Grain internal insect egg rapid detection method, device, system and computer readable medium fusing insect egg and insect hole structure characteristics

Abstract

The application relates to the technical field of grain quality and safety detection, and discloses a grain internal insect egg rapid detection method, device, system and computer readable medium fusing insect egg and insect hole structure characteristics, wherein the detection method comprises the following steps: acquiring a grain pile gray digital image and performing three-dimensional reconstruction to obtain a multi-grain pile stereogram; performing segmentation processing on the multi-grain pile stereogram to obtain a single-grain or multi-grain grain unit image; identifying an insect hole area in the single-grain or multi-grain grain unit image based on pest biological characteristics; identifying whether the insect hole area is an insect egg area based on insect hole structure characteristics; and identifying whether the insect egg area is a living insect egg based on insect egg geometric characteristics and physical characteristics. The application applies CT tomography technology to the detection of grain internal insect eggs, combines the structure characteristics and biological characteristics of insect eggs and insect holes, directly detects the insect eggs in the internal insect eggs of the grain in the egg stage, and can realize less time and high detection accuracy.

Description

Technical Field

[0001] This invention relates to the field of grain quality and safety testing technology, and more specifically to a rapid detection method, device, system, and computer-readable medium for insect eggs inside grains that integrates the structural features of insect eggs and insect holes. Background Technology

[0002] According to surveys and statistics, pest infestations cause an annual global food loss of 8%-10%, resulting in enormous economic losses. Pests such as the corn weevil and rice weevil damage stored grain crops and lay their eggs inside the grain, including wheat, rice, sorghum, corn, peanuts, soybeans, and broad beans, completing their entire growth process inside the grain. Because they cannot be detected by the naked eye and continuously erode the grain during their growth and development, they pose a significant threat to stored grain safety.

[0003] Currently, high-definition X-ray two-dimensional imaging and image processing technology can identify the larvae, pupae, and adults of pests inside grains. However, early pest detection still relies on human experience, resulting in low detection efficiency and accuracy. More importantly, it is difficult to detect pest eggs. Pest eggs are concealed and have strong vitality, posing a long-term potential threat. Rapid detection of insect eggs has become a technical problem that the industry needs to solve. Summary of the Invention

[0004] A first aspect of the present invention provides a rapid detection method for insect eggs inside grains that integrates the structural features of insect eggs and insect burrows, comprising the following steps:

[0005] Step 1: Obtain a scanned image of the grain pile, wherein the scanned image of the grain pile is a grayscale digital image;

[0006] Step 2: Perform 3D reconstruction on the scanned grain pile image to obtain a multi-grain grain pile stereoscopic image;

[0007] Step 3: Segment the three-dimensional image of the multi-grain pile to obtain single-grain or multi-grain unit images;

[0008] Step 4: Identify the insect hole region within the image of a single or multiple grain units based on the biological characteristics of the pest;

[0009] Step 5: Identify whether the wormhole region is an egg region based on the structural features of the wormhole; and

[0010] Step 6: Based on the geometric and physical characteristics of the insect eggs, identify whether there are live insect eggs in the egg area.

[0011] A second aspect of the present invention also provides a rapid detection device for insect eggs inside grains that integrates the structural features of insect eggs and insect holes, comprising:

[0012] Image acquisition module for acquiring scanned images of grain piles;

[0013] A 3D reconstruction module for performing 3D reconstruction on scanned images of grain piles to obtain multi-grain grain pile stereo images;

[0014] An image segmentation module used for segmenting three-dimensional images of multi-grain piles to obtain images of single grains or multiple grain units;

[0015] A wormhole region identification module for identifying wormhole regions within images of single or multiple grains of food based on the biological characteristics of pests.

[0016] An egg region identification module for identifying whether a wormhole region is an egg region based on wormhole structural features; and

[0017] An insect egg identification module that identifies whether a region contains live insect eggs based on the geometric and physical characteristics of the eggs.

