A method, device, equipment and storage medium for detecting artillery shell flight information

Abstract

The present invention discloses a method, device, equipment and storage medium for detecting artillery shell flight information. The method comprises the following steps: obtaining flight image information of an artillery shell within a safe distance; tracking the motion of the artillery shell in the flight image information to obtain discrete trajectory points of the artillery shell; generating an artillery shell flight trajectory based on the discrete trajectory points of the artillery shell; determining the muzzle initial velocity of the artillery shell based on the artillery shell flight trajectory, thereby achieving accurate and timely acquisition of artillery shell flight information, and reproducing the artillery shell flight information to researchers or observers, thereby providing a reliable basis for subsequent evaluation of artillery performance.

Description

Technical Field

[0001] The invention relates to the technical field of shooting range measurement and control, and in particular to a method, device, equipment and storage medium for detecting artillery shell flight information. Background Art

[0002] The measurement of flight information such as the initial velocity and flight trajectory of artillery shells is one of the most basic range tests for artillery, and is also one of the basic parameters that characterize artillery performance. Therefore, how to accurately and timely reproduce the flight trajectory, muzzle velocity and other flight information of artillery shells flying rapidly on a wide range to researchers or observers has become an urgent problem to be solved in the production process of enterprises. Summary of the invention

[0003] The object of the present invention is to provide a method, device, equipment and storage medium for detecting artillery shell flight information, so as to obtain artillery shell flight information accurately and timely.

[0004] To achieve the above object, the present invention provides a method for detecting shell flight information, comprising:

[0005] Obtain flight image information of artillery shells within a safe distance;

[0006] Tracking the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile;

[0007] Generating a cannonball flight trajectory based on the discrete trajectory points of the cannonball;

[0008] Based on the projectile flight trajectory, the muzzle velocity of the projectile is determined.

[0009] Furthermore, in the above-mentioned method for detecting the artillery shell flight information, the motion tracking of the artillery shell in the flight image information is performed to obtain the discrete trajectory points of the artillery shell, including:

[0010] After obtaining the position of the shell in the initial frame image of the flight image information, the positions of other frame images of the flight image information are obtained according to the following steps:

[0011] (10) Taking the position of the shell in the previous frame image as the initial center position of the shell in the current frame image, taking half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth, determining the target area, and calculating the multi-feature histogram distribution probability of the target area;

[0012] (20) calculating a weight value of the target area according to the multi-feature histogram distribution probability;

[0013] (30) calculating the predicted center position of the shell in the current frame image according to the weight value of the target area;

[0014] (40) calculating the distance between the predicted center position of the shell in the current frame image and the initial center position of the shell in the current frame image according to a preset estimation coefficient;

[0015] (50) if the distance is less than a preset threshold, determining the predicted center position of the shell in the current frame image as the target center position of the shell in the current frame image, and taking the target center position of the shell in the current frame image as a discrete trajectory point of the shell;

[0016] (60) If the distance is less than a preset threshold, after adjusting the initial center position of the shell in the current frame image, return to step (10) and use half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth to determine the target area and calculate the multi-feature histogram distribution probability of the target area.

[0017] Furthermore, in the above-mentioned method for detecting artillery flight information, calculating the multi-feature histogram distribution probability of the target area includes:

[0018] Calculate the multi-feature histogram distribution probability of the target area based on the preset multi-feature histogram distribution probability calculation formula;

[0019] The multi-feature histogram distribution probability calculation formula is:

[0020]

[0021] Among them, q m (y j ) represents the multi-feature histogram distribution probability of the target area, C represents the normalization constant, k represents the kernel function, y j represents the initial center position of the shell in the current frame image, h represents the search window bandwidth, and x i represents the multi-feature histogram distribution probability of the current frame image, b1(x i ) The characteristic value of the color space of the current frame image, b2(x i ) represents the eigenvalue in the grayscale gradient direction, and u represents the feature grouping of the current frame image.

[0022] Furthermore, in the above-mentioned method for detecting artillery flight information, the weight value of the target area is calculated according to the multi-feature histogram distribution probability, including:

[0023] Substituting the multi-feature histogram distribution probability into a preset weight calculation formula to obtain a weight value of the target area;

[0024] The weight calculation formula is:

[0025]

[0026] Among them, wi Indicates the weight value of the target area.

[0027] Furthermore, in the above-mentioned method for detecting the flight information of the artillery shell, the predicted center position of the artillery shell in the current frame image is calculated according to the weight value of the target area, including:

[0028] Substituting the weight value of the target area into a preset position prediction calculation formula to obtain the predicted center position of the shell in the current frame image;

[0029] The position prediction calculation formula is:

[0030]

[0031] in, Indicates the predicted center position of the shell in the current frame image.

[0032] Furthermore, in the above-mentioned method for detecting the artillery shell flight information, generating the artillery shell flight trajectory based on the discrete trajectory points of the artillery shell includes:

[0033] Constructing a flight trajectory fitting model according to the coordinates of each discrete trajectory point of the shell;

[0034] The flight trajectory fitting model is solved to obtain the projectile flight trajectory.

[0035] Furthermore, in the above-mentioned method for detecting the flight information of the artillery shell, determining the muzzle velocity of the artillery shell based on the flight trajectory of the artillery shell includes:

[0036] Arbitrarily select a first position of the shell in the image at the first moment and a second position of the shell in the image at the second moment;

[0037] Determine a scale between a unit length and a pixel on an image according to the first position of the shell and the second position of the shell;

[0038] Calculating the flight time of the shell between the first position of the shell and the second position of the shell according to the frame difference between the first position of the shell and the second position of the shell;

[0039] Based on the projectile flight trajectory, determining the number of pixels between the first position of the projectile and the second position of the projectile;

[0040] Calculate an average speed of a projectile between a first position of the projectile and a second position of the projectile according to the scale, the flight time, and the number of pixels;

[0041] The average velocity is taken as the muzzle velocity of the projectile.

