A method for associating multi-source heterogeneous information based on discrete point traces

Abstract

The present invention relates to a multi-source heterogeneous information association method based on discrete point traces, which belongs to the field of information fusion technology and solves the problems of difficulty in distinguishing discrete points and missed association in existing dense targets. It includes receiving the multi-source heterogeneous information, identifying the discrete point traces therein and storing them in a history library, and taking other information in the history library as historical point traces; based on identity information and proprietary information, obtaining the associated data pairs of discrete point traces and historical point traces; then based on time and dynamic information, establishing multiple similarity matrices for the remaining discrete point traces and the remaining historical point traces in the history library; according to the preset measurement threshold of each similarity matrix, converting the multiple similarity matrices into multiple 0-1 measurement matrices; based on the 0-1 measurement matrix, obtaining the associated data pairs of the remaining discrete point traces and the remaining historical point traces in the history library; setting the same track number for each group of associated data pairs to obtain the association result. The identification and association of discrete information in dense targets are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of information fusion, and in particular to a multi-source heterogeneous information association method based on discrete point traces. Background Art

[0002] As the types and number of sensors continue to increase, the types of information are becoming increasingly rich, and the requirements for real-time information fusion are becoming higher and higher. The problem of multi-source heterogeneous information association is one of the key technologies of information fusion. Without information association, there is no way to track the target, and without efficient and reliable information association, the accuracy of target identification is out of the question.

[0003] Multi-source heterogeneous information association is to merge observations or traces from multiple sensors with known or confirmed events so that they belong to the event set, that is, to ensure that the observations contained in each event set come from the same entity with a high probability or a probability close to 1. The traces that are not merged, which may include new traces from the target or traces generated by noise or clutter, are retained until the next moment for further processing.

[0004] In the field of multi-sensor information fusion, a single target is generally used as the object of association processing, and the information association method based on target motion information is mainly used. The technologies that can be adopted mainly include static association methods, such as measurement-measurement association of the same or different dimensions, and dynamic information association methods, such as measurement-track association, track-track association, etc. The most typical representative of the specific association method is the nearest neighbor method. Its basic idea is to establish a mapping relationship between the two closest measurement information and the target number. It is simple to implement, has a small amount of calculation, and is widely used in actual engineering.

[0005] However, when using the nearest neighbor method, if the target information is sparse discrete points, the traditional approach is to delete them directly and not use them as evidence for target identification. In actual applications, the detection platform obtains information about the other party's target. Some sparse discrete points play an important role in target identification. Direct deletion leads to information leakage, which in turn leads to a decrease in target recognition rate. Moreover, when the targets are dense and in a state of motion such as crossing or bifurcation, if the discrete points are not identified, the result of "misidentification" will occur, which reduces the target recognition rate. Summary of the invention

[0006] In view of the above analysis, an embodiment of the present invention aims to provide a multi-source heterogeneous information association method based on discrete point traces, so as to solve the problems of difficulty in distinguishing discrete points and missed association in existing dense targets.

[0007] On the one hand, an embodiment of the present invention provides a multi-source heterogeneous information association method based on discrete point traces, comprising the following steps: receiving multi-source heterogeneous information, identifying discrete point traces therein, storing them in a history library, and using other information in the history library as historical point traces;

[0008] Based on identity information and proprietary information, a set of associated data pairs of discrete traces and historical traces is obtained; then based on time and dynamic information, multiple similarity matrices are established for the remaining discrete traces and the remaining historical traces in the historical database;

[0009] According to the preset measurement threshold of each similarity matrix, multiple similarity matrices are converted into multiple 0-1 measurement matrices; based on the multiple 0-1 measurement matrices, the associated data pairs of the remaining discrete points in the history library and the remaining historical points are obtained and added into the associated data pair set;

[0010] The same track number is set for each set of associated data pairs in the associated data pair set to obtain an associated result.

[0011] Based on the further improvement of the above method, other information in the history library is used as historical traces, including: according to the acquisition time of discrete traces, the Kalman filtering method is used to extrapolate the track point prediction of other multi-source heterogeneous information in the history library to the acquisition time of discrete traces to obtain historical traces.

[0012] Based on the further improvement of the above method, based on the identity information and proprietary information, the associated data pairs of discrete points and historical points are obtained, including:

[0013] Take out each discrete point trace in turn, and compare each discrete point trace with each historical point trace in pairs; when a discrete point trace only has the same identity information and proprietary information as a historical point trace, the association is successful; otherwise, the association fails.

