A trajectory feature modeling method for aerial target classification and behavior recognition

Abstract

The present invention relates to the application field of target trajectory prediction, and discloses a trajectory feature modeling method for aerial target classification and behavior recognition, the main purpose of which is to achieve a fixed-length, interpretable feature representation for high-dimensional, different-scale aerial target trajectory time series information. Flight behaviors mainly include level flight and turning of civil aircraft, dive of bombers, complex behavior of fighters, O-shaped reconnaissance of reconnaissance aircraft and other flight behaviors. First, the aerial target trajectory data is preprocessed; based on the speed range of different flight targets, the speed feature of the preprocessed data is represented; based on the different turning amplitude ranges of different flight targets, a one-way double-walking algorithm is designed to represent the turning feature of the flight trajectory; then, combined with the target flight trajectory behavior prior, the flight trajectory is locally encoded and the local behavior feature is obtained; finally, the obtained features are combined, and a clustering algorithm is used to perform unsupervised recognition of the aerial target behavior and category.

Description

Technical Field

[0001] The present invention belongs to the field of space-based infrared data processing and target trajectory prediction applications, and provides a trajectory feature modeling method for aerial target classification and behavior recognition, in particular, a process of predicting enemy combat ideas and plans by sensing target trajectory information through various battlefield sensors to conduct a comprehensive analysis of flight behavior and target categories, and specifically involves an identification method for extracting features of aerial maneuverable target flight behavior, performing cluster analysis on target categories, and thus judging enemy combat intentions. Background Art

[0002] With the prominent position of air supremacy in modern military warfare, the continuous evolution of the aerial battlefield situation and the renewal of weapons and equipment, quickly and accurately identifying the flight behavior of enemy targets and target categories is an important part of battlefield situation assessment. The aerial battlefield has become an important field of military games among various countries. In order to fully perceive the aerial battlefield situation, the continuous emergence of visible light, radar, and infrared imaging sensors has formed a full-dimensional and multi-dimensional detection capability for aerial targets. Due to the particularity of the band used for infrared imaging, it has the advantages of low dependence on the environment, can work all day, high sensitivity, and strong resistance to electromagnetic interference. Therefore, infrared imaging detectors are widely used in military and civilian fields in various countries.

[0003] The detection system of aerial targets based on space-based infrared early warning data is a point target. It has no geometric and texture characteristics, and it is difficult to realize the category recognition of aerial targets based on traditional image processing models. The maneuverability characteristics of aerial targets are obvious, and the movement rules are complex and changeable. For example, the trajectory of civil aircraft is smooth and linear, and the speed of medium and large bombers, early warning aircraft, and tankers is relatively stable, but the flight trajectory is S-shaped or "8"-shaped. The movement trajectory of small fighters is the most complex, with large speed changes and various flight actions in three-dimensional space, such as U-turns, dives, and somersaults. Therefore, the movement trajectory information of aerial targets detected by space-based infrared can be used to express the speed, turning amplitude, and local movement behavior characteristics of high-dimensional target movement trajectories, so as to realize the behavior judgment of complex flight trajectories of aerial targets and the category recognition of aircraft. Based on the above factors, this paper proposes a trajectory feature modeling method for aerial target classification and behavior recognition, which is of great significance in the situation awareness of the aerial battlefield. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a trajectory feature modeling method for aerial target classification and behavior recognition. In combination with the aerial target flight prior, speed feature representation, turning amplitude feature representation, and local motion behavior feature representation are used to perform fixed-dimensional feature expression on the high-dimensional aerial target flight trajectory information that is difficult to model directly, which facilitates subsequent behavior recognition and target recognition model modeling. At the same time, the algorithm has fast operation speed and is interpretable, and is easily integrated into the air situation awareness system, which can assist the military in real-time detection, analysis, and identification of aerial target behavior.

