A Muzzle Position Recognition Method and System Based on Infrared Scattering Signals

Abstract

The present invention relates to a muzzle position recognition method and system based on infrared scattering signals, belonging to the technical field of muzzle recognition. Among them, the method includes: collecting a target infrared image and a target active infrared image; calculating an enhanced target infrared image and an enhanced target active infrared image based on the target infrared image and the target active infrared image, and calculating an active infrared recognition area based on the enhanced target infrared image and the enhanced target active infrared image; calculating the center point of the shooting area according to the active infrared recognition area, collecting target image data, preprocessing and recognizing the target image data to obtain a target lamp recognition result, and calculating the pixel center point of the target lamp; presetting a pixel point distance threshold, determining the target target lamp pixel center point according to the pixel point distance threshold, the center point of the shooting area, and the pixel center point of the target lamp, and calculating the actual space coordinates of the target target lamp according to the target target lamp pixel center point. The muzzle position recognition is realized through infrared scattering signals.

Description

Technical Field

[0001] The present invention belongs to the technical field of muzzle recognition, and particularly relates to a muzzle position recognition method and system based on infrared scattering signals. Background Art

[0002] In traditional shooting training, laser shooting systems are widely used. The system determines the shooting position by emitting a laser beam towards the target and using a receiver to capture the reflected signal of the laser beam. However, laser shooting systems have some inherent limitations and problems:

[0003] 1. Safety issues: Laser beams may cause harm to the eyes in some cases, especially when the power output is high or when used improperly.

[0004] 2. Environmental interference: Laser beams are easily affected in bright light or complex environments (such as haze, sand and dust), resulting in signal loss or misjudgment.

[0005] 3. High environmental requirements: When traditional laser shooting systems conduct shooting training at night, due to insufficient lighting conditions, users cannot determine the aiming target, resulting in an insufficient gaming experience for users. Summary of the Invention

[0006] To solve the above problems existing in the prior art, the present invention provides a muzzle position recognition method and system based on infrared scattering signals.

[0007] The object of the present invention can be achieved by the following technical solutions:

[0008] Collect the infrared image of the target through the infrared thermal imager built in the AR camera, emit an active infrared signal through the infrared emitter, obtain the trigger pulling signal, and the intelligent terminal controls the infrared thermal imager to collect the active infrared image of the target according to the trigger pulling signal;

[0009] Calculate the enhanced target infrared image and the enhanced target active infrared image through a preprocessing model according to the target infrared image and the target active infrared image, and calculate the active infrared recognition area through an analysis model according to the enhanced target infrared image and the enhanced target active infrared image;

[0010] Calculate the center point of the shooting area according to the active infrared recognition area, collect the target image data through the AR camera, perform preprocessing on the target image data to obtain the preprocessed target data, calculate the target light recognition result through the recognition model according to the preprocessed target data, and calculate the pixel center point of the target light according to the target light recognition result;

[0011] Preset a pixel distance threshold, determine the target target light pixel center point according to the pixel distance threshold, the center point of the shooting area, and the center point of the target light pixel. Calculate the actual space coordinates of the target target light through a coordinate conversion model according to the target target light pixel center point, and the intelligent terminal generates an adaptive signal according to the actual space coordinates of the target target light to control the corresponding target light to turn off.

[0012] Specifically, the preprocessing model includes:

[0013] Perform filtering processing on the target infrared image and the target active infrared image to obtain a denoised target infrared image and a denoised target active infrared image;

[0014] Perform image enhancement on the denoised target infrared image and the denoised target active infrared image through the Retinex algorithm to obtain the enhanced target infrared image and the enhanced target active infrared image.

[0015] Specifically, the analysis model includes:

[0016] Obtain the edge of the target infrared image and the edge of the target active infrared image through wavelet multi-scale detection according to the enhanced target infrared image and the enhanced target active infrared image;

[0017] Extract edge feature points of the target infrared image and edge feature points of the target active infrared image through the canny operator according to the edge of the target infrared image and the edge of the target active infrared image;

[0018] Obtain matching pairs by calculating the similarity according to the edge feature points of the target infrared image and the edge feature points of the target active infrared image;

[0019] Eliminate the matching pairs according to the target active infrared image through background difference method to obtain the active infrared recognition area.

