A method for image target shooting data processing for impact point prediction

Abstract

This invention relates to the field of shooting training technology, specifically to a method for image target shooting data processing for impact point prediction, comprising the following steps: obtaining impact point coordinates through trajectory calculation and decomposing horizontal and vertical components; calculating and sorting the deviation distance between the impact point and the target center; dividing the data trajectory set using trend analysis and calculating directional consistency and amplitude stability; screening deviation groups and assigning calibration weights, and combining stable groups and assigning continuation weights; integrating and generating dynamic weight data; and generating a target display optimization control instruction set by combining distribution concentration and cross-regional trend parameters. In this invention, obtaining and sorting impact point coordinates through trajectory calculation provides basic data for trajectory analysis; dividing groups through trend analysis and calculating directional consistency and amplitude stability improves trajectory recognition and prediction accuracy; combining calibration and continuation weights enhances personalized feedback; and fine-tuning the target through impact point sequence screening improves feedback reliability and training effectiveness.

Description

Technical Field

[0001] This invention relates to the field of shooting training technology, and in particular to a method for processing image target shooting data for impact point prediction. Background Technology

[0002] The field of shooting training technology encompasses training methods and devices for improving the skills of shooting personnel, mainly covering target setting, shooting posture training, aiming control, firing practice, and environmental simulation. The core content lies in constructing a training system that conforms to real shooting scenarios, enabling shooters to train under multiple environmental conditions, and combining visual targets, optical positioning, trigger response, and image feedback to form a complete training process.

[0003] The image-based target simulation shooting method refers to the use of image display combined with target projection to create a visible shooting target in the training scenario, and then detecting the target by firing simulated bullets or laser signals. The target presentation and firing feedback in shooting training encompasses the image projection to form the target, the sensing device receiving the firing signal, and the judgment device confirming the firing position. This is primarily achieved by generating a target image through projection or display devices, recording the firing trajectory and firing signal with a firing sensing device, and then recording and analyzing the firing point through a judgment mechanism, thus constituting a complete image-based target simulation training method.

[0004] Existing target simulation methods largely rely on target images generated by projection or display devices and shooting signals recorded by sensors. While these methods provide some feedback, in practical applications, target adjustments often lack real-time, fine-grained control. Insufficient feedback on shooting trajectories and dynamic adjustments to the target result in a lack of timely and accurate feedback on shooter performance during training. This is especially true in scenarios with complex shooting trajectories and significant environmental influences, where existing methods struggle to capture and accurately reflect subtle changes at each impact point in real time. This leads to insufficiently refined training results and hinders long-term, systematic progress. Trainees may continue inaccurate training without timely adjustments, limiting skill improvement. Furthermore, existing technologies struggle to accurately quantify differences between groups when handling trajectory group analysis, easily overlooking the training needs of some individuals and failing to provide personalized training suggestions and guidance for each shooter. Summary of the Invention

[0005] To address the technical problems existing in the prior art, embodiments of the present invention provide a method for processing image target shooting data for impact point prediction, comprising the following steps:

[0006] To achieve the above objectives, the present invention employs the following technical solution: a method for processing image target shooting data for impact point prediction, comprising the following steps:

[0007] S1: Obtain the target landing point coordinates by calculating the trajectory during the shooting process and decompose them into horizontal and vertical components. Calculate the deviation distance between each shooting landing point and the target center and sort them to generate landing point deviation data.

[0008] S2: Based on the impact point deviation data, the impact points with similar trends of change are divided into data trajectory sets by a trend analysis algorithm. The consistency of impact point direction and amplitude stability of the data trajectory sets are calculated and summarized to generate a data trajectory set feature set.

[0009] S3: Based on the data trajectory set feature set, calculate the consistency deviation of the shooting point direction of multiple groups and filter out the groups that exceed the direction consistency threshold to assign calibration weights. Assign the group with the best amplitude stability a continuation weight and integrate it with the calibration weights to generate dynamic weight data.

[0010] S4: Based on the deviation distance, sort the landing points and filter the landing point segments whose adjacent radius distance difference does not reach the distance interval threshold. Calculate the distribution concentration by the ratio of the number of landing points in the segment to the span. Use the dynamic weight data to judge the landing point change trend to obtain the cross-region trend parameter set. Combine the distribution concentration to construct the digital aiming point position adjustment command and the auxiliary aiming point display command, and generate the target display optimization control command set.

[0011] S5: Based on the target display optimization control instruction set, when the virtual aiming point displacement direction does not match the cross-regional trend parameter set, adjust the virtual aiming point displacement direction; when the distribution concentration parameter is close to the distribution concentration threshold, perform a secondary adjustment of the virtual aiming point, and generate an image target display adjustment optimization instruction set.

[0012] As a further embodiment of the present invention, the landing point deviation data specifically includes radius distance, sorting sequence, and distance distribution interval; the data trajectory set feature set includes direction consistency parameters, amplitude stability parameters, and group division identifiers; the dynamic weight data specifically refers to calibration weight, continuity weight, and weight integration value; the target display optimization control instruction set includes digital aiming point position adjustment instructions, auxiliary aiming point display instructions, and cross-regional trend parameter set; and the image target display adjustment optimization instruction set specifically includes correcting direction parameters, secondary offset direction, and updating display control parameters.

[0013] As a further aspect of the present invention, the specific steps of S1 are as follows:

[0014] S101: Based on the trajectory calculation results during the shooting process, extract the target impact point coordinate data in the image, calculate the horizontal coordinate component and the vertical coordinate component for each impact point coordinate, and store the data of multiple impact points in the same sequence to generate the impact point coordinate component sequence.

[0015] S102: Call the sequence of landing point coordinate components, calculate the Euclidean distance between the horizontal and vertical coordinate components of each landing point and the target center coordinates in the Cartesian coordinate system, summarize the distances of multiple landing points, and generate a sequence of landing point radius distance values.

[0016] S103: Based on the sequence of landing radius distance values, sort all landing distance values ​​in ascending order, record the sorted values ​​in the same sequence, and generate landing deviation data.

[0017] As a further aspect of the present invention, the specific steps of S2 are as follows:

[0018] S201: Based on the static characteristics of the landing point distribution reflected by the landing point deviation data, a trend analysis algorithm is used to detect the rate of change and direction difference of multiple landing point values ​​in the original landing point coordinate data, and the landing points are divided into multiple data trajectory sets according to the similarity of the change trend, generating data trajectory set division results.