[0042] The present invention also provides a device for detecting shell flight information, comprising:

[0043] An acquisition module is used to acquire flight image information of the shell within a safe distance;

[0044] A tracking module, used for tracking the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile;

[0045] A trajectory generation module, used to generate a projectile flight trajectory based on the discrete trajectory points of the projectile;

[0046] The velocity detection module is used to determine the muzzle velocity of the projectile based on the projectile flight trajectory.

[0047] The present invention also provides a device for detecting artillery shell flight information, including a memory and a processor;

[0048] The memory stores a computer program, and when the computer program is executed by the processor, the steps of the method for detecting the flight information of a shell as described in any one of the above items are implemented.

[0049] The present invention also provides a storage medium, wherein the storage medium stores one or more programs, and the one or more programs can be executed to implement the method for detecting the flight information of a shell as described in any one of the above items.

[0050] The method of the present invention has the following advantages:

[0051] By acquiring flight image information of a shell within a safe distance; tracking the motion of the shell in the flight image information to obtain discrete trajectory points of the shell; generating a shell flight trajectory based on the discrete trajectory points of the shell; and determining the muzzle velocity of the shell based on the shell flight trajectory, accurate and timely acquisition of shell flight information is achieved, and the shell flight information is reproduced to researchers or observers, providing a reliable basis for subsequent evaluation of artillery performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 The figure is a flow chart of an embodiment of a method for detecting artillery shell flight information of the present invention.

[0053] Figure 2 It is a schematic structural diagram of an embodiment of a device for detecting artillery shell flight information of the present invention.

[0054] Figure 3 It is a structural diagram of the image acquisition device.

[0055] Figure 4 for Figure 3 Exploded diagram.

[0056] Figure 5 It is a schematic diagram of the structure of a network transmission device embodiment of the present invention.

[0057] Figure 6 for Figure 5 Exploded diagram. DETAILED DESCRIPTION

[0058] The technical scheme of the present invention will be clearly and completely described below in conjunction with specific embodiments, but those skilled in the art should understand that the embodiments described below are only used to illustrate the present invention and should not be regarded as limiting the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] The preferred embodiments of the present invention will be described in detail below in conjunction with examples. It should be understood that the following examples are provided only for the purpose of illustration and are not intended to limit the scope of protection of the present invention. Those skilled in the art may make various modifications and substitutions to the present invention without departing from the purpose and spirit of the present invention, and all of these modifications and substitutions fall within the scope of the claims of the present invention.

[0060] The experimental methods used in the following examples are conventional methods unless otherwise specified. The materials, reagents, etc. used in the following examples are commercially available unless otherwise specified.

[0061] Example 1

[0062] Figure 1 FIG. 1 is a flow chart of an embodiment of a method for detecting shell flight information of the present invention, as shown in FIG. Figure 1 As shown, the method for detecting the artillery shell flight information of this embodiment may specifically include the following steps:

[0063] 100. Obtain flight image information of the shell within a safe distance;

[0064] In a specific implementation process, an image acquisition device may be used to acquire flight image information of a screen shell within a safe distance.

[0065] Specifically, a preset algorithm can be used to analyze the muzzle video of the image acquisition device in real time. When it is detected that a shell is fired from the muzzle, the flight image information of the shell within a safe distance can be obtained by triggering.

[0066] In a specific implementation process, the muzzle video of the image acquisition device can be analyzed in real time by one or more of the following algorithms:

[0067] The first is an image background difference algorithm. The process of analyzing the muzzle video of the image acquisition device based on this algorithm may include the following steps:

[0068] (1) Analyze the muzzle video collected by the image acquisition device to obtain the background image and foreground image corresponding to the muzzle video;

[0069] In a specific implementation process, the grayscale value of each pixel in each frame of the muzzle video can be obtained; pixels with grayscale values ​​of specified values ​​are determined as background pixels, and a background image is generated; pixels with grayscale values ​​not of the specified values ​​are determined as foreground pixels, and a foreground image is generated.

[0070] Specifically, since the pixel change frequency of the shell is faster than that of the background, this is used as the main feature to determine the state of the pixel - foreground (shell) and background. This feature includes two levels: pixel level and frame level.

[0071] Set the input image resolution to M*N, detect at the pixel level, distinguish foreground objects from backgrounds, and adaptively update pixels that meet the conditions to backgrounds. Define the pixel state matrix Dk(M,N), record the pixel states in the k-th frame image, 0 indicates that the pixel state is a background pixel, non-zero indicates that the pixel state is a foreground pixel, as shown in equations (1) and (2):

[0072]

[0073]

[0074] Among them, I c (a, b) is the color value of pixel (a, b) in the cth frame of the input image, F c (a, b) is a binary matrix indicating whether the color value of pixel (a, b) changes from the c-ε frame to the c-th frame; T f is the preset grayscale value, which can be set to 80; ε is the number of frames for the color value of the pixel to process the change state.

[0075] (2) subtracting the grayscale value of the foreground image from the grayscale value of the background image to obtain the grayscale value of the difference image;

[0076] In a specific implementation process, the grayscale value of the foreground image is subtracted from the grayscale value of the background image to obtain the grayscale value of the difference image.

[0077] (3) Detect whether the grayscale value of the difference image is greater than a preset grayscale value; if so, execute step (4); if not, execute step (5);

[0078] (4) Determine the firing of the shells;

[0079] If the grayscale value of the difference image is greater than the preset grayscale value, it is determined to fire the shell.

[0080] (5) Ensure that no shells have been fired.

[0081] If the grayscale value of the difference image is less than or equal to the preset grayscale value, it is determined that the shell has not been fired.

