Model-based termite identification monitoring early warning method and system

Abstract

The invention discloses a termite identification monitoring early warning method and system based on a model, and the method comprises the steps: obtaining an area to be identified, placing an ant gnawing bait, shooting the area to be identified when an ant gnaws the termite gnawing bait, and obtaining a shot image; a termite recognition model is set, a termite recognition value in the shot image is calculated, and when the termite recognition value exceeds a preset threshold value, the ants are termites; all ants in the shot image are recognized, the number of the recognized termites is counted, and when the number of the termites exceeds a preset number threshold value, warning information is sent out.

Description

Technical Field

[0001] The present invention belongs to the technical field of termite identification, and more specifically, relates to a model-based termite identification, monitoring and early warning method and system. Background Art

[0002] The primary impact of termites on buildings is their destruction of wood and other organic matter. They feed on the cellulose in wood, causing damage to wooden structures such as beams, floors, and door and window frames. In severe cases, this can compromise a building's load-bearing capacity and even threaten its safety. Termites often nest inside wood, making them difficult to detect and causing long-term, hidden damage that can ultimately lead to structural instability, property damage, and high repair costs. Therefore, termite-proofing measures and regular inspections are essential during building design and construction to prevent termite infestation.

[0003] However, the current identification of termites still mainly relies on manual inspection, resulting in low efficiency. Summary of the Invention

[0004] To solve the above technical problems, the present invention proposes a model-based termite identification, monitoring and early warning method, comprising:

[0005] Acquire an area to be identified and place ant-eating bait therein; when ants gnaw on the termite-eating bait, photograph the area to be identified and obtain a photographed image;

[0006] Setting a termite recognition model to calculate a termite recognition value in the captured image, and when the termite recognition value exceeds a preset threshold, the ants are termites;

[0007] All ants in the captured image are identified, and the number of identified termites is counted. When the number of termites exceeds a preset threshold, an alarm message is issued.

[0008] Furthermore, the termite recognition model includes:

[0009]

[0010] Among them, R is the termite recognition value, α ijis the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j), I′(i+k, j+k) is the new image pixel after detail enhancement at the captured image position (i+k, j+k), and δ is the adjustment factor of the termite recognition model.

[0011] Furthermore, the correlation degree α between the captured image (i, j) and its adjacent areas ij include:

[0012] α ij =exp(-λ·(|I′(i,j)-I′(i+k,j+k)| β′ ))

[0013] Here, λ is a first adjustment factor of the correlation between the captured image (i, j) and its adjacent areas, and β′ is a second adjustment factor of the correlation between the captured image (i, j) and its adjacent areas.

[0014] Furthermore, the morphological constraint mapping value M(I′(i, j)) of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0015]

[0016] Wherein, β is the first adjustment factor of the morphological constraint mapping value, δ′(i, j) is the average pixel value of the area where the captured image position (i, j) is located, γ is the second adjustment factor of the morphological constraint mapping value, and δ″ is the third adjustment factor of the morphological constraint mapping value.

[0017] Furthermore, the new image I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0018]

[0019] Where r is the point in the perturbation set, R is the perturbation set, I(i, j) is the pixel at position (i, j) in the captured image, I(i+r, j+r) is the pixel at position (i+r, j+r) in the captured image, n is the first adjustment factor of the new image, α′ is the second adjustment factor of the new image, and γ is the third adjustment factor of the new image.

[0020] Furthermore, the perturbation set R is a classic 8-neighborhood perturbation set or an extended neighborhood perturbation set.

[0021] Furthermore, all adjustment factors are fitted by ant colony algorithm or gradient descent method.

[0022] Furthermore, the method further includes marking the termites identified in the captured image and displaying the mark on a large screen.

[0023] The present invention also proposes a model-based termite identification, monitoring and early warning system, comprising:

[0024] An image capturing module is used to capture an area to be identified and place ants gnawing on the bait. When ants gnaw on the bait, the area to be identified is captured and an image is captured.

[0025] A termite recognition module, configured to set a termite recognition model and calculate a termite recognition value in the captured image. When the termite recognition value exceeds a preset threshold, the ants are termites.