[0019] S202: Call the data trajectory set division result, for the landing point in each group, calculate the directional consistency of the group based on the angle difference of the direction of change of the landing point coordinate position, and record the directional consistency of multiple groups in the same sequence to obtain the directional consistency sequence;

[0020] S203: Based on the directional consistency sequence, and combined with the numerical range of each group in the data trajectory set division result, calculate the stability rate of multiple groups in the range, and summarize the directional consistency and stability rate accordingly to establish a data trajectory set feature set.

[0021] As a further aspect of the present invention, the specific steps of S3 are as follows:

[0022] S301: Based on the feature set of the data trajectory set, calculate the deviation between the directional consistency of multiple groups and the group directional reference value, compare the deviation with the set directional consistency threshold, filter out groups that exceed the directional consistency threshold and assign corresponding calibration weights, and generate a calibration weight distribution;

[0023] S302: Call the calibration weight distribution, compare the amplitude stability of the feature set of the data trajectory set, filter the group with the best stability and set the continuation weight, store the group number and the continuation weight value to obtain the continuation weight record;

[0024] S303: Based on the calibration weight distribution and continuation weight record, perform numerical integration under the same group number, and weight the calibration weight and continuation weight to generate dynamic weight data;

[0025] The directional consistency threshold is set by evaluating the consistency of the landing directions of multiple groups.

[0026] As a further aspect of the present invention, the group direction reference value is obtained by statistically analyzing the direction data of all trajectory landing points within the same group, collecting the direction angle values ​​of multiple landing points within the group, summing the direction angles and dividing by the number of landing points to generate an average direction angle as the reference value.

[0027] As a further aspect of the present invention, the specific steps of S4 are as follows:

[0028] S401: Based on the deviation distance, sort the landing point radius distances, filter the landing point segments where the radius difference between adjacent landing points does not reach the distance interval threshold, count the number of landing points in the filtered segments and measure the segment span, calculate the span ratio by the number of landing points and the span value, and generate the distribution concentration.

[0029] S402: Call the distribution concentration, and based on the changes in the weight values ​​of multiple group landing points in the dynamic weight data, detect the increasing or decreasing trend of weight changes with the sequence, calculate the continuous change direction and summarize it into a trend parameter set to obtain a cross-regional trend parameter set;

[0030] S403: Based on the distribution concentration and the cross-regional trend parameter set, combine the landing point offset direction in the coordinate reference system, construct digital aiming point position adjustment instructions and auxiliary aiming point display instructions respectively, and integrate them to generate a target display optimization control instruction set;

[0031] The distance interval threshold is set by statistically analyzing the difference between adjacent values ​​of the landing point deviation distance.

[0032] As a further aspect of the present invention, the specific steps of S5 are as follows:

[0033] S501: Based on the target display optimization control instruction set, compare the virtual aiming point displacement direction with the direction parameters in the cross-regional trend parameter set, detect whether the angle difference between the two exceeds the direction consistency threshold, and combine the cross-regional trend parameter set to correct the virtual aiming point displacement direction and generate a direction correction angle.

[0034] S502: Call the direction correction angle. When the distribution concentration parameter is close to the distribution concentration threshold, adjust the virtual aiming point a second time according to the corrected displacement direction. During the adjustment process, the offset correction coefficient is superimposed and the current offset direction is calculated to obtain the secondary offset direction.

[0035] S503: Based on the secondary offset direction and the corrected aiming point displacement, recombine the offset vector in the coordinate system and update the display control parameters to generate an image target display adjustment and optimization instruction set;

[0036] The directional consistency threshold is set by statistically calculating the angle difference between the displacement direction of the virtual aiming point and the directional parameters in the cross-regional trend parameter set.

[0037] As a further aspect of the present invention, the distribution concentration threshold is set by statistically analyzing the ratio of the number of landing points to the span of the landing point segment, calculating the average ratio and fluctuation range, and combining the distinguishing features of densely populated landing point segments and discrete segments.

[0038] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0039] In this invention, the coordinates of the impact points are obtained by calculating the trajectory during the shooting process, and the radius distances between each impact point and the target center are sorted according to the horizontal and vertical components, providing accurate basic data for subsequent shooting trajectory analysis. Through trend analysis algorithms, groups with similar impact point change trends are divided, and the identification and prediction of trajectories are optimized by calculating the directional consistency parameters and amplitude stability parameters of these groups. Dynamic adjustment of the group feature sets improves the accuracy of impact point analysis, and the combination of calibration and continuation weights enhances the personalized feedback capability of shooting training, making it possible to accurately evaluate the training effects of multiple shooters. Furthermore, by sorting and filtering the impact point radius sequence, more refined target adjustments are made, avoiding deviations caused by uneven or unstable distribution of the shooting group, and improving the reliability and effectiveness of shooting feedback. This series of operations not only enhances the real-time performance and accuracy of the training process but also allows for rapid adjustments based on the actual performance of the shooters, improving the overall training effect. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of the steps of the present invention. Detailed Implementation

[0042] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0043] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0044] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0045] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0046] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0047] Please see Figure 1 This invention provides a method for processing image target shooting data for impact point prediction, comprising the following steps:

[0048] S1: Obtain the target landing point coordinates by calculating the trajectory during the shooting process and decompose them into horizontal and vertical components. Calculate the deviation distance between each shooting landing point and the target center and sort them to generate landing point deviation data.

[0049] S2: Based on the impact point deviation data, the impact points with similar changing trends are divided into data trajectory sets by the trend analysis algorithm. The consistency of impact point direction and amplitude stability of the data trajectory sets are calculated and summarized to generate a data trajectory set feature set.

[0050] S3: Based on the feature set of the data trajectory set, calculate the consistency deviation of the shooting point direction of multiple groups and filter out the groups that exceed the direction consistency threshold to assign calibration weights. Assign the group with the best amplitude stability the continuation weight and integrate it with the calibration weight to generate dynamic weight data.

[0051] S4: Based on the deviation distance, sort the landing points and filter the landing point segments whose adjacent radius distance difference does not reach the distance interval threshold. Calculate the distribution concentration by the ratio of the number of landing points in the segment to the span. Use dynamic weight data to judge the landing point change trend to obtain the cross-region trend parameter set. Combine the distribution concentration to construct the digital aiming point position adjustment command and the auxiliary aiming point display command, and generate the target display optimization control command set.