[0018] A third aspect of the present invention provides a rapid detection system for insect eggs inside grains that integrates the structural features of insect eggs and insect burrows, comprising:

[0019] One or more processors;

[0020] The memory stores operable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, including the process of performing the aforementioned method.

[0021] A fourth aspect of the invention also provides a computer-readable medium for storing software, the software comprising instructions executable by one or more computers, the operation comprising a process of performing the aforementioned method. Attached Figure Description

[0022] The accompanying drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component shown in the various figures may be denoted by the same reference numeral. For clarity, not every component is labeled in each figure. Embodiments of various aspects of the invention will now be described by way of example and with reference to the accompanying drawings, wherein:

[0023] Figure 1 This is a schematic diagram of a rapid scanning and detection system for insect eggs inside grains according to an embodiment of the present invention.

[0024] Figure 2 This is a flowchart illustrating a rapid detection method for insect eggs inside grains according to an embodiment of the present invention.

[0025] Figure 3 It is based on the present invention Figure 2 A schematic diagram showing the location of insect eggs detected by the detection method in this embodiment.

[0026] Figure 4 It is based on the present invention Figure 2 The detection method in this embodiment detected a two-dimensional image of wheat grains containing insect eggs and a schematic diagram of the characteristic structure of the insect eggs.

[0027] Figure 5 This is a schematic diagram of the functional module principle of a rapid detection device for insect eggs inside grains that integrates the structural features of insect eggs and insect holes according to an embodiment of the present invention.

[0028] Figure 6 This is a schematic diagram of a computer system according to an embodiment of the present invention. Detailed Implementation

[0029] To better understand the technical content of the present invention, specific embodiments are described below in conjunction with the accompanying drawings.

[0030] Various aspects of the invention are described in this disclosure with reference to the accompanying drawings, which illustrate numerous illustrative embodiments. The embodiments of this disclosure are not necessarily intended to encompass all aspects of the invention. It should be understood that the various concepts and embodiments described above, as well as those described in more detail below, can be implemented in any of many ways, because the concepts and embodiments disclosed herein are not limited to any particular implementation. Furthermore, some aspects of the invention disclosed may be used alone or in any suitable combination with other aspects of the invention disclosed.

[0031] Combination Figure 1 , 2 The exemplary embodiment of the rapid scanning detection system for insect eggs inside grains shown includes a scanning instrument 1, an X-ray source 2, a sample stage 3, a detector 4, and a computer system 6.

[0032] The sample 5 to be tested is piled in a cylindrical container and placed on the sample stage 3. The beam emitted by the X-ray source 2 penetrates the sample and is received by the detector 4. The detector 4 communicates with the computer system 6 and sends the digital signal of the scanned image to the computer system 6. The computer system 6 performs image processing and analysis to identify and detect insect eggs inside the grain and displays the detection process or results on the screen of the computer system 6 in real time.

[0033] In an optional embodiment, the sample to be tested 5 can be a grain crop such as wheat, rice, sorghum, corn, peanut, soybean, or broad bean.

[0034] In the following example, we will use wheat as an example to illustrate the process of identifying and detecting insect eggs inside grains.

[0035] like Figure 2As shown, an exemplary method for rapid detection of insect eggs inside wheat grains is illustrated, including the following steps:

[0036] Step 1: Obtain scanned images of the grain pile, which include multiple grayscale digital images;

[0037] Step 2: Perform 3D reconstruction on the scanned image of the grain pile to obtain a multi-grain grain pile stereoscopic image;

[0038] Step 3: Segment the three-dimensional image of the multi-grain pile to obtain single-grain or multi-grain unit images;

[0039] Step 4: Based on the biological characteristics of pests, identify the insect hole regions within images of single or multiple grain units;

[0040] Step 5: Based on the structural features of the wormhole, identify whether the wormhole region is an egg region; and

[0041] Step 6: Based on the geometric and physical characteristics of the insect eggs, identify whether there are live insect eggs in the egg area.

