodiment of the present disclosure. Figure 7 As shown, the multi-aircraft target collaborative allocation device 200 based on image detection includes: a processor 210 and a memory 220 for storing executable instructions of the processor 210. The processor 210 is configured to implement any of the above-mentioned multi-aircraft target collaborative allocation methods based on image detection when executing the executable instructions.

[0066] Here, it should be noted that the number of processors 210 may be one or more. Meanwhile, in the multi-aircraft target collaborative allocation device 200 based on image detection in the embodiment of the present disclosure, an input device 230 and an output device 240 may also be included. The processor 210, the memory 220, the input device 230 and the output device 240 may be connected via a bus or in other ways, which are not specifically limited here.

[0067] The memory 220 is a computer-readable storage medium that can be used to store software programs, computer executable programs, and various modules, such as the program or module corresponding to the multi-aircraft target collaborative allocation method based on image detection in the embodiment of the present disclosure. The processor 210 executes various functional applications and data processing of the multi-aircraft target collaborative allocation device 200 based on image detection by running the software programs or modules stored in the memory 220.

[0068] The input device 230 may be used to receive input numbers or signals. The signals may be key signals related to the settings and function controls of the device / terminal / server. The output device 240 may include display devices such as display screens.

[0069] <Storage Medium Embodiment> According to a fourth aspect of the present disclosure, a non-volatile computer-readable storage medium is also provided, on which computer program instructions are stored. When the computer program instructions are executed by the processor 210, any of the above-mentioned methods for collaborative allocation of multi-aircraft targets based on image detection is implemented.

[0070] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for cooperative allocation of multi-aircraft targets based on image detection, characterized in that: include: Acquire a regional image of the working area, and identify multiple targets and reference points constituting a group target from the regional image; Calculating the positional relationship between each of the targets and the reference point, and sorting each of the targets based on the positional relationship between each of the targets and the reference point; Divide the sorted targets into a plurality of groups equal to the number of the aircraft, and assign a corresponding group to each of the aircraft according to the number of each of the aircraft; Each of the aircraft selects a target from the corresponding group as a cooperative collision target; Wherein, the reference point selected by each of the aircraft is the same designated reference object.

2. The method according to claim 1, characterized in that When a reference point is identified from the regional image, the method includes: Obtaining a bounding box of each of the objects; Calculating a bounding box of the group of objects based on the boundaries of each of the objects; Based on the bounding box of the group object, the reference point is identified.

3. The method according to claim 1, characterized in that When calculating the positional relationship between each of the targets and the reference point, it includes: Selecting a target closest to the reference point from among the targets as a reference target; constructing an initial vector based on the reference target and the reference point; Calculating the line vector between each of the targets and the reference point; Based on the line vector between each of the targets and the reference point and the initial vector, the positional relationship between each of the targets and the reference point is calculated.

4. The method according to claim 1, characterized in that: When the sorted targets are divided into a plurality of groups equal to the number of aircraft, the method comprises: Acquire the total number of the aircraft and the total number of the targets; Calculating the number of targets in each formation based on the total number of the aircraft and the total number of the targets; According to the number of targets in each group, the sorted targets are divided into a number of groups equal to the number of aircraft.

5. The method according to claim 1, characterized in that When a target is selected from the corresponding group as a cooperative collision target, it is achieved based on the distance between each target in the group and the reference point.

6. A multi-aircraft target collaborative allocation device based on image detection, characterized in that: include: An image recognition module, used for acquiring a regional image of the operation area, and identifying a plurality of targets and reference points constituting a group target from the regional image; A sorting module, used for calculating the positional relationship between each of the targets and the reference point, and sorting each of the targets based on the positional relationship between each of the targets and the reference point; A grouping module, used to divide the sorted targets into a plurality of groups equal to the number of the aircraft, and assign a corresponding group to each of the aircraft according to the number of each of the aircraft; An allocation module, used to enable each of the aircraft to select a target from a corresponding group as a cooperative collision target; Wherein, the reference point selected by each of the aircraft is the same designated reference object.

7. The device according to claim 6, characterized in that The sorting module, when calculating the positional relationship between each of the targets and the reference point, is specifically used to: Selecting a target closest to the reference point from among the targets as a reference target; constructing an initial vector based on the reference target and the reference point; Calculating the line vector between each of the targets and the reference point; Based on the line vector between each of the targets and the reference point and the initial vector, the positional relationship between each of the targets and the reference point is calculated.

8. The device according to claim 6, characterized in that When the grouping module divides the sorted targets into a plurality of groups equal in number to the number of aircraft, it is specifically used to: Acquire the total number of the aircraft and the total number of the targets; Calculating the number of targets in each formation based on the total number of the aircraft and the total number of the targets; According to the number of targets in each group, the sorted targets are divided into a number of groups equal to the number of aircraft.

9. A multi-aircraft target collaborative allocation device based on image detection, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 5 when executing the executable instructions.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images