[0005] In order to solve the above technical problems and achieve the above objectives, the technical solution adopted by the present invention is as follows: A trajectory feature modeling method for aerial target classification and behavior recognition comprises the following steps:

[0006] Step 1: Preprocess the aerial target trajectory data and proceed to step 2;

[0007] Step 2: Perform velocity feature representation on the preprocessed target trajectory data, and then proceed to step 3;

[0008] Step 3: Perform turning feature representation on the preprocessed target trajectory data and proceed to step 4;

[0009] Step 4: Perform local behavior feature representation on the preprocessed target trajectory data and proceed to step 5

[0010] Step 5: Combine the speed feature vector, turning feature vector, and local behavior feature vector obtained in steps 2 to 4, that is, use clustering method for unsupervised recognition, or manually design logic for target recognition. In the above technical solution, step 1 specifically includes the following steps:

[0011] Step 1.1: Remove duplicate trajectory points from the target trajectory data set and go to step 1.2;

[0012] Step 1.2: Perform an equidistant interpolation operation on the new target trajectory data set obtained in step 1.1 to ensure that the time interval between two adjacent trajectory points is uniform, and obtain the final preprocessed target trajectory data. The preprocessed target trajectory data mainly includes the number of trajectory points , the horizontal coordinate of each trajectory point on the earth observation detector With vertical coordinate Therefore, the trajectory of an aerial target can be described as ,in , .

[0013] In the above technical solution, the step 2 specifically includes the following steps:

[0014] Step 2.1: The aerial target trajectory data obtained in step 1.2 , using formula (1) and formula (2) to calculate the front The lateral offset vector of the trajectory point With the longitudinal offset vector Formula (1) and formula (2) are as follows:

[0015]

[0016]

[0017] in, , , they respectively said The time between track points The lateral and longitudinal offsets within.

[0018] Step 2.2: Substitute the lateral offset vector obtained in step 2.1 With the longitudinal offset vector The velocity vector is calculated by formula (3): , formula (3) is as follows:

[0019] (3)

[0020] in, represents the time interval between two trajectory points, The value of .

[0021] Step 2.3: Substitute the velocity vector extracted in step 2.2 Perform bin counting statistics and binning , that is, the speed is counted separately in In the interval, we get Speed ​​statistics distribution in each interval .

[0022] Step 2.4: The velocity statistical distribution obtained in step 2.3 is used to obtain the final velocity feature vector through equation (4): , formula (4) is as follows:

[0023]

[0024] in, .

[0025] In the above technical solution, the step 3 specifically includes the following steps:

[0026] Step 3.1: The aerial target trajectory data obtained in step 1.2 Perform multiple local trajectory sampling, the number of sampling times is ,in , The total number of trajectory points. The minimum number of trajectory points in a local trajectory is set to , maximum value setting ;

[0027] Step 3.2: In each local trajectory sampling of step 3.1, firstly Perform equal probability extraction as the initial point of the local trajectory , and the value of the initial point in each local trajectory sampling is not repeated;

[0028] Step 3.3: In each local trajectory sampling of step 3.1, obtain arrive A random integer , as the number of trajectory points of this local trajectory, and the random integer It can be repeated in each sampling, and the end point of the local trajectory is ;

[0029] Step 3.4: The local trajectory obtained by sampling each local trajectory in step 3.1 is expressed as , the number of trajectory points is ,in , ;

[0030] Step 3.5: The local trajectory obtained by step 3.4 , calculate the initial direction of the local trajectory and final direction , and then calculate the turning amplitude of the local trajectory through formula (5) , formula (5) is as follows:

[0031]

[0032] Step 3.6: The results obtained from Steps 3.1 to 3.5 The turning amplitude of each local trajectory is then counted and binned. , the turning range is Count each section and get the turning amplitude vector of each section , the final turning feature is obtained through formula (6) , formula (6) is as follows:

[0033]

[0034] In the above technical solution, step 4 specifically includes the following steps:

[0035] Step 4.1: The aerial target trajectory data obtained in step 1.2 , starting from the initial point, the step size is set to , divided equally into Local trajectory data, where , Indicates rounding down, that is, discarding the final trajectory points with less than The local trajectory of .