[0042] In embodiments of the present invention, the scanned image of the wheat pile can be obtained using computed tomography (CT) technology (e.g., X-ray-based CT scan) to obtain a cross-sectional grayscale digital image of the wheat to be inspected inside the container. Based on this, three-dimensional reconstruction can be performed on the scanned image to obtain a three-dimensional image of the multi-grain wheat pile.

[0043] It should be understood that the sample to be tested is cleaned and loaded before scanning: the wheat is cleaned of impurities by sieve and the infected wheat is placed in a glass cylinder with an inner diameter of .

[0044] In an optional embodiment, the 3D reconstruction process can be completed based on the software processing corresponding to the CT scanner.

[0045] In an embodiment of the present invention, 20g of contaminated grains were placed in a glass cylinder with an inner diameter of 3cm for testing, and then placed on the sample stage 3 for testing.

[0046] CT scan imaging was performed using a flat panel detector, and data acquisition was performed using the instrument's built-in software to obtain a dataset of digital grayscale images of the grain pile. After reconstruction, the volume pixels of the resulting three-dimensional image were 15 micrometers.

[0047] Since the amount of data after scanning the grain pile is large, direct analysis would place high demands on both the processor's hardware and software, and would also affect the efficiency and accuracy of the analysis. Therefore, in the embodiments of the present invention, data analysis is performed using single or multiple grains after segmentation, which would greatly improve the processing speed and accuracy.

[0048] In optional embodiments, threshold segmentation or watershed algorithms can be used to segment the three-dimensional image of a multi-grain pile to obtain single-grain or multi-grain unit images.

[0049] In another embodiment, other object segmentation algorithms can be used to segment the image and obtain images of single grains or multiple grains, such as clustering-based (e.g., K-means) segmentation, graph-based segmentation, and other segmentation algorithms.

[0050] In embodiments of the present invention, identifying insect-hole regions within images of single or multiple grain units based on pest biological characteristics includes:

[0051] Based on the spherical or near-spherical voids in the grayscale image, determine whether they are located in the shallow layer below the surface of a single grain and are in a closed state. If so, they are identified as wormhole areas; otherwise, they are identified as non-wormhole areas.

[0052] In grain crops susceptible to pest infestation, such as wheat, rice, sorghum, corn, peanuts, soybeans, and broad beans, stored grain pests like corn weevils and rice weevils not only feed on the crops but also lay eggs inside, causing continuous infestation. Furthermore, these pests seal the openings of their egg-laying cavities. This biological behavior makes identifying and controlling pest infestations in grain crops challenging. Existing detection methods, such as staining, can only identify surface cavities and pits in the grains, failing to effectively identify the internal eggs. These eggs, however, continue to erode the grains during their growth and development, exhibiting concealment and strong vitality, maintaining a long-term potential for damage and causing sustained grain loss, posing a significant threat to stored grain safety.

[0053] Therefore, in the embodiments of the present invention, a three-dimensional image of a wheat pile is reconstructed based on computed tomography and three-dimensional reconstruction, thereby reproducing the internal features of the grains.

[0054] Based on the biological characteristics of stored grain pests laying eggs, the location of insect eggs is searched in the three-dimensional space of the segmented grain. Spherical or near-spherical cavities are identified, and their coordinates within a single grain are located. It is determined whether the cavities are located in the shallow layer below the surface of the grain and whether both ends are closed, thus identifying the insect-burrow area. Otherwise, it is considered a non-insect-burrow area, such as areas damaged by surface biting or impact. Figure 3 As shown, the location of the wormhole area is usually close to the surface of the grain.

