Quick and accurate image recognition method and system for burst damage of active damage element

Abstract

The invention relates to an active damage element burst damage rapid and accurate image identification method and system, and the method comprises the steps: carrying out the gray processing of a shot image in response to an obtained shot image, and obtaining a reference damage image; dividing an area on the reference damage image to obtain a damage area and a non-damage area; the damaged area is divided according to area features, a main area and sub-areas are obtained, and the area features comprise shapes and colors; determining an affiliation relationship between the main region and the sub-region; and classifying the main regions according to the affiliation relationship of the sub-regions to obtain a burst damage main region and a non-burst damage main region. According to the active damage element burst damage rapid and accurate image identification method and system disclosed by the invention, the areas on the shot image can be rapidly divided and classified, and then the burst damage areas are determined for providing data reference for subsequent adjustment.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method and system for rapid and accurate image recognition of explosive damage caused by active damage elements. Background Art

[0002] The development stages of destructive elements are mainly divided into two stages: using inert materials and using active materials. Inert material destructive elements mainly rely on mechanical damage to cause damage to the target, while active material destructive elements use both mechanical damage and explosive damage to cause damage to the target.

[0003] The core difference between the two lies in the different materials used. The active material has both mechanical strength similar to that of metal and chemical energy equivalent to that of high-energy explosives. After colliding with the target, it can cause primary destruction to the weak surface of the target and then cause secondary destruction after entering the interior of the target.

[0004] The effectiveness of active destructive elements needs to be evaluated during both test evaluation and actual use. The purpose of the evaluation is to determine the ratio of mechanical damage to explosion damage, and then make targeted adjustments. The current method used is image processing, but due to the small spacing between damaged areas, there is a certain degree of identification difficulty. Summary of the invention

[0005] The present application provides a method and system for rapid and accurate image recognition of explosive damage of active damage elements, which can quickly divide and classify areas on a captured image, and then determine the explosive damage area to provide data reference for subsequent adjustments.

[0006] The above-mentioned purpose of the present application is achieved through the following technical solutions: In a first aspect, the present application provides a method for rapid and accurate image recognition of active damage element burst damage, comprising: In response to the obtained captured image, grayscale processing is performed on the captured image to obtain a reference damaged image; Divide the area on the reference damaged image into damaged areas and non-damaged areas; The damaged area is divided into main areas and sub-areas according to regional features, and the regional features include shape and color; Determine the ownership relationship between the main area and sub-areas; The main area is classified according to the belonging relationship of the sub-areas to obtain the main area of ​​explosion damage and the main area of ​​non-explosion damage; When a sub-region is associated with at least two main regions, the classification of the main region is determined according to the edge features of the main region.

[0007] In a possible implementation manner of the first aspect, dividing the area on the reference damaged image to obtain the damaged area and the non-damaged area includes: The reference damage image is divided using edge extraction to obtain multiple feature areas; The feature regions are classified according to their shape features. The feature regions of the same type have similar shape features. Divide the classified characteristic areas into damaged areas and non-damaged areas; The characteristic region belonging to the damaged region has a similar shape and / or color; the non-damaged region is a portion of the reference damaged image that does not belong to the damaged region.

[0008] In a possible implementation manner of the first aspect, classifying the feature areas according to the shape features includes: Determine the edge of the feature area and analyze the edge features of the feature area, the edge features include shape change features and color change features; The feature areas are classified according to their edge features, and the classification includes mechanical damage and explosion damage.

[0009] In a possible implementation manner of the first aspect, analyzing the shape change feature and the color change feature in the edge feature of the feature area includes: An analysis reference line is randomly established on the feature area, and both ends of the analysis reference line are located outside the feature area; Calculate the color change trend on the analysis reference line and determine the rotation direction according to the color change trend on the analysis reference line, or randomly rotate the analysis reference line and then calculate the color change trend on the analysis reference line; Determine the change points on the analysis reference line; Assign a change point type, which includes shape change and color change; The change point whose type is shape change is used as the shape change feature of the edge feature, and the change point whose type is color change is used as the shape and color change feature of the edge feature.

[0010] In a possible implementation manner of the first aspect, determining the change point on the analysis reference line includes: Use the pixel points on the analysis reference line to establish an analysis characteristic curve; The analysis characteristic curve is transferred into the time domain and the frequency domain for decomposition to obtain an analysis characteristic curve group; The change point is determined according to the starting position point and the ending position point of the analysis characteristic curve in the analysis characteristic curve group.