[0020] Specifically, the preprocessing includes:

[0021] Perform color space conversion on the target image data to obtain a converted image, perform gray correction on the converted image to obtain a corrected image, perform filtering processing on the corrected image to obtain a denoised image, and perform histogram equalization on the denoised image to obtain the preprocessed data of the target.

[0022] Specifically, the recognition model includes:

[0023] Perform scale normalization on the preprocessed data of the target to obtain normalized data, and perform two-dimensional mutation position detection on the normalized data through the Harris corner detector to obtain interest points;

[0024] The convex hull of the points of interest is obtained in advance by the Graham algorithm according to the points of interest, and the color feature is calculated according to the convex hull of the points of interest;

[0025] The translation normalization is performed according to the convex hull of the points of interest to obtain a translated convex hull. The pixel coordinates of the translated convex hull are mapped to polar coordinates to obtain a mapped convex hull. The Zernike moments are calculated according to the mapped convex hull, and the color feature of the reference target lamp and the Zernike moments of the reference target lamp are obtained;

[0026] The similarity value is calculated according to the color feature, the Zernike moments, the color feature of the reference target lamp, and the Zernike moments of the reference target lamp. A similarity threshold is preset, and the similarity value is screened according to the similarity threshold to obtain the target lamp recognition result.

[0027] Specifically, the determination of the target target lamp pixel center point according to the pixel point distance threshold, the center point of the shooting area, and the target lamp pixel center point specifically includes:

[0028] The distance data is calculated according to the center point of the shooting area and the target lamp pixel center point, and it is judged whether the distance data is greater than the pixel point distance threshold. If so, the number of points meeting the requirements is counted, and the coordinates of the points meeting the requirements are recorded; if not, no processing is performed;

[0029] Judgment is made according to the number of points meeting the requirements. If the number of points meeting the requirements is greater than 1, a screening rule is preset, and the coordinates of the points meeting the requirements are screened according to the screening rule to obtain the target target lamp pixel center point; if the number of points meeting the requirements is equal to 1, the coordinates of the points meeting the requirements are used as the target target lamp pixel center point.

[0030] Specifically, the coordinate conversion model includes:

[0031] The pixel coordinates of the target target lamp pixel center point are converted into NDC coordinates, a projection matrix is obtained, the NDC coordinates are converted into clip space coordinates according to the projection matrix, a view matrix is obtained, and the clip space coordinates are converted into world coordinates according to the view matrix to obtain the actual space coordinates of the target target lamp.

[0032] A muzzle position recognition system based on infrared scattering signals includes: a data acquisition module, a preprocessing module, an identification module, and a control module;

[0033] The data acquisition module is used to collect the infrared image of the target through the infrared thermal imager built in the AR camera, emit active infrared signals through the infrared emitter, obtain the trigger pull signal, and the intelligent terminal controls the infrared thermal imager to collect the active infrared image of the target according to the trigger pull signal;

[0034] The preprocessing module is used to calculate an enhanced target infrared image and an enhanced target active infrared image through a preprocessing model based on the target infrared image and the target active infrared image, and calculate an active infrared recognition area through an analysis model based on the enhanced target infrared image and the enhanced target active infrared image;

[0035] The recognition module is used to calculate the center point of the shooting area according to the active infrared recognition area, collect target image data through an AR camera, preprocess the target image data to obtain preprocessed target data, calculate a target light recognition result through a recognition model according to the preprocessed target data, and calculate the pixel center point of the target light according to the target light recognition result;

[0036] The control module is used to preset a pixel point distance threshold, determine the target target light pixel center point according to the pixel point distance threshold, the shooting area center point, and the target light pixel center point, calculate the actual space coordinates of the target target light through a coordinate conversion model according to the target target light pixel center point, and the intelligent terminal generates an adaptive signal according to the actual space coordinates of the target target light to control the corresponding target light to turn off.