[0082] The second is a phenomenon area detection algorithm. The process of analyzing the muzzle video of the image acquisition device based on this algorithm may include the following steps:

[0083] (11) analyzing the image information of the shell in the target area acquired by the image acquisition device to obtain a background image and a foreground image corresponding to the image information;

[0084] (12) Subtracting the grayscale value of the foreground image from the grayscale value of the background image to obtain a grayscale value of a difference image;

[0085] (13) If the grayscale value of the difference image is greater than a preset grayscale value, the image information is segmented to obtain a segmented area of ​​the explosion characteristic in the foreground image;

[0086] When firing artillery shells, if only relying on color or shape changes, the explosion may not be effectively identified. When firing artillery shells, in addition to the flames, smoke will also be generated, so the smoke feature method can also be used to improve the recognition of the explosion image. The shape characteristics of the flames in the image are shown as rapid changes in a short period of time, while the smoke can be shown as long-term, large-area and accompanied by diffusion. Therefore, according to the uncertainty of the smoke, after the background image of the current image is collected, the background difference method is used to detect the target area in the digital image. When the image of the target area is detected, the Ostu algorithm is used to segment the image, and appropriate thresholds are selected for the smoke and area. When the smoke area is greater than the threshold, it is considered that smoke is generated, that is, the explosion is identified, otherwise it is considered as no explosion. The Ostu algorithm uses the clustering idea to divide the grayscale of the image into two parts according to the grayscale level, so that the grayscale value difference between the two parts is the largest and the grayscale difference between each part is the smallest. A suitable grayscale level is found for division by calculating the variance.

[0087] (14) Detect whether the segmented area of ​​the explosion feature in the foreground image is larger than a preset area; if so, execute step (15); if not, execute step (16);

[0088] (15) Determine the firing of the shells;

[0089] If the segmented area of ​​the explosion characteristic is larger than a preset area, it is determined to fire the shell.

[0090] (16) Ensure that no shells have been fired.

[0091] If the segmented area of ​​the explosion characteristic is less than or equal to the preset area, it is determined that the shell has not been fired.

[0092] The third fire light characteristic recognition algorithm is based on which the process of analyzing the muzzle video of the image acquisition device may include the following steps:

[0093] (23) obtaining a grayscale change value of a specified point in the image information at a preset time interval;

[0094] (24) determining the fire light change rate of the designated point according to the grayscale change value and the preset time interval;

[0095] (25), detecting whether the fire light change rate is equal to a preset change rate, if so, executing step (26), if not, executing step (27);

[0096] (26) Determine the firing of the shells;

[0097] If the fire light change rate is greater than or less than the preset change rate, it is determined to fire the shell.

[0098] (27) Confirm that no shells were fired.

[0099] If the fire light change rate is equal to the preset change rate, it is determined that no shell has been fired.

[0100] In a specific implementation process, the above three methods for obtaining the explosion state information of the shells in the target area can be used separately or in combination. When the three methods are used in combination, corresponding weight values ​​can be set for different methods, and then the weights are summed according to the weight values ​​of the three methods to determine whether to fire the shells.

[0101] 101. Tracking the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile;

[0102] In a specific implementation process, the position of the shell in the initial frame image of the flight image information can be obtained by the above-mentioned image background difference algorithm. Then, the positions of other frame images of the flight image information are obtained according to the following steps:

[0103] (10) Taking the position of the shell in the previous frame image as the initial center position of the shell in the current frame image, taking half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth, determining the target area, and calculating the multi-feature histogram distribution probability of the target area;

[0104] Specifically, the multi-feature histogram distribution probability of the target area can be calculated based on a preset multi-feature histogram distribution probability calculation formula;

[0105] The multi-feature histogram distribution probability calculation formula (3) is:

[0106]

[0107] Among them, q m (y j ) represents the multi-feature histogram distribution probability of the target area, C represents the normalization constant, k represents the kernel function, y j represents the initial center position of the shell in the current frame image, h represents the search window bandwidth, and x i represents the multi-feature histogram distribution probability of the current frame image, b1(x i ) The characteristic value of the color space of the current frame image, b2(x i ) represents the eigenvalue in the grayscale gradient direction, and u represents the feature grouping of the current frame image.

[0108] (20) calculating a weight value of the target area according to the multi-feature histogram distribution probability;

[0109] Specifically, the multi-feature histogram distribution probability can be substituted into a preset weight calculation formula to obtain the weight value of the target area;

[0110] The weight calculation formula (4) is:

[0111]

[0112] Among them, w i Indicates the weight value of the target area.

[0113] (30) calculating the predicted center position of the shell in the current frame image according to the weight value of the target area;

[0114] Specifically, the weight value of the target area can be substituted into a preset position prediction calculation formula to obtain the predicted center position of the shell in the current frame image;

[0115] The position prediction calculation formula (5) is:

[0116]

[0117] in, Indicates the predicted center position of the shell in the current frame image.

[0118] (40) calculating the distance between the predicted center position of the shell in the current frame image and the initial center position of the shell in the current frame image according to a preset estimation coefficient;

[0119] (50) if the distance is less than a preset threshold, determining the predicted center position of the shell in the current frame image as the target center position of the shell in the current frame image, and taking the target center position of the shell in the current frame image as a discrete trajectory point of the shell;

[0120] (60) If the distance is less than a preset threshold, after adjusting the initial center position of the shell in the current frame image, return to step (10) and use half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth to determine the target area and calculate the multi-feature histogram distribution probability of the target area.

[0121] 102. Generate a cannonball flight trajectory based on the discrete trajectory points of the cannonball;

[0122] In a specific implementation process, a flight trajectory fitting model can be constructed according to the coordinates of each discrete trajectory point of the projectile; based on the least squares principle, the flight trajectory fitting model is solved to obtain the projectile flight trajectory.

[0123] 103. Based on the flight trajectory of the projectile, determine the muzzle velocity of the projectile.

[0124] Specifically, the first position L1 of the shell in the image at the first moment and the second position L2 of the shell in the image at the second moment can be arbitrarily selected; according to the first position L1 of the shell and the second position L2 of the shell, the scale S between the unit length and the pixel point on the image is determined. P ; Calculate the flight time t of the projectile between the first position L1 of the projectile and the second position L2 of the projectile according to the frame difference between the first position L1 of the projectile and the second position L2 of the projectile; Determine the number of pixels n between the first position of the projectile and the second position of the projectile based on the flight trajectory of the projectile; According to the scale S P , the flight time t and the number of pixels n, calculate the average speed n of the shell between the first position of the shell and the second position of the shell, the calculation formula of the average speed is V=S p *n / t; the average velocity is taken as the muzzle velocity of the shell.