[0052] S5: Based on the target display optimization control instruction set, when the virtual aiming point displacement direction does not match the cross-regional trend parameter set, the virtual aiming point displacement direction is adjusted. When the distribution concentration parameter is close to the distribution concentration threshold, the virtual aiming point is adjusted a second time, generating an image target display adjustment optimization instruction set.

[0053] The landing point deviation data specifically includes radius distance, sorting sequence, and distance distribution interval. The data trajectory set feature set includes directional consistency parameters, amplitude stability parameters, and group division identifiers. The dynamic weight data specifically refers to calibration weight, continuity weight, and weight integration value. The target display optimization control instruction set includes digital aiming point position adjustment instructions, auxiliary aiming point display instructions, and cross-regional trend parameter set. The image target display adjustment optimization instruction set specifically includes correcting direction parameters, secondary offset direction, and updating display control parameters.

[0054] The specific steps of S1 are as follows:

[0055] S101: Based on the trajectory calculation results during the shooting process, extract the target impact point coordinate data in the image, calculate the horizontal coordinate component and the vertical coordinate component for each impact point coordinate, and store the data of multiple impact points in the same sequence to generate the impact point coordinate component sequence.

[0056] Based on the trajectory calculation results during the shooting process, the trajectory calculation uses a high-speed camera system to capture target images. These images are then transmitted to image processing, where the image analysis identifies the center position of the impact point and outputs coordinate data in pixels. The image resolution is set to 800 pixels wide and 600 pixels high, with the origin of the coordinate system located at the top left corner of the image. The positive directions are horizontal to the right and vertical to the bottom. The trajectory calculation module processes the video stream in real time, recording the impact point coordinates when an impact event is detected. The coordinate data is stored in an array format, and during extraction, array elements are read. Each element contains horizontal and vertical coordinate values. For example, in a shooting experiment, three impact points are generated. Image analysis is used to obtain the coordinates: impact point 1 has a horizontal coordinate of 100 pixels and a vertical coordinate of 150 pixels; impact point 2... The horizontal coordinate is 110 pixels and the vertical coordinate is 145 pixels. The horizontal coordinate of landing point 3 is 105 pixels and the vertical coordinate is 155 pixels. For each landing point coordinate, the horizontal coordinate component is calculated by directly taking the horizontal coordinate value, and the vertical coordinate component is calculated by directly taking the vertical coordinate value. Then the component pairs are stored in a sequence. The sequence adopts a list data structure. An empty list is initialized. Each landing point coordinate is traversed and a tuple containing the horizontal and vertical coordinate values ​​is added to the list. The landing point 1 tuple (100, 150) is added, the landing point 2 tuple (110, 145) is added, and the landing point 3 tuple (105, 155) is added. The landing point coordinate component sequence is generated as the list (100, 150), (110, 145), (105, 155).

[0057] S102: Call the sequence of landing point coordinate components, calculate the Euclidean distance between the horizontal and vertical coordinate components of each landing point and the target center coordinates in the Cartesian coordinate system, summarize the distances of multiple landing points, and generate a sequence of landing point radius distance values.

[0058] The system calls the sequence of impact point coordinate components (100, 150), (110, 145), (105, 155). The target center coordinates are preset to 100 pixels horizontally and 100 pixels vertically. Based on a Cartesian coordinate system, for each impact point, the difference between its horizontal coordinate component and the horizontal coordinate of the target center is calculated, and the difference between its vertical coordinate component and the vertical coordinate of the target center is calculated. The square of the difference is calculated, the two squared values ​​are added together, and the square root of the sum is taken to obtain the Euclidean distance. For impact point 1, the horizontal coordinate is 100, the horizontal coordinate of the target center is 100, and the difference is 0. The vertical coordinate is 150, the vertical coordinate of the target center is 100, and the difference is 50. The square of the difference of 0 is 0, the square of the difference of 50 is 2500, and the sum is 0 + 2500 = 2500, with a square root of 50. For impact point 2, the horizontal coordinate is 110, the horizontal coordinate of the target center is 100, and the difference is... For point 10, with a vertical coordinate of 145 and a target center vertical coordinate of 100, the difference is 45. The square of the difference 10 is 100, and the square of the difference 45 is 2025. The sum is 100 + 2025 = 2125, and the square root is 46.10 (approximate value). For point 3, with a horizontal coordinate of 105 and a target center horizontal coordinate of 100, the difference is 5. The vertical coordinate of 155 and the target center vertical coordinate of 100, the difference is 55. The square of the difference 5 is 25, and the square of the difference 55 is 3025. The sum is 25 + 3025 = 3050, and the square root is 55.22 (approximate value). Similarly, calculate the other coordinates 60.0 pixels, 58.0 pixels, and 56.0 pixels. Summarize the distances of multiple points to generate a sequence of point radius distance values ​​as a list [50, 46.10, 55.22, 60.0, 58.0, 56.0].

[0059] S103: Based on the sequence of landing radius distance values, sort all landing distance values ​​in ascending order, record the sorted values ​​in the same sequence, and generate landing deviation data;

[0060] Based on the landing radius distance value sequence list [50, 46.10, 55.22, 60.0, 58.0, 56.0], all landing distance values ​​are sorted in ascending order. The sorting process involves comparing the numerical values, traversing the sequence elements, comparing adjacent values, and swapping the positions if the previous value is greater than the next value. This process is repeated until the entire sequence is in ascending order. The initial sequence elements are 50, 46.10, 55.22, 60.0, 58.0, 56.0. The first value 50 is compared with the second value 46.10. Since 50 is greater than 46.10, their positions are swapped, and the sequence becomes 46.10, 50, 55.22. The second value 50 is compared with the third value 55.22. Since 50 is less than 55.22, they are not swapped. The other data positions are sorted in the same way, and the sorted values ​​are recorded in the same sequence, generating the landing deviation data as a list [46.10, 50, 55.22, 56.0, 58.0, 60.0].

[0061] The specific steps of S2 are as follows:

[0062] S201: Based on the static characteristics of the landing point distribution reflected by the landing point deviation data, a trend analysis algorithm is used to detect the rate of change and directional differences of multiple landing point values ​​in the original landing point coordinate data. The landing points are divided into multiple data trajectory sets according to the similarity of the change trends, and the data trajectory set division results are generated.