[0037] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the muzzle position recognition method based on infrared scattering signals as described above.

[0038] A storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the muzzle position recognition method based on infrared scattering signals as described above when executed by a computer processor.

[0039] The beneficial effects of the present invention are as follows:

[0040] (1) By providing an infrared scattering signal transmitter, the infrared scattering signal transmitter emits an infrared scattering signal, the image data of the target target light is obtained according to the infrared scattering signal, and the aiming point is recognized according to the image data, which solves the problem of inability to recognize the target point under dark conditions, as well as the insecurity and instability of the laser shooting system.

[0041] (2) By providing a preprocessing model and an analysis model, the preprocessing model and the analysis model clean and recognize the target infrared image and the target active infrared image to obtain an active infrared recognition area, which solves the interference caused by external infrared scattering signals to the recognition system.

[0042] (3) By setting up an identification model, preprocessing is performed based on the active infrared identification area to obtain target preprocessing data. The center point of the target lamp pixel is calculated through the identification model according to the target preprocessing data. The actual space coordinates are obtained through coordinate conversion based on the center point of the target lamp pixel, and the corresponding target lamp is turned off according to the actual space coordinates, realizing the hit feedback of shooting through the infrared scattering signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0044] Figure 1 It is a schematic flowchart of the muzzle position identification method based on infrared scattering signal of the present invention;

[0045] Figure 2 It is a schematic structural diagram of the target device in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, describe in detail the specific embodiments, structures, features and their effects of the present invention.

[0047] Please refer to Figure 1 , a muzzle position identification method based on infrared scattering signal,

[0048] S1: The infrared thermal imager built in the AR camera is used to collect the infrared image of the target, and the active infrared signal is emitted by the infrared emitter to obtain the trigger pulling signal. The intelligent terminal controls the infrared thermal imager to collect the active infrared image of the target according to the trigger pulling signal;

[0049] S2: The enhanced infrared image of the target and the enhanced active infrared image of the target are calculated through the preprocessing model according to the infrared image of the target and the active infrared image of the target. The active infrared identification area is calculated through the analysis model according to the enhanced infrared image of the target and the enhanced active infrared image of the target;

[0050] S3: Calculate the center point of the shooting area according to the active infrared identification area, collect the target image data through the AR camera, perform preprocessing on the target image data to obtain the target preprocessing data, calculate the target lamp identification result through the identification model according to the target preprocessing data, and calculate the center point of the target lamp pixel according to the target lamp identification result;

[0051] S4: Preset a pixel point distance threshold. Determine the target target light pixel center point according to the pixel point distance threshold, the center point of the shooting area, and the center point of the target light pixel. Calculate the actual spatial coordinates of the target target light through the coordinate conversion model. The intelligent terminal generates an adaptive signal according to the actual spatial coordinates of the target target light to control the corresponding target light to turn off.

[0052] In this embodiment, the target is composed of a target light matrix, and each target light has an independent number. During shooting training, a target target light is set up, and infrared scattering signals are emitted through the muzzle for shooting training.

[0053] Specifically, the preprocessing model includes:

[0054] Perform filtering processing on the target infrared image and the target active infrared image to obtain a denoised target infrared image and a denoised target active infrared image;

[0055] It should be noted that the filtering processing includes median filtering, mean filtering, and Gaussian filtering;

[0056] Perform image enhancement on the denoised target infrared image and the denoised target active infrared image through the Retinex algorithm to obtain the enhanced target infrared image and the enhanced target active infrared image.

