Automatic pressing method and device, equipment and storage medium

Abstract

The invention provides an automatic pressing method, device and equipment and a storage medium, and the method comprises the steps: carrying out image shooting through image shooting equipment, obtaining first image data, and transmitting the first image data to a positioning system; carrying out forced target identification on the received first image data by using a preset computer identification algorithm through the positioning system to obtain a first identification result; according to the first identification result and the equipment information of the image shooting equipment, calculating a first launching coordinate of the forced target, and sending the first launching coordinate to mortar equipment; and pose adjustment is carried out through the mortar equipment according to the received first launching coordinates, and forced striking operation is carried out after pose adjustment is completed. According to the method, full-automatic operation of the mortar is achieved through cooperative work of the automatic striking system, manual intervention is reduced, the combat response speed and striking precision are improved, and the casualty risk of operators is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicles, and in particular to an automatic mortar method, device, equipment and storage medium. Background Art

[0002] In modern warfare and military operations, mortars, as an important indirect fire support weapon, are widely used to attack enemy hidden targets. However, traditional mortar operations require manual operation of a series of complex steps, including target identification, distance measurement, and angle adjustment, which is not only time-consuming and laborious, but may also expose the operator's position in combat, increasing the risk of casualties. Summary of the invention

[0003] The main purpose of the present invention is to solve the technical problem that the mortaring method of the existing mortar easily exposes the position of the operator and increases the risk of casualties.

[0004] A first aspect of the present invention provides an automatic mortar method, the automatic mortar method comprising: Capturing an image by the image capturing device to obtain first image data, and sending the first image data to the positioning system; The positioning system uses a preset computer recognition algorithm to identify the first image data received to perform a target recognition to obtain a first recognition result; Calculate the first launch coordinates of the mortar target according to the first recognition result and the device information of the image shooting device, and send the first launch coordinates to the mortar device; The mortar device performs a posture adjustment according to the received first launching coordinates, and performs a mortaring operation after the posture adjustment is completed.

[0005] Optionally, in a first implementation manner of the first aspect of the present invention, the image capturing device is a drone or a smart telescope; capturing an image by the image capturing device to obtain first image data, and sending the first image data to the positioning system includes: When the image capturing device is a drone, planning a flight path of the drone, obtaining corresponding flight path data, and controlling the flight of the drone according to the flight path data; When the drone flies according to the flight path data, the drone takes images to obtain first image data, and the first image data is sent to the positioning system. When the image capturing device is an intelligent telescope, in response to a setting operation for the capturing parameters of the intelligent telescope, the capturing parameters of the intelligent telescope are set, and the capturing angle and focal length of the intelligent telescope are adjusted based on the capturing parameters; The first image data is obtained by shooting an image through the smart telescope after adjusting the shooting angle and focal length; In response to an image uploading operation for the smart telescope, the first image data is sent to the positioning system.

[0006] Optionally, in a second implementation of the first aspect of the present invention, the identifying the first image data received by the positioning system using a preset computer recognition algorithm to perform a target identification to obtain a first recognition result includes: Preprocessing the received first image data by the positioning system using a preset computer recognition algorithm to obtain a preprocessed image, and performing edge detection on the preprocessed image to obtain an edge image; Performing initial feature extraction on the edge image to obtain initial image feature data of the edge image, and matching the initial image feature data with a preset striking target feature library to obtain a matching result; Screening candidate objects from the edge image according to the matching results, and performing fine feature analysis on the candidate objects to obtain fine image feature data; The fine image feature data is input into a preset object classification model to obtain a classification result, and it is determined whether there is a target to be hit in the first image data based on the classification result to obtain a first recognition result.

[0007] Optionally, in a third implementation manner of the first aspect of the present invention, calculating the first launch coordinates of the mortar target according to the first recognition result and the device information of the image capturing device, and sending the first launch coordinates to the mortar device includes: Determine the initial coordinate data of the impact target in the first image data according to the first recognition result; According to the device information of the image capturing device, the initial coordinate data is converted into the camera coordinate system of the image capturing device to obtain corresponding coordinates of the camera coordinate system; The camera coordinate system coordinates are converted into a world coordinate system according to the device coordinates of the image capturing device and a preset coordinate system conversion matrix to obtain corresponding world coordinate system coordinates; The environmental information of the image capture device is obtained, and the first launch coordinates of the mortar target are calculated according to the environmental information and the coordinates of the world coordinate system through a preset ballistics model, and the first launch coordinates are sent to the mortar device.