[0063] Based on the landing point deviation data, the sequence contains six landing point distance values: [46.10, 50, 55.22, 56.0, 58.0, 60.0]. First, the static distribution characteristics are analyzed, revealing an overall increasing trend with a slight decline at the end. Based on this distribution characteristic, as a grouping criterion, a trend analysis is then performed on the corresponding landing points in the original time-series coordinate data (from S101).A trend analysis algorithm is used to calculate the rate of change and difference between adjacent original landing point distance values. The execution process first calculates the rate of change of the distance between adjacent landing points, that is, calculates the difference between consecutive values ​​in the sequence. For indices i from 1 to 5, the rate of change ri = d - {i+1} - di, where di represents the i-th distance value in the sequence. Specifically, r-1 = 50 - 46.10 = 3.90, r-2 = 55.22 - 50 = 5.22, r-3 = 60.0 - 55.22 = 4.78, r-4 = 58.0 - 60.0 = -2.0, r-5 = 56.0 - 58. Given j = -2.0, the rate of change sequence is [3.90, 5.22, 4.78, -2.0, -2.0]. Next, the differences between the rates of change are calculated. Specifically, for j from 1 to 4, delta-r-1 = 5.22 - 3.90 = 1.32, delta-r-2 = 4.78 - 5.22 = -0.44, delta-r-3 = -2.0 - 4.78 = -6.78, delta-r-4 = -2.0 - -2.0 = 0, with a difference sequence of [1.32, -0.44, -6.78, 0.0]. r (rate of change difference) refers to the difference between two consecutive rates of change. r (rate of change) refers to the change in distance between two adjacent impact points. A threshold of 2.0 pixels is set for the rate of change difference. This threshold is based on the typical fluctuation range of the rate of change in actual shooting data. Statistical analysis of historical data shows that the rate of change difference is mostly between 0 and 5 pixels; therefore, the median value of 2.0 is used as the criterion to identify significant points of trend change. Next, the absolute value of the difference is checked to see if it exceeds the threshold. That is, for each delta-rj, |delta-rj| is checked to see if it is greater than 2.0. The results are: |1.32| is less than 2.0, no significant change; |-0.44| is less than 2.0, no significant change; |-6.78| is greater than 2.0, a significant change is detected (atj=3). 0| less than 2.0 indicates no significant change. Based on the detection results, the data trajectory set is divided. When |delta-rj| is greater than the threshold, it indicates a trend change. The new group starts from point index j+2. However, considering the point sequence, the group boundary is set as follows: points from the start point of the sequence to the first significant change point constitute one group, and subsequent consecutive points until the next significant change point or the end of the sequence constitute another group. Specifically, since |delta-r-3| is greater than 2.0 when j=3 and there is no significant change when j=4, group 1 contains points 1 to 4, corresponding to distance values ​​[46.10, 50, 55.22, 60.0], and group 2 contains points 5 to 6, corresponding to distance values ​​[58.0, 56.0]. The resulting data trajectory set is divided into two groups: group 1 index 1-4 and group 2 index 5-6.

[0064] S202: Call the data trajectory set division results, for the landing points in each group, calculate the directional consistency of the group based on the angle difference of the direction of change of the landing point coordinate position, and record the directional consistency of multiple groups in the same sequence to obtain the directional consistency sequence;

[0065] The data trajectory set is divided into two groups: Group 1 contains points 1 to 4, and Group 2 contains points 5 to 6. Each group corresponds to the landing point coordinates. The landing point coordinates are calculated based on the target center (100, 100) pixels and the distance value. The angle is set to 30 degrees for simplicity. For Group 1, point 1 is 46.10 pixels away, and its coordinates are calculated as: x = 100 + 46.10 × cos(30°) ≈ 100 + 46.10 × 0.866 ≈ 139.92, y = 100 + 46.10 × sin(30°) ≈ 100 + 46.10 × 0.5 ≈ 123.05. Point 2 is 50 pixels away, so x = 100 + 50 × 0.866 ≈ 143.30, y = 100 + 50 × 0.5 ≈ 1. 25.00, point 3 is 55.22 pixels away, x=100+55.22×0.866≈147.82, y=100+55.22×0.5≈127.61, point 4 is 60 pixels away, x=100+60×0.866≈151.96, y=100+60×0.5≈130.00, the coordinate sequence is (139.92, 123.05), (143.30, 125.00), (147.82, 127.61), (151.96, 130.00), for group 2, point 5 is 58 pixels away, x=100+58×0.866≈150.23, y=100+58×0.5≈129.00, point 6. Distance 56 pixels, x=100+56×0.866≈148.50, y=100+56×0.5≈128.00, coordinate sequence is (150.23, 129.00), (148.50, 128.00). For each group, the direction consistency is calculated based on the angle difference of the direction of change of the landing point coordinate position. First, the vector between consecutive landing points within the group is calculated. For group 1, vector v1 is point 2 minus point 1, i.e. (143.30-139.92, 125.00-123.05)=(3.38, 1.95), vector v2 is point 3 minus point 2, i.e. (147.82-143.30, 127.61-125.00)=(4.52). , 2.61), vector v3 is point 4 minus point 3, that is (151.96-147.82, 130.00-127.61)=(4.14, 2.39), then calculate the angle of each vector using the atan2 function, angle θ=atan2(y component, x component), θ1=atan2(1.95, 3.38)≈30.0°, θ2=atan2(2.61, 4.52)≈30.0°, θ3=atan2(2.39, 4.14)≈30.0°, then calculate the angle difference between consecutive vectors, that is Δθ1=|θ2-θ1|=|30.0-30.0|=0°, Δθ2=|θ3-θ2|=|30.0-30.0|.0|=0°, the angle difference sequence is [0,0]. The directional consistency is defined as the average angle difference, which is (0.0+0.0) / 2=0°. However, since consistency usually represents the degree of consistency, it can be calculated as 1 - the normalized value of the average angle difference. The average angle difference is directly used as the consistency index. The smaller the value, the higher the consistency. For group 2, there are only two points, and vector v4 is point 6 minus point 5, i.e., (148.50-150.23, 128.00-129.0). Given a vector θ₀ = (-1.73, -1.00), and angle θ₄ = atan²(-1.00, -1.73) ≈ 210.0° or -150.0°, since there is only one vector and no continuous vectors to compare, the angle difference cannot be calculated. The direction consistency is set to 0° (indicating no change or perfect consistency). However, for single-vector groups, the consistency can usually be set to a specific value; for simplification, it is set to 0°. The direction consistency of multiple groups is recorded in a sequence, resulting in a direction consistency sequence of [0, 0].