[0036] Step 4.2: For each local trajectory data obtained in step 4.1, calculate its turning range using steps 3.4 and 3.5 . Set the threshold ,like Then the local trajectory is encoded as , which indicates that the local trajectory is a straight line. It is usually set to a value greater than 0.8. , according to the parameters calculated in step 3.3 and The rotation direction of the local trajectory is determined by The encoding is ,like The encoding is .in Indicates that the local trajectory rotates counterclockwise. Indicates clockwise rotation. Finally, the encoding of the entire trajectory is obtained. ,in Indicates Encoding of local trajectories of segments.

[0037] Step 4.3: Encode the entire trajectory obtained in step 4.2 Perform single-segment local trajectory encoding counting statistics. Designed for ,in Express middle for The encoding is counted and the value is expressed as , Express middle for or The encoding is counted and the value is expressed as .

[0038] Step 4.4: Encode the entire trajectory obtained in step 4.2 Make adjacent combinations to get , and count the combined trajectory encoding. At this time, the box Designed for ,in Indicates that the combination of straight line and turn or turn and straight line is counted in the box , the count value is expressed as . Indicates that the combination of consecutive clockwise or counterclockwise turns is counted in the box , the count value is expressed as . Represents the snake behavior count in the box , the count value is expressed as .

[0039] Step 4.5: For the results obtained in steps 4.3 and 4.4 The final local behavior characteristics are obtained through formula (7): , formula (7) is as follows:

[0040]

[0041] In the above technical solution, the step 5 specifically includes the following steps:

[0042] Step 5.1: Velocity features obtained from steps 2.4, 3.6, and 4.5 respectively , Turning Features , local behavior characteristics The feature representation of a trajectory is obtained by combining them, as shown in formula (8):

[0043]

[0044] Among them, the feature representation dimension of the entire trajectory is .

[0045] Step 5.2: Get the final feature representation of the entire trajectory according to step 5.1 , clustering methods can be used for classification, or the type of the trajectory and the category of the target can be identified through manual experience.

[0046] Because the present invention adopts the above technical solution, it has the following beneficial effects:

[0047] 1. Speed ​​feature representation: Through the technical solution of step 2, the present invention can accurately extract and represent the flight speed characteristics of different categories of aerial targets. Speed ​​is an important indicator of aircraft movement. Different categories of aircraft often have differences in speed due to their performance and mission requirements. By statistically analyzing the speed distribution in the flight trajectory data, different types of aircraft can be effectively identified and distinguished. For example, civil aircraft usually fly at a stable speed, while fighter jets may show large speed changes. The present invention helps to distinguish different flight target categories and flight behaviors from the speed distribution statistics through speed feature representation.

[0048] 2. Turn feature representation: The technical solution of step 3 enables the present invention to accurately extract and represent the turning features of different categories of aerial targets. The turning amplitude is an important indicator reflecting the maneuverability of an aircraft. Different categories of aircraft have significant differences in turning performance due to their design and mission requirements. By counting and analyzing the turning amplitude in the flight trajectory data, different types of aircraft can be effectively identified and distinguished. For example, fighter jets need to have strong maneuverability, so their turning amplitude is usually larger, while large transport aircraft or bombers have relatively small turning amplitudes. The present invention helps to distinguish different categories of flying targets and flight behaviors based on the turning amplitude through turning feature representation.

[0049] 3. Representation of local behavior features: The technical solution of step 4 enables the present invention to accurately extract and represent the local flight behavior features of different categories of aerial targets. Local behavior features reflect the movement pattern of an aircraft within a specific time period. Different categories of aircraft have significant differences in local behavior features due to their performance and mission requirements. By counting and analyzing the local behavior features in the flight trajectory data, different types of aircraft can be effectively identified and distinguished. For example, fighter jets may exhibit complex flight maneuvers when performing specific tasks, while civil aircraft mainly fly in a smooth straight line. The present invention, through the representation of local behavior features, helps to accurately identify specific categories of aerial targets through specific flight behavior models.