[0055] In some embodiments, we combine experiments on the depth of oviposition by the maize weevil inside wheat, for example defining the shortest distance from the center of the egg to the wheat surface as D1, and the farthest distance from the egg hole to the wheat surface as D2. Based on the three-dimensionally formed stereoscopic image, we extract the three-dimensional coordinates of the opening of the hole on the wheat surface, the centroid of the egg, and the sealing point of the hole inside the wheat. The values ​​of D1 and D2 are calculated using the following spatial distance formula. To more clearly represent the distance between the egg and the egg hole from the wheat surface, we select multiple locations (preferably 5-10 locations) of eggs and holes for experiments:

[0056]

[0057] In the formula, D represents the distance between two points in space, and x, y, and z represent the x-axis, y-axis, and z-axis values ​​of the measured points in space, respectively.

[0058] By studying the life habits of the maize weevil at different growth stages inside wheat grains, it was found that the weevil lays its eggs inside the grain, with the egg hole just large enough to accommodate one egg. The shortest distance (D1) from the center of the egg to the wheat surface was found to be 0.34 ± 0.04 mm, and the farthest distance (D2) from the egg hole to the wheat surface was found to be 0.67 ± 0.07 mm. Based on the identification and selection of these shallow layer location depth characteristics, the locations of cavities in the shallow layer within a specific depth range below the grain surface were identified as areas where weevil eggs might exist, i.e., weevil burrow areas.

[0059] Further identification is needed to determine whether the identified wormhole areas contain insect eggs, cavities gnawed by stored grain pests, or cavities filled with debris. This is necessary to accurately identify the insect eggs inside the grain.

[0060] In some embodiments, identifying whether a wormhole region is an egg region based on wormhole structural features includes:

[0061] Based on the gradient changes in grayscale within the wormhole area, determine whether it is an area containing worm eggs.

[0062] The insect eggs are located inside the wormhole, but do not completely fill it; gaps exist. Taking wheat grains as an example, the area containing insect eggs is a special existence of "high-density wheat - low-density air - high-density insect eggs," which appears on a grayscale image as a region with obvious contrast between "dark-bright-dark" or "bright-dark-bright."

[0063] Density is a measure of mass within a specific volume and reflects the intrinsic properties of a substance. In embodiments of this invention, based on the principles of CT scanning imaging, grayscale values ​​represent the different absorption rates of X-rays by an object, fundamentally due to the object's varying densities. For the same sample of wheat grains under scanning, the root cause of different image grayscale values ​​lies in the object's different densities.

[0064] Therefore, in the embodiments of the present invention, determining whether a region is an egg region based on the stepwise change in grayscale within the wormhole area includes:

[0065] If the grayscale within the wormhole region exhibits a high-low-high stepwise variation trend, or a low-high-low stepwise variation trend, it is identified as an egg region. If the grayscale within the wormhole region is uniform, it is identified as an erosion cavity.

[0066] like Figure 4 As shown, insect eggs inside wheat grains are close to the grain surface, with clear outlines and obvious gaps between them and the surrounding wheat, making them easy to identify and distinguish. On the density map, they exhibit a clear contrast of "dark-light-dark" or "light-dark-light," while simple erosion cavities show a single brightness level. Based on this, we differentiated and identified egg areas (areas where insect eggs may be present) and erosion cavities (cavities created by stored grain pests) based on the brightness (grayscale gradient trend) on the grayscale image.

[0067] Since insect eggs continuously erode grains during their growth and development, but dead eggs will not further damage the stored grain, we aim to detect and count the number of surviving insect eggs during the actual detection of insect eggs in stored grain, and then make a judgment on whether the eggs are inactive or dead.

[0068] In embodiments of the present invention, identifying whether a region containing an insect egg contains a live insect egg based on the geometric and physical characteristics of the egg includes:

[0069] Based on the geometric and physical characteristics of insect eggs, determine whether the area containing insect eggs contains insect eggs and the survival status of the insect eggs;

[0070] The geometric features of the insect eggs include the length, width, height, specific surface area, volume, and sphericity, which constitute the morphological features.