[0011] In a possible implementation manner of the first aspect, assigning the change point type includes: Determine the color difference on both sides of the change point; When the color difference on both sides of the same change point is within the allowable range, the change point type is shape change. When the color difference on both sides of the same change point exceeds the allowable range, the change point type is color change.

[0012] In a possible implementation manner of the first aspect, when determining the attribution relationship between the main area and the sub-area, the attribution relationship used is including.

[0013] In a second aspect, the present application provides a fast and accurate image recognition device for active damage element burst damage, comprising: An image processing unit, configured to perform grayscale processing on the captured image in response to the captured image, so as to obtain a reference damage image; A first area division unit is used to divide the area on the reference damaged image into damaged areas and non-damaged areas; A second area division unit is used to divide the damaged area according to regional features to obtain a main area and sub-areas, wherein the regional features include shape and color; An ownership relationship determination unit, used to determine the ownership relationship between the main area and the sub-area; A region classification unit is used to classify the main region according to the belonging relationship of the sub-regions to obtain the main region with explosion damage and the main region without explosion damage; When a sub-region is associated with at least two main regions, the classification of the main region is determined according to the edge features of the main region.

[0014] In a third aspect, the present application provides a fast and accurate image recognition system for active damage element burst damage, the system comprising: one or more memories for storing instructions; and One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising: Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0016] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0017] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0018] The chip system may be composed of chips, or may include chips and other discrete devices.

[0019] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic flowchart of the steps of a method for rapid and accurate image recognition of explosive damage of active damage elements provided in this application.

[0021] Figure 2 This is a schematic diagram of a damaged area and a non-damaged area provided in this application.

[0022] Figure 3 It is a schematic diagram of a main area and sub-areas provided in this application.

[0023] Figure 4 It is a schematic diagram for establishing an analysis reference line provided in this application.

[0024] Figure 5 It is a schematic diagram of a rotation analysis reference line provided in this application.

[0025] Figure 6 This is a schematic diagram of the principle of obtaining a change point provided by the present application. DETAILED DESCRIPTION

[0026] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0027] This application discloses a fast and accurate image recognition method for active damage element burst damage, please refer to Figure 1 In some examples, the rapid and accurate image recognition method for active damage element burst damage disclosed in the present application includes the following steps: S101, in response to the obtained captured image, grayscale processing is performed on the captured image to obtain a reference damage image; S102, dividing the area on the reference damaged image into damaged areas and non-damaged areas; S103, dividing the damaged area according to regional features to obtain a main area and sub-areas, where the regional features include shape and color; S104, determining the ownership relationship between the main area and the sub-area; S105, classifying the main area according to the belonging relationship of the sub-areas to obtain the main area of ​​explosion damage and the main area of ​​non-explosion damage; When a sub-region is associated with at least two main regions, the classification of the main region is determined according to the edge features of the main region.

[0028] First, the relevant contents of active destructive elements are introduced. The active destructive elements involved in this application are deployed at the warhead of the weapon. After the warhead explodes, kinetic energy is given to the active destructive elements. At this time, the active destructive elements approach the target. After contacting the target, the active destructive elements destroy the target surface. There are two types of destruction here: mechanical destruction and explosive destruction. Some active destructive elements will pass through the target surface and enter the target surface to cause secondary damage, which is generally explosive destruction.

[0029] The prerequisite for producing mechanical damage is that the skin thickness of the target surface is relatively thin, so active damage elements are mostly used to attack aircraft. During the testing process, the test objects are mostly aircraft.

[0030] Returning to the technical solution provided in the present application, in step S101, in response to the obtained captured image, grayscale processing is performed on the captured image and a baseline damage image is obtained. Here, the captured image is acquired by an image sensor at the test site or an image sensor carried on a weapon, or by a combat unit that launches the weapon.

[0031] After obtaining the reference damaged image, execute step S102. Figure 2 In this step, the area on the reference damage image is divided into damaged areas and non-damaged areas. The damaged area refers to the area on the target surface damaged by the active damage element, and the non-damaged area refers to the area on the target surface that is not damaged by the active damage element. One purpose of dividing the damaged area and the non-damaged area is to determine the area of ​​the damaged area, and the other purpose is to facilitate the subsequent division of the main explosion damage area and the non-explosion damage area.