[0008] Optionally, in a fourth implementation manner of the first aspect of the present invention, determining the initial coordinate data of the strike target in the first image data according to the first recognition result includes: Determine the bounding box coordinate information of the hit target in the first image data according to the first recognition result, and calculate the center point according to the bounding box coordinate information to obtain the pixel coordinates of the center point of the hit target; Converting the center point pixel coordinates into normalized image coordinates according to the device information of the image shooting device, and performing depth recognition on the impact target according to the first image data to obtain corresponding depth recognition information; Depth information is added to the normalized image coordinates according to the depth identification information, and error correction is performed on the normalized image coordinates after the depth identification information is added, so as to obtain initial coordinate data of the impact target in the first image data.

[0009] Optionally, in a fifth implementation of the first aspect of the present invention, the step of adjusting the posture of the mortar device according to the received first launch coordinates and performing the mortar operation after the posture adjustment is completed includes: Calculating, by the mortar device, a horizontal distance and a height difference between the mortar target and the mortar device according to the received first launch coordinates; Calculating initial posture information of the mortar device according to the horizontal distance and the height difference, and correcting the initial posture information to obtain target posture information; The mortar equipment performs posture adjustment according to the target posture information, and performs mortaring operation after the posture adjustment is completed.

[0010] Optionally, in a sixth implementation of the first aspect of the present invention, after the mortar device performs posture adjustment according to the received first launch coordinates and performs the mortaring operation after the posture adjustment is completed, it also includes: The image capturing device is used to capture an image of the mortar device after the mortar device completes the mortaring operation, to obtain second image data, and the second image data is sent to the positioning system; The positioning system uses a preset computer recognition algorithm to identify the received second image data again to identify the target, obtain a second recognition result, and determine whether the striking operation is successful according to the second recognition result; If the mortar operation is unsuccessful, calculating the second launch coordinates of the mortar target again according to the second recognition result and the device information of the image shooting device, and sending the second launch coordinates to the mortar device; The mortar equipment adjusts its position again according to the received second launching coordinates, and performs the mortaring operation again.

[0011] A second aspect of the present invention provides an automatic mortar device, which is applied to an automatic mortar system. The automatic mortar system includes an image shooting device, a positioning system and a mortar device. The automatic mortar device includes: A shooting module, used for shooting an image through the image shooting device to obtain first image data, and sending the first image data to the positioning system; An object recognition module, used to identify the first image data received by the positioning system using a preset computer recognition algorithm to perform target recognition to obtain a first recognition result; A coordinate calculation module, used for calculating the first launch coordinates of the mortar target according to the first recognition result and the device information of the image shooting device, and sending the first launch coordinates to the mortar device; The mortar module is used to adjust the position of the mortar device according to the received first launch coordinates, and perform mortar operations after the position adjustment is completed.

[0012] The third aspect of the present invention provides an automatic mortar device, comprising: a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected via a line; the at least one processor calls the instructions in the memory so that the automatic mortar device executes the steps of the above-mentioned automatic mortar method.

[0013] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the above-mentioned automatic mortar method.

[0014] The above-mentioned automatic mortar method, device, equipment and storage medium use an image shooting device to shoot an image, obtain first image data, and send the first image data to the positioning system; use the positioning system to use a preset computer recognition algorithm to identify the received first image data to identify the mortar target and obtain a first recognition result; calculate the first launch coordinates of the mortar target according to the first recognition result and the equipment information of the image shooting device, and send the first launch coordinates to the mortar equipment; adjust the posture according to the received first launch coordinates by the mortar equipment, and perform the mortar operation after the posture adjustment is completed. This method realizes the fully automated operation of the mortar through the collaborative work of the automatic mortar system, reduces manual intervention, improves the combat response speed and strike accuracy, and effectively reduces the risk of casualties of operators.

