Breeding type determination method, program product, electronic equipment and storage medium
By calculating the red light and near-infrared reflectivity in the multispectral imaging data of aquaculture ponds, the breeding type was determined, and the difference identification problem of remote sensing classification of aquaculture ponds was solved, and the precise distinction between fish and crab farming and non-fish and crab farming was achieved.
Patent Information
- Application Number
- CN202510425244.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-07
- Publication Date
- 2025-07-08
AI Technical Summary
The existing technology lacks universal remote sensing classification methods for aquaculture ponds, and it is particularly difficult to distinguish the differences between farming ponds of different breeding varieties and forms.
By obtaining multispectral imaging data of the area to be identified, the classification index of surface red light reflectivity and near-infrared reflectivity is calculated, and the breeding types are determined using preset index thresholds, including fish and crab farming and non-fish crab farming.
Accurate remote sensing classification of aquaculture ponds is realized, and the areas of fish and crab farming and non-fish crab farming are accurately distinguished, improving the classification accuracy.
Smart Images
Figure CN120279329A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of aquaculture, and more particularly, to a method for determining aquaculture types, a program product, an electronic device, and a storage medium. Background Art
[0002] Remote sensing observation has the characteristics of large area and good timeliness, and has been applied to the extraction and monitoring of aquaculture ponds.
[0003] However, the remote sensing extraction technology for aquaculture ponds is not yet mature. In particular, there is little research on the differences between aquaculture ponds with different aquaculture species and aquaculture forms, and there is no universal remote sensing classification method for aquaculture ponds. Summary of the Invention
[0004] In view of this, the purpose of the embodiments of this application is to provide a method for determining aquaculture types, a program product, an electronic device, and a storage medium to solve the above technical problems.
[0005] In a first aspect, an embodiment of this application provides a method for determining aquaculture types, and the method includes:
[0006] Obtain multispectral imaging data of the area to be identified; wherein, the multispectral imaging data includes: the surface red light reflectance of the area to be identified for the red light band B4 and the surface near-infrared reflectance for the near-infrared band B8A;
[0007] Calculate a first classification index of the area to be identified according to the surface red light reflectance, the surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within a first preset time period;
[0008] Determine the aquaculture type to which the area to be identified belongs according to the first classification index and a preset index threshold; wherein, the aquaculture type includes fish and crab aquaculture and non-fish and crab aquaculture.
[0009] In the above implementation process, the aquaculture type determination method includes: obtaining multispectral imaging data of the area to be recognized; wherein, the multispectral imaging data includes: the surface red light reflectance of the area to be recognized for the red light band B4 and the surface near-infrared reflectance for the near-infrared band B8A; calculating a first classification index of the area to be recognized according to the surface red light reflectance, the surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within a first preset time period; determining the aquaculture type to which the area to be recognized belongs according to the first classification index and a preset index threshold; wherein, the aquaculture type includes fish and crab aquaculture and non-fish and crab aquaculture. This method calculates the first classification index of the area to be recognized through the surface red light reflectance and the surface near-infrared reflectance of the area to be recognized within a first preset time period; and accurately determines the aquaculture type to which the area to be recognized belongs according to the first classification index and the preset index threshold. Therefore, based on the aquaculture type determination method provided in this application, remote sensing classification of aquaculture ponds can be achieved based on multispectral imaging data.
[0010] Optionally, in the embodiment of this application, the first preset time period includes: a first time period when the area to be recognized is in a non-frozen state; calculating the first classification index of the area to be recognized according to the surface red light reflectance, the surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within the first preset time period includes: according to the surface red light reflectance ρ B4 , the surface near-infrared reflectance ρ B8A , the central wavelength λ of the red light band B4 B4 , the central wavelength λ of the near-infrared band B8A B8A and calculate the first classification index LASCI of the area to be recognized.
[0011] In the above implementation process, by based on the surface red light reflectance, the surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within the first time period when the area to be recognized is in a non-frozen state, the first classification index of the area to be recognized can be calculated more accurately.
