Automatic identification method and system for projectile body head shape factor

Abstract

The invention discloses an automatic identification method and system for a projectile body head shape factor, and belongs to the technical field of image processing and target detection, and the method comprises the steps: obtaining a projectile body penetration image; performing semantic segmentation on the projectile body penetration image by using a preset image segmentation model to obtain a projectile body binary mask; carrying out projectile body contour detection on the projectile body binary mask by adopting a preset contour detection algorithm, and obtaining a projectile body outer contour pixel point set based on a projectile body contour detection result; based on the projectile body outer contour pixel point set, a projectile body head shape area contour point set is extracted; fitting a projectile body head shape curve based on the projectile body head shape area contour point set; and calculating a projectile body head shape factor based on the projectile body head shape curve. By adopting the technical scheme of the invention, efficient, accurate and automatic extraction of the geometric features of the projectile body head shape can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing and target detection, and in particular to a method and system for automatically identifying a projectile head form factor. Background Art

[0002] The projectile head shape factor is an important characteristic parameter that measures the sharpness of the projectile head shape in high-speed penetration models. Its efficient and high-precision intelligent identification and extraction are of great research significance. In application scenarios such as armor-piercing projectiles and high-speed aircraft, slight changes in the head shape factor can have a significant impact on penetration depth and attitude stability. Therefore, its high-precision and high-efficiency automated identification has become a key technical challenge in projectile intelligent modeling and evaluation. Currently, the identification and extraction of projectile head shape factors mainly rely on manual intervention. Common methods include manually annotating the projectile contour in the image, auxiliary geometric fitting, and calculating the corresponding parameters accordingly.

[0003] This type of traditional method is not only labor-intensive, but also limited by the subjective judgment of the operator, which can easily lead to poor repeatability of the results. In addition, during the polynomial fitting process, the order selection and parameter adjustment lack stability control, which can easily lead to problems such as large fluctuations in fitting accuracy and poor stability, affecting the reliability of the recognition results. At the same time, when dealing with actual working conditions with complex backgrounds, low image contrast, or drastic changes in the missile posture, traditional manual or rule-based algorithms are insufficient in robustness and adaptability, and are easily affected by noise interference, uneven lighting, or occlusion factors, resulting in recognition failure or large errors. In addition, this type of method is usually unable to seamlessly connect with subsequent geometric modeling and numerical analysis processes, making it difficult to support high-throughput processing of large numbers of missile images, and difficult to meet the current needs of intelligent and automated development. Summary of the Invention

[0004] The present invention provides a method and system for automatically identifying the projectile head form factor to solve the technical problems that the existing projectile head form factor identification and extraction schemes are not only labor-intensive but also limited by the subjective judgment of the operator, which easily leads to poor repeatability of the results and poor reliability of the identification results. It is difficult to support high-throughput processing of a large number of projectile images and is difficult to meet the current needs of intelligent and automated development.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In one aspect, the present invention provides a method for automatically identifying a projectile head form factor, comprising:

[0007] Acquire projectile penetration images;

[0008] The projectile penetration image is semantically segmented using a preset image segmentation model to obtain a binary mask image of the projectile.

[0009] The projectile body contour is detected on the binary mask image of the projectile body using a preset contour detection algorithm, and a pixel point set of the projectile body contour is obtained based on the projectile body contour detection result;

[0010] Based on the pixel point set of the projectile's outer contour, the contour point set of the projectile's head shape area is extracted;

[0011] The projectile head shape curve is fitted based on the projectile head shape area contour point set;

[0012] Based on the projectile head shape curve, calculate the projectile head shape factor.

[0013] Furthermore, the image segmentation model has an adaptive strategy, which can adaptively select the optimal segmentation strategy according to the image texture complexity, texture background or target clarity, thereby automatically extracting the projectile area and generating a binary mask image of the projectile.

[0014] Furthermore, the contour detection algorithm is an edge detection algorithm based on image structure information and region connectivity judgment.