[0015] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a first embodiment of an automatic mortar method in an embodiment of the present invention; Figure 2 A schematic diagram of an embodiment of an automatic mortar device in an embodiment of the present invention; Figure 3 It is a schematic diagram of an embodiment of the automatic mortar device in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. 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.

[0019] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device end including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or device ends.

[0020] To facilitate understanding of this embodiment, firstly, an automatic mortar method disclosed in an embodiment of the present invention is described in detail. The automatic mortar method is applied to an automatic mortar system, which includes an image capture device, a positioning system and a mortar device. Figure 1 As shown, the method comprises the following steps: 101. Capture an image using an image capturing device to obtain first image data, and send the first image data to a positioning system; In one embodiment of the present invention, the image capturing device is a drone or a smart telescope; capturing images through the image capturing device to obtain first image data, and sending the first image data to the positioning system includes: when the image capturing device is a drone, planning a flight path of the drone, obtaining corresponding flight path data, and controlling the flight of the drone according to the flight path data; when the drone flies according to the flight path data, capturing images through the drone to obtain first image data, and sending the first image data to the positioning system; when the image capturing device is a smart telescope, in response to a setting operation for the shooting parameters of the smart telescope, setting the shooting parameters of the smart telescope, and adjusting the shooting angle and focal length of the smart telescope based on the shooting parameters; capturing images through the smart telescope after adjusting the shooting angle and focal length to obtain first image data; and in response to an image upload operation for the smart telescope, sending the first image data to the positioning system.

[0021] Specifically, first, when the image shooting device is a drone, the flight path of the drone needs to be planned. By analyzing the geographic information of the target area and evaluating the obstacle distribution, the coordinate data of the flight path points are determined, and the corresponding flight path data are generated. The selection of these flight path points needs to ensure that the drone can cover the target area and obtain high-quality image data. Next, the drone is controlled to fly according to the flight path data. The flight control system uses the flight path data as input to adjust the flight attitude and speed of the drone in real time to ensure that the drone flies along the predetermined path. When the drone flies according to the flight path data, the camera on the drone is used to shoot images to obtain the first image data. The image shooting process needs to consider the lighting conditions and shooting angles to ensure that the acquired image data is clear and covers the target area. Subsequently, the first image data is sent to the positioning system through the wireless communication module. The data transmission process needs to be encrypted to ensure the security and integrity of the image data during the transmission process. When the image shooting device is an intelligent telescope, it is first necessary to respond to the shooting parameter setting operation for the intelligent telescope and set the shooting parameters of the intelligent telescope, including the shooting angle, focal length and exposure time. The setting of these parameters can be operated through the control interface of the intelligent telescope. Based on the set shooting parameters, the smart telescope will adjust its shooting angle and focal length to ensure that it can accurately aim at the target area and obtain clear image data. The first image data is obtained by shooting an image with the smart telescope after adjusting the shooting angle and focal length. The image shooting process needs to consider the characteristics of the ambient lighting and the target area to ensure that the acquired image data is clear and accurate. Subsequently, in response to the image upload operation for the smart telescope, the first image data is sent to the positioning system through a wired or wireless communication module. The data transmission process also needs to be encrypted to ensure the security and integrity of the image data.

[0022] 102. Using a preset computer recognition algorithm to identify the received first image data, the positioning system performs target recognition to obtain a first recognition result; In one embodiment of the present invention, the positioning system uses a preset computer recognition algorithm to identify the first image data received as a target to obtain a first recognition result, which includes: the positioning system uses a preset computer recognition algorithm to preprocess the first image data received to obtain a preprocessed image, and performs edge detection on the preprocessed image to obtain an edge image; performs initial feature extraction on the edge image to obtain initial image feature data of the edge image, and matches the initial image feature data with a preset target feature library to obtain a matching result; screens candidate objects from the edge image according to the matching result, and performs fine feature analysis on the candidate objects to obtain fine image feature data; inputs the fine image feature data into a preset object classification model to obtain a classification result, and determines whether there is a target in the first image data according to the classification result to obtain a first recognition result.