[0057] Specifically, the analysis model includes:

[0058] Obtain the edge of the target infrared image and the edge of the target active infrared image through wavelet multi-scale detection based on the enhanced target infrared image and the enhanced target active infrared image;

[0059] Extract the edge feature points of the target infrared image and the edge feature points of the target active infrared image through the canny operator based on the edge of the target infrared image and the edge of the target active infrared image;

[0060] Obtain matching pairs by calculating the similarity based on the edge feature points of the target infrared image and the edge feature points of the target active infrared image;

[0061] The similarity calculation formula is:

[0062] ,

[0063] Among them, F is the similarity, f 1 (x, y) is the target infrared image, f 2 (x, y) is the target active infrared image,a 1 , b 1 is the local mean and variance of the target infrared image near the p feature points, a 2 , b 2 is the local mean and variance of the target active infrared image near the q feature points, m is the size of the matching window, x, y is a variable parameter representing coordinates;

[0064] The active infrared recognition region is obtained by removing the matching pairs from the target active infrared image through background difference method.

[0065] Specifically, the calculation formula for the center point of the shooting area is:

[0066] ,

[0067] where, C x is the abscissa of the center point of the shooting area, C y is the ordinate of the center point of the shooting area, N is the number of pixel points in the shooting area, i is a variable parameter, X i is the i abscissa of the Y i is the i ordinate of the

[0068] It should be noted that the calculation method of the center point of the target lamp pixel is the same as that of the center point of the involved area.

[0069] Specifically, the preprocessing includes:

[0070] The color space of the target image data is converted to obtain a converted image, the converted image is gray-corrected to obtain a corrected image, the corrected image is filtered to obtain a denoised image, and the denoised image is histogram-equalized to obtain the preprocessed data of the target.

[0071] It should be noted that the gray correction includes gray level correction, gray scale change, and histogram correction, and the filtering process includes median filtering, mean filtering, and Gaussian filtering.

[0072] Specifically, the recognition model includes:

[0073] Perform scale normalization on the target preprocessed data to obtain normalized data, and perform two-dimensional mutation position detection on the normalized data through a Harris corner detector to obtain interest points;

[0074] Obtain the convex hull of the interest points in advance through the Graham algorithm based on the interest points, and calculate the color feature based on the convex hull of the interest points;

[0075] The color feature calculation formula is:

[0076] ,

[0077] Hk is the color feature, numk is the number of pixels with the color of the convex hull of the interest points being k ; num is the total number of pixel points of the convex hull of the interest points, k is a variable parameter, L is the number of color bins;

[0078] Perform translation normalization on the convex hull of the interest points to obtain a translated convex hull, map the pixel coordinates of the translated convex hull to polar coordinates to obtain a mapped convex hull, calculate the Zernike moments based on the mapped convex hull, and obtain the reference target lamp color feature and the reference target lamp Zernike moments;

[0079] The Zernike moment calculation formula is:

[0080] ,

[0081] where, Vnm(x, y) is the zernike moment, x, y is the pixel coordinate, Rnm(ρ) is the radial polynomial, j is the imaginary unit, m is the degree of repetition, n is the order, ρ, θ is the polar coordinate representation of the point (x, y) ;

[0082] Calculate the similarity value based on the color feature, the Zernike moment, the reference target lamp color feature, and the reference target lamp Zernike moment, preset the similarity threshold, and screen the similarity value according to the similarity threshold to obtain the target lamp recognition result;

[0083] The similarity value calculation formula is:

[0084] ,

[0085] where, S is the similarity value,W c 、W z is the weight value, k is the variable parameter, L is the number of color handles, n is the number of Zernike moments, H k （Q） is the color feature, H k （I） is the color feature of the reference target lamp, Z k （Q） is the Zernike moment, Z k （I） is the Zernike moment of the reference target lamp.

[0086] Specifically, the determination of the target target lamp pixel center point according to the pixel point distance threshold, the center point of the shooting area, and the center point of the target lamp pixel specifically includes:

[0087] Calculate the distance data based on the center point of the shooting area and the center point of the target lamp pixel, and determine whether the distance data is greater than the pixel point distance threshold. If so, count the number of points that meet the requirements and record the coordinates of the points that meet the requirements; if not, do not process;

[0088] Make a judgment based on the number of points that meet the requirements. If the number of points that meet the requirements is greater than 1, set a preset screening rule, and screen the coordinates of the points that meet the requirements according to the screening rule to obtain the target target lamp pixel center point; if the number of points that meet the requirements is equal to 1, use the coordinates of the points that meet the requirements as the target target lamp pixel center point.

