Method and system for verifying track correlation using clustering and geometric pattern analysis

Abstract

A method for verifying track correlation according to one embodiment of the technical concept of the present disclosure comprises the steps of: obtaining a first track group and a second track group composed of tracks received from a plurality of sources, respectively; and, when an initial correlation occurs between a first track included in the first track group and a second track included in the second track group, verifying the initial correlation by comparing the geometric patterns of the first track group and the second track group, wherein the step of verifying the initial correlation by comparing the geometric patterns applies different geometric matching methods depending on whether the number of tracks in the first track group and the number of tracks in the second track group are the same.

Description

Technology Field

[0001] The technical concept of the present disclosure is a method and system for verifying track correlation using clustering and geometric pattern analysis. Background Technology

[0002] Central control centers, such as air traffic control systems or defense surveillance systems, receive track information detected and tracked from multiple different sources, including internal sensors or external interconnected systems, to generate and manage integrated airborne situational information. In this process, track correlation technology is essential to identify whether different tracks represent the same physical target.

[0003] General track correlation techniques utilize state information, such as position and velocity, included in track data received from each source, as well as covariance information representing the estimation error. To compare tracks received at different times, position and covariance predictions are performed through time compensation; subsequently, the identity of two tracks is determined through a matching technique that comprehensively compares kinematic and non-kinematic information.

[0004] However, these conventional correlation techniques have the following problems.

[0005] First, the performance of correlation depends significantly on the inherent characteristics of the sensors providing track information and the data reception cycle. In particular, track information received from external integration systems has a long transmission cycle, which can lead to significant errors in predicting status information.

[0006] Second, these prediction errors increase further when the target performs complex maneuvers such as ascent, descent, acceleration, deceleration, and turning. As a result, for multiple aircraft flying in close formation, track swapping frequently occurs, where they fail to correlate despite having the same trajectory, or incorrectly correlate different trajectories into the same trajectory.

[0007] Third, if such incorrect correlations and subsequent disconnections occur repeatedly, the aerial situation display screen becomes unstable, providing inaccurate information to the operator. This ultimately leads to a serious problem that causes confusion in the operator's perception of the battlefield situation and undermines the reliability of the entire system.

[0008] Therefore, there is a need to develop new technology that can overcome the problems of conventional technology and, in particular, improve the accuracy and stability of correlation for maneuvering nearby tracks. The problem to be solved

[0009] The problem that the present invention aims to solve is to provide a method and system that prevents errors such as track swapping that occur when performing correlation on proximity maneuver tracks received from various sources, and improves the accuracy and stability of correlation by verifying the initial correlation results. means of solving the problem

[0010] To achieve the above objectives, a method for verifying track correlation according to one aspect of the technical concept of the present disclosure comprises the steps of: acquiring a first track group and a second track group composed of tracks received from a plurality of sources, respectively; and, when an initial correlation occurs between a first track included in the first track group and a second track included in the second track group, verifying the initial correlation by comparing the geometric patterns of the first track group and the second track group, wherein the step of verifying the initial correlation by comparing the geometric patterns applies different geometric matching methods depending on whether the number of tracks in the first track group and the number of tracks in the second track group are the same.

[0011] According to one embodiment, the geometric matching method may correspond to a method of calculating and matching the first center point of the first track group and the second center point of the second track group when the number of tracks in the first track group and the number of tracks in the second track group are the same.

[0012] According to one embodiment, the step of comparing the geometric pattern may include aligning the first center point and the second center point, and then generating possible one-to-one pairing combinations between each track of the first track group and each track of the second track group.

[0013] According to one embodiment, the step of comparing the geometric patterns may further include the step of calculating an accumulated error by summing the distance errors between the paired tracks for each generated pairing combination.

[0014] According to one embodiment, the step of comparing the geometric patterns may further include the step of comparing the calculated cumulative errors and selecting the pairing combination having the smallest cumulative error.

[0015] According to one embodiment, the verifying step may include a step of finally verifying the initial correlation as valid when the distances of all paired track pairs included in the selected pairing combination each satisfy a preset individual threshold.