[0023] Specifically, first, the image capturing device (such as a drone or a smart telescope) sends the collected first image data to the positioning system. After receiving the image data, the positioning system first performs preprocessing. The purpose of preprocessing is to improve the image quality, remove noise, and prepare for subsequent edge detection and feature extraction. Preprocessing includes image denoising, grayscale, and histogram equalization. Next, edge detection is performed on the preprocessed image to obtain an edge image. Edge detection is to extract the edge of an object by detecting areas with large grayscale changes in the image. Common edge detection algorithms include Sobel, Canny, etc. After obtaining the edge image, initial feature extraction is performed to obtain initial image feature data of the edge image. The purpose of initial feature extraction is to extract data that can describe the characteristics of the target object from the image, such as shape, texture, etc. Various feature extraction algorithms can be used for initial feature extraction, such as SIFT, SURF, etc. The initial image feature data is matched with a preset mortar target feature library to obtain a matching result. Feature matching is to compare the extracted feature data with the data in the feature library and calculate the similarity to determine whether there is a target object. According to the matching results, candidate objects are screened from the edge image, and fine feature analysis is performed on the candidate objects to obtain fine image feature data. Fine feature analysis is to extract more detailed features of the initially screened targets to improve the accuracy of recognition. The fine image feature data is input into a preset object classification model to obtain a classification result. The object classification model is usually obtained by training with a machine learning or deep learning algorithm, and can determine the category of the target object based on the input feature data. Finally, based on the classification result, it is determined whether there is a forced target in the first image data to obtain a first recognition result. The judgment process can be achieved by setting a threshold or using a post-processing algorithm.

[0024] 103. Calculate the first launch coordinates of the mortar target according to the first recognition result and the device information of the image shooting device, and send the first launch coordinates to the mortar device; In one embodiment of the present invention, the calculation of the first launch coordinates of the mortar target according to the first recognition result and the equipment information of the image capturing device, and sending the first launch coordinates to the mortar device includes: determining the initial coordinate data of the mortar target in the first image data according to the first recognition result; converting the initial coordinate data to the camera coordinate system of the image capturing device according to the equipment information of the image capturing device to obtain corresponding camera coordinate system coordinates; converting the camera coordinate system coordinates to the world coordinate system according to the equipment coordinates of the image capturing device and a preset coordinate system conversion matrix to obtain corresponding world coordinate system coordinates; acquiring the environmental information of the image capturing device, and calculating the first launch coordinates of the mortar target according to the environmental information and the world coordinate system coordinates through a preset ballistics model, and sending the first launch coordinates to the mortar device.

[0025] Specifically, first, the initial coordinate data of the target in the first image data is determined according to the first recognition result. The initial coordinate data can be expressed as the pixel coordinates in the image: ,These coordinate data are the positioning results of the target in the image based on the computer recognition algorithm. Next, according to the device information of the image shooting device, the initial coordinate data is converted to the camera coordinate system of the image shooting device. The device information of the image shooting device includes the location of the device and attitude (pitch angle , Roll Angle , yaw angle ). Initial coordinate data After the internal parameters of the device (focal length and the principal point coordinates ) is converted to normalized image coordinates The formula is as follows: ; By normalizing the image coordinates and depth information , we can get the coordinates in the camera coordinate system : ; Then, the coordinates in the camera coordinate system are converted to the world coordinate system. Through the coordinates in the camera coordinate system Combined with the location of the device get: ; ; ; After obtaining the coordinates in the world coordinate system, the next step is to obtain the environmental information of the image capture device and calculate the first launch coordinates of the mortar target based on the environmental information and the world coordinate system coordinates through the preset ballistics model. Environmental information includes wind speed ,wind direction and air density The ballistics model can be described as a system that includes the initial velocity , Emission Angle and the acceleration due to gravity The equation is used to calculate the flight trajectory of the projectile. Assume that the launch coordinates are , can be calculated by the following formula: ; in, is the flight time, is the drag coefficient, is the cross-sectional area, is the mass of the shell. In addition, the launch coordinates can also be calculated by other means, which is not limited in this embodiment. The calculated first launch coordinates are sent to the mortar device through the wireless communication module. During the sending process, data encryption processing is required to ensure the security and integrity of the launch coordinates during the transmission process. Data encryption can be processed using a symmetric encryption algorithm (such as AES) or an asymmetric encryption algorithm (such as RSA).