[0032] In step S103, the damaged area is divided according to the regional characteristics. Figure 3 , and obtain a main area and a sub-area. The main area is directly caused by the active damage element, and the sub-area is indirectly caused by the active damage element. In this application, the sub-area is generated by the active damage element during the explosion.

[0033] The main area here refers to the mechanical damage and explosion damage types in the damage area, and the sub-area refers to the explosion damage derivative type in the damage area.

[0034] In step S104, the ownership relationship between the main area and the sub-area needs to be determined. Combining the content in the previous text, it can be seen that the ownership relationship here means that the reason for the appearance of the sub-area is because of the main area, that is, the two belong to the same active damage element.

[0035] In step S105, the main area is classified according to the affiliation of the sub-areas to obtain the main area with explosive damage and the main area without explosive damage. Combining the content mentioned in the previous article, it can be seen that the main area with sub-areas is defined as the main area with explosive damage, otherwise it is defined as the main area without explosive damage.

[0036] Of course, at this time, there may be a situation where a sub-region is associated with at least two main regions. At this time, it is necessary to determine the classification of the main region according to the edge features of the main region. This part of the content will be further described in the subsequent content.

[0037] In some possible implementations, when determining the relationship between the main area and the sub-area, the relationship used is inclusion. Here, inclusion is defined as the main area being located inside the sub-area, or a portion of the main area being located inside the sub-area. The generally required value here is that at least 70% of the edge of the main area is located inside the sub-area.

[0038] In general, through the above method, the main area of ​​explosive damage and the main area of ​​non-explosive damage on the target surface can be quickly determined. After determination, subsequent analysis work can be carried out. For example, quantitative analysis work can be carried out at this time. For example, by calculating the ratio of the main area of ​​explosive damage and the main area of ​​non-explosive damage, it can be judged whether the parameters such as the impact speed and flight distance of the active damage element are appropriate.

[0039] In some examples, the specific method of dividing the area on the reference damaged image and obtaining the damaged area and the non-damaged area is: S201, dividing the reference damage image using an edge extraction method to obtain a plurality of feature regions; S202, classifying the feature regions according to shape features, where the feature regions of the same type have similar shape features; S203, dividing the classified feature area into a damaged area and a non-damaged area; The characteristic region belonging to the damaged region has a similar shape and / or color; the non-damaged region is a portion of the reference damaged image that does not belong to the damaged region.

[0040] In step S201, firstly, the reference damaged image is segmented using an edge extraction method, where the edge extraction method is implemented using an edge detection algorithm, including a Sobel operator, a Prewitt operator, a Roberts operator, a Canny operator, and the like.

[0041] Then, in step S202, the characteristic regions are classified according to the shape features. The characteristic regions of the same type have similar shape features. Specifically, the shape of the impact-type damage is similar to the shape of the active damage element. Here, the impact-type damage generated by different angles of the active damage element needs to be collected and a database needs to be established. That is, the impact-type damage can be determined by comparison. The characteristic of the explosion-type damage is that it has irregular edges. After the edge detection algorithm is used to extract the edge, the area surrounded by the irregular edge is used as the damage area.

[0042] from Figure 2 It can be seen that the damaged area has obvious damage characteristics, which can be identified as follows: The characteristic area of ​​mechanical destruction is similar in shape to the shape of active damage elements. This is because the characteristic area of ​​mechanical destruction is generated by impact and has relatively regular edges. The characteristic of explosion destruction is that its shape edges have obvious irregularities.

[0043] The core of these two feature regions lies in whether the edges are regular. One way to determine whether the edges are regular is to first segment the edge of a feature region, because the edge of a feature region is generally composed of multiple segments.

[0044] Then calculate the regularity and irregularity of the edge. The specific method is to establish a straight line on the segmented edge. The straight line needs to be as parallel to the corresponding edge as possible. For example, a rectangular area can be obtained based on the edge, and then the center line of the rectangular area is used as a reference for establishing the straight line. The established straight line is parallel to the center line of the rectangular area.

[0045] Multiple points are taken at intervals on the segmented edge, and then the minimum straight-line distance between these points and the straight line is calculated.