[0125] The method for detecting the flight information of artillery shells in the present embodiment obtains the flight image information of artillery shells within a safe distance; tracks the motion of artillery shells in the flight image information to obtain discrete trajectory points of artillery shells; generates the flight trajectory of artillery shells based on the discrete trajectory points of artillery shells; determines the muzzle velocity of artillery shells based on the artillery shell flight trajectory, thereby achieving accurate and timely acquisition of artillery shell flight information, and reproducing the artillery shell flight information to researchers or observers, providing a reliable basis for subsequent evaluation of artillery performance.

[0126] It should be noted that the method of the embodiment of the present invention can be performed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present invention, and the multiple devices will interact with each other to complete the method.

[0127] Example 2

[0128] Figure 2 FIG. 1 is a schematic diagram of the structure of an embodiment of a device for detecting shell flight information of the present invention. Figure 2 As shown, the device for detecting the artillery shell flight information of this embodiment may include an acquisition module 200 , a tracking module 201 , a trajectory generation module 202 and a speed detection module 203 .

[0129] An acquisition module 200 is used to acquire flight image information of a shell within a safe distance;

[0130] Specifically, a preset algorithm can be used to analyze the muzzle video of the image acquisition device in real time. When it is detected that a shell is fired from the muzzle, the flight image information of the shell within a safe distance can be obtained by triggering.

[0131] In a specific implementation process, the muzzle video of the image acquisition device can be analyzed in real time by one or more of the following algorithms:

[0132] The first is an image background difference algorithm. The process of analyzing the muzzle video of the image acquisition device based on this algorithm may include the following steps:

[0133] (1) Analyze the muzzle video collected by the image acquisition device to obtain the background image and foreground image corresponding to the muzzle video;

[0134] In a specific implementation process, the grayscale value of each pixel in each frame of the muzzle video can be obtained; pixels with grayscale values ​​of specified values ​​are determined as background pixels, and a background image is generated; pixels with grayscale values ​​not of the specified values ​​are determined as foreground pixels, and a foreground image is generated.

[0135] Specifically, since the pixel change frequency of the shell is faster than that of the background, this is used as the main feature to determine the state of the pixel - foreground (shell) and background. This feature includes two levels: pixel level and frame level.

[0136] Set the input image resolution to M*N, detect at the pixel level, distinguish foreground objects from background, and adaptively update the pixels that meet the conditions to background. Define the pixel state matrix Dk(M,N), record the pixel state in the k-th frame image, 0 indicates that the pixel state is a background pixel, non-0 indicates that the pixel state is a foreground pixel, as shown in the above-mentioned formulas (1) and (2).

[0137] (2) subtracting the grayscale value of the foreground image from the grayscale value of the background image to obtain the grayscale value of the difference image;

[0138] In a specific implementation process, the grayscale value of the foreground image is subtracted from the grayscale value of the background image to obtain the grayscale value of the difference image.

[0139] (3) Detect whether the grayscale value of the difference image is greater than a preset grayscale value; if so, execute step (4); if not, execute step (5);

[0140] (4) Determine the firing of the shells;

[0141] If the grayscale value of the difference image is greater than the preset grayscale value, it is determined to fire the shell.

[0142] (5) Ensure that no shells have been fired.

[0143] If the grayscale value of the difference image is less than or equal to the preset grayscale value, it is determined that the shell has not been fired.

[0144] The second is a phenomenon area detection algorithm. The process of analyzing the muzzle video of the image acquisition device based on this algorithm may include the following steps:

[0145] (11) analyzing the image information of the shell in the target area acquired by the image acquisition device to obtain a background image and a foreground image corresponding to the image information;

[0146] (12) Subtracting the grayscale value of the foreground image from the grayscale value of the background image to obtain a grayscale value of a difference image;

[0147] (13) If the grayscale value of the difference image is greater than a preset grayscale value, the image information is segmented to obtain a segmented area of ​​the explosion characteristic in the foreground image;

[0148] When firing artillery shells, if only relying on color or shape changes, the explosion may not be effectively identified. When firing artillery shells, in addition to the flames, smoke will also be generated, so the smoke feature method can also be used to improve the recognition of the explosion image. The shape characteristics of the flames in the image are shown as rapid changes in a short period of time, while the smoke can be shown as long-term, large-area and accompanied by diffusion. Therefore, according to the uncertainty of the smoke, after the background image of the current image is collected, the background difference method is used to detect the target area in the digital image. When the image of the target area is detected, the Ostu algorithm is used to segment the image, and appropriate thresholds are selected for the smoke and area. When the smoke area is greater than the threshold, it is considered that smoke is generated, that is, the explosion is identified, otherwise it is considered as no explosion. The Ostu algorithm uses the clustering idea to divide the grayscale of the image into two parts according to the grayscale level, so that the grayscale value difference between the two parts is the largest and the grayscale difference between each part is the smallest. A suitable grayscale level is found for division by calculating the variance.

[0149] (14) Detect whether the segmented area of ​​the explosion feature in the foreground image is larger than a preset area; if so, execute step (15); if not, execute step (16);

[0150] (15) Determine the firing of the shells;

[0151] If the segmented area of ​​the explosion characteristic is larger than a preset area, it is determined to fire the shell.

[0152] (16) Ensure that no shells have been fired.

[0153] If the segmented area of ​​the explosion characteristic is less than or equal to the preset area, it is determined that the shell has not been fired.

[0154] The third fire light characteristic recognition algorithm is based on which the process of analyzing the muzzle video of the image acquisition device may include the following steps:

[0155] (23) obtaining a grayscale change value of a specified point in the image information at a preset time interval;

[0156] (24) determining the fire light change rate of the designated point according to the grayscale change value and the preset time interval;

[0157] (25), detecting whether the fire light change rate is equal to a preset change rate, if so, executing step (26), if not, executing step (27);

[0158] (26) Determine the firing of the shells;

[0159] If the fire light change rate is greater than or less than the preset change rate, it is determined to fire the shell.