[0071] The physical characteristics include the density of insect eggs.

[0072] In an optional embodiment, based on the geometric and physical characteristics of the insect eggs, determining whether the area containing the insect eggs contains insect eggs and the survival status of the insect eggs includes:

[0073] If the length, width, height, volume, and physical characteristics of the insect eggs are all within the preset insect egg model range, then it is determined whether the insect egg area contains surviving insect eggs; otherwise, it is determined to be inactive insect eggs or debris filling the cavity.

[0074] like Figure 4 As shown, taking wheat grains infested by pests as an example, the length, width, height, and volume characteristics of individual wheat grains in the three-dimensional reconstructed stereo image can be obtained through image processing and calculation.

[0075] For example, the geometric features of length, width, and height can be obtained based on the minimum bounding rectangle, pixel calculation based on threshold, ellipse fitting, etc. The specific surface area, volume, and sphericity of the spheroid can be further calculated based on the geometric features of length, width, and height, thereby obtaining the morphological features of the insect eggs.

[0076] For example, taking grains infected with corn weevil eggs as an example, we randomly sampled a predetermined number N (N greater than or equal to 100) of infected wheat grains, calculated the morphological characteristics of the eggs, and established an egg model, namely the characteristic value range of its length, width, height (i.e., thickness), specific surface area, volume, and sphericity. The accuracy of the characteristic value range was verified by using a validation set of 2N wheat grains.

[0077] The table below shows the range of characteristic values ​​for corn weevil eggs established by the method according to an embodiment of the present invention.

[0078]

[0079] In embodiments of the present invention, if a cavity is formed by insect bites within the egg region but no eggs are laid, the interior may be filled with debris to form a spherical or near-spherical egg-like structure. However, from the perspective of the geometric structure and biological characteristics of the insect egg, the sphericity of such debris filling is not formed by growth, but is based on random and loose debris filling. Its density (expressed as density) and sphericity are significantly different from the egg structure formed by actual insect egg growth. Therefore, even if its length, width, height, specific surface area, and volume all meet the characteristic value range, we can still judge and eliminate anomalies through the sphericity and density characteristics of the insect egg, such as the identification of debris filling.

[0080] After insect eggs become inactive and die, they lose moisture and gradually shrink. Simultaneously, the eggs themselves undergo changes such as decreased density and reduced size, resulting in a significant difference in density compared to actual insect eggs. Therefore, in actual testing, we can determine whether an area contains live or dead insect eggs by comparing their density characteristics.

[0081] Density is a measure of mass within a specific volume and reflects the intrinsic properties of a substance. Density is typically determined based on the ratio of mass to volume. The mass of an object can be measured using an analytical balance, for example, by weighing a single grain or multiple grains of food. In an alternative embodiment, the volume of an irregularly shaped object can be determined using the displacement method.

[0082] In an embodiment of the present invention, the volume of grain particles is calculated using a method of 3D visualization after reconstruction from CT scan imaging.

[0083] Calculate grain density using the density formula:

[0084] Density ρ = M / V;

[0085] In the formula, ρ represents density; M represents mass; and V represents volume.

[0086] According to the principles of CT scanning imaging, grayscale values ​​reflect the different absorption rates of X-rays by an object, which are fundamentally due to the different densities of the object. For the same scanned sample, the root cause of different image grayscale values ​​lies in the different densities of the object.

[0087] The linear relationship between the two is shown in the following formula. The density of the insect eggs can be calculated using this formula. The main physical quantities affecting the density of a substance are pressure and temperature; the density of gases is significantly affected by pressure and temperature.

[0088]

[0089] Where ρ1, ρ2, and ρ3 represent the densities of air, grains, and insect eggs, respectively; and G1, G2, and G3 represent the gray values ​​of air, grains, and insect eggs, respectively.