[0066] S203: Based on the directional consistency sequence and the amplitude of the numerical range of each group in the data trajectory set division results, calculate the stability rate of multiple groups in the amplitude range, and summarize the directional consistency and stability rate to establish a feature set of the data trajectory set;

[0067] Based on the directional consistency sequence [0, 0], and combined with the numerical range amplitude of each group in the data trajectory set partitioning results, the numerical range amplitude refers to the range of distance values ​​within the group. For group 1, the distance values ​​are [46.10, 50, 55.22, 60.0], with a minimum value of 46.10 and a maximum value of 60.0, resulting in an amplitude of 60.0 - 46.10 = 13.90 pixels. For group 2, the distance values ​​are [58.0, 56.0], with a minimum value of 56.0 and a maximum value of 58.0, resulting in an amplitude of 58.0 - 56.0 = 2.0 pixels. The stability of the multiple groups within the amplitude range is calculated. The stability rate is defined as the reciprocal of the amplitude, indicating that the smaller the amplitude, the higher the stability. It is calculated as stability rate = 1 / amplitude. For group 1, stability rate = 1 / 13.90 ≈ 0.0719, and for group 2, stability rate = 1 / 2.0 = 0.5. The stability rate sequence is [0.0719, 0.5]. Then, the directional consistency and stability rate are summarized. For each group, the directional consistency and stability rate are used as feature pairs. The feature pair for group 1 is (0, 0.0719), and the feature pair for group 2 is (0, 0.5). The feature set of the data trajectory set is established.

[0068] The specific steps for S3 are as follows:

[0069] S301: Based on the feature set of the data trajectory set, calculate the deviation between the orientation consistency of multiple groups and the group orientation reference value, compare the deviation with the set orientation consistency threshold, filter the groups that exceed the orientation consistency threshold and assign corresponding calibration weights, and generate a calibration weight distribution;

[0070] Based on the feature set of the data trajectory set, which contains feature data from two groups: Group 1 has a directional consistency of 0 and a stability rate of 0.0719, and Group 2 has a directional consistency of 0 and a stability rate of 0.5. The directional baseline value is set to 0 degrees, which is based on the assumption that the impact point direction is completely consistent under ideal shooting conditions. Through analysis of multiple historical shooting data, the directional consistency is mostly between 0 and 10 degrees. The minimum baseline value of 0 represents the best consistency. The deviation between the directional consistency of multiple groups and the baseline value is calculated, that is, the absolute value deviation of the directional consistency of each group is calculated. The deviation for Group 1 is |0.0 - 0.0| = 0 degrees, and the deviation for Group 2 is |0.0 - 0.0| = 0 degrees. The directional consistency threshold is set to 5.0 degrees. The threshold is determined by statistically analyzing the distribution of directional consistency in actual shooting data. Historical data shows that 95% of the groups have a directional consistency below 5.0 degrees. Therefore, 5.0 degrees is used as the threshold to distinguish whether calibration is required. The deviation is compared with the threshold to check whether the deviation of each group is greater than 5.0 degrees. Group 1 has a deviation of 0 degrees, which is less than 5.0 degrees and does not exceed the threshold. Group 2 has a deviation of 0 degrees, which is less than 5.0 degrees and does not exceed the threshold. Groups that exceed the threshold are filtered out. Currently, no group exceeds the threshold. The deviation of Group 2 is set to 6.0 degrees (example data). Then it exceeds the threshold and is assigned the corresponding calibration weight. The calibration weight is calculated based on the deviation. The weight formula is wc = deviation / 10.0, where 10.0 is the maximum allowable deviation reference value, which is set based on the actual data deviation range of 0-10 degrees. If the deviation of Group 2 is 6.0 degrees, then wc = 6.0 / 10.0 = 0.6. The calibration weight distribution is generated. For Group 1, the weight is 0 (actual deviation 0.0), and for Group 2, the weight is 0.6 (set deviation 6.0). The distribution is a list [0.0, 0.6].

[0071] Table 1 Group Direction Consistency Data Table

[0072]

[0073] As shown in Table 1, group orientation consistency data is used to generate calibration weight distribution.

[0074] S302: Call the calibration weight distribution, compare the amplitude stability of the feature set of the data trajectory set, select the group with the best stability and set the continuation weight, store the group number and the continuation weight value to obtain the continuation weight record;

[0075] The calibration weight distribution [0, 0.6] is called to compare the amplitude stability rates of the feature sets of the data trajectory set. The stability rate of group 1 in the feature set is 0.0719, and the stability rate of group 2 is 0.5. The higher the stability rate, the smaller and more stable the group amplitude. The group with the best stability is selected, that is, the group with the largest stability rate. Comparing 0.0719 and 0.5, 0.5 is greater than 0.0719. Therefore, group 2 has the best stability. The continuation weight is set. The continuation weight is calculated based on the stability rate. The weight formula is we = stability rate. Since the stability rate is in the range of 0-1 (the stability rate is 1.0 when the amplitude is 1 pixel, and the larger the amplitude, the closer it is to 0), it is directly used as the weight. The stability rate of group 2 is 0.5, so we = 0.5. The group number is stored in correspondence with the continuation weight value. The continuation weight of group 1 is 0.0719, and the continuation weight of group 2 is 0.5. The continuation weight records are obtained as a dictionary {1: 0.0719, 2: 0.5}.

[0076] S303: Based on the calibration weight distribution and continuation weight records, numerical integration is performed under the same group number, and the calibration weight and continuation weight are weighted and synthesized to generate dynamic weight data;

[0077] The directional consistency threshold is set by evaluating the consistency of the landing directions of multiple groups;

[0078] Based on the calibration weight distribution [0, 0.6] and the continuation weight record {1: 0.0719, 2: 0.5}, numerical integration is performed under the same group number. For group 1, the calibration weight is 0 and the continuation weight is 0.0719. For group 2, the calibration weight is 0.6 and the continuation weight is 0.5. The calibration weight and the continuation weight are weighted and synthesized. The weighting formula uses a simple average, that is, dynamic weight = (calibration weight + continuation weight) / 2. For group 1, dynamic weight = (0 + 0.0719) / 2 = 0.03595. For group 2, dynamic weight = (0.6 + 0.5) / 2 = 0.55. The dynamic weight data is generated as a list [0.03595, 0.55].