[0016] According to one embodiment, the verification step may further include the step of rejecting the pairing combination when there is a track pair among the track pairs included in the selected pairing combination that does not satisfy the individual threshold, and selecting the pairing combination having the next smallest cumulative error among the remaining pairing combinations to repeat the final verification.

[0017] According to one embodiment, the geometric matching method may correspond to a method of matching a first reference track selected within the first track group and a second reference track selected within the second track group when the number of tracks within the first track group and the number of tracks within the second track group are different.

[0018] According to one embodiment, the step of comparing the geometric patterns may further include the step of calculating internal geometric correlation information, including relative distances, azimuths, and altitudes between tracks within the first track group and between tracks within the second track group, respectively, before performing matching between the first reference track and the second reference track.

[0019] According to one embodiment, the step of comparing the geometric patterns may further include the step of determining the similarity of the geometric patterns by comparing the calculated internal geometric correlation information after aligning the first reference track and the second reference track.

[0020] According to one embodiment, the step of comparing the geometric pattern may further include the step of repeatedly performing the matching and the similarity determination of the geometric pattern for each possible combination of the first reference track and the second reference track.

[0021] According to one embodiment, the step of comparing the geometric patterns may further include the step of selecting the reference track combination with the highest similarity of geometric patterns based on the result of similarity judgment for each of the combinations.

[0022] According to one embodiment, the verifying step may include a step of finally verifying the initial correlation as valid if, for track pairs determined by the selected reference track combination, the geometric correlation information error of each track pair is within a preset individual threshold.

[0023] According to one embodiment, the method may further include the step of excluding from verification in advance pairs of tracks that cannot be correlated by using non-synchronous characteristic information including at least one of track identification information, platform type information, and radar cross-sectional area information, before comparing the geometric patterns.

[0024] According to one embodiment, the method may further include the step of performing time compensation to correct state information of tracks received from the plurality of sources to the same point in time before acquiring the first track group and the second track group.

[0025] A track correlation verification system comprising at least one computing device according to one embodiment of the technical concept of the present disclosure comprises a memory for storing instructions, and at least one processor configured to be operatively connected to the memory, wherein when the instructions are executed, the processor obtains a first track group and a second track group composed of tracks received from a plurality of sources, and, when an initial correlation occurs between a first track included in the first track group and a second track included in the second track group, the processor verifies the initial correlation by comparing the geometric patterns of the first track group and the second track group, wherein the at least one processor compares the geometric patterns by applying different geometric matching methods depending on whether the number of tracks in the first track group and the number of tracks in the second track group are the same.

[0026] According to one embodiment of the technical concept of the present disclosure, a computer-readable non-transient storage medium is provided for storing instructions that cause the processor to perform the above-described track correlation verification method. Effects of the invention

[0027] The correlation verification method according to the technical concept of the present disclosure can improve the accuracy of correlation by effectively preventing the trajectory swapping phenomenon that is prone to occur in close-movement trajectory groups by analyzing the geometric pattern of the entire trajectory group and verifying the correlation.

[0028] In addition, the present disclosure prevents repeated setting and unsetting by suppressing the occurrence of incorrect correlations, thereby providing the operator with stable and consistent air situation information, which can increase situational awareness and operational efficiency.

[0029] The effects obtainable through the technical concept of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present invention belongs from the description below. Brief explanation of the drawing

[0030] A brief description of each drawing is provided to help to better understand the drawings cited in the present disclosure. FIG. 1 is a block diagram schematically showing the configuration of a track correlation verification system according to one embodiment of the present disclosure. FIG. 2 is a flowchart showing the overall operation flow of a track correlation verification method according to one embodiment of the present disclosure. FIG. 3 is a flowchart showing the detailed operation flow of a center point shifting technique applied when the number of members of a track group is the same, according to one embodiment of the present disclosure. Figure 4 is a conceptual diagram to explain the operating principle of the center point shifting technique illustrated in Figure 3. FIG. 5 is a flowchart showing the detailed operation flow of a reference point shifting technique applied when the number of members of a track group is different, according to another embodiment of the present disclosure. Figure 6 is a conceptual diagram to explain the operating principle of the reference point movement technique illustrated in Figure 5. FIG. 7 is a block diagram schematically showing the hardware configuration of a computing device constituting a trajectory correlation verification system according to an exemplary embodiment of the present disclosure. Specific details for implementing the invention

[0031] Exemplary embodiments according to the technical concept of the present disclosure are provided to more fully explain the technical concept of the present disclosure to those skilled in the art, and the following embodiments may be modified in various different forms, and the scope of the technical concept of the present disclosure is not limited to the following embodiments. Rather, these embodiments are provided to make the present disclosure more faithful and complete and to fully convey the technical concept of the present invention to those skilled in the art.