[0012] Optionally, in the embodiments of the present application, the method for determining the preset index threshold includes: obtaining the fish and crab spectral imaging data of the fish and crab breeding area and the non-fish and crab spectral imaging data of the non-fish and crab breeding area; wherein, the fish and crab spectral imaging data includes: the red light reflectance of the fish and crab surface in the red light band B4 and the near-infrared reflectance of the fish and crab surface in the near-infrared band B8A in the fish and crab breeding area; the non-fish and crab spectral imaging data includes: the red light reflectance of the non-fish and crab surface in the red light band B4 and the near-infrared reflectance of the non-fish and crab surface in the near-infrared band B8A in the non-fish and crab breeding area; calculating the fish and crab classification index of the fish and crab breeding area according to the red light reflectance of the fish and crab surface, the near-infrared reflectance of the fish and crab surface, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within the first preset time period; calculating the non-fish and crab classification index of the non-fish and crab breeding area according to the red light reflectance of the non-fish and crab surface, the near-infrared reflectance of the non-fish and crab surface, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within the first preset time period; determining the training classification results of the fish and crab breeding area and the non-fish and crab breeding area according to the fish and crab classification index, the non-fish and crab classification index, and the current index threshold; calculating the current classification accuracy corresponding to the current index threshold according to the training classification results; when the current classification accuracy meets the accuracy requirement, determining the current index threshold as the preset index threshold; when the current classification accuracy does not meet the accuracy requirement, updating the current index threshold until the classification accuracy corresponding to the updated current index threshold meets the accuracy requirement.
[0013] In the above implementation process, by obtaining the fish and crab spectral imaging data of the fish and crab breeding area and the non-fish and crab spectral imaging data of the non-fish and crab breeding area, and calculating the current classification accuracy corresponding to the current index threshold according to the fish and crab classification index of the fish and crab breeding area and the non-fish and crab classification index of the non-fish and crab breeding area; and when the current classification accuracy does not meet the accuracy requirement, updating the current index threshold until the classification accuracy corresponding to the updated current index threshold meets the accuracy requirement. To determine the preset index threshold that can meet the actual accuracy requirement.
[0014] Optionally, in the embodiments of the present application, the multispectral imaging data further includes: the surface red edge reflectance of the non-fish and crab breeding area in the red edge band B5; the method further includes: calculating the second classification index of the non-fish and crab breeding area according to the surface red light reflectance, the surface red edge reflectance, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; determining the breeding type of the non-fish and crab breeding area according to the change rate of the second classification index within the second preset time period; wherein, the breeding type of the non-fish and crab breeding area includes sea cucumber breeding and shrimp breeding.
[0015] In the above implementation process, according to the surface red light reflectance, surface red edge reflectance, central wavelength of the red light band B4, and central wavelength of the red edge band B5, the second classification index of the non-fish and crab farming area can be calculated; and according to the change rate of the second classification index, the farming type of the non-fish and crab farming area can be further determined, so as to more precisely determine the farming type of the area to be recognized.
[0016] Optionally, in the embodiment of the present application, calculating the second classification index of the non-fish and crab farming area according to the surface red light reflectance, the surface red edge reflectance, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5 includes: according to the surface red light reflectance ρ B4 , the surface red edge reflectance ρ B5 , the central wavelength λ of the red light band B4 B4 , the central wavelength λ of the red edge band B5 B5 and calculate the second classification index SPCI of the non-fish and crab farming area.
[0017] Optionally, in the embodiment of the present application, the second preset time period includes: two second preset sub-time periods when the area to be recognized is in a non-frozen state; determining the farming type of the non-fish and crab farming area according to the change rate of the second classification index within the second preset time period includes: determining the farming type of the non-fish and crab farming area according to the change rate of the second classification index within each second preset sub-time period, the second change threshold, and the third change threshold.
[0018] In the above implementation process, by based on the change rate of the second classification index within the second preset sub-time period when the area to be recognized is in a non-frozen state, the farming type of the non-fish and crab farming area can be determined more accurately.