[0015] Furthermore, a preset contour detection algorithm is used to perform contour detection on the binary mask image of the projectile. Based on the contour detection result of the projectile, a pixel point set of the projectile outer contour is obtained, including:

[0016] The preset contour detection algorithm is used to detect the projectile contour on the binary mask image of the projectile, and the detected projectile contour coordinates are mapped to the original image for visual display;

[0017] Based on the visualization display results, a contour matching scoring mechanism is introduced to quantitatively evaluate the degree of overlap between the extracted projectile contour and the actual projectile contour to verify the contour extraction accuracy, forming a closed-loop mechanism from image semantic segmentation to contour geometry restoration to accuracy feedback to obtain the pixel point set of the projectile's outer contour.

[0018] Furthermore, based on the projectile outer contour pixel point set, the projectile head shape area contour point set is extracted, including:

[0019] The projectile image is uniformly set to face downward in the coordinate system;

[0020] Find the point with the largest Y coordinate value in the image coordinate system among the pixel points of the projectile's outer contour as the starting point of the projectile head shape area;

[0021] Starting from the starting point, traverse along the direction of the contour point sequence; during the traversal process, the tangent direction changes, curvature distribution changes and polynomial fitting errors between consecutive contour points are analyzed in real time. When the tangent direction change is greater than the preset direction change threshold, the curvature distribution change is greater than the preset curvature distribution change threshold or the polynomial fitting error is greater than the preset error threshold, the current point is automatically determined to be the end point of the projectile head shape area, thereby realizing the adaptive closed extraction of the edge segment of the projectile head shape area.

[0022] Furthermore, a projectile head shape curve is fitted based on the projectile head shape area contour point set, including:

[0023] Based on the contour point set of the projectile head shape area, an adaptive polynomial fitting model is used to build a model and fit the projectile head shape curve; wherein, the adaptive polynomial fitting model automatically searches for fitting schemes of different orders under the minimum mean square error criterion through an objective function optimization algorithm, and determines the optimal order and fitting coefficient according to the mean square error threshold; and the adaptive polynomial fitting model supports the use of segmented fitting and splicing strategies.

[0024] Furthermore, the fitting expression of the projectile head shape curve is:

[0025] y=-0.00165x 2 +0.53477x+315.6507

[0026] Wherein, y represents the ordinate of the point where the contour points of the projectile head shape area are concentrated; x represents the abscissa of the point where the contour points of the projectile head shape area are concentrated.

[0027] Furthermore, based on the projectile head shape curve, the projectile head shape factor is calculated, including:

[0028] Based on the projectile head shape curve, the geometric characteristic parameters required for calculating the projectile head shape factor are extracted;

[0029] Based on the extracted geometric feature parameters, the preset physical calculation formula of the projectile head shape factor is used to automatically complete the quantitative calculation of the projectile head shape factor at the current stage and output the calculation results; the physical calculation formula is:

[0030]

[0031] Among them, N * represents the head shape factor; R represents half of the maximum width of the bullet in the x direction; y ′ represents the first-order derivative of y; h represents the length of the projectile along the y direction; y represents the ordinate of the point where the contour points of the projectile head shape area are concentrated; x represents the abscissa of the point where the contour points of the projectile head shape area are concentrated.

[0032] On the other hand, the present invention also provides a projectile head form factor automatic identification system, comprising:

[0033] Image input module, used to obtain projectile penetration images;

[0034] An image segmentation model is used to perform semantic segmentation on the projectile penetration image using a preset image segmentation model to obtain a binary mask image of the projectile;

[0035] Contour extraction module for:

[0036] The projectile body contour is detected on the binary mask image of the projectile body using a preset contour detection algorithm, and a pixel point set of the projectile body contour is obtained based on the projectile body contour detection result;

[0037] Based on the pixel point set of the projectile's outer contour, the contour point set of the projectile's head shape area is extracted;

[0038] A fitting modeling module is used to fit the projectile head shape curve based on the projectile head shape area contour point set;

[0039] The head shape factor calculation module is used to calculate the projectile head shape factor based on the projectile head shape curve.