[0014] Based on the further improvement of the above method, the rows of the similarity matrix correspond to each discrete point trace, the columns correspond to each historical point trace, and the element values ​​correspond to the multi-source heterogeneous information comparison value of each discrete point trace and each historical point trace;

[0015] The similarity matrix includes: a time similarity matrix and a dynamic information similarity matrix; the multi-source heterogeneous information comparison value includes: a time information comparison value and a dynamic information comparison value.

[0016] Based on the further improvement of the above method, according to the preset measurement threshold of each similarity matrix, multiple similarity matrices are converted into multiple 0-1 measurement matrices, including:

[0017] Under the condition that the measurement threshold of the preset time similarity matrix is ​​less than the preset time similarity matrix, the element values ​​of the time similarity matrix are traversed, and under the condition that the measurement threshold of the dynamic similarity matrix is ​​less than the preset dynamic similarity matrix, the element values ​​that meet the conditions are obtained respectively, and then according to the rule of taking the minimum value for each row and the maximum value for each column, the element values ​​that meet the conditions are optimized again, and the element values ​​that meet the rules are set to 1, otherwise, the element values ​​are set to 0, and the 0-1 time measurement matrix corresponding to the time similarity matrix and the 0-1 dynamic information measurement matrix corresponding to the dynamic information similarity matrix are obtained respectively.

[0018] Based on the further improvement of the above method, based on multiple 0-1 metric matrices, the associated data pairs of the remaining discrete points in the history library and the remaining historical points are obtained and added to the associated data pair set, including:

[0019] The number of elements with the value of 1 at the same position in the 0-1 time measurement matrix and the 0-1 dynamic information measurement matrix is ​​counted. When the number is greater than the preset threshold, the discrete point trace corresponding to the position is successfully associated with the historical point trace and added to the associated data pair set.

[0020] Based on the further improvement of the above method, multi-source heterogeneous information is received and discrete points therein are identified, including: identifying discrete points in the multi-source heterogeneous information within the same information fusion cycle, and identifying discrete points in the multi-source heterogeneous information during multiple information fusion cycles.

[0021] Based on the further improvement of the above method, the discrete points in the multi-source heterogeneous information in the same information fusion cycle are identified, including:

[0022] According to the information fusion cycle, multi-source heterogeneous information containing multiple data from the same type of sensors is added to the set to be clustered, and other multi-source heterogeneous information is added to the preliminary clustering set;

[0023] The clustering set is clustered, and the multi-source heterogeneous information closest to the cluster center in each class is added to the preliminary clustering set. The other multi-source heterogeneous information in each class is put into the cache area, and the multi-source heterogeneous information not classified into any class is identified as discrete point traces.

[0024] Based on the further improvement of the above method, the discrete points in the multi-source heterogeneous information during multiple information fusion cycles are identified, including:

[0025] Based on the same identity information, the associated data pairs of the multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the historical database are identified and added to the associated data pair set;

[0026] According to the preset dynamic information association threshold, candidate historical points are obtained from the remaining multi-source heterogeneous information in the history library;

[0027] Based on dynamic information, the association gate between the remaining multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the candidate historical traces is calculated, and the associated data pairs between the remaining multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the candidate historical traces are identified according to the association gate. The multi-source heterogeneous information that fails to be associated in the preliminary clustering set is identified as discrete traces.

[0028] Based on the further improvement of the above method, the preset dynamic information association thresholds include: longitude association threshold, latitude association threshold and altitude association threshold;

[0029] Obtain candidate historical points from the remaining multi-source heterogeneous information in the history library, including:

[0030] Each remaining multi-source heterogeneous information in the preliminary clustering set is taken out in turn, and compared with each remaining multi-source heterogeneous information in the historical database, and the longitude difference, latitude difference and altitude difference of the dynamic information in the multi-source heterogeneous information are obtained. When the absolute values ​​of the three differences are all less than the corresponding association thresholds, the multi-source heterogeneous information in the historical database is included in the candidate historical point traces, and the Kalman filtering method is used to predict and extrapolate the track points related to the multi-source heterogeneous information in the historical database, and extrapolate to the acquisition time of the multi-source heterogeneous information in the preliminary clustering set compared with it, so as to obtain the candidate historical point traces.

[0031] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0032] 1. Through clustering of multi-source heterogeneous information in the same period and associating information in different periods, discrete points can be accurately identified while obtaining the associated data of multi-source heterogeneous information. Then, the discrete points are solved through the construction of a multi-dimensional similarity matrix and the design of association optimization rules, which solves the problems of difficulty in distinguishing discrete points and missed associations, providing the premise and guarantee for improving the target recognition rate.