[0019] Optionally, in the embodiments of the present application, the method for determining the second change threshold and the third change threshold includes: obtaining the sea cucumber spectral imaging data of the sea cucumber breeding area and the shrimp spectral imaging data of the shrimp breeding area; wherein, the sea cucumber spectral imaging data includes: the red light reflectance of the sea cucumber surface in the red light band B4 and the red edge reflectance of the sea cucumber surface in the red edge band B5 in the sea cucumber breeding area; the shrimp spectral imaging data includes: the red light reflectance of the shrimp surface in the red light band B4 and the red edge reflectance of the shrimp surface in the red edge band B5 in the shrimp breeding area; calculating the sea cucumber classification index of the sea cucumber breeding area according to the red light reflectance of the sea cucumber surface, the red edge reflectance of the sea cucumber surface, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; calculating the shrimp classification index of the shrimp breeding area according to the red light reflectance of the shrimp surface, the red edge reflectance of the shrimp surface, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; determining the training breeding type of the non-fish and crab breeding area according to the change rate of the sea cucumber classification index, the change rate of the shrimp classification index, the second current change threshold, and the third current change threshold in each second preset sub-time period; calculating the current classification accuracy corresponding to the second current change threshold and the third current change threshold according to the training breeding type; when the current classification accuracy meets the accuracy requirement, determining the second current change threshold as the second change threshold and the third current change threshold as the third change threshold; when the current classification accuracy does not meet the accuracy requirement, updating the second current change threshold and / or the third current change threshold until the classification accuracy corresponding to the updated second current change threshold and the third current change threshold meets the accuracy requirement.
[0020] In the above implementation process, by obtaining the sea cucumber spectral imaging data of the sea cucumber breeding area and the shrimp spectral imaging data of the shrimp breeding area, and calculating the current classification accuracy corresponding to the second current change threshold and the third current change threshold according to the sea cucumber classification index of the sea cucumber breeding area and the shrimp classification index of the shrimp breeding area; and when the current classification accuracy does not meet the accuracy requirement, updating the second current change threshold and / or the third current change threshold until the classification accuracy corresponding to the updated second current change threshold and the third current change threshold meets the accuracy requirement. To determine the second change threshold and the third change threshold that can meet the actual accuracy requirement.
[0021] In a second aspect, the embodiments of the present application provide a computer program product, including a computer program / instructions, which when executed by a processor implement the breeding type determination method as described in any one of the above first aspects.
[0022] In a third aspect, an embodiment of the present application further provides an electronic device; the electronic device includes:
[0023] a memory;
[0024] a processor;
[0025] A computer program executable by the processor is stored on the memory. When the computer program is executed by the processor, the aquaculture type determination method according to any one of the first aspects is executed.
[0026] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium. Computer program instructions are stored on the computer-readable storage medium. When the computer program instructions are run by a processor, the aquaculture type determination method according to any one of the first aspects is executed.
[0027] The beneficial effects of the present application at least include: The aquaculture type determination method calculates the first classification index of the area to be recognized through the surface red light reflectance and surface near-infrared reflectance of the area to be recognized within the first preset time period; and accurately determines the aquaculture type to which the area to be recognized belongs according to the first classification index and the preset index threshold. Therefore, based on the aquaculture type determination method provided by the present application, remote sensing classification of aquaculture ponds can be realized based on multispectral imaging data. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.
[0029] Figure 1 A flowchart of an aquaculture type determination method provided by an embodiment of the present application;
[0030] Figure 2 A numerical diagram of the first classification index of an aquaculture pond provided by an embodiment of the present application;
[0031] Figure 3 A classification accuracy diagram corresponding to different preset index thresholds provided by an embodiment of the present application;
[0032] Figure 4 A flowchart of another aquaculture type determination method provided by an embodiment of the present application;
[0033] Figure 5 A numerical diagram of the second classification index of an aquaculture pond provided by an embodiment of the present application;
[0034] Figure 6 A schematic diagram of classification accuracy corresponding to different change thresholds provided by an embodiment of the present application;
[0035] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners
[0036] The embodiments of the technical solutions of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solutions of the present application more clearly, and therefore are only examples and cannot be used to limit the protection scope of the present application.
[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.
[0038] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present application, "a plurality of" means two or more unless otherwise specifically defined.