[0050] In summary, the present invention can effectively model and analyze the flight behavior of aerial targets by comprehensively utilizing speed characteristics, turning characteristics and local behavior characteristics, thereby realizing accurate identification and classification of different types of aircraft. This method has high practicality and reliability, and provides strong technical support for aerial battlefield situation awareness. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a schematic diagram of the aerial target behavior trajectory data used in the present invention;

[0052] Figure 2It is a speed statistical distribution diagram of different flight speed intervals of aerial targets in the present invention;

[0053] Figure 3 It is a statistical distribution diagram of turning characteristics of aerial targets in the present invention;

[0054] Figure 4 This is a schematic diagram of the coding result of the aerial target behavior in the present invention;

[0055] Figure 5 It is a schematic diagram of the recognition result in the present invention;

[0056] Figure 6 Design a solution flow for the entire algorithm. DETAILED DESCRIPTION

[0057] The present invention is further described in detail below in conjunction with test examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0058] The technical problem to be solved by the present invention is to provide a trajectory feature modeling method for aerial target classification and behavior recognition. The method combines the aerial target flight priors with speed feature representation, turning amplitude feature representation, and local motion behavior feature representation to perform fixed-dimensional feature expression on the high-dimensional aerial target flight trajectory information that is difficult to model directly, so as to facilitate subsequent behavior recognition and target recognition model modeling. The entire algorithm design process is as follows: Figure 6 As shown, the steps include:

[0059] Step 1.1: Remove duplicate trajectory points from the target trajectory data set and go to step 1.2;

[0060] In this example, the number of track points after removing duplicate track points from the target track data , including 120 horizontal axes and 120 vertical coordinates .

[0061] Step 1.2: Perform an equidistant interpolation operation on the new target trajectory data set obtained in step 1.1 to ensure that the time interval between two adjacent trajectory points is uniform, and obtain the final preprocessed target trajectory data. The preprocessed target trajectory data mainly includes the number of trajectory points , the horizontal coordinate of each trajectory point on the earth observation detector With vertical coordinate Therefore, the trajectory of an aerial target can be described as ,in , .

[0062] In this example, the preprocessed aerial target trajectory can be expressed as ,in , , which lists 20 flight trajectories after preprocessing such as Figure 1 shown.

[0063] Step 2.1: The aerial target trajectory data obtained in step 1.2 , using formula (1) and formula (2) to calculate the front of the target trajectory The lateral offset vector of the trajectory point With the longitudinal offset vector Formula (1) and formula (2) are as follows:

[0064]

[0065]

[0066] in, , , they respectively said The time between track points The lateral and longitudinal offsets within.

[0067] In this example, , , they respectively said The time between track points The lateral and longitudinal offsets within the time interval The velocity distribution results are as follows: Figure 2 shown.

[0068] Step 2.2: Substitute the lateral offset vector obtained in step 2.1 With the longitudinal offset vector The velocity vector is calculated by formula (3): , formula (3) is as follows:

[0069]

[0070] in, represents the time interval between two trajectory points, The value of .

[0071] Step 2.3: Substitute the velocity vector extracted in step 2.2 Perform bin counting statistics and binning , that is, the speed is counted separately in In the interval, we get Speed ​​statistics distribution in each interval .

[0072] In this example, the extracted velocity vector Perform bin counting statistics and specific binning strategies , that is, the speed is counted in 10 intervals, and the Statistical distribution on 10 intervals .

[0073] Step 2.4: The velocity statistical distribution obtained in step 2.3 is used to obtain the final velocity feature vector through equation (4): , formula (4) is as follows:

[0074] (4)

[0075] in, .