[0032] In this disclosure, terms such as "first," "second," etc. are used to describe various members, regions, layers, parts, and / or components; however, it is obvious that these members, parts, regions, layers, parts, and / or components should not be limited by these terms. These terms do not imply a specific order, hierarchy, or superiority, and are used solely to distinguish one member, region, part, or component from another. Accordingly, the first member, region, part, or component described below may refer to the second member, region, part, or component without departing from the teachings of the technical concept of this disclosure. For example, without departing from the scope of rights of this disclosure, the first component may be named the second component, and similarly, the second component may be named the first component.

[0033] Unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by those skilled in the art to which the concept of this disclosure belongs. Furthermore, commonly used terms, such as those defined in advance, should be interpreted as having a meaning consistent with what they mean in the context of the relevant technology, and should not be interpreted in an overly formal sense unless explicitly defined herein.

[0034] Where an embodiment can be implemented differently, a specific process or sequence of steps may be performed differently from the order described. For example, two processes or steps described in succession may be performed substantially simultaneously or in the reverse order of the order described.

[0035] In addition, terms such as “~part,” “~device,” “~device,” and “~module” described in this specification refer to a unit that processes at least one function or operation, and may be implemented as hardware or software or a combination of hardware and software such as a processor, microprocessor, microcontroller, CPU (Central Processing Unit), AP (Application Processor), GPU (Graphics Processing Unit), NPU (Neural Processing Unit), APU (Accelerate Processor Unit), DSP (Drive Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), etc., and may also be implemented in a form combined with memory that stores data necessary for processing at least one function or operation.

[0036] Furthermore, it is intended to clarify that the classification of components in this specification is merely based on the primary function each component is responsible for. That is, two or more components described below may be combined into a single component, or a single component may be divided into two or more components based on more subdivided functions. Additionally, each component described below may additionally perform some or all of the functions of other components in addition to its primary function, and it is obvious that some of the primary functions of each component may be exclusively performed by other components.

[0037] The term 'and / or' as used herein includes each of the mentioned members and all combinations of one or more.

[0038] Hereinafter, embodiments according to the technical concept of the present disclosure will be described in detail with reference to the attached drawings.

[0039] FIG. 1 is a block diagram schematically showing the configuration of a track correlation verification system according to one embodiment of the present disclosure.

[0040] Referring to FIG. 1, the track correlation verification system (10; hereinafter abbreviated as 'system') according to the present invention is a system for providing stable and accurate aerial situation information to an operator by determining and verifying the identity between tracks received from multiple sources. For example, the system (10) can receive track information from multiple sources, such as its own sensor (20) and other interconnected systems (30). Here, the own sensor (20) may refer to a surveillance sensor, such as a radar, directly operated by the system (10), and other interconnected systems (30) may include, for example, a command and control system of a superior or adjacent unit, aerial and maritime surveillance assets that share information through a tactical data link, or an alliance system of a friendly nation performing joint operations.

[0041] The system (10) may include a plurality of functional units for processing such track information. Specifically, the system (10) may include a track preprocessing unit (110), a clustering unit (120), an initial correlation determination unit (130), a correlation verification unit (140), a track management unit (150), and a track provision unit (160). These functional units may be implemented by being integrated or distributed on at least one computing device.

[0042] The track preprocessing unit (110) can perform various preprocessing processes on track information received from multiple sources.