[0040] Furthermore, the system also includes a result visualization display and export module for visually displaying and exporting the calculation results of the projectile head form factor.

[0041] On the other hand, the present invention further provides an electronic device, comprising a processor and a memory; wherein the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the above method.

[0042] In yet another aspect, the present invention further provides a computer-readable storage medium, wherein the storage medium stores at least one instruction, and the instruction is loaded and executed by a processor to implement the above method.

[0043] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0044] The present invention achieves high-precision segmentation and contour extraction of the projectile head shape region by introducing a visual segmentation model and edge detection technology. Combined with an automatic closed region recognition method based on regional connectivity and geometric topology constraints, it can quickly lock onto the target head shape region without manual intervention, improving processing efficiency and recognition stability. An adaptive polynomial fitting model, combined with an objective function optimization algorithm, dynamically determines the optimal fitting order and parameter configuration to achieve precise modeling of complex contours. The system as a whole adopts a modular architecture design and an automatic process control mechanism, with each functional unit operating collaboratively to automate the entire process from image import to head shape factor output, enabling efficient, accurate, and automated extraction of projectile head shape geometric features. A visual interface and result verification mechanism are also included to enhance the system's transparency and controllability. Compared to traditional methods that rely on manual analysis, the present invention boasts higher recognition accuracy, adaptability, and automation, making it suitable for projectile head shape structure assessment tasks under complex working conditions. It has significant application value and technological advancement. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 is a flow chart of a method for automatically identifying a projectile head form factor provided by an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of the projectile head shape provided by an embodiment of the present invention;

[0048] Figure 3 This is a system block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0050] First, it should be noted that in the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplarily" is intended to present concepts in a concrete manner. In addition, in the embodiments of the present invention, the meaning of "and / or" can be both or either of the two.

[0051] First embodiment

[0052] This embodiment provides a method for automatically identifying the projectile head form factor, which can be implemented by an electronic device. The execution process of the method is as follows: Figure 1 As shown in the figure, by integrating visual segmentation, contour extraction, polynomial curve fitting optimization and other technologies, efficient, accurate and automatic extraction of the geometric features of the projectile head shape is achieved.

[0053] Specifically, the projectile head form factor automatic identification method includes the following steps:

[0054] S1, obtain the projectile penetration image;

[0055] It should be noted that, in this embodiment, the image data obtained of the projectile during the penetration process can be derived from the projectile penetration cloud map generated by finite element simulation, or from dynamic images captured by a high-speed camera in an actual projectile penetration experiment. This embodiment does not make any specific limitations on this.

[0056] S2, using a preset image segmentation model to perform semantic segmentation on the projectile penetration image to obtain a binary mask image of the projectile;

[0057] It should be noted that in this embodiment, the image segmentation model is a pre-trained large visual segmentation model (such as SAM or its variants), or a customized deep learning image segmentation network is used to perform semantic-level segmentation on the image. The model has an adaptive strategy, general semantic perception capabilities or specialized training capabilities for projectile structural features. It can adaptively select the optimal segmentation strategy based on conditions such as image texture complexity, texture background, or target clarity, thereby automatically and effectively extracting the projectile area and generating a high-quality binary mask image. This effectively suppresses complex background interference and improves the robustness and versatility of mask segmentation.

[0058] S3, using a preset contour detection algorithm to perform projectile contour detection on the binary mask image of the projectile, and obtaining a projectile outer contour pixel point set based on the projectile contour detection result;

[0059] It should be noted that the contour detection algorithm used in S3 above can be any existing contour detection algorithm. Specifically, in this embodiment, the contour detection algorithm is an edge detection algorithm based on image structure information and regional connectivity judgment. This algorithm combines the pixel gradient directional consistency, pixel density distribution, regional connectivity, and edge closure criteria to effectively identify the continuous structure of contour curves in high curvature or low-contrast backgrounds, thereby enabling stable contour extraction in complex backgrounds or high-curvature boundaries.