[0033] 2. For multi-source heterogeneous information in the same period, the initial cluster center is dynamically selected based on the maximum density iterative processing method through identity information matching and improved fuzzy C-means clustering, which solves the problem that the initial cluster center is highly dependent on artificial and prior information, realizes fuzzy clustering of multiple information from the same sensor in the same period and rough selection of sparse discrete points, and solves the problems of low utilization rate of existing identity information and difficulty in determining sparse points;

[0034] 3. For heterocyclic information association, a dynamic design criterion for the association gate is designed, and a method based on identity information matching and dynamic association of multi-cycle and multi-dimensional information is implemented, which solves the possible erroneous association problem under the conditions of dense multi-target complex motion, as well as the secondary determination of sparse discrete points;

[0035] 4. Adopt the association process of classified and hierarchical processing, gradually obtain the associated data from multi-target and multi-source heterogeneous information in a dense environment, reduce the computational complexity of the association, screen out discrete points step by step, and construct a multi-dimensional similarity matrix for discrete point traces, thus solving the problem of high complexity of information association.

[0036] In the present invention, the above-mentioned technical solutions can also be combined with each other to achieve more preferred combination solutions. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can become obvious from the description, or can be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like components throughout the drawings.

[0038] Figure 1 This is a flow chart of a multi-source heterogeneous information association method based on discrete point traces in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0040] A specific embodiment of the present invention discloses a multi-source heterogeneous information association method based on information fusion cycle, such as Figure 1 As shown, the following steps are included:

[0041] S11: receiving multi-source heterogeneous information, identifying discrete points therein, storing them in a history database, and using other information in the history database as historical points;

[0042] It should be noted that this embodiment receives multi-source heterogeneous information radiated, emitted, and transmitted by multiple sensors of different types, different working mechanisms, and different data rates equipped on the target platform through an information association processing platform, such as acquisition time, dynamic information, identity information, and proprietary information, and stores the multi-source heterogeneous information into the target information library with the sensor type as the index.

[0043] Assume that the information fusion processing cycle is T, the multi-source heterogeneous information is MultInfo, and each sensor information is SenInfo. SenInfo consists of sensor type senClass, information acquisition time t, target identity information staticInfo, target dynamic information dynaInfo, and target-specific information specialInfo acquired by the sensor. The target dynamic information dynaInfo includes: target longitude senLon, target latitude senLat, target altitude senAlti, target distance senDis, target azimuth senAzi, and target pitch senPitch. That is:

[0044] SenInfo={senClass,t,senLon,senLat,senAlt i,senDis,senAzi,senPitch,staticInfo,spec ialInfo}

[0045] Exemplarily, the target identity information is a 24-bit address code of the sensor, and the proprietary information is an icon of the sensor.

[0046] For the received multi-source heterogeneous information, discrete points therein are identified, including: step S111 identifying discrete points in the multi-source heterogeneous information within the same information fusion cycle, and step S112 identifying discrete points in the multi-source heterogeneous information during multiple information fusion cycles.

[0047] S111: Identify discrete points in multi-source heterogeneous information within the same information fusion cycle;

[0048] Specifically, the identification process includes:

[0049] 1) According to the information fusion cycle, multi-source heterogeneous information containing multiple data from the same type of sensors is added to the set to be clustered, and other multi-source heterogeneous information is added to the preliminary clustering set;

[0050] Assume that the i-th information fusion processing cycle T i Internal multi-source heterogeneous information is recorded as:

[0051]

[0052] Where N represents the number of sensor categories in the i-th cycle, M j Indicates the nth j The number of multi-source heterogeneous information of the sensor type, n j represents the jth sensor category, Indicates the nth j Type t of sensor k Multi-source heterogeneous information at all times.

[0053] The information fusion processing cycle is related to the performance of the sensor and the processing efficiency of the information association processing platform, and is exemplarily set to 40 ms.

[0054] For the same information fusion period T i For the multi-source heterogeneous information obtained within, if the same type of sensor contains multiple data, it is added to the set to be clustered to cluster the same period information; if the same type of sensor contains only one data, it is added to the preliminary clustering set, and step S112 is executed to perform heterogeneous period association.

[0055] 2) Cluster the clustering set. The multi-source heterogeneous information closest to the cluster center in each class is added to the preliminary clustering set. The other multi-source heterogeneous information in each class is put into the cache area. The multi-source heterogeneous information that is not classified into any class is identified as discrete point traces.

[0056] It should be noted that clustering the cluster set includes: firstly identifying the same type of multi-source heterogeneous information in the same information fusion cycle based on the same identity information, taking the information fusion cycle as the clustering center, and then clustering the remaining multi-source heterogeneous information in the cluster set.