[0076] In this example, the velocity statistical distribution is obtained by formula (4) to obtain the final velocity 10-dimensional feature vector .

[0077] Step 3.1: The aerial target trajectory data obtained in step 1.2 Perform multiple local trajectory sampling, the number of sampling times is ,in , The total number of trajectory points. The minimum number of trajectory points in a local trajectory is set to , maximum value setting ;

[0078] In this example, the aerial target trajectory data obtained in step 1.2 Perform multiple local trajectory sampling, the number of sampling times is , where the specific assignment , the total number of trajectory points , , .

[0079] Step 3.2: In each local trajectory sampling of step 3.1, firstly Perform equal probability extraction as the initial point of the local trajectory , and the value of the initial point in each local trajectory sampling is not repeated;

[0080] Step 3.3: In each local trajectory sampling of step 3.1, obtain arrive A random integer , as the number of trajectory points of this local trajectory, and the random integer It can be repeated in each sampling, and the end point of the local trajectory is ;

[0081] Step 3.4: The local trajectory obtained by sampling each local trajectory in step 3.1 is expressed as , the number of trajectory points is ,in , .

[0082] Step 3.5: The local trajectory obtained by step 3.4 , calculate the initial direction of the local trajectory and final direction , and then calculate the turning amplitude of the local trajectory through formula (5) , formula (5) is as follows:

[0083]

[0084] Step 3.6: The results obtained from Steps 3.1 to 3.5 The turning amplitude of each local trajectory is then counted and binned. , the turning range is Count each section and get the turning amplitude vector of each section , the final turning feature is obtained through formula (6) , formula (6) is as follows:

[0085]

[0086] In this example, we can get The turning amplitude of each local trajectory is counted, and then binned and counted. , the turning range is Statistical counting is performed in each interval, and the results are as follows Figure 3 As shown, the final turning feature is obtained through formula (6): , and get the 8-dimensional feature vector .

[0087] Step 4.1: The aerial target trajectory data obtained in step 1.2 , starting from the initial point, the step size is set to , divided equally into Local trajectory data, where , Indicates rounding down, that is, discarding the final trajectory points with less than The local trajectory of .

[0088] In this example, the aerial target trajectory data obtained in step 1.2 , starting from the initial point, the step size is set to , the total number of trajectory points .

[0089] Step 4.2: For each local trajectory data obtained in step 4.1, calculate its turning range using steps 3.4 and 3.5 . Set the threshold ,like Then the local trajectory is encoded as , which indicates that the local trajectory is a straight line. It is usually set to a value greater than 0.8. , according to the parameters calculated in step 3.3 and The rotation direction of the local trajectory is determined by The encoding is ,like The encoding is .in Indicates that the local trajectory rotates counterclockwise. Indicates clockwise rotation. Finally, the encoding of the entire trajectory is obtained. ,in Indicates Encoding of local trajectories of segments.

[0090] In this example, for each local trajectory data obtained in step 4.1, the turning range is calculated using steps 3.4 and 3.5. . Set the threshold ,in Indicates that the local trajectory rotates counterclockwise. Indicates clockwise rotation. Get the encoding of the entire trajectory ,in Indicates The encoding of the local trajectory of the segment is as follows Figure 4 shown.

[0091] Step 4.3: Encode the entire trajectory obtained in step 4.2 Perform single-segment local trajectory encoding counting statistics. Designed for ,in Express middle for The encoding is counted and the value is expressed as , Express middle for or The encoding is counted and the value is expressed as .

[0092] Step 4.4: Encode the entire trajectory obtained in step 4.2 Make adjacent combinations to get , and count the combined trajectory encoding. At this time, the box Designed for ,in Indicates that the combination of straight line and turn or turn and straight line is counted in the box , the count value is expressed as . Indicates that the combination of consecutive clockwise or counterclockwise turns is counted in the box , the count value is expressed as . Represents the snake behavior count in the box , the count value is expressed as .