[0090] The density ρ2 of grains is calculated based on M / V, where M represents the mass of the grain and V represents the volume of the grain.

[0091] The aforementioned air density ρ1 is determined based on the altitude and temperature of the test area.

[0092] Because the power supply radiation during CT scanning affects the temperature of the sample itself, the internal air temperature also changes, and the surrounding air is also affected during irradiation. Therefore, to ensure the reliability of the experimental results, when selecting air grayscale values, sampling points were taken around the cavities inside the wheat fertile soil where insect eggs were located.

[0093] The grayscale value range in a 16-bit image is 0 to 65535.

[0094] We used Avizo to read the 3D image files reconstructed from CT scans and extracted the image grayscale values. We randomly selected 30 points from the scanned sample as representative points, recorded their grayscale values, and averaged them.

[0095] The grayscale values ​​G1, G2, and G3 for air, grain, and insect eggs are as follows:

[0096] By reading the grayscale values ​​of the grayscale image, the grayscale values ​​of several points in the image area between the insect egg and the grain in the insect egg area are randomly selected and averaged to obtain the air grayscale value G1. The grayscale values ​​of several points in the corresponding part of the image area of ​​the non-insect hole area of ​​the grain are randomly selected and averaged to obtain the wheat grayscale value G2. The grayscale values ​​of several points in the image area inside the insect egg in the insect egg area are randomly selected and averaged to obtain the insect egg grayscale value G3.

[0097] As a preferred approach, the aforementioned points can be selected from representative points, with the number controlled within 20-50 points, and the number of points selected for G1, G2, and G3 should be the same, for example, the average value of the gray values ​​of 30 points can be taken for each.

[0098] Therefore, the density characteristic value of insect eggs can be estimated. Furthermore, based on this density characteristic value, it can be used to determine whether the egg area is filled with debris or contains dead eggs, which can then be removed, thus truly identifying the actual live insect eggs.

[0099] In a further embodiment, the method of the present invention further includes:

[0100] The number of insect eggs per unit mass of grain is counted. This allows for a further assessment of the risk of pest infestation, the severity of pest damage, and the development of appropriate pest control and subsequent storage plans.

[0101] like Figure 5 As shown in the embodiment of the present invention, a rapid detection device for insect eggs inside grains that integrates the structural features of insect eggs and insect holes is also proposed, comprising:

[0102] Image acquisition module for acquiring scanned images of grain piles;

[0103] A 3D reconstruction module for performing 3D reconstruction on scanned images of grain piles to obtain multi-grain grain pile stereo images;

[0104] An image segmentation module used for segmenting three-dimensional images of multi-grain piles to obtain images of single grains or multiple grain units;

[0105] A wormhole region identification module for identifying wormhole regions within images of single or multiple grains of food based on the biological characteristics of pests.

[0106] An egg region identification module for identifying whether a wormhole region is an egg region based on wormhole structural features; and

[0107] An insect egg identification module that identifies whether a region contains live insect eggs based on the geometric and physical characteristics of the eggs.

[0108] The methods of the foregoing embodiments of the present invention, in particular Figure 2The process of the illustrated embodiment can be implemented in a computing system with data interface, data storage, and data processing functions. The computing system includes hardware and system software and functional software deployed on the hardware system. The aforementioned rapid detection method for insect eggs inside grains can be configured to be integrated into a functional software in the form of a computer instruction set, and can be executed by the computing system to realize the rapid detection process of insect eggs inside grains.

[0109] In some embodiments, the aforementioned computing system may be a handheld electronic device, a portable laptop computer system, a desktop computer system, or a server system, etc.

[0110] by Figure 6 Taking the computer system shown as an example, it may include a CPU, ROM, RAM, user interface, communication module, and display. These components / modules are interconnected via a bus and are integrated or set up independently within a circuit board or integrated circuit.

[0111] The communication module can be either a wired or wireless communication module, such as a 4G or 5G wireless network communication module.