[0039] Please refer to Figure 1 A schematic flowchart of a method for determining a farming type provided by an embodiment of the present application. The method for determining the farming type may include the following steps:
[0040] S101. Obtain multispectral imaging data of the area to be recognized; wherein, the multispectral imaging data includes: the surface red light reflectance of the area to be recognized for the red light band B4 and the surface near-infrared reflectance for the near-infrared band B8A;
[0041] S102. Calculate a first classification index of the area to be recognized according to the surface red light reflectance, the surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within a first preset time period;
[0042] S103. Determine the farming type to which the area to be recognized belongs according to the first classification index and a preset index threshold; wherein, the farming type includes fish and crab farming and non-fish and crab farming.
[0043] Among them, in step S101, the area to be recognized may include one or more aquaculture ponds. When the area to be recognized includes multiple aquaculture ponds, the multiple aquaculture ponds in the area to be recognized can be first recognized based on the shape of the aquaculture ponds and the method of object-oriented classification or machine learning classification; then, based on the aquaculture type determination method provided in this application, the aquaculture type of each aquaculture pond can be determined. When the area to be recognized includes multiple aquaculture ponds, the aquaculture types to which different areas in the area to be recognized belong can also be directly determined according to the multi-spectral imaging data of the area. The multi-spectral imaging data can be from satellite images (for example, Sentinel-2 satellite images). The surface red light reflectance refers to the surface reflectance of the area to be recognized for the red light band B4, and the surface near-infrared reflectance refers to the surface reflectance of the area to be recognized for the near-infrared band B8A.
[0044] Among them, in step S102, the red light band B4 refers to a band with a central wavelength of 665 nanometers and a bandwidth of 30 nanometers; the near-infrared band B8A refers to a band with a central wavelength of 865 nanometers and a bandwidth of 20 nanometers. The above first preset time period can be determined based on the time when the area to be recognized is in a non-frozen state; the duration of the first preset time period can be one month, or half a month, six months, or ten months. The specific time range of the first preset time period can be adjusted according to the actual application situation (for example, the regional location or regional climate of the area to be recognized, etc.). The first classification index of the area to be recognized can be calculated based on the first difference between the surface red light reflectance and the surface near-infrared reflectance and the second difference between the central wavelength of the red light band B4 and the central wavelength of the near-infrared band B8A. Specifically, the first classification index of the area to be recognized can be calculated based on the ratio of the first difference to the second difference, or based on the ratio of the second difference to the first difference; this application does not make specific limitations on this.
[0045] Among them, in step S103, the aquaculture type to which the area to be recognized belongs can be determined based on the magnitude relationship between the mean value of the first classification index within a certain period of time and the preset index threshold. When calculating the first classification index of the area to be recognized based on the ratio of the first difference to the second difference, or based on the ratio of the second difference to the first difference: the preset index threshold can be 0.
[0046] Please refer to Figure 2 , Figure 2 which is a numerical schematic diagram of the first classification index of an aquaculture pond provided by an embodiment of this application. Figure 2It shows the situation where each 10 days is a node and "calculate the first classification index of the area to be recognized based on the ratio of the first difference and the second difference", and specifically shows the schematic diagram of the numerical change of the first classification index of sea cucumber breeding ponds, prawn breeding ponds and fish and crab breeding ponds in the Liaoning area during the non-freezing period (from March to November). As Figure 2 shown, based on the magnitude relationship between the first classification index within the first preset time period (which can be at least a period of time from March or from July to November) and the preset index threshold (for example, 0), it can be accurately determined whether the area to be recognized is fish and crab breeding or non-fish and crab breeding.
[0047] It can be seen that the breeding type determination method provided by the embodiments of the present application can calculate the first classification index of the area to be recognized through the surface red light reflectance and the surface near-infrared reflectance of the area to be recognized within the first preset time period; and accurately determine the breeding type to which the area to be recognized belongs according to the first classification index and the preset index threshold. Therefore, based on the breeding type determination method provided by the present application, remote sensing classification of aquaculture ponds can be realized based on multi-spectral imaging data.
[0048] In some optional embodiments, the first preset time period includes: the first time period when the area to be recognized is in a non-freezing state; S102. Calculate the first classification index of the area to be recognized according to the surface red light reflectance, the surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within the first preset time period, including: according to the surface red light reflectance ρ B4 、the surface near-infrared reflectance ρ B8A 、the central wavelength λ B4 of the red light band B4, the central wavelength λ B8A of the near-infrared band B8A, and calculate the first classification index LASCI of the area to be recognized.