[0026] Furthermore, the determining of the initial coordinate data of the impact target in the first image data according to the first recognition result includes: determining the bounding box coordinate information of the impact target in the first image data according to the first recognition result, and performing center point calculation according to the bounding box coordinate information to obtain the center point pixel coordinates of the impact target; converting the center point pixel coordinates into normalized image coordinates according to the device information of the image capture device, and performing depth recognition on the impact target according to the first image data to obtain corresponding depth recognition information; performing depth information addition processing on the normalized image coordinates according to the depth recognition information, and performing error correction on the normalized image coordinates after the depth recognition information is added to obtain the initial coordinate data of the impact target in the first image data.

[0027] Specifically, first, the bounding box coordinate information of the target in the first image data is determined according to the first recognition result. The bounding box coordinate information generally includes the coordinates of the upper left corner and the lower right corner of the bounding box. Through these coordinate information, the pixel coordinates of the center point of the bounding box can be calculated. After the pixel coordinates of the center point are calculated, they need to be converted into normalized image coordinates. The calculation of normalized image coordinates requires the internal reference parameters of the image shooting device. Next, the depth recognition of the target is performed to obtain the corresponding depth recognition information. For the image data taken by the drone, the front and back image data can be used for depth recognition. This method is usually based on the principle of stereo vision. For the image data taken by the smart telescope, since it is usually a fixed single-view image, other methods need to be used for depth recognition, usually using a laser rangefinder or other depth sensor. However, there may be certain errors in the coordinates obtained by direct use of the preliminary calculation, so error correction is required. Error correction can be performed by averaging multiple measurement data or by sensor fusion. Assume that sensor fusion is used for error correction.

[0028] 104. Performing a posture adjustment according to the received first launching coordinates through the mortar equipment, and performing a mortar operation after the posture adjustment is completed.

[0029] In one embodiment of the present invention, the mortar device performs a posture adjustment according to the received first launch coordinates, and performs a mortar operation after the posture adjustment is completed, including: calculating the horizontal distance and the height difference between the mortar target and the mortar device according to the received first launch coordinates by the mortar device; calculating the initial posture information of the mortar device according to the horizontal distance and the height difference, and correcting the initial posture information to obtain target posture information; the mortar device performs a posture adjustment according to the target posture information, and performs a mortar operation after the posture adjustment is completed.

[0030] Specifically, first, when the mortar device receives the first launch coordinate After that, the first step is to calculate the horizontal distance and height difference between the mortar target and the mortar equipment. Assume that the current position coordinates of the mortar equipment are , horizontal distance and height difference The calculation formula is as follows: ; Getting the horizontal distance and height difference After that, we need to calculate the initial position information of the mortar equipment based on these data. The initial position information includes the launch angle and elevation , used to adjust the direction and inclination of the mortar equipment. Assume that the initial launch angle of the mortar equipment is , the elevation angle is ,The calculation formula of the initial pose information is as follows: ; However, directly using the initial pose information may result in certain errors, so correction is required to obtain more accurate target pose information. The correction process usually needs to take into account environmental factors, such as wind speed. and wind direction By adjusting the horizontal rotation angle and elevation angle, the actual posture of the mortar device is matched with the target posture. After the posture adjustment is completed, the mortar device performs mortaring operations according to the adjusted posture, fires shells and completes the attack. In addition, the posture adjustment can also be performed in other ways, which are not limited in this embodiment.