[0043] As a primary example, the track preprocessing unit (110) can align the time references between track information through time compensation for each track information. The self-sensor (20) and other interconnected systems (30) may have different data update cycles, and accordingly, each track information may be acquired and received at different times. Since directly comparing track information with such different time references results in inaccurate results, the track preprocessing unit (110) can align each track information to a common time reference. As an example of a specific time compensation method, the track preprocessing unit (110) sets a common reference time (such as the current system time), and if the received track information is for a time past the reference time, the track preprocessing unit (110) can predict (extrapolate) the expected position and error covariance at the reference time using dynamic characteristic information (e.g., position, velocity, acceleration, etc.) included in the track information.

[0044] According to the embodiment, the track preprocessing unit (110) may perform preprocessing processes such as additional data cleansing processes, such as coordinate system transformation or noise filtering.

[0045] The clustering unit (120) can group preprocessed track information based on each source. For example, the clustering unit (120) can form a first track group with tracks received from its own sensor (20) and form a second track group with tracks received from other interconnected systems (30).

[0046] The initial correlation determination unit (130) can determine whether initial correlation has occurred between the tracks of each clustered track group. Here, initial correlation may be a term used to distinguish it from the correlation that is finally determined according to the correlation verification described later. For example, the initial correlation determination unit (130) can determine whether initial correlation has occurred between the tracks included in each clustered track group through a comparison matching technique that compares dynamic characteristic information such as position and speed, and other additional information.

[0047] The correlation verification unit (140) can verify the validity of the initial correlation result generated by the initial correlation determination unit (130). In particular, the correlation verification unit (140) according to an embodiment of the present disclosure may apply different verification methods depending on whether the number of members in each trajectory group to which the two correlated trajectories belong, i.e., the number of trajectories, is the same. For example, the correlation verification unit (140) may analyze the similarity of the pattern by using a method of aligning the geometric center points of each group when the number of members in each trajectory group is the same, and by using a method of aligning the reference trajectories selected in each group when the number of members is different. The detailed operation of these verification methods will be described later with reference to FIGS. 3 to 6.

[0048] The track management unit (150) can manage tracks, such as creating new tracks or updating or deleting existing tracks, by reflecting the correlation results finally verified by the correlation verification unit (140) in the entire track list of the system. The track provision unit (160) can visually display the track information finally confirmed through the track management unit (150) to the operator or provide it in the form of data to other linked systems.

[0049] FIG. 2 is a flowchart showing the overall operation flow of a track correlation verification method according to one embodiment of the present disclosure.

[0050] Referring to FIG. 2, the track correlation verification system (10) receives track information from multiple sources (S210) and can perform necessary preprocessing, such as time compensation, through the track preprocessing unit (110).

[0051] Subsequently, the system (10) (clustering unit (120)) can cluster the preprocessed tracks into multiple track groups corresponding to each source (S220). For example, when track information is received from a self-sensor (20) and another interconnected system (30) as shown in FIG. 1, the preprocessed tracks can be clustered into a first track group corresponding to the self-sensor (20) and a second track group corresponding to the other interconnected system (30).

[0052] Next, the system (10) (initial correlation determination unit (130)) can determine the initial correlation between tracks belonging to two different groups among a plurality of clustered track groups (S230).

[0053] The system (10) determines whether such initial correlation has occurred (S240), and if correlation has occurred (YES of S240), it can proceed with a subsequent verification step for the correlation.

[0054] On the other hand, if no initial correlation occurs (NO in S240), the system (10) can manage the corresponding tracks as independent individual tracks without proceeding to a subsequent verification step. Subsequently, in the next processing cycle in which new track information is received, the system (10) may attempt to set the initial correlation again (S230) based on the updated track information. For example, a specific track in the first track group and a specific track in the second track group may physically represent the same target, but due to a temporary prediction error, it may be determined that no correlation occurred in the initial correlation determination (S230). In this case, the system (10) processes the two tracks as separate tracks, and when new track information is received in the next cycle and the prediction error is reduced, then the initial correlation occurs (YES in S240) and the system can enter the verification step (S250) of the present disclosure.

[0055] When entering the verification phase, the system (10) (correlation verification unit (140)) can determine whether the number of members (number of tracks) is the same among the track groups involved in the initial correlation (S250).