[0046] The fluctuation range of these minimum straight-line distances is counted. The fluctuation range is the difference between the maximum and minimum values ​​of the minimum straight-line distances. When determining the maximum and minimum values, one or two maximum values ​​and one or two minimum values ​​need to be removed first.

[0047] After obtaining the fluctuation range, the edge of the feature area is classified according to the fluctuation range. The classification method is to compare the fluctuation range with a set value. When the fluctuation range is on the left side of the set value (less than), the area corresponding to the edge of the feature area is a mechanical damage type, otherwise it is an explosion damage type.

[0048] The explosion damage derivative type area is located around the explosion damage type area and also has irregular edges.

[0049] The non-damaged area is the part that does not belong to the damaged area on the baseline damage image. The explosion damage derivative area and the non-damaged area have color differences. Here, the explosion damage derivative area needs to be processed separately, that is, when the mechanical damage area and the explosion damage area are obtained, the surrounding areas of these two areas are included in the investigation range of the explosion damage derivative area.

[0050] The edges of the explosion damage derivative area are also irregular, and are processed using the edge classification method described above, and finally the remaining area is regarded as a non-damaged area.

[0051] Finally, in step S203, the classified feature regions are divided into damaged regions and non-damaged regions. Figure 2 shown.

[0052] The purpose of determining the area of ​​the damage zone is to determine the scope of damage to the target surface (degree of damage), whether the deployment method and flight method of the active damage element are appropriate, and whether the departure distance of the active damage element is appropriate. Of course, this is just an example and is not a limitation of this application.

[0053] The present application also provides another method for distinguishing between mechanical damage and explosion damage. This method is mainly used to distinguish between mechanical damage and explosion damage that are both located in the explosion damage derivative area. At this time, it is impossible to rely on the explosion damage derivative area for distinction.

[0054] The specific way to classify feature areas according to shape features is: S301, determining the edge of the feature area and analyzing the edge features of the feature area, the edge features including shape change features and color change features; S302, classifying the feature area according to the edge features of the feature area, the classification includes mechanical damage class and explosion damage class.

[0055] In step S301 and step S302, it is first necessary to determine the edge of the feature area and analyze the edge features of the feature area. The edge features include shape change features and color change features. Then, the feature area is classified according to the edge features of the feature area. The classification includes mechanical destruction and explosion destruction.

[0056] See also Figure 4 and Figure 5 ,The specific method of analyzing the shape change features and color change features in the edge features of the feature area is as follows: S401, randomly establishing an analysis reference line on the feature region, where both ends of the analysis reference line are located outside the feature region; S402, calculating the color change trend on the analysis reference line and determining the rotation direction according to the color change trend on the analysis reference line, or randomly rotating the analysis reference line and then calculating the color change trend on the analysis reference line; S403, determining a change point on the analysis reference line; S404, assigning a change point type, where the change point type includes shape change and color change; S405 , taking the change point of shape change as the shape change feature of the edge feature and taking the change point of color change as the shape and color change feature of the edge feature.

[0057] In step S401 to step S405, firstly, an analysis reference line is randomly established on the feature region, and both ends of the analysis reference line are required to be located outside the feature region. Then, the color change trend on the analysis reference line is calculated and the rotation direction is determined according to the color change trend on the analysis reference line. The purpose of determining the rotation direction is to enable the analysis reference line to pass through the center of the feature region. Figure 5 The dotted line in the figure represents the rotated analysis reference line.

[0058] When the color change trend cannot be determined, the color change trend on the analysis reference line is calculated after randomly rotating the analysis reference line.

[0059] The color change trend means that the color on the analysis reference line is obviously different, rather than being unchanging.

[0060] Then determine the change points on the analysis reference line and assign them types, which include shape change and color change. Finally, use the shape change type as the shape change feature of the edge feature and the color change type as the color change feature of the edge feature.

[0061] The specific method for determining the change point on the analysis reference line is: Use the pixel points on the analysis reference line to establish an analysis characteristic curve; The analysis characteristic curve is transferred into the time domain and the frequency domain for decomposition to obtain an analysis characteristic curve group; The change point is determined according to the starting position point and the ending position point of the analysis characteristic curve in the analysis characteristic curve group.

[0062] See also Figure 6 In the above method, the analysis reference line is processed by wavelet decomposition, and an analysis characteristic curve group is obtained. The curves in the analysis characteristic curve group have a starting point and an end point. These starting points and end points are counted, and the gathering area of ​​the starting points and the end points is the location of the change point.