[0093] Step 4.5: For the results obtained in steps 4.3 and 4.4 The final local behavior characteristics are obtained through formula (7): , formula (7) is as follows:

[0094]

[0095] In the above technical solution, the step 5 specifically includes the following steps:

[0096] In this example, the results of steps 4.3 and 4.4 are The final 5-dimensional feature vector of local behavior features is obtained by formula (7): .

[0097] Step 5.1: Velocity features obtained from steps 2.4, 3.6, and 4.5 respectively , Turning Features , local behavior characteristics The feature representation of a trajectory is obtained by combining them, as shown in formula (7):

[0098]

[0099] Among them, the feature representation dimension of the entire trajectory is .

[0100] Step 5.2: Get the final feature representation of the entire trajectory according to step 5.1 , clustering methods can be used for classification, or the type of the trajectory and the category of the target can be identified through manual experience.

[0101] In this example, the k-means clustering method is used for classification, which is divided into 3 categories. The results are as follows Figure 5 shown.

Claims

1. A trajectory feature modeling method for aerial target classification and behavior recognition, characterized by: The steps include: Step 1: Preprocess the aerial target trajectory data; Step 2: Perform speed feature representation on the preprocessed target trajectory data. Specifically, extract a speed vector based on the preprocessed target trajectory data, perform bin counting and statistics on the extracted speed vector to obtain speed statistical distribution of m intervals, and calculate the final speed feature vector based on the obtained speed statistical distribution of the m intervals; Step 3: Perform turning feature representation on the preprocessed target trajectory data. Specifically, calculate the turning amplitude of the local trajectory based on the preprocessed target trajectory data, then divide the turning amplitude into e intervals for bin counting and statistics, obtain the turning amplitude vector of each interval, and calculate the final turning feature based on the obtained turning amplitude vector of each interval; Step 4: local behavior feature representation is performed on the preprocessed target trajectory data. Specifically, the whole trajectory code is calculated based on the preprocessed target trajectory data, and then the obtained whole trajectory code is subjected to single-segment local trajectory code bin count statistics and adjacent combination, and combined trajectory code bin count statistics is performed. Based on the results of the single-segment local trajectory code bin count statistics and the results of the combined trajectory code bin count statistics, the final local behavior feature is calculated; Step 5: Combine the speed feature vector, turning feature vector, and local behavior feature vector obtained in steps 2 to 4, perform unsupervised recognition through clustering method, or design logic for target recognition.

2. The trajectory feature modeling method for aerial target classification and behavior recognition according to claim 1 is characterized in that: The step 1 comprises the following steps: Step 1.1: Remove duplicate trajectory points from the target trajectory data set and go to step 1.2; Step 1.2: Perform an equidistant interpolation operation on the new target trajectory data set obtained in step 1.1 to ensure that the time interval between two adjacent trajectory points is uniform, and obtain the final preprocessed target trajectory data. The preprocessed target trajectory data includes the number of trajectory points. , the horizontal coordinate of each trajectory point on the earth observation detector With vertical coordinate , an aerial target trajectory is described as ,in , .

3. The trajectory feature modeling method for aerial target classification and behavior recognition according to claim 2 is characterized in that: The step 2 specifically includes the following steps: Step 2.1: The aerial target trajectory data obtained in step 1.2 , using formula (1) and formula (2) to calculate the front The lateral offset vector of the trajectory point With the longitudinal offset vector , formula (1) and formula (2) are as follows: in, , , which respectively represent the lateral and longitudinal offsets of the ith trajectory point within the trajectory point interval time t; Step 2.2: Substitute the lateral offset vector obtained in step 2.1 With the longitudinal offset vector The velocity vector is calculated by formula (3): , formula (3) is as follows: Among them, t represents the time interval between two trajectory points, and the value of i is ; Step 2.3: Substitute the velocity vector extracted in step 2.2 Perform bin counting statistics and binning , that is, the speed is counted separately in In the interval, we get Speed ​​statistics distribution in each interval ; Step 2.4: The velocity statistical distribution obtained in step 2.3 is used to obtain the final velocity feature vector through equation (4): , formula (4) is as follows: in, .