[0089] In this embodiment, the screening rule is to traverse the coordinates of the points that meet the requirements in the order of top - right - bottom - left in the camera coordinate system, stop traversing once the result is retrieved, and output the retrieved result.

[0090] Specifically, the coordinate conversion model includes:

[0091] Convert the pixel coordinates of the target target lamp pixel center point into NDC coordinates, obtain the projection matrix, convert the NDC coordinates into clip space coordinates according to the projection matrix, obtain the view matrix, and convert the clip space coordinates into world coordinates according to the view matrix to obtain the actual space coordinates of the target target lamp;

[0092] The calculation formula for the NDC coordinates is:

[0093] ,

[0094] Among them, Xndc and Yndc are NDC coordinates, Xp and Yp are pixel coordinates, width is the viewport width, height is the viewport height;

[0095] The calculation formula for the clipping space coordinates is:

[0096] ,

[0097] Among them, Xc, Yc, Zc, Wc is the clipping space coordinate, p is the projection matrix, Xndc, Yndc is the NDC coordinate;

[0098] The calculation formula for the world coordinates is:

[0099] ,

[0100] Among them, Xa, Ya, Za, Wa is the world coordinate, M, V is the view matrix, Xc, Yc, Zc, Wc is the clipping space coordinate.

[0101] A muzzle position recognition system based on infrared scattering signals, comprising: a data acquisition module, a preprocessing module, an identification module, and a control module;

[0102] The data acquisition module is used to collect the infrared image of the target through the infrared thermal imager built in the AR camera, emit active infrared signals through the infrared emitter, obtain the trigger pull signal, and the intelligent terminal controls the infrared thermal imager to collect the active infrared image of the target according to the trigger pull signal;

[0103] The preprocessing module is used to calculate the enhanced infrared image of the target and the enhanced active infrared image of the target through the preprocessing model according to the infrared image of the target and the active infrared image of the target, and calculate the active infrared recognition area through the analysis model according to the enhanced infrared image of the target and the enhanced active infrared image of the target;

[0104] The identification module is used to calculate the center point of the shooting area according to the active infrared recognition area, collect the target image data through the AR camera, preprocess the target image data according to the target image data, calculate the target light recognition result through the recognition model according to the preprocessed target data, and calculate the pixel center point of the target light according to the target light recognition result;

[0105] The control module is configured to preset a pixel distance threshold, determine a target target light pixel center point based on the pixel distance threshold, the center point of the shooting area, and the center point of the target light pixel, calculate the actual spatial coordinates of the target target light through a coordinate conversion model based on the target target light pixel center point, and the intelligent terminal generates an adaptive signal according to the actual spatial coordinates of the target target light to control the corresponding target light to turn off.

[0106] In this embodiment, the implementation steps of the shooting game according to the muzzle position recognition method based on infrared scattering signals are as follows:

[0107] Step 1: Infrared scattering signals are emitted through the muzzle, and a target infrared image and a target active infrared image are acquired by an AR camera mounted on the firearm.

[0108] Step 2: The AR camera transmits the acquired target infrared image and target active infrared image to the intelligent terminal. The intelligent terminal calculates the aiming point according to steps S2 - S3 and visualizes the aiming point.

[0109] Step 3: The user triggers the trigger. After the intelligent terminal receives the trigger signal, it acquires the last frame of the target active infrared image and calculates the finally shot target light according to steps S2 - S4.

[0110] Step 4: The intelligent terminal generates an adaptive signal according to the actual spatial coordinates of the target light to control the corresponding target light to turn off, thereby realizing shooting feedback.

[0111] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.