[0060] The specific implementation process is as follows: the system automatically extracts pixel points from the projectile's outer contour and maps their coordinates onto the original image for visualization. To improve recognition accuracy, the system introduces a contour matching scoring mechanism that quantitatively evaluates the degree of overlap between the extracted contour and the actual target contour, assisting users in quickly verifying contour accuracy. The mapped contour is automatically overlaid on the original image and supports intelligent visualization of the contour matching score, forming a closed-loop mechanism from image semantic segmentation to contour geometric restoration and accuracy feedback. This improves the robustness and integrity of contour extraction.

[0061] S4, extracting the contour point set of the projectile head area based on the projectile outer contour pixel point set;

[0062] It should be noted that, in this embodiment, the initial reference point of the projectile head-shaped area is to uniformly set the projectile image in the coordinate system as head-down, and to use the point corresponding to the maximum value of the Y-axis coordinate as the starting point of the projectile head-shaped area; Figure 2 As shown, the tip of the projectile head is facing downward. In the image coordinate system, the contour point corresponding to the maximum Y-axis coordinate is used as the starting point of the projectile head area. Based on the left-right symmetric structure of the projectile, only the right side contour is selected for analysis, and the continuous contour segment starting from the starting point on this side is intercepted as the candidate boundary of the head area.

[0063] Based on the above, the process of extracting the contour point set of the projectile head shape area in this embodiment is as follows:

[0064] The system automatically searches for the point with the largest Y coordinate value in the image coordinate system within the contour point set as the starting point of the projectile head shape region, and traverses the contour point sequence in the direction (e.g., counterclockwise). During the traversal process, the system analyzes in real time the changes in tangent direction, curvature distribution characteristics, and polynomial fitting errors between consecutive contour points. When a sudden change in tangent direction occurs or the fitting residual exceeds a set threshold, the system automatically determines the current point as the end point of the projectile head shape region. This enables adaptive closed extraction of the projectile head edge segment, avoids manually setting boundaries or template matching, significantly enhances the system's adaptability to different projectile structures, and improves the algorithm's universality and robustness.

[0065] S5, fitting the projectile head shape curve based on the projectile head shape area contour point set;

[0066] It should be noted that the algorithm model for fitting the projectile head shape curve based on the projectile head shape area contour point set in the above S5 can be any existing fitting model algorithm. Specifically, in this embodiment, the head shape area contour point set extracted in the above step is accurately modeled using an adaptive polynomial fitting model. The adaptive polynomial fitting model introduces a target optimization algorithm, which automatically searches for fitting schemes of different orders under the minimum mean square error criterion through the objective function optimization algorithm, and determines the optimal order and fitting coefficient of the fitting polynomial according to the fitting error threshold, ensuring that the modeling has good computational efficiency and generalization ability while meeting the accuracy requirements; the curve fitting expression in this embodiment is shown in formula (1). In addition, for complex contour areas, the model supports the use of segmented fitting and splicing strategies, so as to use segmented fitting in combination with the boundary splicing algorithm to continuously and accurately model the complex contour areas. Ensure the continuity and physical consistency of the fitting curve, while improving the overall modeling accuracy and efficiency.

[0067] y=f(x)=-0.00165x 2 +0.53477x+315.6507 (1)

[0068] Where y represents the ordinate of the point where the projectile head shape contour points are concentrated, and x represents the abscissa of the point where the projectile head shape contour points are concentrated. This curve shows the change curve of the projectile head shape 1 / 2 area in the xy two-dimensional coordinate system.

[0069] S6, calculate the projectile head shape factor based on the projectile head shape curve;

[0070] It should be noted that, in this embodiment, the implementation process of the above S6 is as follows:

[0071] Based on the fitted curve model, representative geometric feature parameters are automatically extracted. Combined with the physical calculation formula for the projectile head shape factor, the quantitative calculation of the projectile head shape factor at the current stage is automatically completed, and parameter results that can be used for subsequent analysis, evaluation, or structural optimization are output. The head shape factor calculation formula is shown in (2). This calculation process supports parameterized configuration, template definition, and result visualization, and is applicable to various projectile structures and application scenarios.