[0049] Among them, the first preset time period can include: at least a period of time from March or from July to November. Exemplarily, the first preset time period can include one or more periods of time in March, can also include one or more periods of time from July to November, or can also include at least a period of time in March and at least a period of time from July to November at the same time. Figure 2 What is shown is " The case of "calculating the first classification index LASCI of the area to be recognized". By based on the surface red light reflectance, surface near-infrared reflectance, central wavelength of the red light band B4, and central wavelength of the near-infrared band B8A within the first time period when the area to be recognized is in a non-frozen state, the first classification index of the area to be recognized can be calculated more accurately.
[0050] In some alternative embodiments, the method for determining the preset index threshold includes: obtaining the fish and crab spectral imaging data of the fish and crab breeding area and the non-fish and crab spectral imaging data of the non-fish and crab breeding area; wherein, the fish and crab spectral imaging data includes: the fish and crab surface red light reflectance of the fish and crab breeding area for the red light band B4, the fish and crab surface near-infrared reflectance for the near-infrared band B8A; the non-fish and crab spectral imaging data includes: the non-fish and crab surface red light reflectance of the non-fish and crab breeding area for the red light band B4, the non-fish and crab surface near-infrared reflectance for the near-infrared band B8A; calculating the fish and crab classification index of the fish and crab breeding area according to the fish and crab surface red light reflectance, the fish and crab surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within the first preset time period; calculating the non-fish and crab classification index of the non-fish and crab breeding area according to the non-fish and crab surface red light reflectance, the non-fish and crab surface near-infrared reflectance, the central wavelength of the red light band B4, and the central wavelength of the near-infrared band B8A within the first preset time period; determining the training classification results of the fish and crab breeding area and the non-fish and crab breeding area according to the fish and crab classification index, the non-fish and crab classification index, and the current index threshold; calculating the current classification accuracy corresponding to the current index threshold according to the training classification results; when the current classification accuracy meets the accuracy requirement, determining the current index threshold as the preset index threshold; when the current classification accuracy does not meet the accuracy requirement, updating the current index threshold until the classification accuracy corresponding to the updated current index threshold meets the accuracy requirement.
[0051] Among them, the fish and crab farming area refers to the farming area used for farming fish and crabs. The non-fish and crab farming area may include the farming area actually used for farming sea cucumbers or shrimps. It should be noted that in the actual farming process, there may also be some shrimps or sea cucumbers in the fish and crab farming area, and there may also be some fish in the sea cucumber farming area. The farming type determined in this application refers to the main farming type of the area. The fish and crab classification index may include the probability that the fish and crab farming area is determined as the farming type of fish and crab farming, and the non-fish and crab classification index may include the probability that the non-fish and crab farming area is determined as the farming type of non-fish and crab farming. When the fish and crab classification index is greater than or equal to the current index threshold, it indicates that the fish and crab farming area can be correctly classified. The training classification results include the classification results of the fish and crab farming area and the non-fish and crab farming area. Therefore, according to the fish and crab classification index, the non-fish and crab classification index, and the current index threshold, the above training classification results can be calculated; and the current classification accuracy (that is, the probability that different farming areas can be correctly classified) can be calculated according to the training classification results. The preset index threshold can be determined by using the step-by-step search method, and during the search process, the current index threshold is updated according to the set step size. By obtaining the fish and crab spectral imaging data of the fish and crab farming area and the non-fish and crab spectral imaging data of the non-fish and crab farming area, and according to the fish and crab classification index of the fish and crab farming area and the non-fish and crab classification index of the non-fish and crab farming area, the current classification accuracy corresponding to the current index threshold is calculated; and when the current classification accuracy does not meet the accuracy requirement, the current index threshold is updated until the classification accuracy corresponding to the updated current index threshold meets the accuracy requirement. To determine the preset index threshold that can meet the actual accuracy requirement.