[0057] Specifically, the multi-source heterogeneous information in the cluster set is first matched by identity information. Assume that for the i-th fusion processing cycle T i Get the nth j Class sensor information includes M j Multi-source heterogeneous information, M j >1, and the identity information in the multi-source heterogeneous information is not empty, then traverse multiple multi-source heterogeneous information, compare them two by two, and classify the multi-source heterogeneous information with the same identity information into one category, and use the information fusion cycle T i As the cluster center, select the distance T i The most recent r Multi-source heterogeneous information at all times As the clustering result, add the preliminary clustering set, where t r The calculation formula is as follows:

[0058]

[0059] Where r represents the number of moments, r=1,2,...,M j .

[0060] Considering that identity information is the unique identifier of multi-source heterogeneous information, the association efficiency of multi-source heterogeneous information is improved through the priority matching of identity information. If the identity information fails to match, it means that the identity information of the target does not always exist. Then, the dynamic information in the multi-source heterogeneous information is used to cluster the remaining multi-source heterogeneous information in the clustering set, including:

[0061] ① Traverse the remaining multi-source heterogeneous information in the set to be clustered, and determine multiple cluster centers and information sets in turn;

[0062] Specifically, the process of determining cluster centers and information sets includes:

[0063] A piece of multi-source heterogeneous information is selected from the remaining multi-source heterogeneous information in the set to be clustered as the initial center. According to the preset initial distance threshold d1, the multi-source heterogeneous information whose Euclidean distance with the initial center is less than the initial distance threshold is obtained as the selected set. Each multi-source heterogeneous information in the selected set is selected in turn, and the number of multi-source heterogeneous information whose Euclidean distance is less than the initial distance threshold is calculated. The multi-source heterogeneous information with the largest number is taken as the first clustering center C1, and the multi-source heterogeneous information whose Euclidean distance with the first clustering center is less than the initial distance threshold is taken as the first category of information set; it should be noted that the initial clustering center is dynamically selected based on the maximum density iterative processing method, which solves the problem of strong dependence of the initial clustering center on artificial and prior information.

[0064] Calculate the Euclidean distance between the multi-source heterogeneous information except the first type of information set and the first cluster center C1 in turn, and select the multi-source heterogeneous information with the largest distance as the second cluster center C2. If the maximum distance is greater than the preset minimum distance d min , take the difference between the maximum distance and the initial distance threshold as the second clustering distance, and obtain the multi-source heterogeneous information whose Euclidean distance to the second cluster center is less than the second clustering distance as the second type of information set;

[0065] By analogy, calculate the mth cluster center C m , until the Euclidean distance between the m+1th cluster center and the mth cluster center is less than the minimum distance d min When , the iteration ends, and m cluster centers and m types of information sets are obtained.

[0066] ② Calculate the average value of multi-source heterogeneous information in each type of information set;

[0067] For each cluster center, the average value of all multi-source heterogeneous information in each type of information set is calculated using the following formula:

[0068]

[0069] Among them, C i represents the i-th cluster center, i=1,2,...,m, It represents the average value of multi-source heterogeneous information in the i-th information set, and SenInfo represents each piece of multi-source heterogeneous information in each information set.

[0070] Preferably, since there are multiple attribute values ​​in the multi-source heterogeneous information, the target distance senDis can be selected to calculate the average value.

[0071] ③ Obtain the sum of square errors between each piece of multi-source heterogeneous information and the average value of the multi-source heterogeneous information in each type of information set as the clustering criterion function value. The formula is as follows:

[0072]

[0073] ④ When the clustering criterion function value is less than the preset error threshold, or the difference between two adjacent clustering criterion function values ​​obtained is less than the error threshold, exit the iteration; otherwise, return to step S131, select a new multi-source heterogeneous information from the remaining set to be clustered as the initial center, and determine the new clustering center and information set again.

[0074] After steps ① to ④, the multi-source heterogeneous information closest to the cluster center in each category is added to the preliminary clustering set, and the other multi-source heterogeneous information in each category is placed in the cache area. The multi-source heterogeneous information that is not classified into any category is identified as discrete points and stored in the history library.

[0075] Preferably, different flags are set to represent the status of multi-source heterogeneous information, and a two-dimensional data structure is used to store different flags of the multi-source heterogeneous information and the information corresponding to each flag, which facilitates the acquisition of corresponding data information and compresses data storage space.

[0076] S112: Identify discrete points in multi-source heterogeneous information during multiple information fusion cycles.