[0072]

[0073] Among them, N * It represents the head shape factor, which shows consistency in reflecting the sharpness of the projectile head shape; R represents half of the maximum width of the projectile in the x direction; y ′ Represents the first derivative of the y function; h represents the length of the projectile along the y direction; y represents the ordinate of the point where the contour points of the projectile head shape area are concentrated; x represents the abscissa of the point where the contour points of the projectile head shape area are concentrated.

[0074] By encapsulating all the above steps into a unified recognition system framework and adopting modular design and automated control processes, we can achieve full-process automatic recognition from image import, mask segmentation, contour extraction, structure modeling, to factor output without human intervention, with high precision, high reliability and high adaptability.

[0075] In summary, this embodiment establishes a full-process recognition solution from image input to parameter output, integrating technologies such as visual segmentation, contour extraction, and polynomial curve fitting optimization. This solution balances recognition accuracy, processing efficiency, stability, and system adaptability, establishing an intelligent closed-loop recognition framework from image input to head shape factor output. This framework provides technical support for tasks such as projectile structure modeling, trajectory analysis, and damage prediction, enabling efficient, accurate, and automated extraction of projectile head shape geometric features. This solution is suitable for projectile head shape factor identification and assessment tasks under complex operating conditions, possessing significant engineering promotion value and technological leadership.

[0076] Second embodiment

[0077] This embodiment provides a projectile head form factor automatic recognition system. The projectile head form factor automatic recognition system adopts a modular design and includes the following modules:

[0078] Image input module, used to obtain projectile penetration images;

[0079] An image segmentation model is used to perform semantic segmentation on the projectile penetration image using a preset image segmentation model to obtain a binary mask image of the projectile;

[0080] Contour extraction module for:

[0081] The projectile body contour is detected on the binary mask image of the projectile body using a preset contour detection algorithm, and a pixel point set of the projectile body contour is obtained based on the projectile body contour detection result;

[0082] Based on the pixel point set of the projectile's outer contour, the contour point set of the projectile's head shape area is extracted;

[0083] A fitting modeling module is used to fit the projectile head shape curve based on the projectile head shape area contour point set;

[0084] A head shape factor calculation module is used to calculate the projectile head shape factor based on the projectile head shape curve;

[0085] The result visualization and export module is used to visualize and export the calculation results of the projectile head shape factor.

[0086] This embodiment integrates the aforementioned functional modules into a unified software system platform, employing a modular design and automated process control mechanisms to sequentially complete the entire process of image import, segmentation and recognition, contour extraction, structural modeling, and factor output. The system supports automated process control and visual display and export of results. It boasts high precision, stability, and adaptability, enabling automated identification of projectile head form factors without manual intervention, significantly improving engineering analysis efficiency.

[0087] It should be noted that the projectile head form factor automatic identification system of this embodiment corresponds to the projectile head form factor automatic identification method of the above-mentioned first embodiment; the functions implemented by each functional module in the projectile head form factor automatic identification system of this embodiment correspond one-to-one to each process step in the projectile head form factor automatic identification method of the above-mentioned first embodiment; therefore, they will not be repeated here.

[0088] Third embodiment

[0089] This embodiment provides an electronic device, such as Figure 3 As shown, the electronic device includes: a processor and a memory; wherein the processor and the memory can be connected via a communication bus; the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment described above. In addition, the electronic device may also include a transceiver; the processor and the transceiver can be connected via a communication bus, and the transceiver is used to communicate with other devices.

[0090] Next, combine Figure 3 A detailed introduction to the various components of the electronic device is given below:

[0091] Among them, the processor is the control center of the electronic device, and the electronic device may include multiple processors, each of which may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here can be a processor or a general term for multiple processing elements. For example, the processor is one or more central processing units (CPUs), or other general-purpose processors, application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement an embodiment of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor can perform various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0092] In a specific implementation, as an embodiment, the processor may include one or more CPUs, such as Figure 3 The CPU0 and CPU1 shown in FIG are, of course, only exemplary.