[0079] The specific steps of S4 are as follows:

[0080] S401: Based on the deviation distance, sort the landing point radius distances, filter the landing point segments where the radius difference between adjacent landing points does not reach the distance interval threshold, then count the number of landing points in the filtered segments and measure the segment span, calculate the span ratio by comparing the number of landing points with the span value, and generate the distribution concentration.

[0081] Based on the deviation distance, the sequence contains six impact radius distance values, [50, 46.10, 55.22, 60.0, 58.0, 56.0], used to simulate impact point data from multiple shots. The execution process first sorts the deviation distances in ascending order, resulting in the sequence [46.10, 50.0, 55.22, 56.0, 58.0, 60.0]. Then, the radius difference between adjacent impact points is calculated; that is, for indices i from 1 to 5, the difference di is calculated as the difference between the (i+1)th and ith values ​​in the sequence. The values ​​are calculated as follows: d-1 = 50.0 - 46.10 = 3.90, d-2 = 55.22 - 50.0 = 5.22, d-3 = 56.0 - 55.22 = 0.78, d-4 = 58.0 - 56.0 = 2.0, d-5 = 60.0 - 58.0 = 2.0. The difference sequence is [3.90, 5.22, 0.78, 2.0, 2.0]. The distance interval threshold is set statistically based on the difference sequence, and the average value of the difference sequence is calculated. The average value is (3.90 + 5.22 + ... (0.78 + 2.0 + 2.0) / 5 = 13.9 / 5 = 2.78 pixels. Based on actual shooting data, the difference is mostly between 0 and 5 pixels. The median value of 2.0 pixels is taken as the threshold to identify dense sections and filter sections where the radius difference between adjacent impact points does not reach the distance interval threshold. That is, it checks whether each difference is less than 2.0 pixels. In the difference sequence, 0.78 is less than 2.0, and 2.0 = 2.0 is not considered not reaching the threshold (strictly less than is set). Therefore, only the difference of 0.78 corresponds to the distance between points 3 and 4. The segment contains points 3 and 4, with corresponding distance values ​​of 55.22 and 56.0. The number of landing points in the segment is 2. The segment span is measured, which is the difference between the maximum and minimum distance values ​​within the segment. The maximum value is 56.0 and the minimum value is 55.22. The span value is 56.0 - 55.22 = 0.78 pixels. The span ratio is calculated by dividing the number of landing points by the span value, i.e., 2 / 0.78 ≈ 2.564. The distribution concentration is generated as 2.564 (the concentration is set to the span ratio value).

[0082] Table 2. Difference in Radius Between Adjacent Landing Points

[0083]

[0084] As shown in Table 2, the difference in radius between adjacent landing points is used to set thresholds and filter segments.

[0085] S402: Call the distribution concentration, based on the changes in the weight values ​​of multiple group landing points in the dynamic weight data, detect the increasing or decreasing trend of weight with the sequence, calculate the continuous change direction and summarize it into a trend parameter set, and obtain the cross-regional trend parameter set;

[0086] The distribution concentration is 2.564. Based on the dynamic weight data (from step S303), the dynamic weight sequence is set to correspond to the landing point sequence. The landing point sequence has six points. Based on the previous group division, group 1 contains points 1 to 4 with a weight of 0.03595, and group 2 contains points 5 to 6 with a weight of 0.55. Therefore, the weight sequence is [0.03595, 0.03595, 0.03595, 0.03595, 0.55, 0.55]. The trend of weight increase or decrease with the sequence is detected, i.e., the weight change between consecutive landing points is calculated. For index j from 1 to 5, the change value cj = the (j+1)th value in the weight sequence - the jth value, calculated as c-1 = 0.03595 - 0.03595 = 0.0, c-2 = 0.03595 - 0.0. 3595=0.0, c-3=0.03595-0.03595=0.0, c-4=0.55-0.03595=0.51405, c-5=0.55-0.55=0, the change sequence is [0, 0, 0, 0.51405, 0]. Calculate the continuous change direction, that is, for each change value, determine the sign: positive indicates increase, negative indicates decrease, 0 indicates no change. The direction sequence is [no change, no change, no change, increase, no change]. Summarize this into a trend parameter set, which includes the change point location (index 4 where the change occurs), change magnitude (0.51405), and change direction (increase). The resulting cross-region trend parameter set is in dictionary form: {change point: 4, magnitude: 0.51405, direction: increase}.

[0087] S403: Based on the distribution concentration and cross-regional trend parameter set, the target offset direction is combined under the coordinate reference system to construct and integrate the digital aiming point position adjustment command and the auxiliary aiming point display command to generate the target display optimization control command set.

[0088] The distance interval threshold is set by statistically analyzing the difference between adjacent values ​​of the landing point deviation distance;

[0089] Based on the distribution concentration of 2.564 and the cross-regional trend parameter set {change points: 4, amplitude: 0.51405, direction: increasing}, the offset direction of the landing point is combined under the coordinate reference system. The target center of the coordinate reference system is set to (100, 100) pixels. The landing point coordinates are calculated based on distance and angle. The angle is set to 30 degrees for simplification. Point 1 is 46.10 pixels away, with coordinates (100 + 46.10 × cos(30°) ≈ 139.92, 100 + 46.10 × sin(30°) ≈ 123.05). Point 2 is 50.0 pixels away, with coordinates... The target is marked (143.30, 125.00), point 3 is 55.22 pixels away, coordinates (147.82, 127.61), point 4 is 56.0 pixels away, coordinates (148.50, 128.00), point 5 is 58.0 pixels away, coordinates (150.23, 129.00), point 6 is 60.0 pixels away, coordinates (151.96, 130.00), the offset direction is calculated by the vector angle between the point and the target center, angle θ = atan2(y-100, x-100), the angle of point 1 is atan2(23.05, 3). 9.92)≈30.0°, Point 2 angle≈30.0°, Point 3 angle≈30.0°, Point 4 angle≈30.0°, Point 5 angle≈30.0°, Point 6 angle≈30.0° (set consistently). Combining trend parameters, the change point is at index 4, the direction increases, and a digital aiming point position adjustment command is constructed. The command is based on distribution concentration and trend amplitude. The displacement is calculated as trend amplitude multiplied by concentration: 0.51405×2.564≈1.318. The direction is along an angle of 30°. The digital aiming point position adjustment command is (displacement: 1.318 pixels, square...). To construct an auxiliary aiming point display command, the command is based on the position of the changing point. The auxiliary point is set at coordinates (148.50, 128.00) of point 4, with a size of 10 pixels and a color of red. The auxiliary aiming point display command is: coordinates (148.50, 128.00), size: 10, color: red. The virtual aiming point displacement direction parameter of 30 degrees and displacement amount parameter of 1.318 pixels are integrated to generate a target display optimization control command set [digital aiming point position adjustment command, auxiliary aiming point display command].