[0160] (27) Confirm that no shells were fired.

[0161] If the fire light change rate is equal to the preset change rate, it is determined that no shell has been fired.

[0162] In a specific implementation process, the above three methods for obtaining the explosion state information of the shells in the target area can be used separately or in combination. When the three methods are used in combination, corresponding weight values ​​can be set for different methods, and then the weights are summed according to the weight values ​​of the three methods to determine whether to fire the shells.

[0163] A tracking module 201 is used to track the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile;

[0164] In a specific implementation process, the position of the shell in the initial frame image of the flight image information can be obtained by the above-mentioned image background difference algorithm. Then, the positions of other frame images of the flight image information are obtained according to the following steps:

[0165] (10) Taking the position of the shell in the previous frame image as the initial center position of the shell in the current frame image, taking half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth, determining the target area, and calculating the multi-feature histogram distribution probability of the target area;

[0166] Specifically, the multi-feature histogram distribution probability of the target area can be calculated based on a preset multi-feature histogram distribution probability calculation formula;

[0167] The multi-feature histogram distribution probability calculation formula (3) refers to the above-mentioned related records and will not be repeated here.

[0168] (20) calculating a weight value of the target area according to the multi-feature histogram distribution probability;

[0169] Specifically, the multi-feature histogram distribution probability can be substituted into a preset weight calculation formula to obtain the weight value of the target area;

[0170] The weight calculation formula (4) is referred to the above-mentioned related records and will not be repeated here.

[0171] (30) calculating the predicted center position of the shell in the current frame image according to the weight value of the target area;

[0172] Specifically, the weight value of the target area can be substituted into a preset position prediction calculation formula to obtain the predicted center position of the shell in the current frame image;

[0173] The position prediction calculation formula (5) is referred to the above-mentioned related records and will not be repeated here.

[0174] (40) calculating the distance between the predicted center position of the shell in the current frame image and the initial center position of the shell in the current frame image according to a preset estimation coefficient;

[0175] (50) if the distance is less than a preset threshold, determining the predicted center position of the shell in the current frame image as the target center position of the shell in the current frame image, and taking the target center position of the shell in the current frame image as a discrete trajectory point of the shell;

[0176] (60) If the distance is less than a preset threshold, after adjusting the initial center position of the shell in the current frame image, return to step (10) and use half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth to determine the target area and calculate the multi-feature histogram distribution probability of the target area.

[0177] A trajectory generation module 202, for generating a projectile flight trajectory based on the discrete trajectory points of the projectile;

[0178] In a specific implementation process, a flight trajectory fitting model can be constructed according to the coordinates of each discrete trajectory point of the projectile; based on the least squares principle, the flight trajectory fitting model is solved to obtain the projectile flight trajectory.

[0179] The velocity detection module 203 is used to determine the muzzle velocity of the projectile based on the projectile flight trajectory.

[0180] Specifically, the first position L1 of the shell in the image at the first moment and the second position L2 of the shell in the image at the second moment can be arbitrarily selected; according to the first position L1 of the shell and the second position L2 of the shell, the scale S between the unit length and the pixel point on the image is determined. P ; Calculate the flight time t of the projectile between the first position L1 of the projectile and the second position L2 of the projectile according to the frame difference between the first position L1 of the projectile and the second position L2 of the projectile; Determine the number of pixels n between the first position of the projectile and the second position of the projectile based on the flight trajectory of the projectile; According to the scale S P , the flight time t and the number of pixels n, calculate the average speed n of the shell between the first position of the shell and the second position of the shell, the calculation formula of the average speed is V=S p *n / t; the average velocity is taken as the muzzle velocity of the shell.

[0181] The device for detecting the flight information of artillery shells in the present embodiment obtains the flight image information of artillery shells within a safe distance; tracks the motion of artillery shells in the flight image information to obtain discrete trajectory points of artillery shells; generates the flight trajectory of artillery shells based on the discrete trajectory points of artillery shells; determines the muzzle velocity of artillery shells based on the artillery shell flight trajectory, thereby achieving accurate and timely acquisition of artillery shell flight information, and reproducing the artillery shell flight information to researchers or observers, providing a reliable basis for subsequent evaluation of artillery performance.

[0182] The present invention also provides a device for detecting artillery shell explosion information, comprising a memory and a processor; the memory stores a computer program, and when the computer program is executed by the processor, the steps of the method for detecting artillery shell explosion information of the above embodiment are implemented.

[0183] The present invention also provides a storage medium, wherein the storage medium stores one or more programs, and the one or more programs can be executed to implement the method for detecting artillery shell explosion information described in the above embodiment.

[0184] Example 3

[0185] In a specific implementation process, the image acquisition device can be implemented using the following solutions:

[0186] Figure 3 It is a structural diagram of the image acquisition device. Figure 4 for Figure 3 An exploded diagram of Figure 3 to Figure 4 As shown, the wireless audio and video acquisition device of this embodiment may include a video acquisition module 11, an audio acquisition module 12, a wireless communication module (not shown in the figure), a first transmission antenna 13, a first device housing 14 and a controller (not shown in the figure).

[0187] In a specific implementation process, the controller and the wireless communication module are arranged inside the first device housing 14; the video acquisition module 11 and the audio acquisition module 12 are respectively arranged on the first device housing 14, and the video acquisition module 11 and the audio acquisition module 12 are both electrically connected to the controller; a first antenna connection structure 141 connected to the wireless communication module is arranged on one side of the first device housing 14; a second antenna connection structure (not shown in the figure) is arranged at one end of the first transmission antenna 13; the first antenna connection structure 141 and the second antenna connection structure are detachably connected to realize the connection or disconnection between the first transmission antenna 13 and the wireless communication module. In this way, it is equivalent to integrating the first transmission antenna 13 with the first device housing 14, and the connection line between the first transmission antenna 13 and the wireless communication module is located inside the first device housing 14, so that the product has a higher degree of integration, a longer service life, stronger environmental adaptability, a reduced failure rate, and a more stable operation.