[0026] The alarm module is used to identify all ants in the captured image and count the number of identified termites, and issue an alarm message when the number of termites exceeds a preset threshold.

[0027] Furthermore, the termite recognition model includes:

[0028]

[0029] Among them, R is the termite recognition value, α ij is the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j), I′(i+k, j+k) is the new image pixel after detail enhancement at the captured image position (i+k, j+k), and δ is the adjustment factor of the termite recognition model.

[0030] like Figure 5 and 6 As shown, in general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:

[0031] The present invention automatically identifies termites through artificial intelligence, significantly improving the accuracy and efficiency of termite identification and ensuring building safety to the greatest extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0033] Figure 2 is a schematic structural diagram of embodiment 2 of the present invention;

[0034] Figure 3 This is a rendering of Example 1 of the present invention;

[0035] Figure 4 This is a visual display diagram of Example 1 of the present invention;

[0036] Figure 5 and Figure 6 It is the overall effect diagram of the present invention. DETAILED DESCRIPTION

[0037] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0038] The method provided by the present invention can be implemented in the following terminal environment, wherein the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0039] A processor can include one or more processing cores. It connects various components within the terminal using various interfaces and circuits. It executes instructions, programs, code sets, or instruction sets stored in storage media, and accesses data stored in storage media to perform various terminal functions and process data.

[0040] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets, or instructions.

[0041] The display is used to show the user interface of each application.

[0042] In addition, those skilled in the art will appreciate that the structure of the terminal described above does not limit the terminal. The terminal may include more or fewer components, or a combination of certain components, or a different arrangement of components. For example, the terminal may also include a radio frequency circuit, an input unit, a sensor, an audio circuit, a power supply, and other components, which will not be described in detail here.

[0043] Example 1

[0044] like Figure 1 This embodiment proposes a model-based termite identification, monitoring and early warning method, including:

[0045] Step 101: obtaining an area to be identified and placing ant bait. When ants gnaw on the termite bait, the area to be identified is photographed and an image is obtained.

[0046] Step 102, set the termite recognition model (effect as Figure 3 ), calculating a termite identification value in the captured image, and when the termite identification value exceeds a preset threshold, the ants are termites;

[0047] Specifically, the termite identification model includes:

[0048]

[0049] Among them, R is the termite recognition value, α ij is the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j) (it represents the neighborhood area around the position (i, j), specifically, P(i, j) contains the neighborhood set centered on the position (i, j), the purpose of which is to capture the morphological changes of the termite), I′(i+k, j+k) is the new image pixel after detail enhancement at the captured image position (i+k, j+k), and δ is the adjustment factor of the termite recognition model.

[0050] This embodiment designs a correlation calculation method to capture the overall distribution of termites in the image. Specifically, the correlation α between the captured image (i, j) and its adjacent areas ij include:

[0051] α ij =exp(-λ·(|I′(i,j)-I′(i+k,j+k)| β′ ))

[0052] Here, λ is a first adjustment factor of the correlation between the captured image (i, j) and its adjacent areas, and β′ is a second adjustment factor of the correlation between the captured image (i, j) and its adjacent areas.

[0053] Specifically, the morphological constraint mapping value M(I′(i, j)) of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0054]

[0055] Where β is the first adjustment factor of the morphological constraint mapping value, δ′(i, j) is the average pixel value of the area where the captured image position (i, j) is located (the area where the captured image position (i, j) is located can be selected from pixels within a certain range around the position (i, j), such as a 3x3 or 5x5 window), γ is the second adjustment factor of the morphological constraint mapping value, and δ" is the third adjustment factor of the morphological constraint mapping value.

[0056] Specifically, the new image I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0057]

[0058] Where r is the point in the perturbation set, R is the perturbation set, I(i, j) is the pixel at position (i, j) in the captured image, I(i+r, j+r) is the pixel at position (i+r, j+r) in the captured image, n is the first adjustment factor of the new image, α′ is the second adjustment factor of the new image, and γ is the third adjustment factor of the new image.

[0059] Specifically, the perturbation set R is a classic 8-neighborhood perturbation set or an extended neighborhood perturbation set.

[0060] Specifically, all adjustment factors are fitted by using an ant colony algorithm or a gradient descent method.