[0077] Specifically, the identification process includes:

[0078] 1) Based on the same identity information, identify the associated data pairs of the multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the historical database, and add them to the associated data pair set;

[0079] It should be noted that for the preliminary clustering set and the multi-source heterogeneous information in the historical library, the identity information is still used for matching and identification first. Once the identity information is the same, it means that the association is successful, and the associated data pair is added without further processing. If the identity information is not matched successfully, the subsequent steps are executed based on dynamic information to associate the remaining multi-source heterogeneous information in the preliminary clustering set and the remaining multi-source heterogeneous information in the historical library.

[0080] 2) According to the preset dynamic information association threshold, candidate historical points are obtained from the remaining multi-source heterogeneous information in the historical database;

[0081] It should be noted that the preset dynamic information association thresholds include: longitude association threshold e Lon , latitude correlation threshold e Lat and the highly correlated threshold e Alti ;

[0082] The process of obtaining candidate historical points from the remaining multi-source heterogeneous information in the history library includes:

[0083] ① Take out each remaining multi-source heterogeneous information in the preliminary clustering set in turn, compare it with each remaining multi-source heterogeneous information in the historical database, and obtain the longitude difference, latitude difference and altitude difference of the dynamic information in the multi-source heterogeneous information. When the absolute values ​​of the three differences are all less than the corresponding association threshold, the multi-source heterogeneous information in the historical database is included in the candidate historical point traces.

[0084] Specifically, assume that the remaining multi-source heterogeneous information in the history library is:

[0085]

[0086] Among them, TN is the number of remaining targets in the history library, S l Indicates his l The number of targets for each target, Indicates his l The tth target p The composition of multi-source heterogeneous information at each moment is the same as that of SenInfo.

[0087] It should be noted that the number of cycles stored in the history library and the number of targets for each cycle, that is, the storage depth, are related to the movement and speed of the target platform itself. For example, the history library stores data of 3 cycles, and the storage depth of each cycle is 10s. The historical data is stored and updated according to the first-in-first-out rule.

[0088] If in the preliminary clustering set the i-th fusion processing cycle T i Within, nth j Sensor Type k Multi-source heterogeneous information at all times Central longitude Dimensions and height With History Library Central longitude Dimensions and height If the following equation is satisfied, Candidates for inclusion in the list of historical sites:

[0089]

[0090] ② For the candidate historical points, the Kalman filter method is used to predict and extrapolate the track points related to the multi-source heterogeneous information in the historical database, and extrapolate to the time when the multi-source heterogeneous information in the preliminary clustering set for comparison is obtained. The track points are extrapolated to t kAt each moment, time and space calibration is achieved through filtering, and then association is achieved, which improves the accuracy of the association.

[0091] For example, the current time is 10s, and the historical track points have information from 1s to 9s. Assuming that the motion model is uniform linear motion, the historical track points can be extrapolated to the 10th second through Kalman filtering.

[0092] 3) Based on dynamic information, the association gate between the remaining multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the candidate historical traces is calculated, and the associated data pairs between the remaining multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the candidate historical traces are identified according to the association gate. The multi-source heterogeneous information in the preliminary clustering set that fails to be associated is identified as discrete traces.

[0093] It should be noted that, according to the distance covariance and azimuth covariance of different sensors, the corresponding correlation gates are obtained, including the distance correlation gate ΔR(t i ) and the azimuth-correlated gate Δθ(t i ), the formula is:

[0094]

[0095] Among them, σ rS1 , σ θS1 They represent the distance covariance and orientation covariance of multi-source heterogeneous information in the preliminary clustering set, σ rS2 , σ θS2 They represent the distance covariance and orientation covariance of multi-source heterogeneous information in the candidate historical points, respectively. K represents the influence coefficient, ranging from 0 to 1. i It indicates the time when the multi-source heterogeneous information in the preliminary clustering set is obtained. Through the dynamic design of the correlation gate, the dependence of the correlation gate on expert experience is reduced.

[0096] According to formula (5), each remaining multi-source heterogeneous information in the preliminary clustering set is taken out in turn, and each multi-source heterogeneous information in the candidate historical point trace is compared with each other. The distance association gate and the azimuth association gate, as well as the distance difference and the azimuth difference of the multi-source heterogeneous information are calculated two by two. When the absolute value of the distance difference is less than the distance association gate, and the absolute value of the azimuth difference is less than the azimuth association gate, the two multi-source heterogeneous information are successfully associated and added to the associated data pair set. Otherwise, the association fails, and the multi-source heterogeneous information that fails to be associated in the preliminary clustering set is marked as a discrete point and stored in the history library.