[0063] When the obtained convergence area is a point, the point is directly used as the change point. When the obtained convergence area is multiple points, these points are connected by a line segment, and then the midpoint of the line segment is used as the change point.

[0064] Next, you need to determine the type of change point, as follows: Determine the color difference on both sides of the change point; When the color difference on both sides of the same change point is within the allowable range, the change point type is shape change. When the color difference on both sides of the same change point exceeds the allowable range, the change point type is color change.

[0065] For areas of mechanical damage, the change points include a color change type change point and a shape change type change point. The corresponding situation is that the active damage element causes damage to the area, and there is bending deformation at the damaged edge. Because of the bending deformation, the color of the same area has a certain difference in light and dark. The point at the junction of light and dark is the change point of the color change type.

[0066] And the distance between these two change points is short, which is a significant feature.

[0067] For the explosion damage area, the change points include two color change type change points, and the distance between the two color change type change points is large, which is also a significant feature. At the same time, there may be a shape change type change point between the two color change type change points, but it is not considered in this case.

[0068] By determining the type and distance of the change points, the characteristic areas of mechanical damage and explosion damage can be effectively distinguished. The distance value used in the distance determination is generally determined based on the data collected during the test. The distance in the first case is generally controlled at 2-5mm, and the distance in the second case is generally controlled at more than 5mm.

[0069] The present application also provides a fast and accurate image recognition device for active damage element burst damage, comprising: An image processing unit, configured to perform grayscale processing on the captured image in response to the captured image, so as to obtain a reference damage image; A first area division unit is used to divide the area on the reference damaged image into damaged areas and non-damaged areas; A second area division unit is used to divide the damaged area according to regional features to obtain a main area and sub-areas, wherein the regional features include shape and color; An ownership relationship determination unit, used to determine the ownership relationship between the main area and the sub-area; A region classification unit is used to classify the main region according to the belonging relationship of the sub-regions to obtain the main region with explosion damage and the main region without explosion damage; When a sub-region is associated with at least two main regions, the classification of the main region is determined according to the edge features of the main region.

[0070] Furthermore, the area on the reference damaged image is divided to obtain damaged areas and non-damaged areas, including: The reference damage image is divided using edge extraction to obtain multiple feature areas; The feature regions are classified according to their shape features. The feature regions of the same type have similar shape features. Divide the classified characteristic areas into damaged areas and non-damaged areas; The characteristic region belonging to the damaged region has a similar shape and / or color; the non-damaged region is a portion of the reference damaged image that does not belong to the damaged region.

[0071] Furthermore, classifying the feature regions according to the shape features includes: Determine the edge of the feature area and analyze the edge features of the feature area, the edge features include shape change features and color change features; The feature areas are classified according to their edge features, and the classification includes mechanical damage and explosion damage.

[0072] Further, analyzing the shape change feature and the color change feature in the edge feature of the feature area includes: An analysis reference line is randomly established on the feature area, and both ends of the analysis reference line are located outside the feature area; Calculate the color change trend on the analysis reference line and determine the rotation direction according to the color change trend on the analysis reference line, or randomly rotate the analysis reference line and then calculate the color change trend on the analysis reference line; Determine the change points on the analysis reference line; Assign a change point type, which includes shape change and color change; The change point whose type is shape change is used as the shape change feature of the edge feature, and the change point whose type is color change is used as the shape and color change feature of the edge feature.

[0073] Further, determining the change point on the analysis reference line includes: Use the pixel points on the analysis reference line to establish an analysis characteristic curve; The analysis characteristic curve is transferred into the time domain and the frequency domain for decomposition to obtain an analysis characteristic curve group; The change point is determined according to the starting position point and the ending position point of the analysis characteristic curve in the analysis characteristic curve group.

[0074] Furthermore, the types of change points are assigned including: Determine the color difference on both sides of the change point; When the color difference on both sides of the same change point is within the allowable range, the change point type is shape change. When the color difference on both sides of the same change point exceeds the allowable range, the change point type is color change.

[0075] Furthermore, when determining the ownership relationship between the main area and the sub-area, the ownership relationship used is include.