[0188] Specifically, the first antenna connection structure 141 may include an antenna terminal, and the second antenna connection structure may include an antenna port. An external thread structure is provided at one end of the antenna terminal; an internal thread structure is provided at one end of the antenna port; and the external thread structure and the internal thread structure may cooperate with each other to achieve a detachable connection between the first antenna connection structure 141 and the second antenna connection structure.

[0189] It should be noted that the present embodiment is not limited to the above-mentioned structure. For example, a Universal Serial Bus (USB) port may be provided on one side of the first device housing 14, and a USB connector may be provided at one end of the first transmission antenna 13. The first transmission antenna 13 may be connected to the wireless transmitter by inserting the USB connector on the first transmission antenna 13 into the USB port on the first device housing 14, and the first transmission antenna 13 may be disconnected from the wireless transmitter by unplugging the USB connector on the first transmission antenna 13 from the USB port on the first device housing 14.

[0190] The wireless audio and video acquisition device of this embodiment is configured with a first antenna connection structure 141 connected to the wireless transmitter on one side of the first device housing 14, a second antenna connection structure is configured on one side of the first transmission antenna 13, and the first antenna connection structure 141 is detachably connected to the second antenna connection structure to achieve connection or disconnection between the first transmission antenna 13 and the wireless communication module. In this way, the first transmission antenna 13 can be quickly replaced by plugging and unplugging, thereby improving the practicality of the wireless audio and video acquisition device.

[0191] In a specific implementation process, Figure 3-Figure 4As shown, the video acquisition module 11 may include a camera 111 and a cover 112 ; the camera 111 and the cover 112 are respectively mounted on the first device housing 14 , and the camera 111 is fixed inside the cover 112 .

[0192] In a specific implementation process, in order to achieve shooting at different angles, a rotating component (not shown in the figure) can be set on the first device housing 14, and the rotating component may include a rotating base and a rotating axis; the cover body 112 and the camera 111 are respectively arranged on the rotating component; the rotating component is used to drive the cover body 112 and the camera 111 to rotate.

[0193] In a specific implementation process, due to the overall thickness of the camera 111 and the cost of the camera 111 with a higher focal length, the focal length of the camera 111 is usually not very high, which may result in the inability to obtain a clearer image. Therefore, in order to solve the above technical problems, the present invention can set the slot A corresponding to the rotation trajectory of the camera 111 in the first device housing 14, that is, if the camera 111 rotates 180°, a 180° arc-shaped slot A can be set, and if the camera 111 rotates 360°, a 360° circular slot A can be set.

[0194] In a specific implementation process, the wireless audio and video acquisition device also includes a rotating connector (not shown in the figure) and a focus lens 15. The first end of the rotating connector is connected to the rotating component; the focus lens 15 is arranged after the slot A, connected to the second end of the rotating connector, and the focus lens 15 is located in the direction of the camera 111; the rotating component is also used to drive the rotating connector and the focus lens 15 to rotate. In this way, the focus of the camera 111 can be expanded by installing the focus lens 15 in the slot A, so that the camera 111 can capture farther and clearer images. Among them, the focus lens 15 can be a convex lens or a liquid crystal lens, etc., and this embodiment does not make specific restrictions.

[0195] In a specific implementation process, the wireless audio and video acquisition device may also include a first sliding component 16, which is disposed on the first device housing 14; the first sliding component 16 is used to be slidably connected to a device bracket supporting the wireless audio and video acquisition device. Specifically, the first device housing 14 may include a main housing and a bottom plate, and the first sliding component 16 may be mounted on the bottom plate, such as a sliding buckle. After the first sliding component 16 is placed on the device bracket, the signal strength can be adjusted by sliding, and then the first sliding component 16 can be fixed on the device bracket.

[0196] In a specific implementation process, an antenna extension interface (not shown in the figure) can also be set on the first transmission antenna 13. By inserting other first transmission antennas 13 into the antenna extension interface, the total length of the normal first transmission antenna 13 can be increased, thereby expanding the coverage of the wireless signal.

[0197] In a specific implementation process, a heat dissipation structure (not shown in the figure) may also be provided on the side of the first device housing 14. For example, the heat dissipation structure may include but is not limited to a heat dissipation slot and / or a heat dissipation hole.

[0198] In a specific implementation process, the wireless audio and video acquisition device of this embodiment may further include a signal indication component (not shown in the figure); the signal indication component is electrically connected to the controller. The signal indication component is used to indicate the signal strength. For example, the signal indication component can be implemented by a row of indicator lights, and different signal strengths correspond to different luminous colors.

[0199] In a specific implementation process, the wireless audio and video acquisition device of this embodiment may further include a power indicator component 20; the power indicator component 20 is electrically connected to the controller. The power indicator component 20 is used to indicate the remaining power. For example, the signal indicator component can be implemented by a row of indicator lights.

[0200] In a specific implementation process, a solar panel (not shown in the figure) can also be set on the first device housing 14 or the enclosure housing of the first transmission antenna 13. In this way, when used outdoors, the solar panel can be used to absorb solar energy and convert it into electrical energy to power the wireless audio and video acquisition device.

[0201] In a specific implementation process, in a specific implementation process, the network port 17, the switch 18, the power interface 19, the rechargeable battery (not shown in the figure) and the like.

[0202] In a specific implementation process, the image information collected by the image acquisition device can be transmitted through the following network transmission devices.

[0203] Figure 5 is a schematic diagram of the structure of a network transmission device embodiment of the present invention, Figure 6 for Figure 5 An exploded diagram of Figure 5 to Figure 6 As shown, the network transmission device of this embodiment may include a second device housing 21, a controller (not shown in the figure), a wireless transmitter (not shown in the figure), a second transmission antenna 22 and a fixing member 23.