[0052] Please refer to Figure 3 , Figure 3 which is a schematic diagram of the classification accuracy corresponding to different index thresholds provided by an embodiment of this application. Figure 3 The abscissa represents the current index threshold, and the ordinate represents the classification accuracy. OA represents the overall accuracy, that is, the probability that the number of correctly classified samples accounts for the total number of verified samples. PA represents the mapping accuracy, that is, the number of samples X Figure 3 corresponding to non-fish and crab farming) but the actual farming variety is j ij accounts for the probability of the total number of samples classified as farming variety i. UA represents the user accuracy (before being equal to the mapping accuracy PA, that is, when the index threshold is less than 0.1, it is higher than the mapping accuracy PA; after being equal, that is, when the index threshold is greater than 0.1, it is lower than the mapping accuracy PA), that is, the number of samples X ij classified as farming variety i but the actual farming variety is j Figure 3It can be seen that starting from -2, as the current exponential threshold increases, the overall accuracy gradually rises and reaches a maximum of 84.75% at 0.11. Subsequently, the overall accuracy slowly decreases but remains around 80%. When the current exponential threshold reaches -0.57, the overall accuracy reaches 75%, and as the current exponential threshold increases, although the overall accuracy sometimes decreases, it always remains above 75%. Based on Figure 3 It can be seen that when the current exponential threshold is between -0.31 and 1.42, a good classification effect can be obtained, and the overall accuracy reaches over 80%. Therefore, the preset exponential threshold can be set between -0.31 and 1.42 (for example, 0.11). And as the current exponential threshold increases, the mapping accuracy of the sea cucumber or prawn group rises rapidly. When the current exponential threshold is greater than 0.1, the mapping accuracy reaches over 90%. However, as the current exponential threshold increases, the user accuracy of non-fish and crab farming gradually decreases but always remains around 80%.
[0053] Please refer to Figure 4 , Figure 4 which is a schematic flowchart of another method for determining the farming type provided by the embodiment of the present application. In some alternative embodiments, the multispectral imaging data further includes: the surface red edge reflectance of the non-fish and crab farming area for the red edge band B5; the method further includes: S104. Calculate the second classification index of the non-fish and crab farming area according to the surface red light reflectance, the surface red edge reflectance, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; S105. Determine the farming type of the non-fish and crab farming area according to the change rate of the second classification index within the second preset time period; wherein, the farming type of the non-fish and crab farming area includes sea cucumber farming and shrimp farming.
[0054] Among them, the red edge band B5 refers to a band with a central wavelength of 705 nanometers and a bandwidth of 15 nanometers. The above-mentioned second preset time period can be determined based on the time when the area to be recognized is in a non-frozen state; the duration of the second preset time period can be one month, or half a month, three months, or eight months. The specific time range of the second preset time period can be adjusted according to the actual application situation (for example, the regional location or regional climate of the area to be recognized, etc.). The second classification index of the non-fish and crab farming area can be calculated according to the third difference between the surface red light reflectance and the surface red edge reflectance, and the fourth difference between the central wavelength of the red light band B4 and the central wavelength of the red edge band B5. Specifically, the second classification index of the area to be recognized can be calculated based on the ratio of the third difference to the fourth difference, or based on the ratio of the fourth difference to the third difference; the present application does not make specific limitations on this.
[0055] Please refer to Figure 5 , Figure 5A numerical schematic diagram of the second classification index of an aquaculture pond provided by an embodiment of the present application. Figure 5 It shows: taking every 10 days as a node and "calculating the second classification index of the area to be identified based on the ratio of the third difference and the fourth difference", and specifically shows a numerical schematic diagram of the second classification index of sea cucumber aquaculture ponds and prawn aquaculture ponds in the Liaoning region during the non-freezing period (from March to November). As Figure 5 shown, based on the change rate of the second classification index within the second preset time period (which can be at least a period of time from March to mid-April, or at least a period of time from mid-April to July), the aquaculture type of the non-fish and crab aquaculture area can be further determined. According to the surface red light reflectance, surface red edge reflectance, central wavelength of the red light band B4, and central wavelength of the red edge band B5, the second classification index of the non-fish and crab aquaculture area can be calculated; and based on the change rate of the second classification index, the aquaculture type of the non-fish and crab aquaculture area can be further determined. To more precisely determine the aquaculture type of the area to be identified. It is also possible to determine the distribution of sea cucumber aquaculture ponds, the classification of shrimp aquaculture ponds, or the distribution of fish and crab aquaculture ponds in coastal areas or other aquaculture areas based on the aquaculture type determination method provided by the present application.