4. The trajectory feature modeling method for aerial target classification and behavior recognition according to claim 2 is characterized in that: The step 3 specifically includes the following steps: Step 3.1: The aerial target trajectory data obtained in step 1.2 Perform multiple local trajectory sampling, the number of sampling times is ,in , The total number of trajectory points, the minimum number of trajectory points in the local trajectory is set to , maximum value setting ; Step 3.2: In each local trajectory sampling of step 3.1, firstly Perform equal probability extraction as the initial point of the local trajectory , and the value of the initial point in each local trajectory sampling is not repeated, where N-Smax is the maximum starting point of the local sampling; Step 3.3: In each local trajectory sampling of step 3.1, obtain arrive A random integer , as the number of trajectory points of this local trajectory, and the random integer It can be repeated in each sampling, and the end point of the local trajectory is ; Step 3.4: The local trajectory obtained by sampling each local trajectory in step 3.1 is expressed as , the number of trajectory points is ,in , ; Step 3.5: The local trajectory obtained by step 3.4 , calculate the initial direction of the local trajectory and final direction , and then calculate the turning amplitude of the local trajectory through formula (5) , formula (5) is as follows: Step 3.6: The results obtained from Steps 3.1 to 3.5 The turning amplitude of each local trajectory is then counted and binned. , the turning range is divided into Count each section and get the turning amplitude vector of each section , the final turning feature is obtained through formula (6) , formula (6) is as follows: 。 5. The trajectory feature modeling method for aerial target classification and behavior recognition according to claim 4 is characterized in that: The step 4 specifically comprises the following steps: Step 4.1: The aerial target trajectory data obtained in step 1.2 , starting from the initial point, the step size is set to , divided equally into Local trajectory data, where , Indicates rounding down, that is, discarding the final trajectory points with less than The local trajectory of Step 4.2: For each local trajectory data obtained in step 4.1, calculate its turning range using steps 3.4 and 3.5 , set the threshold ,like Then the local trajectory is encoded as , which indicates that the local trajectory is a straight line. Set to a value greater than 0.8, if , according to the parameters calculated in step 3.3 and The rotation direction of the local trajectory is determined by The encoding is ,like The encoding is ,in Indicates that the local trajectory rotates counterclockwise. Indicates clockwise rotation, and the entire trajectory will be encoded ,in Indicates Encoding of segment local trajectories; Step 4.3: Encode the entire trajectory obtained in step 4.2 Perform single-segment local trajectory encoding counting statistics. Designed for ,in Express middle for The encoding is counted and the value is expressed as , Express middle for or The encoding is counted and the value is expressed as ; Step 4.4: Encode the entire trajectory obtained in step 4.2 Make adjacent combinations to get , and count the combined trajectory encoding. At this time, the box Designed for ,in Indicates that the combination of straight line and turn or turn and straight line is counted in the box , the count value is expressed as , Indicates that the combination of consecutive clockwise or counterclockwise turns is counted in the box , the count value is expressed as , Represents the snake behavior count in the box , the count value is expressed as ; Step 4.5: For the results obtained in steps 4.3 and 4.4 The final local behavior characteristics are obtained through formula (7): , formula (7) is as follows: 。 6. The trajectory feature modeling method for aerial target classification and behavior recognition according to claim 1 is characterized in that: The step 5 specifically comprises the following steps: Step 5.1: Velocity features obtained from steps 2.4, 3.6, and 4.5 respectively , Turning Features , local behavior characteristics The feature representation of a trajectory is obtained by combining them, as shown in formula (7): Among them, the feature representation dimension of the entire trajectory is ; Step 5.2: Get the final feature representation of the entire trajectory according to step 5.1 , clustering methods are used for classification, or the type of the trajectory and the category of the target are identified through artificial experience.

Images