[0097] The association of heterogeneous information from multiple sources in different periods realizes the association of non-discrete points in different periods and the secondary determination of discrete points, avoiding the misidentification of dense points and improving the determination accuracy of discrete points.

[0098] At this time, the set of associated data pairs includes: associated data pairs of multi-source heterogeneous information in the preliminary clustering set and multi-source heterogeneous information in the historical library obtained based on the same identity information, and associated data pairs of multi-source heterogeneous information remaining in the preliminary clustering set and multi-source heterogeneous information in the historical library obtained by associating the remaining multi-source heterogeneous information in the preliminary clustering set with the remaining multi-source heterogeneous information in the historical library based on dynamic information.

[0099] Based on the associated data pairs, the multi-source heterogeneous information in the cache area that belongs to the same type as the preliminary clustering set in the same information fusion cycle is added to the associated data pairs, that is, the multi-source heterogeneous information of the same type in the same information fusion cycle is associated with the multi-source heterogeneous information in the corresponding historical library or historical candidate point traces.

[0100] At this time, the discrete points stored in the history library include: multi-source heterogeneous information that is not classified into any category within the same information fusion cycle, and multi-source heterogeneous information that fails to be associated in the preliminary clustering set during multiple information fusion cycles.

[0101] According to the acquisition time of discrete point traces, the Kalman filtering method is used to extrapolate the track point prediction of multi-source heterogeneous information that is not marked as discrete points in the history library to the acquisition time of the discrete point traces.

[0102] The multi-source heterogeneous information of discrete points and historical points includes four categories: time t, dynamic information dynaInfo, identity information staticInfo and proprietary information specialInfo.

[0103] S12: Based on the identity information and proprietary information, a set of associated data pairs of discrete traces and historical traces is obtained; and based on the time and dynamic information, multiple similarity matrices are established for the remaining discrete traces and the remaining historical traces in the history library;

[0104] It should be noted that each discrete trace is taken out in turn, and each discrete trace is compared with each historical trace in pairs. When a discrete trace has the same identity information and proprietary information as only one historical trace, the association is successful, otherwise, the association fails. Specifically, the association fails when: a discrete trace has the same identity information and proprietary information as multiple historical traces, and a discrete trace has different identity information or proprietary information from each historical trace. For discrete traces and historical traces that fail to be associated, judgment and association are performed based on time and dynamic information.

[0105] Assuming that after matching and associating identity information and proprietary information, there are P historical points that have been extrapolated to the latest acquisition time and N unassociated discrete points in the history database, then the N discrete points are compared with the P historical multi-source heterogeneous information in pairs to establish a similarity matrix, including: a time similarity matrix and a dynamic information similarity matrix.

[0106] The rows of the similarity matrix correspond to each discrete point trace, the columns correspond to each historical point trace, and the element value corresponds to the multi-source heterogeneous information comparison value of each discrete point trace and each historical point trace, which is expressed as: Among them, q represents the type of similarity matrix, q=1,2, the similarity matrix is ​​N rows and P columns, a represents the row of the similarity matrix, b represents the column of the similarity matrix, a∈[1,N], b∈[1,P].

[0107] Specifically, the temporal similarity matrix The value obtained by dividing the absolute value of the time difference between each discrete point of the element value in the matrix and the historical multi-source heterogeneous information by the absolute value of the maximum time difference is calculated as follows:

[0108]

[0109] It should be noted that when the time of the historical traces extrapolated to the latest acquisition time is the same as that of the discrete traces, there is no need to establish a time similarity matrix. When the historical traces in the history library cannot be extrapolated, time is used to measure similarity, expand the comparison dimension, and increase the accuracy of the association.

[0110] Dynamic Information Similarity Matrix The element value in the matrix is ​​the value obtained by dividing the absolute value of the dynamic information difference between each discrete point and the historical multi-source heterogeneous information by the absolute value of the maximum dynamic information difference. The calculation formula is as follows:

[0111]

[0112] It should be noted that the dynamic information includes target longitude, target latitude, target altitude, target distance, target azimuth, target pitch, target heading, and target speed. According to actual needs, multiple attributes can be selected and the corresponding similarity matrix can be established according to formula (7).