[0112] The CPU, ROM, and RAM implement various functions by reading and executing instruction sets, such as those from recorded system software or functional software. In embodiments of this disclosure, the control of the rapid detection process for insect eggs inside grains can be implemented, for example, by the CPU, ROM, and RAM working together.

[0113] User interfaces can be input devices used to receive user actions, such as touch panels, virtual buttons, keyboard and mouse input devices, etc.

[0114] A display consists of a device capable of visually conveying information to a user. For example, a display can be an LCD or an LED display device. The display outputs the results of data processing performed by the CPU, ROM, and RAM and presents them to the user.

[0115] It should be understood that each of the aforementioned constituent elements can be constructed using general-purpose components or can be constructed using hardware specifically designed for the function of each constituent element. This configuration can be appropriately modified during implementation.

[0116] A rapid detection system for insect eggs inside grains, which integrates the structural features of insect eggs and insect holes according to an embodiment of the present invention, includes:

[0117] One or more processors;

[0118] The memory stores operable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, including the process of performing the aforementioned method.

[0119] According to embodiments of the present invention, a computer-readable medium for storing software includes instructions executable by one or more computers, and the operation includes a process of performing the aforementioned method.

[0120] While the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the invention. Those skilled in the art can make various modifications and refinements without departing from the spirit and scope of the invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. A rapid detection method for insect eggs inside grains, integrating the structural features of insect eggs and insect holes, characterized in that, Includes the following steps: Step 1: Obtain scanned images of the grain pile, which include multiple grayscale digital images; Step 2: Perform 3D reconstruction on the scanned image of the grain pile to obtain a multi-grain grain pile stereoscopic image; Step 3: Segment the three-dimensional image of the multi-grain pile to obtain single-grain or multi-grain unit images; Step 4: Based on the biological characteristics of pests, identify the insect hole regions within images of single or multiple grain units; Step 5: Based on the structural features of the wormhole, identify whether the wormhole region is an egg region; as well as Step 6: Based on the geometric and physical characteristics of the insect eggs, identify whether there are live insect eggs in the egg area; The method of identifying whether a region contains viable insect eggs based on the geometric and physical characteristics of the eggs includes: Based on the geometric and physical characteristics of insect eggs, determine whether the area containing insect eggs contains insect eggs and the survival status of the insect eggs; The geometric characteristics of the insect eggs include their length, width, height, specific surface area, volume, and sphericity. The physical characteristics include an egg density feature, which is estimated based on a linear relationship between the grayscale values ​​and density of a grayscale image, wherein: The linear relationship is expressed as follows: ； Where ρ1, ρ2, and ρ3 represent the densities of air, grain particles, and insect eggs, respectively; and G1, G2, and G3 represent the gray values ​​of air, grain particles, and insect eggs, respectively. The density ρ2 of the grain particles is calculated based on M / V, where M represents the mass of the grain particles and V represents the volume of the grain particles. The air density ρ1 is determined based on the altitude and temperature of the test area. The grayscale values ​​G1, G2, and G3 for the air, grain particles, and insect eggs are as follows: By reading the grayscale values ​​of the grayscale image, the grayscale values ​​of multiple points in the image area between the insect egg and the grain are randomly selected within the insect egg region and averaged to obtain the air grayscale value G1. The grayscale values ​​of multiple points in the corresponding part of the image area of ​​the non-insect hole area of ​​the grain are randomly selected and averaged to obtain the grain grain grayscale value G2. The grayscale values ​​of multiple points in the image area inside the insect egg within the insect egg region are randomly selected and averaged to obtain the insect egg grayscale value G3.

2. The rapid detection method for insect eggs inside grains based on the fusion of insect egg and wormhole structural features as described in claim 1, characterized in that, The method of identifying insect hole regions within single or multiple grain unit images based on pest biological characteristics includes: Based on the spherical or near-spherical voids in the grayscale image, determine whether they are located in the shallow layer below the surface of a single grain and are all in a closed state. If so, they are identified as wormhole areas; otherwise, they are identified as non-wormhole areas.