[0056] In some alternative embodiments, S104. Calculating the second classification index of the non-fish and crab aquaculture area according to the surface red light reflectance, the surface red edge reflectance, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5 includes: according to the surface red light reflectance ρ B4 、the surface red edge reflectance ρ B5 、the central wavelength λ B4 of the red light band B4, the central wavelength λ B5 of the red edge band B5, and calculating the second classification index SPCI of the non-fish and crab aquaculture area.
[0057] Wherein, Figure 5 what is shown is the situation of " calculating the second classification index SPCI of the non-fish and crab aquaculture area".
[0058] In some alternative embodiments, the second preset time period includes: two second preset sub-time periods when the area to be identified is in a non-freezing state; S105. Determining the aquaculture type of the non-fish and crab aquaculture area according to the change rate of the second classification index within the second preset time period includes: determining the aquaculture type of the non-fish and crab aquaculture area according to the change rate of the second classification index within each second preset sub-time period, the second change threshold, and the third change threshold.
[0059] Among them, one of the second preset time sub-segments may include: at least a period from March to mid-April; the other second preset time sub-segment may include: at least a period from mid-April to July. By based on the change rate of the second classification index within the second preset sub-time period when the area to be recognized is in a non-frozen state, the farming type of the non-fish and crab farming area can be determined more accurately.
[0060] In some alternative embodiments, the method for determining the second change threshold and the third change threshold includes: obtaining sea cucumber spectral imaging data of a sea cucumber farming area and shrimp spectral imaging data of a shrimp farming area; wherein, the sea cucumber spectral imaging data includes: the sea cucumber surface red light reflectance of the sea cucumber farming area for the red light band B4 and the sea cucumber surface red edge reflectance for the red edge band B5; the shrimp spectral imaging data includes: the shrimp surface red light reflectance of the shrimp farming area for the red light band B4 and the shrimp surface red edge reflectance for the red edge band B5; calculating the sea cucumber classification index of the sea cucumber farming area according to the sea cucumber surface red light reflectance, the sea cucumber surface red edge reflectance, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; calculating the shrimp classification index of the shrimp farming area according to the shrimp surface red light reflectance, the shrimp surface red edge reflectance, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; determining the training farming type of the non-fish and crab farming area according to the change rate of the sea cucumber classification index, the change rate of the shrimp classification index, the second current change threshold, and the third current change threshold within each second preset sub-time period; calculating the current classification accuracy corresponding to the second current change threshold and the third current change threshold according to the training farming type; when the current classification accuracy meets the accuracy requirement, determining the second current change threshold as the second change threshold and the third current change threshold as the third change threshold; when the current classification accuracy does not meet the accuracy requirement, updating the second current change threshold and / or the third current change threshold until the classification accuracy corresponding to the updated second current change threshold and the third current change threshold meets the accuracy requirement.
[0061] Among them, the sea cucumber farming area refers to the farming area for farming sea cucumbers and / or jellyfish, and the shrimp farming area refers to the farming area for farming shrimp. It should be noted that in actual farming, the sea cucumber farming area may also be mixed with some jellyfish. The sea cucumber classification index can include the probability that the sea cucumber farming area is determined as the farming type of sea cucumber farming, and the shrimp classification index can include the probability that the shrimp farming area is determined as the farming type of shrimp farming. Taking the second change threshold corresponding to at least a period from March to mid-April and the third change threshold corresponding to at least a period from mid-April to July as an example, it can be indicated that the sea cucumber farming area can be correctly classified when the change rate of the sea cucumber classification index within one of the second preset time sub-segments (at least a period from March to mid-April) is lower than the second current change threshold and the change rate within another second preset time sub-segment (at least a period from mid-April to July) is higher than the third current change threshold. The training farming types include the classification results of the sea cucumber farming area and the classification results of the shrimp farming area. Therefore, according to the change rate of the sea cucumber classification index, the change rate of the shrimp classification index, the second current change threshold, and the third current change threshold within each second preset sub-time period, the training farming type of the non-fish and crab farming area can be calculated; and the current classification accuracy (that is, the probability that different farming areas can be correctly classified) can be calculated according to the training farming type of the non-fish and crab farming area. Similarly, the second change threshold and the third change threshold can be determined by using the step-by-step search method, and during the search process, the second change threshold and / or the third change threshold can be updated according to the set threshold update step. By obtaining the sea cucumber spectral imaging data of the sea cucumber farming area and the shrimp spectral imaging data of the shrimp farming area, and calculating the current classification accuracy corresponding to the second current change threshold and the third current change threshold according to the sea cucumber classification index of the sea cucumber farming area and the shrimp classification index of the shrimp farming area; and when the current classification accuracy does not meet the accuracy requirement, the second current change threshold and / or the third current change threshold are updated until the classification accuracy corresponding to the updated second current change threshold and the third current change threshold meets the accuracy requirement. To determine the second change threshold and the third change threshold that can meet the actual accuracy requirement.