[0204] In a specific implementation process, the controller and the wireless transmitter are both arranged inside the second device housing 21, and the controller is electrically connected to the wireless transmitter; an antenna port (not shown in the figure) connected to the wireless transmitter is arranged on one side of the second device housing 21; a connection structure 221 is arranged on one side of the second transmission antenna 22; the connection structure 221 cooperates with the antenna port to achieve connection or disconnection between the transmission antenna and the wireless transmitter. In this way, the transmission antenna is integrated with the device housing, and no external feeder is required to connect the transmission antenna to the wireless transmitter, so that the product has a higher degree of integration, a longer service life, stronger environmental adaptability, a lower failure rate, and a more stable operation.

[0205] Specifically, a Universal Serial Bus (USB) port can be set on one side of the second device housing 21, and a USB connector can be set on one side of the second transmission antenna 22. The second transmission antenna 22 can be connected to the wireless transmitter by inserting the USB connector on the second transmission antenna 22 into the USB port on the second device housing 21, and the second transmission antenna 22 can be disconnected from the wireless transmitter by unplugging the USB connector on the second transmission antenna 22 from the USB port on the second device housing 21.

[0206] It should be noted that the present embodiment is not limited to the matching mode of USB port and USB connector, and the user can select other types of ports and connectors according to actual needs.

[0207] In a specific implementation process, the first end of the fixing member 23 can be detachably connected to the second device housing 21, and the second end of the fixing member 23 can be detachably connected to the second transmission antenna 22. In this way, while ensuring that the second transmission antenna 22 can be disassembled and replaced, the stability between the second transmission antenna 22 and the second device housing 21 can be strengthened.

[0208] In a specific implementation process, the first end of the fixing member 23 is connected to the second device housing 21 through a first bolt assembly, and the second end of the fixing member 23 is connected to the transmission antenna through a second bolt assembly. Specifically, the fixing member 23 can be L-shaped, so that the L-shaped fixing member 23 can include two 90° folded edges, and one folded edge end of the L-shaped fixing member 23 can be fixed to the second device housing 21 through the first bolt assembly, and when the antenna needs to be replaced, the bolt assembly is loosened to separate one folded edge end of the L-shaped fixing member 23 from the second device housing 21. Similarly, the other folded edge end of the L-shaped fixing member 23 can be fixed to the second transmission antenna 22 through the second bolt assembly, and when the antenna needs to be replaced, the bolt assembly is loosened to separate one folded edge end of the L-shaped fixing member 23 from the second transmission antenna 22.

[0209] The network transmission device of this embodiment is provided with an antenna port connected to the wireless transmitter on one side of the second device housing 21, and a connection structure 221 is provided on one side of the second transmission antenna 22; the connection structure 221 and the port of the second transmission antenna 22 can cooperate, so as to realize the connection or disconnection between the second transmission antenna 22 and the wireless transmitter, so that the second transmission antenna 22 can be quickly replaced by plugging and unplugging. The first end of the fixing member 23 is detachable from the second device housing 21, and the second end of the fixing member 23 is detachably connected to the second transmission antenna 22. In this way, while ensuring that the second transmission antenna 22 can be disassembled and replaced, the stability between the second transmission antenna 22 and the second device housing 21 can also be strengthened.

[0210] In a specific implementation process, Figure 6 As shown, the network transmission device may further include a second sliding component 23, which is disposed on the device housing; the second sliding component 23 is used to be slidably connected to the device bracket supporting the network transmission device. Specifically, the second device housing 21 may include a main housing 111 and a bottom plate 112, and the second sliding component 23 may be installed on the bottom plate 112, such as a sliding buckle. After the second sliding component 23 is placed on the device bracket, the signal strength can be adjusted by sliding, and then the second sliding component 23 can be fixed on the device bracket.

[0211] In a specific implementation process, an antenna extension interface (not shown in the figure) can also be set on the second transmission antenna 22. By inserting other second transmission antennas 22 into the antenna extension interface, the total length of the normal second transmission antenna 22 can be increased, thereby expanding the coverage of the wireless signal.

[0212] In a specific implementation process, Figure 1 As shown, at least one side of the second device housing 21 that is not provided with an antenna port is provided with a heat dissipation structure B. The heat dissipation structure B may include but is not limited to a heat dissipation slot and / or a heat dissipation hole. Figure 1-Figure 2 As shown, a heat dissipation slot can be opened in the main housing 111 to improve the heat dissipation capacity of the network transmission equipment.

[0213] In a specific implementation process, the cross-sectional size of the side of the second device housing 21 where the antenna port is arranged can be set to be smaller than the size of the side of the second transmission antenna 22 facing the second device housing 21 according to actual needs. For example, when the network transmission device is used as a signal sending device, it can be arranged according to this structure.

[0214] In a specific implementation process, according to actual needs, the cross-sectional size of the side of the second device housing 21 where the antenna port is set can be greater than or equal to the size of the side of the second transmission antenna 22 facing the second device housing 21. For example, when the network transmission device is used as a signal receiving device, it can be set according to this structure.

[0215] In a specific implementation process, the network transmission device of this embodiment may further include a signal indication component 24; the signal indication component 24 is electrically connected to the controller. The signal indication component 24 is used to indicate the signal strength. For example, the signal indication component 24 may be implemented by a row of indicator lights, and different signal strengths correspond to different luminous colors.

[0216] In a specific implementation process, a solar panel (not shown in the figure) can also be set on the second device housing 21 or the enclosing housing of the second transmission antenna 22. In this way, when used outdoors, the solar panel can be used to absorb solar energy and convert it into electrical energy to power the network transmission equipment.