[0112] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0113] The program code contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, and the like, or any suitable combination of the foregoing. The computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0114] As described above, the above are only the preferred embodiments of the present invention, and there is no any form of limitation to the present invention. Although the present invention has been disclosed as above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments of the equivalent changes within the scope of the technical solution of the present invention without departing from the technical solution of the present invention. However, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A muzzle position recognition method based on infrared scattering signals, characterized in that, Including: Collect the infrared image of the target through the built-in infrared thermal imager of the AR camera, emit an active infrared signal through the infrared emitter to obtain the trigger pulling signal, and the intelligent terminal controls the infrared thermal imager to collect the active infrared image of the target according to the trigger pulling signal; Calculate the enhanced infrared image of the target and the enhanced active infrared image of the target according to the infrared image of the target and the active infrared image of the target through the preprocessing model, and calculate the active infrared recognition area according to the enhanced infrared image of the target and the enhanced active infrared image of the target through the analysis model; The analysis model includes: obtaining the edge of the infrared image of the target and the edge of the active infrared image of the target through wavelet multi-scale detection according to the enhanced infrared image of the target and the enhanced active infrared image of the target; Extract the edge feature points of the infrared image of the target and the edge feature points of the active infrared image of the target through the canny operator according to the edge of the infrared image of the target and the edge of the active infrared image of the target; Obtain the matching pairs by calculating the similarity according to the edge feature points of the infrared image of the target and the edge feature points of the active infrared image of the target; Eliminate the matching pairs according to the active infrared image of the target through background difference method to obtain the active infrared recognition area; Calculate the center point of the shooting area according to the active infrared recognition area, collect the target image data through the AR camera, preprocess the target image data to obtain the preprocessed target data, calculate the target light recognition result according to the preprocessed target data through the recognition model, and calculate the pixel center point of the target light according to the target light recognition result; The recognition model includes: Perform scale normalization on the preprocessed target data to obtain the normalized data, and perform two-dimensional mutation position detection on the normalized data through the Harris corner detector to obtain the interest points; Obtain the convex hull of the interest points through the Graham algorithm according to the interest points, and calculate the color feature according to the convex hull of the interest points; Perform translation normalization on the convex hull of the interest points to obtain the translated convex hull, map the pixel coordinates of the translated convex hull to polar coordinates to obtain the mapped convex hull, calculate the zernike moment according to the mapped convex hull, and obtain the reference target light color feature and the reference target light zernike moment; Calculate the similarity value according to the color feature, the zernike moment, the reference target light color feature, and the reference target light zernike moment, preset the similarity threshold, and screen the similarity value according to the similarity threshold to obtain the target light recognition result; Preset the pixel point distance threshold, determine the target target light pixel center point according to the pixel point distance threshold, the shooting area center point, and the target light pixel center point, calculate the actual space coordinates of the target target light according to the target target light pixel center point through the coordinate conversion model, and the intelligent terminal generates an adaptive signal according to the actual space coordinates of the target target light to control the corresponding target light to turn off.

2. The muzzle position recognition method based on infrared scattering signals according to claim 1, characterized in that The preprocessing model includes: Perform filtering processing on the infrared image of the target and the active infrared image of the target to obtain the noise-reduced infrared image of the target and the noise-reduced active infrared image of the target; The enhanced target infrared image and the enhanced target active infrared image are obtained by performing image enhancement on the noise-reduced target infrared image and the noise-reduced target active infrared image through the Retinex algorithm.

3. The muzzle position recognition method based on infrared scattering signals according to claim 1, wherein, The preprocessing includes: Performing color space conversion on the target image data to obtain a converted image, performing gray correction on the converted image to obtain a corrected image, performing filtering processing on the corrected image to obtain a denoised image, and performing histogram equalization on the denoised image to obtain the target preprocessing data.