[0061] Step 103: Identify all ants in the captured image and count the number of identified termites. When the number of termites exceeds a preset threshold, issue an alarm.

[0062] like Figure 4 What is shown is a visual display diagram, which specifically includes marking the termites identified in the captured image and displaying it on a large screen.

[0063] Example 2

[0064] like Figure 2 As shown, this embodiment proposes a model-based termite identification, monitoring and early warning system, including:

[0065] An image capturing module is used to capture an area to be identified and place ants gnawing on the bait. When ants gnaw on the bait, the area to be identified is captured and an image is captured.

[0066] A termite recognition module, configured to set a termite recognition model and calculate a termite recognition value in the captured image. When the termite recognition value exceeds a preset threshold, the ants are termites.

[0067] Specifically, the termite identification model includes:

[0068]

[0069] Among them, R is the termite recognition value, α ij is the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j), I′(i+k, j+k) is the new image pixel after detail enhancement at the captured image position (i+k, j+k), and δ is the adjustment factor of the termite recognition model.

[0070] Specifically, the correlation degree α between the captured image (i, j) and its adjacent areas ij include:

[0071] α ij =exp(-λ·(|I′(i,j)-I′(i+k,j+k)| β′ ))

[0072] Here, λ is a first adjustment factor of the correlation between the captured image (i, j) and its adjacent areas, and β′ is a second adjustment factor of the correlation between the captured image (i, j) and its adjacent areas.

[0073] Specifically, the morphological constraint mapping value M(I′(i,j)) of the termite in the new image pixel I′(i,j) after detail enhancement at the captured image position (i,j) includes:

[0074]

[0075] Where β is the first adjustment factor of the morphological constraint mapping value, δ′(i, j) is the average pixel value of the area where the captured image position (i, j) is located, γ is the second adjustment factor of the morphological constraint mapping value, and δ″ is the third adjustment factor of the morphological constraint mapping value.

[0076] Specifically, the new image I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0077]

[0078] Where r is the point in the perturbation set, R is the perturbation set, I(i, j) is the pixel at position (i, j) in the captured image, I(i+r, j+r) is the pixel at position (i+r, j+r) in the captured image, n is the first adjustment factor of the new image, α′ is the second adjustment factor of the new image, and γ is the third adjustment factor of the new image.

[0079] Specifically, the perturbation set R is a classic 8-neighborhood perturbation set or an extended neighborhood perturbation set.

[0080] Specifically, all adjustment factors are fitted by using an ant colony algorithm or a gradient descent method.

[0081] The alarm module is used to identify all ants in the captured image and count the number of identified termites, and issue an alarm message when the number of termites exceeds a preset threshold.

[0082] Specifically, the method further includes marking the termites identified in the captured image and displaying the mark on a large screen.

[0083] Example 3

[0084] An embodiment of the present invention further provides a storage medium storing a plurality of instructions, wherein the instructions are used to implement the model-based termite identification, monitoring and early warning method.

[0085] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0086] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, obtaining an area to be identified and placing ant-eating bait, and when ants gnaw on the termite-eating bait, photographing the area to be identified and acquiring a photographed image;

[0087] Step 102: Setting a termite recognition model to calculate a termite recognition value in the captured image. When the termite recognition value exceeds a preset threshold, the ants are termites.

[0088] Specifically, the termite identification model includes:

[0089]

[0090] Among them, R is the termite recognition value, α ij is the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j), I′(i+k,j+k) is the new image pixel after detail enhancement at the captured image position (i+k,j+k), and δ is the adjustment factor of the termite recognition model.

[0091] Specifically, the correlation degree α between the captured image (i, j) and its adjacent areas ij include:

[0092] α ij =exp(-λ·(|I′(i,j)-I′(i+k,j+k)| β′ ))

[0093] Here, λ is a first adjustment factor of the correlation between the captured image (i, j) and its adjacent areas, and β′ is a second adjustment factor of the correlation between the captured image (i, j) and its adjacent areas.

[0094] Specifically, the morphological constraint mapping value M(I′(i, j)) of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0095]

[0096] Wherein, β is the first adjustment factor of the morphological constraint mapping value, δ′(i, j) is the average pixel value of the area where the captured image position (i, j) is located, γ is the second adjustment factor of the morphological constraint mapping value, and δ″ is the third adjustment factor of the morphological constraint mapping value.