[0113] S13: according to the preset measurement threshold of each similarity matrix, converting multiple similarity matrices into multiple 0-1 measurement matrices; based on the multiple 0-1 measurement matrices, obtaining the associated data pairs of the remaining discrete points in the history library and the remaining historical points, and adding them to the associated data pair set;

[0114] Specifically, according to the preset measurement threshold of each similarity matrix, multiple similarity matrices are converted into multiple 0-1 measurement matrices, including:

[0115] Under the condition that the measurement threshold of the preset time similarity matrix is ​​less than the preset time similarity matrix, the element values ​​of the time similarity matrix are traversed, and under the condition that the measurement threshold of the dynamic similarity matrix is ​​less than the preset dynamic similarity matrix, the element values ​​that meet the conditions are obtained respectively, and then according to the rule of taking the minimum value for each row and the maximum value for each column, the element values ​​that meet the conditions are optimized again, and the element values ​​that meet the rules are set to 1, otherwise, the element values ​​are set to 0, and the 0-1 time measurement matrix corresponding to the time similarity matrix and the 0-1 dynamic information measurement matrix corresponding to the dynamic information similarity matrix are obtained respectively.

[0116] The number of elements with the value of 1 at the same position in the 0-1 time measurement matrix and the 0-1 dynamic information measurement matrix is ​​counted. When the number is greater than the preset threshold, the discrete point trace corresponding to the position is successfully associated with the historical point trace and added to the associated data pair set.

[0117] S14: Setting the same track number for each group of associated data pairs to obtain an associated result.

[0118] It should be noted that the correlation relationship of multi-source heterogeneous information is used for target identification. In practice, the correlation results are sent to the target multi-attribute identification system based on information fusion, and finally the binary attributes of information are expanded to multi-attributes, the recognition of the target is improved, and more hidden relationships are excavated.

[0119] Compared with the prior art, the present embodiment provides a multi-source heterogeneous information association method based on discrete point traces. By clustering multi-source heterogeneous information of the same period and associating information of different periods, the discrete points are accurately identified while obtaining the associated data of the multi-source heterogeneous information. Then, the discrete points are constructed through the construction of a multi-dimensional similarity matrix and the design of association optimization rules, which solves the problems of difficulty in distinguishing discrete points and missed associations, and provides a premise and guarantee for improving the target recognition rate. For multi-source heterogeneous information of the same period, the initial clustering center is dynamically selected based on the maximum density iterative processing method through identity information matching and improved fuzzy C-means clustering, which solves the problem that the initial clustering center has a strong dependence on artificial and prior information, and realizes The fuzzy clustering of multiple information from the same sensor in the same period and the rough selection of sparse discrete points solves the problems of low utilization of existing identity information and difficulty in judging sparse points. For the association of information in different periods, a dynamic design criterion for the association gate is designed, and a method based on identity information matching and dynamic association of multi-period and multi-dimensional information is implemented to solve the problem of erroneous association that may occur under dense multi-target and complex motion conditions, as well as the secondary judgment of sparse discrete points. The association process of classified and hierarchical processing is adopted to gradually obtain association data from multi-target and multi-source heterogeneous information in dense environments, reduce the computational complexity of association, screen out discrete points step by step, and construct a multi-dimensional similarity matrix for discrete point traces, solving the problem of high complexity of information association.

[0120] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0121] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A multi-source heterogeneous information association method based on discrete point traces, characterized in that: The steps include: Receive the multi-source heterogeneous information, identify the discrete points therein, store them in a history library, and use other information in the history library as historical points; the multi-source heterogeneous information comes from multiple sensors equipped on the target platform, including: acquisition time, dynamic information, identity information and proprietary information, and is indexed by sensor type; wherein the dynamic information includes: target longitude, target latitude, target altitude, target distance, target azimuth and target pitch; the identity information is the 24-bit address code of the sensor; the proprietary information is the icon of the sensor; Based on identity information and proprietary information, a set of associated data pairs of discrete traces and historical traces is obtained; then based on time and dynamic information, multiple similarity matrices are established for the remaining discrete traces and the remaining historical traces in the historical database; According to the preset measurement threshold of each similarity matrix, multiple similarity matrices are converted into multiple 0-1 measurement matrices; based on the multiple 0-1 measurement matrices, the associated data pairs of the remaining discrete points and the remaining historical points in the history library are obtained and added into the associated data pair set; Setting the same track number for each set of associated data pairs in the associated data pair set to obtain an associated result; The receiving of the multi-source heterogeneous information and identifying discrete points therein includes: identifying discrete points in the multi-source heterogeneous information within the same information fusion cycle, and identifying discrete points in the multi-source heterogeneous information during multiple information fusion cycles; The identifying of discrete points in multi-source heterogeneous information within the same information fusion cycle includes: According to the information fusion cycle, multi-source heterogeneous information containing multiple data from the same type of sensors is added to the set to be clustered, and other multi-source heterogeneous information is added to the preliminary clustering set; Cluster the cluster set, add the multi-source heterogeneous information closest to the cluster center in each class into the preliminary cluster set, put the other multi-source heterogeneous information in each class into the buffer area, and identify the multi-source heterogeneous information not classified into any class as discrete point traces; The identifying of discrete points in multi-source heterogeneous information during multiple information fusion cycles includes: Based on the same identity information, the associated data pairs of the multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the historical database are identified and added to the associated data pair set; According to a preset dynamic information association threshold, candidate historical point traces are obtained from the remaining multi-source heterogeneous information in the history library; Based on dynamic information, the association gate between the remaining multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the candidate historical traces is calculated, and the associated data pairs between the remaining multi-source heterogeneous information in the preliminary clustering set and the multi-source heterogeneous information in the candidate historical traces are identified according to the association gate. The multi-source heterogeneous information that fails to be associated in the preliminary clustering set is identified as discrete traces.