[0056] If, as a result of the judgment, the number of members between track groups is the same (YES of S250), the correlation verification unit (140) can perform verification based on the center point shifting technique for the corresponding track groups (S260). The center point shifting technique corresponds to a method of analyzing the consistency of the overall pattern by aligning the geometric center points of the track groups, and a detailed explanation thereof will be described later with reference to FIGS. 3 and FIGS. 4.

[0057] On the other hand, if the number of members is different (NO of S250), the correlation verification unit (140) can perform verification based on a reference point shifting technique for the corresponding track groups (S270). The reference point shifting technique (3170) corresponds to a method of aligning reference tracks selected in each group to analyze the similarity of geometric correlations within the group, and a detailed explanation thereof will be provided later with reference to FIGS. 5 and FIGS. 6.

[0058] Once verification is complete, the system (10) (track management unit (150)) can update and manage the correlation results that are finally determined to be valid by reflecting them in the system's entire track list (S280).

[0059] According to an embodiment, the system (10) (track providing unit (160)) can visually display updated track information to the operator or provide it to another linked system (S290).

[0060] FIG. 3 is a flowchart showing the detailed operation flow of a center point shifting technique applied when the number of members of a track group is the same, according to one embodiment of the present disclosure. FIG. 4 is a conceptual diagram for explaining the operating principle of the center point shifting technique illustrated in FIG. 3.

[0061] Referring to FIGS. 3 and 4, the system (10) (correlation verification unit (140)) can calculate the geometric center point of each track group (e.g., first track group and second track group) having the same number of members, and perform alignment so that the calculated geometric center points match (S310).

[0062] This step may correspond to the process of establishing criteria for comparing the overall spatial distribution of the above-mentioned track groups. 410 in FIG. 4 represents the initial track state before the start of verification, and in the initial track state, it can be confirmed that the first track group (Sen 1, Sen 2, Sen 3) received from the first source (e.g., self sensor (20)) and the second track group (Other 1, Other 2, Other 3) received from the second source (e.g., Other interconnection system (30)) are spatially separated.

[0063] In this initial track state, as illustrated in 420 of FIG. 4, the correlation verification unit (140) can calculate a first center point by calculating the arithmetic mean of the position coordinates of all tracks belonging to the first track group. And, the correlation verification unit (140) can calculate a second center point for the second track group in the same way.

[0064] As illustrated in 430 of FIG. 4, the correlation verification unit (140) can virtually translate all tracks of the first track group or the second track group so as to align the calculated first center point and the second center point. Through this alignment process, the geometric patterns of each track group can be compared regardless of the absolute position of each track group.

[0065] Next, the correlation verification unit (140) can exclude from verification any combinations corresponding to a pre-set correlation restriction condition for all one-to-one pairing combinations that can be generated between tracks of a matched track group (S320).

[0066] For example, the correlation verification unit (140) can first verify the non-identical characteristic information of each track before generating all possible one-to-one pairing combinations between tracks of a track group with aligned center points. For example, the correlation verification unit (140) can identify track pairs that are not likely to be the same target because the platform type or friend-or-foe identification information is clearly different, such as when a specific track of the first track group is identified as a 'fighter jet' and a corresponding candidate track of the second track group is identified as a 'passenger aircraft'. Subsequently, the correlation verification unit (140) can improve the efficiency of the verification process by reducing unnecessary calculations by fundamentally excluding all pairing combinations including such unsuitable track pairs from the subsequent error calculation target.

[0067] Next, the correlation verification unit (140) calculates the cumulative error of the combination by summing the relative distance errors of all track pairs included in the combination for each valid pairing combination (S330).

[0068] This step may correspond to a process of quantitatively evaluating how well each pairing combination matches geometrically. The correlation verification unit (140) can calculate a cumulative error for each valid pairing combination that has passed step S320. To explain using the example illustration in FIG. 4, the correlation verification unit (140) can calculate the spatial distance (e.g., Euclidean distance, etc.) between two tracks as an error for all one-to-one paired track pairs (e.g., Sen1-Ta1, Sen2-Ta2, Sen3-Ta3) included in each combination, and can determine the 'cumulative error' value by summing the distance errors of all track pairs belonging to the combination.