[0097] Specifically, the new image I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0098]

[0099] Where r is the point in the perturbation set, R is the perturbation set, I(i, j) is the pixel at position (i, j) in the captured image, I(i+r, j+r) is the pixel at position (i+r, j+r) in the captured image, n is the first adjustment factor of the new image, α′ is the second adjustment factor of the new image, and γ is the third adjustment factor of the new image.

[0100] Specifically, the perturbation set R is a classic 8-neighborhood perturbation set or an extended neighborhood perturbation set.

[0101] Specifically, all adjustment factors are fitted by using an ant colony algorithm or a gradient descent method.

[0102] Step 103: Identify all ants in the captured image and count the number of identified termites. When the number of termites exceeds a preset threshold, issue an alarm.

[0103] Specifically, the method further includes marking the termites identified in the captured image and displaying the mark on a large screen.

[0104] Example 4

[0105] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the model-based termite identification, monitoring and early warning method.

[0106] Specifically, the electronic device of this embodiment may be a computer terminal, which may include: one or more processors, and a storage medium.

[0107] The storage medium can be used to store software programs and modules, such as the corresponding program instructions / modules for a model-based termite identification, monitoring, and early warning method in an embodiment of the present invention. The processor executes the software programs and modules stored in the storage medium to perform various functional applications and data processing, thereby implementing the aforementioned model-based termite identification, monitoring, and early warning method. The storage medium can include high-speed random access memory (RAM) and non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some embodiments, the storage medium can further include storage media remotely located relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0108] The processor can call the information and application stored in the storage medium through the transmission system to perform the following steps: Step 101, obtain an area to be identified and place ant-eating bait, when ants gnaw on the termite-eating bait, photograph the area to be identified and obtain the photographed image;

[0109] Step 102: Setting a termite recognition model to calculate a termite recognition value in the captured image. When the termite recognition value exceeds a preset threshold, the ants are termites.

[0110] Specifically, the termite identification model includes:

[0111]

[0112] Among them, R is the termite recognition value, α ijis the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j), I′(i+k,j+k) is the new image pixel after detail enhancement at the captured image position (i+k,j+k), and δ is the adjustment factor of the termite recognition model.

[0113] Specifically, the correlation degree αij between the captured image (i, j) and its adjacent areas includes:

[0114] α ij =exp(-λ·(|I′(i,j)-I′(i+k,j+k)| β′ ))

[0115] Here, λ is a first adjustment factor of the correlation between the captured image (i, j) and its adjacent areas, and β′ is a second adjustment factor of the correlation between the captured image (i, j) and its adjacent areas.

[0116] Specifically, the morphological constraint mapping value M(I′(i,j)) of the termite in the new image pixel I′(i,j) after detail enhancement at the captured image position (i,j) includes:

[0117]

[0118] Where β is the first adjustment factor of the morphological constraint mapping value, δ′(i, j) is the average pixel value of the area where the captured image position (i, j) is located, γ is the second adjustment factor of the morphological constraint mapping value, and δ" is the third adjustment factor of the morphological constraint mapping value.

[0119] Specifically, the new image I′(i, j) after detail enhancement at the captured image position (i, j) includes:

[0120]

[0121] Where r is the point in the perturbation set, R is the perturbation set, I(i, j) is the pixel at position (i, j) in the captured image, I(i+r, j+r) is the pixel at position (i+r, j+r) in the captured image, n is the first adjustment factor of the new image, α′ is the second adjustment factor of the new image, and γ is the third adjustment factor of the new image.

[0122] Specifically, the perturbation set R is a classic 8-neighborhood perturbation set or an extended neighborhood perturbation set.

[0123] Specifically, all adjustment factors are fitted by using an ant colony algorithm or a gradient descent method.

[0124] Step 103: Identify all ants in the captured image and count the number of identified termites. When the number of termites exceeds a preset threshold, issue an alarm.

[0125] Specifically, the method further includes marking the termites identified in the captured image and displaying the mark on a large screen.