3. The rapid detection method for insect eggs inside grains based on the fusion of insect egg and wormhole structural features according to claim 1, characterized in that, The method of identifying whether a wormhole region is an egg region based on wormhole structural features includes: Based on the gradient changes in grayscale within the wormhole area, determine whether it is an area containing worm eggs.

4. The rapid detection method for insect eggs inside grains based on the fusion of insect egg and wormhole structural features according to claim 3, characterized in that, The method of determining whether a region is an egg region based on the gradient changes in grayscale within the wormhole area includes: If the grayscale within the wormhole region exhibits a high-low-high stepwise variation trend, or a low-high-low stepwise variation trend, it is identified as an egg region. If the grayscale within the wormhole region is uniform, it is identified as an erosion cavity.

5. The rapid detection method for insect eggs inside grains based on the fusion of insect egg and wormhole structural features according to claim 1, characterized in that, The determination of whether an area contains insect eggs and their survival status based on the geometric and physical characteristics of the insect eggs includes: If the length, width, height, volume, specific surface area, sphericity, and physical characteristics of the insect egg are all within the range of the preset insect egg model, then it is determined whether the insect egg area contains live insect eggs; otherwise, it is determined to be inactive insect eggs or debris filling the cavity.

6. A rapid detection device for insect eggs inside grains that integrates the structural features of insect eggs and insect holes, characterized in that, include: An image acquisition module is used to acquire scanned images of grain piles, which are grayscale digital images. A 3D reconstruction module for performing 3D reconstruction on scanned images of grain piles to obtain multi-grain grain pile stereo images; An image segmentation module used for segmenting three-dimensional images of multi-grain piles to obtain images of single grains or multiple grain units; A wormhole region identification module is used to identify wormhole regions within images of single or multiple grains of food based on the biological characteristics of pests. An egg region identification module for identifying whether a wormhole region is an egg region based on wormhole structural features; as well as An insect egg identification module used to identify whether there are live insect eggs within an area based on the geometric and physical characteristics of the insect eggs; The geometric characteristics of the insect eggs include the length, width, height, specific surface area, volume, and sphericity of the eggs. The physical characteristics include an egg density feature, which is estimated based on a linear relationship between the grayscale values ​​and density of a grayscale image, wherein: The linear relationship is expressed as follows: ； Where ρ1, ρ2, and ρ3 represent the densities of air, grain particles, and insect eggs, respectively; and G1, G2, and G3 represent the gray values ​​of air, grain particles, and insect eggs, respectively. The density ρ2 of the grain particles is calculated based on M / V, where M represents the mass of the grain particles and V represents the volume of the grain particles. The air density ρ1 is determined based on the altitude and temperature of the test area. The grayscale values ​​G1, G2, and G3 for the air, grain particles, and insect eggs are as follows: By reading the grayscale values ​​of the grayscale image, the grayscale values ​​of multiple points in the image area between the insect egg and the grain are randomly selected within the insect egg region and averaged to obtain the air grayscale value G1. The grayscale values ​​of multiple points in the corresponding part of the image area of ​​the non-insect hole area of ​​the grain are randomly selected and averaged to obtain the grain grain grayscale value G2. The grayscale values ​​of multiple points in the image area inside the insect egg within the insect egg region are randomly selected and averaged to obtain the insect egg grayscale value G3.

7. A rapid detection system for insect eggs inside grains that integrates the structural features of insect eggs and insect holes, characterized in that, include: One or more processors; A memory that stores operable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, including the process of performing the method of any one of claims 1-5.

8. A computer-readable medium for storing software, characterized in that, The software includes instructions executable by one or more computers, which, when executed by one or more computers, implement the process of the method as described in any one of claims 1-5.

Images