[0069] When the calculation of cumulative errors for all valid pairing combinations is completed, the correlation verification unit (140) can compare the calculated cumulative errors and select the pairing combination with the smallest cumulative error (S340).

[0070] Afterwards, the correlation verification unit (140) can finally verify whether the relative distance of each of the track pairs included in the selected pairing combination satisfies all conditions below a preset threshold (S350).

[0071] If any single track pair does not satisfy the condition below the threshold (NO in S350), the correlation verification unit (140) rejects the corresponding pairing combination (S360) and can repeat the final verification step (S350) again for the combination with the next smallest cumulative error among the remaining pairing combinations. If, as a result of the repetition, there is no pairing combination satisfying the condition below the threshold, the correlation verification unit (140) can determine that the corresponding initial correlation is invalid.

[0072] On the other hand, if all track pairs satisfy the threshold condition (YES of S350), the correlation verification unit (140) confirms that the initial correlation is valid and can transmit the correlation result to the track management unit (150) (S370).

[0073] For example, the correlation result may be transmitted to the track management unit (150) in the form of information such as 'Sen1 track of the first track group and Ta1 track of the second track group are the same target'.

[0074] FIG. 5 is a flowchart illustrating the detailed operation flow of a reference point shifting technique applied when the number of members in a track group differs, according to another embodiment of the present disclosure. FIG. 6 is a conceptual diagram for explaining the operating principle of the reference point shifting technique illustrated in FIG. 5.

[0075] Referring to FIGS. 5 and 6, the system (10) (correlation verification unit (140)) can calculate geometric correlation information within each track group (S510).

[0076] This step may correspond to a process for comparing the similarity of internal pattern or constellation information unique to each group in situations where a one-to-one correspondence between groups is impossible due to differences in the number of members between groups. 610 in FIG. 6 represents the initial track state before the start of verification, and in this example, the first track group (Sen 1, Sen 2, Sen 3) consists of three tracks, and the second track group (Ta 1, Ta 2) consists of two tracks.

[0077] In this initial state, as illustrated in 620 of FIG. 6, the correlation verification unit (140) can obtain internal geometric correlation information, such as relative distance, azimuth, and altitude between tracks included within each group, by analyzing it in advance.

[0078] Next, the correlation verification unit (140) may exclude from verification combinations corresponding to pre-set correlation constraint conditions for track pairs to be compared later (S520). This is intended to reduce unnecessary computations and improve verification efficiency by utilizing non-synchronous characteristic information, etc., as previously explained in step S320 of FIG. 3.

[0079] Next, the correlation verification unit (140) can perform pattern comparison and error calculation through reference point movement (S530).

[0080] This step may correspond to a process of quantitatively evaluating the pattern similarity of two groups. Specifically, the correlation verification unit (140) may select one track from the first track group as the first reference track and select another track from the second track group as the second reference track to form a pair of reference points, and virtually align these pairs of reference points. Subsequently, an error can be calculated by comparing how similarly the internal geometric correlation information of the remaining tracks, calculated in advance in step S510, matches with the aligned reference points. Figure 630 conceptually illustrates this reference point shifting process and shows that alignment and pattern comparison are repeatedly performed for all possible combinations of reference points, such as when 'Sen1-Ta1' is aligned as a pair of reference points and when 'Sen2-Ta1' is aligned as a pair of reference points.

[0081] When the error calculation for all valid reference point combinations is completed, the correlation verification unit (140) can compare the calculated errors and select the reference point combination with the highest pattern similarity, i.e., the smallest error (S540).

[0082] Afterwards, the correlation verification unit (140) can finally verify whether the geometric correlation information error of each track pair determined by the selected reference point combination satisfies all conditions within a preset individual threshold (S550).

[0083] If any single track pair does not satisfy the threshold condition (NO in S550), the correlation verification unit (140) rejects the corresponding reference point combination (S560) and can repeat the final verification step (S550) on the combination with the next highest similarity among the remaining reference point combinations. If, as a result of the verification, there is no reference point combination satisfying the threshold condition, the correlation verification unit (140) can determine that the corresponding initial correlation is invalid.