[0090] The specific steps of S5 are as follows:

[0091] S501: Based on the target display optimization control instruction set, the virtual aiming point displacement direction is compared with the direction parameters in the cross-regional trend parameter set. The angle difference between the two is detected to see if it exceeds the direction consistency threshold. The virtual aiming point displacement direction is corrected in combination with the cross-regional trend parameter set, and the direction correction angle is generated.

[0092] Based on the target display optimization control instruction set, [digital aiming point position adjustment instruction, auxiliary aiming point display instruction], the instruction set includes a virtual aiming point displacement direction parameter of 30 degrees and a displacement amount parameter of 1.318 pixels, as well as a cross-area trend parameter set. This parameter set includes a direction parameter of 36 degrees, which is obtained by calculating the average angle of two landing points near the trend change point. Specifically, it is the average of the angles of point 4 (30 degrees) and point 5 (40 degrees), which is 35 degrees, adjusted to 36 degrees. The direction consistency threshold is set to 5 degrees, and this threshold is determined by analyzing angles. The difference data is determined, including values ​​of 2 degrees, 3 degrees, 4 degrees, 5 degrees, and 6 degrees. The average value of these values ​​is 4 degrees, and the standard deviation is approximately 1.5 degrees. Therefore, 5 degrees is selected as the threshold. The angle difference between the virtual aiming point displacement direction of 30 degrees and the direction parameter of 36 degrees is detected, and the absolute difference is calculated to be 6 degrees. 6 degrees is compared with the threshold of 5 degrees. Since 6 degrees is greater than 5 degrees, it exceeds the threshold. Combined with the cross-regional trend parameter set, the virtual aiming point displacement direction is corrected by 1.318 pixels, which is corrected to the direction parameter angle of 36 degrees, generating a direction correction angle of 36 degrees.

[0093] S502: Call the direction correction angle. When the distribution concentration parameter is close to the distribution concentration threshold, the virtual aiming point is adjusted a second time according to the corrected displacement direction. During the adjustment process, the offset correction coefficient is superimposed and the current offset direction is calculated to obtain the secondary offset direction.

[0094] The direction correction angle is set to 36 degrees, and the distribution concentration parameter is set to 2.1. This value comes from the adjustment example in the previous steps. The distribution concentration threshold is set to 2.0. This threshold is obtained by calculating the average value of the concentration data 1.5, 2.0, 2.5, and 3.0, which is 2.25 and rounded down. The distribution concentration of 2.1 is checked to see if it is close to the threshold of 2.0. Close is defined as the absolute value of the difference being less than 0.5. The difference is calculated to be 0.1. Since 0.1 is less than 0.5, it is close to the threshold. The virtual aiming point is adjusted a second time according to the corrected displacement direction of 36 degrees. During the adjustment process, an offset correction coefficient of 0.1 is superimposed. This coefficient is a typical value selected based on experience in the range of 0.05 to 0.2. The current offset direction is calculated using addition. Current offset direction = 36 degrees + 0.1 × 36 degrees = 36 degrees + 3.6 degrees = 39.6 degrees, resulting in the secondary offset direction of 39.6 degrees.

[0095] S503: Based on the secondary offset direction and the corrected aiming point displacement, recombine the offset vector in the coordinate system and update the display control parameters to generate an image target display adjustment and optimization instruction set;

[0096] The directional consistency threshold is set by statistically calculating the angle difference between the displacement direction of the virtual aiming point and the directional parameters in the cross-regional trend parameter set.

[0097] Based on the secondary offset direction of 39.6 degrees and the corrected aiming point displacement of 1.318 pixels, the offset vector is recombined in the coordinate reference system. The horizontal component of the offset vector is calculated using a cosine function; the cosine value of 39.6 degrees is approximately 0.771. Multiplying this by the displacement of 1.318 yields a horizontal component of approximately 1.016 pixels. The vertical component of the offset vector is then calculated using a sine function; the sine value of 39.6 degrees is approximately 0.637. Multiplying this by the displacement of 1.318 yields a vertical component of approximately 0.840 pixels. The vector is water. The horizontal and vertical coordinates are adjusted by 1.016 pixels and 0.840 pixels respectively. The display control parameters are updated. The new position of the virtual aiming point is based on the original position with a horizontal coordinate of 100 pixels and a vertical coordinate offset of 100 pixels. The new horizontal coordinate is 100 + 1.016 = 101.016 and the new vertical coordinate is 100 + 0.840 = 100.840. The display parameters include a size of 10 pixels and a color of red. The generated image target display adjustment and optimization instruction set is a list containing the new coordinates 101.016 and 100.840, a size of 10, and a color of red.