[0031] Furthermore, after the mortar device performs a posture adjustment according to the received first launching coordinates and performs the mortaring operation after the posture adjustment is completed, it also includes: performing an image capture by the image capture device after the mortar device completes the mortaring operation to obtain second image data, and sending the second image data to the positioning system; using a preset computer recognition algorithm by the positioning system to identify the received second image data again to identify the mortar target, obtain a second recognition result, and determine whether the mortaring operation is successful based on the second recognition result; if the mortaring operation is unsuccessful, calculating the second launching coordinates of the mortar target again based on the second recognition result and the device information of the image capture device, and sending the second launching coordinates to the mortar device; performing a posture adjustment by the mortar device again based on the received second launching coordinates, and performing the mortaring operation again.

[0032] Specifically, in military operations, ensuring the complete destruction of the target is the key. The first mortar operation may fail to completely destroy the target due to a variety of reasons, including changes in the target's position, mortar shooting errors, and interference from environmental factors. If the target is not completely destroyed, the enemy may quickly recover or reuse the target, which will pose a serious threat to the success of the mission. Therefore, the purpose of the second mortar operation is to ensure the complete destruction of the target and avoid enemy counterattacks and reuse. In addition, the image data after the first mortar operation can provide important feedback on the actual damage to the target. These data can be used to analyze the accuracy of the first operation. If the first operation fails to accurately hit the key parts of the target, it may be necessary to adjust the launch coordinates and the firing angle again to ensure the accuracy and effectiveness of the second operation. Accurate operations can not only increase the probability of mission success, but also reduce ammunition waste and operation time. In addition, environmental factors such as wind speed, wind direction, temperature, and air pressure will affect the flight trajectory of the projectile. After the first mortar operation, the environmental conditions may have changed, and these changes will affect the effectiveness of the second operation. Through the second mortar, the launch parameters can be adjusted according to the latest environmental information to ensure that the projectile can accurately hit the target. In addition, the enemy may take countermeasures, change the location of the target or deploy new defenses, and re-mortaring can help cope with these changes. Multiple mortars can improve the effectiveness of the operation. The results of the first mortar operation can be used as data input to optimize the strategy and parameter settings of the second operation. Through continuous feedback and adjustment, the hit rate and killing effect of the operation can be gradually improved. For example, if the target is not destroyed after the first operation, the second operation can focus on the key weaknesses of the target, thereby increasing the probability of destroying the target. Such a circular feedback mechanism helps to optimize the mortar strategy and improve the success rate of the overall operation. In actual military operations, tactical requirements may require multiple mortar operations. For example, in order to ensure the complete clearance of a certain area, it may be necessary to carry out continuous strikes on multiple targets, or to carry out multiple strikes on the same target to ensure that it completely loses its combat effectiveness. In addition, multiple mortars can also create continuous threat pressure, making it difficult for the enemy to recover and counterattack. The process of the second mortar is essentially similar to that of the first mortar, and if the mortar target is still not destroyed after the second mortar, continuous mortar operations will be carried out until the mortar target is destroyed.

[0033] In this embodiment, an image is captured by an image capturing device to obtain first image data, and the first image data is sent to a positioning system; the positioning system uses a preset computer recognition algorithm to identify the received first image data to identify the mortar target, and obtains a first recognition result; the first launch coordinates of the mortar target are calculated according to the first recognition result and the device information of the image capturing device, and the first launch coordinates are sent to the mortar device; the mortar device performs posture adjustment according to the received first launch coordinates, and performs the mortar operation after the posture adjustment is completed. This method realizes the fully automated operation of the mortar through the collaborative work of the automatic mortar system, reduces manual intervention, improves the combat response speed and strike accuracy, and effectively reduces the risk of casualties of operators.

[0034] The automatic mortar method in the embodiment of the present invention is described above. The automatic mortar device in the embodiment of the present invention is described below. The automatic mortar device is applied to the automatic mortar system. The automatic mortar system includes an image shooting device, a positioning system and a mortar device. Figure 2 , an embodiment of the automatic mortar device in the embodiment of the present invention includes: A shooting module 201 is used to shoot an image through the image shooting device to obtain first image data, and send the first image data to the positioning system; The object recognition module 202 is used to identify the target of the first image data received by the positioning system using a preset computer recognition algorithm to obtain a first recognition result; A coordinate calculation module 203, configured to calculate a first launch coordinate of the mortar target according to the first recognition result and the device information of the image shooting device, and send the first launch coordinate to the mortar device; The mortar module 204 is used to adjust the position of the mortar device according to the received first launch coordinates, and perform a mortar operation after the position adjustment is completed.