[0217] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0218] In the description of the present invention, it is necessary to understand that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0219] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for detecting artillery shell flight information, characterized in that: include: Obtain flight image information of artillery shells within a safe distance; Tracking the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile; Generating a cannonball flight trajectory based on the discrete trajectory points of the cannonball; Determining the muzzle velocity of the projectile based on the projectile flight trajectory; Tracking the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile includes: After obtaining the position of the shell in the initial frame image of the flight image information, the positions of other frame images of the flight image information are obtained according to the following steps: (10) Taking the position of the shell in the previous frame image as the initial center position of the shell in the current frame image, taking half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth, determining the target area, and calculating the multi-feature histogram distribution probability of the target area; (20) calculating a weight value of the target area according to the multi-feature histogram distribution probability; (30) calculating the predicted center position of the shell in the current frame image according to the weight value of the target area; (40) calculating the distance between the predicted center position of the shell in the current frame image and the initial center position of the shell in the current frame image according to a preset estimation coefficient; (50) if the distance is less than a preset threshold, determining the predicted center position of the shell in the current frame image as the target center position of the shell in the current frame image, and taking the target center position of the shell in the current frame image as a discrete trajectory point of the shell; (60) If the distance is less than the preset threshold, the initial center position of the shell in the current frame image is adjusted, and then the process returns to step (10) and uses half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth to determine the target area and calculate the multi-feature histogram distribution probability of the target area; Determining the muzzle velocity of the projectile based on the projectile flight trajectory includes: Arbitrarily select a first position of the shell in the image at the first moment and a second position of the shell in the image at the second moment; Determine a scale between a unit length and a pixel on an image according to the first position of the shell and the second position of the shell; Calculating the flight time of the shell between the first position of the shell and the second position of the shell according to the frame difference between the first position of the shell and the second position of the shell; Based on the projectile flight trajectory, determining the number of pixels between the first position of the projectile and the second position of the projectile; Calculate an average speed of a projectile between a first position of the projectile and a second position of the projectile according to the scale, the flight time, and the number of pixels; The average velocity is taken as the muzzle velocity of the projectile.

2. The method for detecting shell flight information according to claim 1, characterized in that: Calculate the multi-feature histogram distribution probability of the target area, including: Calculate the multi-feature histogram distribution probability of the target area based on the preset multi-feature histogram distribution probability calculation formula; The multi-feature histogram distribution probability calculation formula is: Among them, q m (y j ) represents the multi-feature histogram distribution probability of the target area, C represents the normalization constant, k represents the kernel function, y j represents the initial center position of the shell in the current frame image, h represents the search window bandwidth, and x i represents the multi-feature histogram distribution probability of the current frame image, b1(x i ) The characteristic value of the color space of the current frame image, b2(x i ) represents the eigenvalue in the grayscale gradient direction, and u represents the feature grouping of the current frame image.

3. The method for detecting shell flight information according to claim 2, characterized in that: Calculating the weight value of the target area according to the multi-feature histogram distribution probability, including: Substituting the multi-feature histogram distribution probability into a preset weight calculation formula to obtain a weight value of the target area; The weight calculation formula is: Among them, w i Indicates the weight value of the target area.

4. The method for detecting shell flight information according to claim 3, characterized in that: Calculating the predicted center position of the shell in the current frame image according to the weight value of the target area includes: Substituting the weight value of the target area into a preset position prediction calculation formula to obtain the predicted center position of the shell in the current frame image; The position prediction calculation formula is: in, Indicates the predicted center position of the shell in the current frame image.

5. The method for detecting shell flight information according to claim 1, characterized in that: Generating a cannonball flight trajectory based on the discrete trajectory points of the cannonball, including: Constructing a flight trajectory fitting model according to the coordinates of each discrete trajectory point of the shell; The flight trajectory fitting model is solved to obtain the projectile flight trajectory.

6. A device for detecting artillery shell flight information, characterized in that: include: An acquisition module is used to acquire flight image information of the shell within a safe distance; A tracking module, used for tracking the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile; A trajectory generation module, used to generate a projectile flight trajectory based on the discrete trajectory points of the projectile; A velocity detection module, used to determine the muzzle velocity of the projectile based on the projectile flight trajectory; Tracking the motion of the projectile in the flight image information to obtain discrete trajectory points of the projectile includes: After obtaining the position of the shell in the initial frame image of the flight image information, the positions of other frame images of the flight image information are obtained according to the following steps: (10) Taking the position of the shell in the previous frame image as the initial center position of the shell in the current frame image, taking half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth, determining the target area, and calculating the multi-feature histogram distribution probability of the target area; (20) calculating a weight value of the target area according to the multi-feature histogram distribution probability; (30) calculating the predicted center position of the shell in the current frame image according to the weight value of the target area; (40) calculating the distance between the predicted center position of the shell in the current frame image and the initial center position of the shell in the current frame image according to a preset estimation coefficient; (50) if the distance is less than a preset threshold, determining the predicted center position of the shell in the current frame image as the target center position of the shell in the current frame image, and taking the target center position of the shell in the current frame image as a discrete trajectory point of the shell; (60) If the distance is less than the preset threshold, the initial center position of the shell in the current frame image is adjusted, and then the process returns to step (10) and uses half the length and width of the minimum circumscribed rectangle of the shell as the search window bandwidth to determine the target area and calculate the multi-feature histogram distribution probability of the target area; Determining the muzzle velocity of the projectile based on the projectile flight trajectory includes: Arbitrarily select a first position of the shell in the image at the first moment and a second position of the shell in the image at the second moment; Determine a scale between a unit length and a pixel on an image according to the first position of the shell and the second position of the shell; Calculating the flight time of the shell between the first position of the shell and the second position of the shell according to the frame difference between the first position of the shell and the second position of the shell; Based on the projectile flight trajectory, determining the number of pixels between the first position of the projectile and the second position of the projectile; Calculate an average speed of a projectile between a first position of the projectile and a second position of the projectile according to the scale, the flight time, and the number of pixels; The average velocity is taken as the muzzle velocity of the projectile.

7. A device for detecting artillery shell flight information, characterized in that: including memory and processor; The memory stores a computer program, which, when executed by the processor, implements the steps of the method for detecting the flight information of a shell as claimed in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed to implement the method for detecting the flight information of the artillery shell according to any one of claims 1 to 5.

Images