[0076] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0077] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0078] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] Those of ordinary skill 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. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0083] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0084] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0085] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable 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 methods described in each embodiment of the present application. The aforementioned computer-readable 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.

[0086] The present application also provides a fast and accurate image recognition system for active damage element burst damage, the system comprising: one or more memories for storing instructions; and One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0087] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0088] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0089] The chip system may be composed of chips, or may include chips and other discrete devices.

[0090] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0091] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0092] Optionally, the computer instructions are stored in a memory.

[0093] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0094] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0095] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0096] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0097] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A fast and accurate image recognition method for active damage element burst damage, characterized in that: include: In response to the obtained captured image, grayscale processing is performed on the captured image to obtain a reference damage image; Divide the area on the reference damaged image into damaged areas and non-damaged areas; The damaged area is divided into main areas and sub-areas according to regional features, and the regional features include shape and color; Determine the ownership relationship between the main area and sub-areas; The main area is classified according to the belonging relationship of the sub-areas to obtain the main area of ​​explosion damage and the main area of ​​non-explosion damage; When a sub-region is associated with at least two main regions, the classification of the main region is determined according to the edge features of the main region.

2. The rapid and accurate image recognition method of active damage element burst damage according to claim 1 is characterized in that: The area on the reference damaged image is divided into damaged areas and non-damaged areas including: The reference damage image is divided using edge extraction to obtain multiple feature areas; The feature regions are classified according to their shape features. The feature regions of the same type have similar shape features. Divide the classified characteristic areas into damaged areas and non-damaged areas; The characteristic region belonging to the damaged region has a similar shape and / or color; the non-damaged region is a portion of the reference damaged image that does not belong to the damaged region.

3. The rapid and accurate image recognition method of active damage element burst damage according to claim 2 is characterized in that: Classification of feature areas based on shape features includes: Determine the edge of the feature area and analyze the edge features of the feature area, the edge features include shape change features and color change features; The feature areas are classified according to their edge features, and the classification includes mechanical damage and explosion damage.

4. The rapid and accurate image recognition method for active damage element burst damage according to claim 3 is characterized in that: The shape change features and color change features in the edge features of the analysis feature area include: An analysis reference line is randomly established on the feature area, and both ends of the analysis reference line are located outside the feature area; Calculate the color change trend on the analysis reference line and determine the rotation direction according to the color change trend on the analysis reference line, or randomly rotate the analysis reference line and then calculate the color change trend on the analysis reference line; Determine the change points on the analysis reference line; Assign a change point type, which includes shape change and color change; The change point whose type is shape change is used as the shape change feature of the edge feature, and the change point whose type is color change is used as the shape and color change feature of the edge feature.

5. The rapid and accurate image recognition method of active damage element burst damage according to claim 4 is characterized in that: Determining the change points on the analysis reference line includes: Use the pixel points on the analysis reference line to establish an analysis characteristic curve; The analysis characteristic curve is transferred into the time domain and the frequency domain for decomposition to obtain an analysis characteristic curve group; The change point is determined according to the starting position point and the ending position point of the analysis characteristic curve in the analysis characteristic curve group.

6. The rapid and accurate image recognition method for active damage element burst damage according to claim 4 is characterized in that: The types of change points are: Determine the color difference on both sides of the change point; When the color difference on both sides of the same change point is within the allowable range, the change point type is shape change. When the color difference on both sides of the same change point exceeds the allowable range, the change point type is color change.

7. The rapid and accurate image recognition method for active damage element burst damage according to claim 1 is characterized in that: When determining the ownership relationship between the main area and the sub-area, the ownership relationship used is include.

8. A fast and accurate image recognition device for active damage element burst damage, characterized in that: include: An image processing unit, configured to perform grayscale processing on the captured image in response to the captured image, so as to obtain a reference damage image; A first area division unit is used to divide the area on the reference damaged image into damaged areas and non-damaged areas; A second area division unit is used to divide the damaged area according to regional features to obtain a main area and sub-areas, wherein the regional features include shape and color; An ownership relationship determination unit, used to determine the ownership relationship between the main area and the sub-area; A region classification unit is used to classify the main region according to the belonging relationship of the sub-regions to obtain the main region with explosion damage and the main region without explosion damage; When a sub-region is associated with at least two main regions, the classification of the main region is determined according to the edge features of the main region.

9. A fast and accurate image recognition system for active damage element burst damage, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images