[0035] In an embodiment of the present invention, the automatic mortar device runs the above-mentioned automatic mortar method, the automatic mortar device performs image capture through an image capture device to obtain first image data, and sends the first image data to a positioning system; the positioning system uses a preset computer recognition algorithm to identify the received first image data to perform mortar target recognition to obtain a first recognition result; the first launch coordinates of the mortar target are calculated according to the first recognition result and the device information of the image capture device, and the first launch coordinates are sent to the mortar device; the mortar device performs posture adjustment according to the received first launch coordinates, and performs mortaring after the posture adjustment is completed. This method realizes the fully automated operation of the mortar through the collaborative work of the automatic mortar system, reduces manual intervention, improves combat response speed and strike accuracy, and effectively reduces the risk of casualties of operators.

[0036] above Figure 2 The automatic mortar device in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the automatic mortar device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0037] Figure 3 3 is a schematic diagram of the structure of an automatic mortar device provided by an embodiment of the present invention. The automatic mortar device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (for example, one or more processors) and a memory 320, and one or more storage media 330 (for example, one or more mass storage device terminals) storing application programs 333 or data 332. Among them, the memory 320 and the storage medium 330 may be temporary storage or permanent storage. The program stored in the storage medium 330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the automatic mortar device 300. Furthermore, the processor 310 may be configured to communicate with the storage medium 330, and execute a series of instruction operations in the storage medium 330 on the automatic mortar device 300 to implement the steps of the above-mentioned automatic mortar method.

[0038] The automatic mortar device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 3The structure of the automatic mortar device shown does not constitute a limitation on the automatic mortar device provided by the present invention, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0039] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium, and when the instructions are executed on a computer, the computer executes the steps of the automatic mortar method.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0041] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0042] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic mortar method, characterized in that: The automatic mortaring method is applied to an automatic mortaring system, which includes an image shooting device, a positioning system and a mortaring device. The automatic mortaring method includes: Capturing an image by the image capturing device to obtain first image data, and sending the first image data to the positioning system; The positioning system uses a preset computer recognition algorithm to identify the first image data received to perform a target recognition to obtain a first recognition result; Calculate the first launch coordinates of the mortar target according to the first recognition result and the device information of the image shooting device, and send the first launch coordinates to the mortar device; The mortar device performs a posture adjustment according to the received first launching coordinates, and performs a mortaring operation after the posture adjustment is completed.

2. The automatic mortar method according to claim 1, characterized in that: The image shooting device is a drone or a smart telescope; the image shooting is performed by the image shooting device to obtain first image data, and the first image data is sent to the positioning system, including: When the image capturing device is a drone, planning a flight path of the drone, obtaining corresponding flight path data, and controlling the flight of the drone according to the flight path data; When the drone flies according to the flight path data, the drone takes images to obtain first image data, and the first image data is sent to the positioning system. When the image capturing device is an intelligent telescope, in response to a setting operation for the capturing parameters of the intelligent telescope, the capturing parameters of the intelligent telescope are set, and the capturing angle and focal length of the intelligent telescope are adjusted based on the capturing parameters; The first image data is obtained by shooting an image through the smart telescope after adjusting the shooting angle and focal length; In response to an image uploading operation for the smart telescope, the first image data is sent to the positioning system.

3. The automatic mortar method according to claim 1, characterized in that: The method of using a preset computer recognition algorithm to identify the first image data received by the positioning system to identify the target and obtain a first recognition result includes: Preprocessing the received first image data by the positioning system using a preset computer recognition algorithm to obtain a preprocessed image, and performing edge detection on the preprocessed image to obtain an edge image; Performing initial feature extraction on the edge image to obtain initial image feature data of the edge image, and matching the initial image feature data with a preset striking target feature library to obtain a matching result; Screening candidate objects from the edge image according to the matching results, and performing fine feature analysis on the candidate objects to obtain fine image feature data; The fine image feature data is input into a preset object classification model to obtain a classification result, and it is determined whether there is a target to be hit in the first image data based on the classification result to obtain a first recognition result.