2. The multi-source heterogeneous information association method based on discrete point traces according to claim 1 is characterized in that: The method of using other information in the history library as historical traces includes: according to the acquisition time of the discrete traces, using the Kalman filtering method, extrapolating the track point prediction of other multi-source heterogeneous information in the history library to the acquisition time of the discrete traces to obtain the historical traces.

3. The multi-source heterogeneous information association method based on discrete point traces according to claim 2 is characterized in that: The method of obtaining the associated data pairs of the discrete points and the historical points based on the identity information and the proprietary information includes: Take out each discrete point trace in turn, and compare each discrete point trace with each historical point trace in pairs; when a discrete point trace only has the same identity information and proprietary information as a historical point trace, the association is successful; otherwise, the association fails.

4. The multi-source heterogeneous information association method based on discrete point traces according to any one of claims 1 to 3, characterized in that: The rows of the similarity matrix correspond to each discrete point trace, the columns correspond to each historical point trace, and the element values ​​correspond to the multi-source heterogeneous information comparison values ​​of each discrete point trace and each historical point trace; The similarity matrix includes: a time similarity matrix and a dynamic information similarity matrix; the multi-source heterogeneous information comparison value includes: a time information comparison value and a dynamic information comparison value.

5. The multi-source heterogeneous information association method based on discrete point traces according to claim 4 is characterized in that: The method of converting the plurality of similarity matrices into a plurality of 0-1 measurement matrices according to the preset measurement threshold of each similarity matrix comprises: Under the condition that the measurement threshold of the preset time similarity matrix is ​​less than the preset time similarity matrix, the element values ​​of the time similarity matrix are traversed, and under the condition that the measurement threshold of the dynamic similarity matrix is ​​less than the preset dynamic similarity matrix, the element values ​​that meet the conditions are obtained respectively, and then according to the rule of taking the minimum value for each row and the maximum value for each column, the element values ​​that meet the conditions are optimized again, and the element values ​​that meet the rules are set to 1, otherwise, the element values ​​are set to 0, and the 0-1 time measurement matrix corresponding to the time similarity matrix and the 0-1 dynamic information measurement matrix corresponding to the dynamic information similarity matrix are obtained respectively.

6. The multi-source heterogeneous information association method based on discrete point traces according to claim 5 is characterized in that: The step of obtaining the associated data pairs of the remaining discrete points and the remaining historical points in the history library based on the multiple 0-1 metric matrices and adding the associated data pairs to a set of associated data pairs includes: The number of elements with a value of 1 at the same position in the 0-1 time measurement matrix and the 0-1 dynamic information measurement matrix is ​​counted. When the number is greater than a preset threshold, the discrete point trace corresponding to the position is successfully associated with the historical point trace and added to the associated data pair set.

7. The multi-source heterogeneous information association method based on discrete point traces according to claim 6 is characterized in that: The preset dynamic information association thresholds include: a longitude association threshold, a latitude association threshold and an altitude association threshold; The step of obtaining candidate historical points from the remaining multi-source heterogeneous information in the historical database includes: Each remaining multi-source heterogeneous information in the preliminary clustering set is taken out in turn, and compared with each remaining multi-source heterogeneous information in the historical library, and the longitude difference, latitude difference and altitude difference of the dynamic information in the multi-source heterogeneous information are obtained. When the absolute values ​​of the three differences are all less than the corresponding association thresholds, the multi-source heterogeneous information in the historical library is included in the candidate historical point traces, and the Kalman filtering method is used to predict and extrapolate the track points related to the multi-source heterogeneous information in the historical library, and extrapolate to the acquisition time of the multi-source heterogeneous information in the preliminary clustering set compared with it, so as to obtain the candidate historical point traces.

Images