[0093] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0094] Optionally, the memory may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and accessed through the interface circuit ( Figure 3 (not shown) is coupled to the processor, which is not specifically limited in this embodiment of the present invention.

[0095] The transceiver may include a receiver and a transmitter ( Figure 3 The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function. The transceiver can be integrated with the processor or exist independently and communicate with the electronic device through the interface circuit ( Figure 3 (not shown) is coupled to the processor, which is not specifically limited in this embodiment of the present invention.

[0096] In addition, it should be noted that Figure 3 The structure of the electronic device shown in the figure does not constitute a limitation on the device. The actual device may include more or fewer components than shown, or may combine certain components, or arrange the components differently. In addition, the technical effects achieved by the electronic device when executing the method of the first embodiment can refer to the technical effects described in the first embodiment above, and therefore will not be repeated here.

[0097] Fourth embodiment

[0098] This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device. The instructions stored therein can be loaded by a processor in a terminal to execute the method described above.

[0099] Furthermore, it should be noted that the present invention may be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention may take the form of a fully or partially hardware embodiment, a fully or partially software embodiment, or an embodiment combining software and hardware aspects. Furthermore, when implemented using software, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired connection (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium. The semiconductor medium may be a solid state drive.

[0100] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0102] It should also be noted that, in this document, relational terms such as first and second are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. The terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or terminal device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. Without further limitation, an element defined by the phrase "comprising a..." does not preclude the presence of other identical elements in the process, method, article, or terminal device comprising the element. In addition, the term "and / or" is merely a description of an associative relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: the presence of A alone, the presence of A and B simultaneously, or the presence of B alone, where A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding. "At least one" means one or more, and "more" means two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0103] In addition, it can be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0104] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0105] In the several embodiments provided herein, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of functional modules / units is merely a logical functional division. In actual implementation, other division methods may be used, such as multiple units or components being combined or integrated into another device, or some features being ignored or not implemented. Furthermore, the coupling or direct coupling or communication connection shown or discussed between each other may be through some interface, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs. In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0106] If the method 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, or the part that contributes to the prior art, or the 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 and includes several instructions for enabling a computer device (which can be a personal computer, server, or 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 various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0107] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention. It should be noted that, although preferred embodiments of the present invention have been described, those skilled in the art, once understanding the basic inventive concepts of the present invention, may make various improvements and modifications without departing from the principles of the present invention. Such improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as covering the preferred embodiments and all variations and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A method for automatically identifying the projectile head form factor, characterized in that: include: Acquire projectile penetration images; The projectile penetration image is semantically segmented using a preset image segmentation model to obtain a binary mask image of the projectile. The projectile body contour is detected on the binary mask image of the projectile body using a preset contour detection algorithm, and a pixel point set of the projectile body contour is obtained based on the projectile body contour detection result; Based on the pixel point set of the projectile's outer contour, the contour point set of the projectile's head shape area is extracted; The projectile head shape curve is fitted based on the projectile head shape area contour point set; Based on the projectile head shape curve, calculate the projectile head shape factor.

2. The method for automatically identifying the projectile head form factor according to claim 1, wherein: The image segmentation model has an adaptive strategy and can adaptively select the optimal segmentation strategy according to the image texture complexity, texture background or target clarity, thereby automatically extracting the projectile area and generating a binary mask image of the projectile.

3. The method for automatically identifying the projectile head form factor according to claim 1, wherein: The contour detection algorithm is an edge detection algorithm based on image structure information and region connectivity judgment.