[0084] On the other hand, if all track pairs satisfy the threshold condition (YES of S550), the correlation verification unit (140) confirms that the initial correlation is valid and can transmit the correlation result to the track management unit (150) (S570).

[0085] According to the embodiments described above, the system (10) can improve the accuracy of correlation by effectively preventing the phenomenon of track swapping that is prone to occur in close-proximity maneuvering track groups by analyzing the geometric pattern of track groups obtained from various sources and verifying the correlation.

[0086] In addition, the system (10) prevents repeated setting and unsetting by suppressing the occurrence of incorrect correlations, thereby providing the operator with stable and consistent air situation information, which can increase situation awareness and operational efficiency.

[0087] FIG. 7 is a block diagram schematically showing the hardware configuration of a computing device constituting a trajectory correlation verification system according to an exemplary embodiment of the present disclosure.

[0088] The hardware configuration of the computing device (700) shown in FIG. 7 can correspond to the hardware configuration of each of at least one computing device constituting the trajectory correlation verification system (10) shown in FIG. 1.

[0089] Referring to FIG. 7, the computing device (700) may include a communication unit (710), an input unit (720), an output unit (730), a control unit (740), and a memory (750). The control configuration shown in FIG. 7 is an example for convenience of explanation, and the computing device (700) may include more or fewer configurations than the configuration shown in FIG. 7.

[0090] The communication unit (710) may include one or more communication modules that enable communication with other terminals or servers, etc., by connecting the computing device (700) to a network. For example, the communication module may include a mobile communication module such as LTE, 5G, etc., a wireless communication module such as Wi-Fi, etc., and / or various other wired or wireless communication modules. In addition, the communication unit (710) may include at least one antenna for satellite communication. For example, the trajectory correlation verification system (10) may receive trajectory information from its own sensor (20) and / or other interconnection system (30) through the communication unit (710).

[0091] The input unit (720) is configured to acquire information such as user input, video, and audio, and may include various input means such as various mechanical / electronic input means, cameras, and microphones. According to an embodiment, the input unit (720) may include a sensor (20) of the trajectory correlation verification system (10). The output unit (730) is configured to provide information to a user by generating output related to sight, hearing, or touch, and may include a display, speaker, vibration module, etc.

[0092] The control unit (740) can control the overall operation of the computing device (700). The control unit (740) can process signals, data, information, etc. that are input or output through the components described above, or provide specific information or functions according to various applications or algorithms stored in the memory (750). For example, the control unit (740) can control the overall process related to the track correlation verification method disclosed in this specification.

[0093] The control unit (740) may include at least one processor and / or at least one programmable circuit. For example, the control unit (740) may be implemented in hardware such as a CPU, an application processor (AP), an MCU, a GPU, an NPU, an integrated circuit, an ASIC, an FPGA, etc.

[0094] The memory (750) can store programs and data necessary for the operation of the computing device (700). Additionally, the memory (750) can store data generated or acquired through the control unit (740). The memory (750) may be composed of a storage medium such as ROM, RAM, flash memory, SSD, HDD, or a combination of storage media.

[0095] The embodiments of the present disclosure described above can be implemented as computer-readable code on a medium on which a program is recorded. Computer-readable media include all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SSD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0096] The description of the above-described embodiments is merely an example provided with reference to the drawings for a more thorough understanding of the present disclosure, and should not be interpreted as limiting the technical scope of the present disclosure.

[0097] Furthermore, it will be apparent to those skilled in the art to which this disclosure pertains that various changes and modifications are possible within the scope of the basic principles of this disclosure.