4. The muzzle position recognition method based on infrared scattering signals according to claim 1, characterized in that, The specific process of determining the target target lamp pixel center point according to the pixel point distance threshold, the center point of the shooting area, and the center point of the target lamp pixel includes: Calculating distance data based on the center point of the shooting area and the center point of the target lamp pixel, determining whether the distance data is greater than the pixel point distance threshold. If so, counting the number of points that meet the requirements and recording the coordinates of the points that meet the requirements; if not, no processing is performed. Judging according to the number of points that meet the requirements. If the number of points that meet the requirements is greater than 1, setting a preset screening rule, and screening the coordinates of the points that meet the requirements according to the screening rule to obtain the target target lamp pixel center point; if the number of points that meet the requirements is equal to 1, taking the coordinates of the points that meet the requirements as the target target lamp pixel center point.

5. The muzzle position recognition method based on infrared scattering signals according to claim 1, characterized in that The coordinate conversion model includes: Converting the pixel coordinates of the target target lamp pixel center point into NDC coordinates, obtaining a projection matrix, converting the NDC coordinates into clip space coordinates according to the projection matrix, obtaining a view matrix, and converting the clip space coordinates into world coordinates according to the view matrix to obtain the actual space coordinates of the target target lamp.

6. A muzzle position recognition system based on infrared scattering signals, characterized in that, It includes: A data acquisition module, a preprocessing module, an identification module, and a control module; The data acquisition module is used to collect the target infrared image through the built-in infrared thermal imager of the AR camera, emit an active infrared signal through the infrared emitter, obtain a trigger pull signal, and the intelligent terminal controls the infrared thermal imager to collect the target active infrared image according to the trigger pull signal; The preprocessing module is used to calculate the enhanced target infrared image and the enhanced target active infrared image through a preprocessing model according to the target infrared image and the target active infrared image, and calculate the active infrared recognition area through an analysis model according to the enhanced target infrared image and the enhanced target active infrared image; The analysis model includes: obtaining the edge of the target infrared image and the edge of the target active infrared image through wavelet multi-scale detection according to the enhanced target infrared image and the enhanced target active infrared image; Extracting edge feature points of the target infrared image and edge feature points of the target active infrared image through the canny operator according to the edge of the target infrared image and the edge of the target active infrared image; Obtaining matching pairs by calculating the similarity according to the edge feature points of the target infrared image and the edge feature points of the target active infrared image; Eliminating the matching pairs according to the target active infrared image through background difference method to obtain the active infrared recognition area; The recognition module is used to calculate the center point of the shooting area according to the active infrared recognition area, collect the target image data through the AR camera, preprocess the target image data to obtain the preprocessed target data, calculate the target light recognition result through the recognition model according to the preprocessed target data, and calculate the pixel center point of the target light according to the target light recognition result; the recognition model includes: performing scale normalization on the preprocessed target data to obtain normalized data, and performing two-dimensional mutation position detection on the normalized data through a Harris corner detector to obtain interest points; Obtaining an interest point convex hull according to the interest points through a Graham algorithm, and calculating a color feature according to the interest point convex hull; Performing translation normalization on the interest point convex hull to obtain a translation convex hull, mapping the pixel coordinates of the translation convex hull to polar coordinates to obtain a mapped convex hull, calculating Zernike moments according to the mapped convex hull, and obtaining a reference target light color feature and a reference target light Zernike moment; Calculating a similarity value according to the color feature, the Zernike moment, the reference target light color feature, and the reference target light Zernike moment, presetting a similarity threshold, and screening the similarity value according to the similarity threshold to obtain the target light recognition result; The control module is used to preset a pixel point distance threshold, determine the target target light pixel center point according to the pixel point distance threshold, the shooting area center point, and the target light pixel center point, calculate the actual space coordinates of the target target light through a coordinate conversion model according to the target target light pixel center point, and the intelligent terminal generates an adaptive signal according to the actual space coordinates of the target target light to control the corresponding target light to turn off.

7. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the muzzle position recognition method based on infrared scattering signals according to any one of claims 1-5.

8. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions are used to execute the muzzle position recognition method based on infrared scattering signals according to any one of claims 1-5 when executed by a computer processor.

Images