[0126] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0127] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, and can be electrical or other forms.

[0129] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0130] 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. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium 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: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0132] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will readily appreciate that other variations or modifications based on the above descriptions are possible. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A model-based termite identification, monitoring and early warning method, characterized in that: include: Acquire an area to be identified and place ant-eating bait therein; when ants gnaw on the termite-eating bait, photograph the area to be identified and obtain a photographed image; Setting a termite recognition model to calculate a termite recognition value in the captured image, and when the termite recognition value exceeds a preset threshold, the ants are termites; All ants in the captured image are identified, and the number of identified termites is counted. When the number of termites exceeds a preset threshold, an alarm message is issued.

2. The model-based termite identification, monitoring and early warning method according to claim 1, characterized in that: Termite identification models include: Among them, R is the termite recognition value, α ij is the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j), I′(i+k, j+k) is the new image pixel after detail enhancement at the captured image position (i+k, j+k), and δ is the adjustment factor of the termite recognition model.

3. The model-based termite identification, monitoring and early warning method according to claim 2, characterized in that: The correlation degree α between the captured image (i, j) and its adjacent areas ij include: α ij =exp(-λ·(|I′(i,j)-I′(i+k,j+k)| β′ )) Here, λ is a first adjustment factor of the correlation between the captured image (i, j) and its adjacent areas, and β′ is a second adjustment factor of the correlation between the captured image (i, j) and its adjacent areas.

4. The model-based termite identification, monitoring and early warning method according to claim 2, characterized in that: The morphological constraint mapping value M(I′(i,j)) of the termite in the new image pixel I′(i,j) after detail enhancement at the captured image position (i,j) includes: Where β is the first adjustment factor of the morphological constraint mapping value, δ′(i, j) is the average pixel value of the area where the captured image position (i, j) is located, γ is the second adjustment factor of the morphological constraint mapping value, and δ″ is the third adjustment factor of the morphological constraint mapping value.

5. The model-based termite identification, monitoring and early warning method according to claim 2, characterized in that: The new image I′(i, j) after detail enhancement at the captured image position (i, j) includes: Where r is the point in the perturbation set, R is the perturbation set, I(i, j) is the pixel at position (i, j) in the captured image, I(i+r, j+r) is the pixel at position (i+r, j+r) in the captured image, n is the first adjustment factor of the new image, α′ is the second adjustment factor of the new image, and γ is the third adjustment factor of the new image.

6. The model-based termite identification, monitoring and early warning method according to claim 2, characterized in that: The perturbation set R is the classic 8-neighborhood perturbation set or the extended neighborhood perturbation set.

7. A model-based termite identification, monitoring and early warning method according to any one of claims 1 to 6, characterized in that: All adjustment factors are fitted using ant colony algorithm or gradient descent method.

8. The model-based termite identification, monitoring and early warning method according to claim 1, characterized in that: The method also includes marking the termites identified in the captured image and displaying the image on a large screen.

9. A model-based termite identification, monitoring and early warning system, characterized in that: include: An image capturing module is used to capture an area to be identified and place ants gnawing on the bait. When ants gnaw on the bait, the area to be identified is captured and an image is captured. A termite recognition module, configured to set a termite recognition model and calculate a termite recognition value in the captured image. When the termite recognition value exceeds a preset threshold, the ants are termites. The alarm module is used to identify all ants in the captured image and count the number of identified termites, and issue an alarm message when the number of termites exceeds a preset threshold.

10. The model-based termite identification, monitoring and early warning system according to claim 9, characterized in that: Termite identification models include: Among them, R is the termite recognition value, α ij is the correlation between the captured image position (i, j) and its adjacent areas, i is the abscissa of the captured image position (i, j), j is the ordinate of the captured image position (i, j), M(I′(i, j)) is the morphological constraint mapping value of the termite in the new image pixel I′(i, j) after detail enhancement at the captured image position (i, j), which is used to describe the morphological characteristics of the termite, k is a point in the neighborhood set, P(i, j) is the neighborhood set of the position (i, j), I′(i+k,j+k) is the new image pixel after detail enhancement at the captured image position (i+k,j+k), and δ is the adjustment factor of the termite recognition model.

Images