[0098] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for processing image target shooting data for impact point prediction, characterized in that, Includes the following steps: S1: Obtain the target landing point coordinates by calculating the trajectory during the shooting process and decompose them into horizontal and vertical components. Calculate the deviation distance between each shooting landing point and the target center and sort them to generate landing point deviation data. S2: Based on the impact point deviation data, impact points with similar trends in impact point change are divided into data trajectory sets using a trend analysis algorithm. The consistency of impact point direction and amplitude stability of the data trajectory sets are calculated and summarized to generate a data trajectory set feature set. The specific steps of S2 are as follows: S201: Based on the static characteristics of the landing point distribution reflected by the landing point deviation data, a trend analysis algorithm is used to detect the rate of change and directional differences of multiple landing point values ​​in the original landing point coordinate data. The landing points are divided into multiple data trajectory sets according to the similarity of the change trends, and a data trajectory set division result is generated. This includes: using a trend analysis algorithm to calculate the rate of change and the difference between the distance values ​​of adjacent original landing points, setting a threshold for the difference in the rate of change, detecting whether the absolute value of the difference exceeds the threshold, and dividing the data trajectory set according to the detection result. S202: Call the data trajectory set division result, for the landing point in each group, calculate the directional consistency of the group based on the angle difference of the direction of change of the landing point coordinate position, and record the directional consistency of multiple groups in the same sequence to obtain the directional consistency sequence; S203: Based on the directional consistency sequence, combined with the numerical range of each group in the data trajectory set division result, calculate the stability rate of multiple groups in the amplitude range, and summarize the directional consistency and stability rate accordingly to establish a data trajectory set feature set; S3: Based on the data trajectory set feature set, calculate the consistency deviation of the shooting point direction of multiple groups and filter out the groups that exceed the direction consistency threshold to assign calibration weights. Assign the group with the best amplitude stability a continuation weight and integrate it with the calibration weights to generate dynamic weight data. S4: Based on the aforementioned deviation distance, sort the landing points and filter the landing point segments whose adjacent radius distance difference does not reach the distance interval threshold. Calculate the distribution concentration by the ratio of the number of landing points in the segment to the span. Use the dynamic weight data to determine the landing point change trend to obtain the cross-region trend parameter set. Combine the distribution concentration to construct digital aiming point position adjustment instructions and auxiliary aiming point display instructions, generating a target display optimization control instruction set. The specific steps of S4 are as follows: S401: Based on the deviation distance, sort the landing point radius distances, filter the landing point segments where the radius difference between adjacent landing points does not reach the distance interval threshold, count the number of landing points in the filtered segments and measure the segment span, calculate the span ratio by the number of landing points and the span value, and generate the distribution concentration. S402: Call the distribution concentration, and based on the changes in the weight values ​​of multiple group landing points in the dynamic weight data, detect the increasing or decreasing trend of weight changes with the sequence, calculate the direction of continuous change, and summarize it into a trend parameter set; S403: Based on the distribution concentration and the cross-regional trend parameter set, combine the landing point offset direction in the coordinate reference system, construct digital aiming point position adjustment instructions and auxiliary aiming point display instructions respectively, and integrate them to generate a target display optimization control instruction set; The distance interval threshold is set by statistically analyzing the difference between adjacent values ​​of the landing point deviation distance.

2. The image target shooting data processing method for impact point prediction according to claim 1, characterized in that, The landing point deviation data specifically includes radius distance, sorting sequence, and distance distribution interval. The data trajectory set feature set includes direction consistency parameters, amplitude stability parameters, and group division identifiers. The dynamic weight data specifically refers to calibration weight, continuity weight, and weight integration value. The target display optimization control instruction set includes digital aiming point position adjustment instructions, auxiliary aiming point display instructions, and cross-regional trend parameter set.

3. The image target shooting data processing method for impact point prediction according to claim 1, characterized in that, The specific steps of S1 are as follows: S101: Based on the trajectory calculation results during the shooting process, extract the target impact point coordinate data in the image, calculate the horizontal coordinate component and the vertical coordinate component for each impact point coordinate, and store the data of multiple impact points in the same sequence to generate the impact point coordinate component sequence. S102: Call the sequence of landing point coordinate components, calculate the Euclidean distance between the horizontal and vertical coordinate components of each landing point and the target center coordinates in the Cartesian coordinate system, summarize the distances of multiple landing points, and generate a sequence of landing point radius distance values. S103: Based on the sequence of landing radius distance values, sort all landing distance values ​​in ascending order, record the sorted values ​​in the same sequence, and generate landing deviation data.

4. The image target shooting data processing method for impact point prediction according to claim 1, characterized in that, The specific steps for S3 are as follows: S301: Based on the feature set of the data trajectory set, calculate the deviation between the directional consistency of multiple groups and the group directional reference value, compare the deviation with the set directional consistency threshold, filter out groups that exceed the directional consistency threshold and assign corresponding calibration weights, and generate a calibration weight distribution; S302: Call the calibration weight distribution, compare the amplitude stability of the feature set of the data trajectory set, filter the group with the best stability and set the continuation weight, store the group number and the continuation weight value to obtain the continuation weight record; S303: Based on the calibration weight distribution and continuation weight record, perform numerical integration under the same group number, and weight the calibration weight and continuation weight to generate dynamic weight data; The directional consistency threshold is set by evaluating the consistency of the landing directions of multiple groups.

5. The image target shooting data processing method for impact point prediction according to claim 4, characterized in that, The group direction reference value is obtained by statistically analyzing the direction data of all trajectory landing points within the same group, collecting the direction angle values ​​of multiple landing points within the group, summing the direction angles and dividing by the number of landing points to generate an average direction angle as the reference value.

6. The image target shooting data processing method for impact point prediction according to claim 1, characterized in that, The method further includes: S5: Based on the target display optimization control instruction set, when the virtual aiming point displacement direction does not match the cross-regional trend parameter set, adjust the virtual aiming point displacement direction; when the distribution concentration parameter is close to the distribution concentration threshold, perform a secondary adjustment of the virtual aiming point, and generate an image target display adjustment optimization instruction set. The image target display adjustment and optimization instruction set specifically includes correcting direction parameters, secondary offset direction, and updating display control parameters.

7. The image target shooting data processing method for impact point prediction according to claim 6, characterized in that, The specific steps of S5 are as follows: S501: Based on the target display optimization control instruction set, compare the virtual aiming point displacement direction with the direction parameters in the cross-regional trend parameter set, detect whether the angle difference between the two exceeds the direction consistency threshold, and combine the cross-regional trend parameter set to correct the virtual aiming point displacement direction and generate a direction correction angle. S502: Call the direction correction angle. When the distribution concentration parameter is close to the distribution concentration threshold, adjust the virtual aiming point a second time according to the corrected displacement direction. During the adjustment process, the offset correction coefficient is superimposed and the secondary offset direction is calculated. S503: Based on the secondary offset direction and the corrected aiming point displacement, recombine the offset vector in the coordinate system and update the display control parameters to generate an image target display adjustment and optimization instruction set; The directional consistency threshold is set by statistically calculating the angle difference between the displacement direction of the virtual aiming point and the directional parameters in the cross-regional trend parameter set.

8. The image target shooting data processing method for impact point prediction according to claim 7, characterized in that, The distribution concentration threshold is set by statistically analyzing the ratio of the number of landing points to the span of the landing point segment, calculating the average ratio and fluctuation range, and combining the distinguishing features of densely populated and discrete landing point segments.

Images