Claims

Claim 1 A method for verifying track correlation performed by a computer comprises: a step of obtaining a first track group and a second track group composed of tracks received from a plurality of sources, respectively; and a step of verifying the initial correlation by comparing the geometric patterns of the first track group and the second track group when an initial correlation occurs between a first track included in the first track group and a second track included in the second track group, wherein the step of verifying the initial correlation by comparing the geometric patterns includes a step of comparing geometric patterns by applying different geometric registration methods depending on whether the number of tracks in the first track group and the number of tracks in the second track group are the same, and when the number of tracks is the same, the step of comparing geometric patterns includes a step of calculating and matching a first center point of the first track group and a second center point of the second track group, and generating a plurality of possible one-to-one pairing combinations between each track of the first track group and each track of the second track group. A method for verifying track correlation, comprising the step of calculating a cumulative error by summing the distance errors between paired tracks for each generated pairing combination, and selecting a pairing combination based on the calculated cumulative errors. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 A method for verifying track correlation according to claim 1, wherein the step of selecting the pairing combination includes the step of comparing the calculated cumulative errors and selecting the pairing combination having the smallest cumulative error. Claim 6 A method for verifying track correlation according to claim 1, wherein the verifying step comprises the step of finally verifying the initial correlation as valid when the distances of all paired track pairs included in the selected pairing combination each satisfy a preset individual threshold. Claim 7 A method for verifying track correlation according to claim 6, wherein the verification step further comprises the step of rejecting a pairing combination when there is a track pair among the track pairs included in the selected pairing combination that does not satisfy the individual threshold, and selecting a pairing combination having the next smallest cumulative error among the remaining pairing combinations to repeat the final verification. Claim 8 A track correlation verification method according to claim 1, wherein the geometric matching method is a method of matching a first reference track selected within the first track group and a second reference track selected within the second track group when the number of tracks within the first track group and the number of tracks within the second track group are different. Claim 9 A method for verifying track correlation according to claim 8, wherein the step of comparing the geometric patterns further comprises the step of calculating internal geometric correlation information, including relative distances, azimuths, and altitudes between tracks within the first track group and between tracks within the second track group, respectively, before performing matching between the first reference track and the second reference track. Claim 10 A method for verifying track correlation according to claim 9, wherein the step of comparing the geometric patterns further includes the step of determining the similarity of the geometric patterns by comparing the calculated internal geometric correlation information after aligning the first reference track and the second reference track. Claim 11 A method for verifying track correlation according to claim 10, wherein the step of comparing the geometric pattern further comprises the step of repeatedly performing the matching and similarity judgment of the geometric pattern for each possible combination of the first reference track and the second reference track. Claim 12 A method for verifying track correlation according to claim 11, wherein the step of comparing the geometric patterns further includes the step of selecting a reference track combination with the highest similarity of geometric patterns based on the result of similarity judgment for each of the combinations. Claim 13 A method for verifying track correlation according to claim 12, wherein the verifying step comprises the step of finally verifying the initial correlation as valid when, for track pairs determined by the selected reference track combination, the geometric correlation information error of each track pair is within a preset individual threshold value. Claim 14 A method for verifying track correlation according to claim 1, further comprising the step of excluding track pairs that cannot be correlated from the verification target in advance using non-dynamic characteristic information including at least one of track identification information, platform type information, and radar cross-sectional area information, before comparing the geometric patterns. Claim 15 A track correlation verification method according to claim 1, further comprising the step of performing time compensation to correct state information of tracks received from the plurality of sources to the same point in time before acquiring the first track group and the second track group. Claim 16 A track correlation verification system comprising at least one computing device, wherein the system includes a memory for storing instructions; and includes at least one processor configured to be operatively connected to the memory and, when executing the instructions, acquire a first track group and a second track group composed of tracks received from a plurality of sources, and, when an initial correlation occurs between a first track included in the first track group and a second track included in the second track group, verify the initial correlation by comparing the geometric patterns of the first track group and the second track group; wherein the at least one processor compares the geometric patterns by applying different geometric registration methods depending on whether the number of tracks in the first track group and the number of tracks in the second track group are the same, and if the number of tracks is the same, calculates and aligns the first center point of the first track group and the second center point of the second track group, generates a plurality of possible one-to-one pairing combinations between each track of the first track group and each track of the second track group, and for each generated pairing combination, the distance error between the paired tracks A track correlation verification system that calculates cumulative errors by summing them and selects pairing combinations based on the calculated cumulative errors. Claim 17 A computer-readable, non-transient storage medium that stores instructions for causing a processor to perform a track correlation verification method described in any one of claims 1, 5 to 15 when executed by a processor.

Images