4. The automatic mortar method according to claim 1, characterized in that: The calculating the first launch coordinates of the mortar target according to the first recognition result and the device information of the image shooting device, and sending the first launch coordinates to the mortar device comprises: Determine the initial coordinate data of the impact target in the first image data according to the first recognition result; According to the device information of the image capturing device, the initial coordinate data is converted into the camera coordinate system of the image capturing device to obtain corresponding coordinates of the camera coordinate system; The camera coordinate system coordinates are converted into a world coordinate system according to the device coordinates of the image capturing device and a preset coordinate system conversion matrix to obtain corresponding world coordinate system coordinates; The environmental information of the image capture device is obtained, and the first launch coordinates of the mortar target are calculated according to the environmental information and the coordinates of the world coordinate system through a preset ballistics model, and the first launch coordinates are sent to the mortar device.

5. The automatic mortar method according to claim 4, characterized in that: The determining of the initial coordinate data of the impact target in the first image data according to the first recognition result includes: Determine the bounding box coordinate information of the hit target in the first image data according to the first recognition result, and calculate the center point according to the bounding box coordinate information to obtain the pixel coordinates of the center point of the hit target; Converting the center point pixel coordinates into normalized image coordinates according to the device information of the image shooting device, and performing depth recognition on the impact target according to the first image data to obtain corresponding depth recognition information; Depth information is added to the normalized image coordinates according to the depth identification information, and error correction is performed on the normalized image coordinates after the depth identification information is added, so as to obtain initial coordinate data of the impact target in the first image data.

6. The automatic mortar method according to claim 1, characterized in that: The step of adjusting the posture of the mortar device according to the received first launch coordinates and performing the mortar operation after the posture adjustment is completed includes: Calculating, by the mortar device, a horizontal distance and a height difference between the mortar target and the mortar device according to the received first launch coordinates; Calculating initial posture information of the mortar device according to the horizontal distance and the height difference, and correcting the initial posture information to obtain target posture information; The mortar equipment performs posture adjustment according to the target posture information, and performs mortaring operation after the posture adjustment is completed.

7. The automatic mortar method according to claim 1, characterized in that: After the mortar device performs posture adjustment according to the received first launch coordinates and performs the mortaring operation after the posture adjustment is completed, the method further includes: The image capturing device is used to capture an image of the mortar device after the mortar device completes the mortaring operation, to obtain second image data, and the second image data is sent to the positioning system; The positioning system uses a preset computer recognition algorithm to identify the received second image data again to identify the target, obtain a second recognition result, and determine whether the striking operation is successful according to the second recognition result; If the mortar operation is unsuccessful, calculating the second launch coordinates of the mortar target again according to the second recognition result and the device information of the image shooting device, and sending the second launch coordinates to the mortar device; The mortar equipment adjusts its position again according to the received second launching coordinates, and performs the mortaring operation again.

8. An automatic mortar device, characterized in that: The automatic mortar device is applied to an automatic mortar system, which includes an image shooting device, a positioning system and a mortar device. The automatic mortar device includes: A shooting module, used for shooting an image through the image shooting device to obtain first image data, and sending the first image data to the positioning system; An object recognition module, used to identify the first image data received by the positioning system using a preset computer recognition algorithm to perform target recognition to obtain a first recognition result; A coordinate calculation module, used for calculating the first launch coordinates of the mortar target according to the first recognition result and the device information of the image shooting device, and sending the first launch coordinates to the mortar device; The mortar module is used to adjust the position of the mortar device according to the received first launch coordinates, and perform mortar operations after the position adjustment is completed.

9. An automatic mortar device, characterized in that: The automatic mortar device comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the automatic mortar device to perform the steps of the automatic mortar method according to any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the steps of the automatic striking method as described in any one of claims 1-7 are implemented.

Images