4. The method for automatically identifying the projectile head form factor according to claim 3, wherein: The preset contour detection algorithm is used to detect the projectile body contour on the binary mask image. Based on the projectile body contour detection results, the projectile outer contour pixel point set is obtained, including: The preset contour detection algorithm is used to detect the projectile contour on the binary mask image of the projectile, and the detected projectile contour coordinates are mapped to the original image for visual display; Based on the visualization display results, a contour matching scoring mechanism is introduced to quantitatively evaluate the degree of overlap between the extracted projectile contour and the actual projectile contour to verify the contour extraction accuracy, forming a closed-loop mechanism from image semantic segmentation to contour geometry restoration to accuracy feedback to obtain the pixel point set of the projectile's outer contour.

5. The method for automatically identifying the projectile head form factor according to claim 1, wherein: Based on the projectile outer contour pixel point set, the projectile head area contour point set is extracted, including: The projectile image is uniformly set to face downward in the coordinate system; Find the point with the largest Y coordinate value in the image coordinate system among the pixel points of the projectile's outer contour as the starting point of the projectile head shape area; Starting from the starting point, traverse along the direction of the contour point sequence; during the traversal process, the tangent direction changes, curvature distribution changes and polynomial fitting errors between consecutive contour points are analyzed in real time. When the tangent direction change is greater than the preset direction change threshold, the curvature distribution change is greater than the preset curvature distribution change threshold or the polynomial fitting error is greater than the preset error threshold, the current point is automatically determined to be the end point of the projectile head shape area, thereby realizing the adaptive closed extraction of the edge segment of the projectile head shape area.

6. The method for automatically identifying the projectile head form factor according to claim 1, wherein: The projectile head shape curve is fitted based on the projectile head shape area contour point set, including: Based on the contour point set of the projectile head shape area, an adaptive polynomial fitting model is used to build a model and fit the projectile head shape curve; wherein, the adaptive polynomial fitting model automatically searches for fitting schemes of different orders under the minimum mean square error criterion through an objective function optimization algorithm, and determines the optimal order and fitting coefficient according to the mean square error threshold; and the adaptive polynomial fitting model supports the use of segmented fitting and splicing strategies.

7. The method for automatically identifying the projectile head form factor according to claim 1, wherein: The fitting expression of the projectile head shape curve is: y=-0.00165x 2 +0.53477x+315.6507 Wherein, y represents the ordinate of the point where the contour points of the projectile head shape area are concentrated; x represents the abscissa of the point where the contour points of the projectile head shape area are concentrated.

8. The method for automatically identifying the projectile head form factor according to claim 1, wherein: Based on the projectile head shape curve, calculate the projectile head shape factor, including: Based on the projectile head shape curve, the geometric characteristic parameters required for calculating the projectile head shape factor are extracted; Based on the extracted geometric feature parameters, the preset physical calculation formula of the projectile head shape factor is used to automatically complete the quantitative calculation of the projectile head shape factor at the current stage and output the calculation results; the physical calculation formula is: Among them, N * represents the head shape factor; R represents half of the maximum width of the bullet in the x direction; y ′ represents the first-order derivative of y; h represents the length of the projectile along the y direction; y represents the ordinate of the point where the contour points of the projectile head shape area are concentrated; x represents the abscissa of the point where the contour points of the projectile head shape area are concentrated.

9. An automatic recognition system for projectile head form factor, characterized in that: include: Image input module, used to obtain projectile penetration images; An image segmentation model is used to perform semantic segmentation on the projectile penetration image using a preset image segmentation model to obtain a binary mask image of the projectile; Contour extraction module for: The projectile body contour is detected on the binary mask image of the projectile body using a preset contour detection algorithm, and a pixel point set of the projectile body contour is obtained based on the projectile body contour detection result; Based on the pixel point set of the projectile's outer contour, the contour point set of the projectile's head shape area is extracted; A fitting modeling module is used to fit the projectile head shape curve based on the projectile head shape area contour point set; The head shape factor calculation module is used to calculate the projectile head shape factor based on the projectile head shape curve.

10. The projectile head form factor automatic recognition system according to claim 9, characterized in that: The system also includes a result visualization display and export module for visually displaying and exporting the calculation results of the projectile head shape factor.

Images