[0062] Please refer to Figure 6 , Figure 6 which is a schematic diagram of the classification accuracy corresponding to different change thresholds provided by the embodiments of the present application. Figure 6 The abscissa represents the second change threshold T2, and the ordinate represents the third change threshold T3. OA represents the overall accuracy, that is, the probability that the number of correctly classified samples accounts for the total number of verified samples. As Figure 6As shown, when the second change threshold T2 is 0.06, 0.07 or 0.08 and the third change threshold T3 is -0.01, the highest overall accuracy of 80.88% can be obtained; when the second change threshold T2 is between 0.05 and 0.08 and the third change threshold T3 is -0.1, -0.009 or -0.01, the overall accuracy can reach more than 80%. When the second change threshold T2 is greater than 0.02 and the third change threshold T3 is less than 0.01, the overall accuracy can reach more than 75%, and as the second change threshold T2 increases and the third change threshold T3 decreases, the overall accuracy can always remain above 75%.
[0063] The embodiment of the present application also provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the method for determining the breeding type described in any item of the first aspect above is implemented.
[0064] Please refer to Figure 7 , Figure 7 FIG. 10 is a schematic structural diagram of an electronic device 200 provided by an embodiment of the present application. The electronic device 200 includes: a memory 202 and a processor 201; a computer program executable by the processor 201 is stored on the memory 202, and when the computer program is executed by the processor 201, the method for determining the breeding type described in any item of the first aspect is executed.
[0065] Among them, the memory 202 and the processor 201 can be interconnected and communicate with each other through a communication bus 203 and / or other forms of connection mechanisms (not shown). The memory 202 stores a computer program executable by the processor 201, and when the computer program is executed by the processor 201, the method for determining the breeding type described in the first aspect above is executed.
[0066] The embodiment of the present application also provides a computer-readable storage medium, and computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are run by the processor 201, the method for determining the breeding type described in the first aspect above is executed.
[0067] Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM for short), electrically erasable programmable read-only memory (EEPROM for short), erasable programmable read-only memory (EPROM for short), programmable read-only memory (PROM for short), read-only memory (ROM for short), magnetic memory, flash memory, magnetic disk or optical disk.
[0068] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed device / system and method can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and the module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.
[0069] In addition, in each embodiment of the embodiments of the present application, the various functional modules may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0070] The above description is only an optional implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the embodiments of the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the embodiments of the present application.
Claims
1. A method for determining a breeding type, characterized in that, The method includes: Obtaining multi - spectral imaging data of the area to be identified; wherein, the multi - spectral imaging data includes: the surface red light reflectivity of the area to be identified for the red light band B4 and the surface near - infrared reflectivity for the near - infrared band B8A; Calculating a first classification index of the area to be identified according to the surface red light reflectivity, the surface near - infrared reflectivity, the central wavelength of the red light band B4, and the central wavelength of the near - infrared band B8A within a first preset time period; Determining the aquaculture type to which the area to be identified belongs according to the first classification index and a preset index threshold; wherein, the aquaculture type includes fish - crab aquaculture and non - fish - crab aquaculture.
2. The method according to claim 1, characterized in that, The first preset time period includes: a first time period when the area to be identified is in a non - frozen state; The calculating the first classification index of the area to be identified according to the surface red light reflectivity, the surface near - infrared reflectivity, the central wavelength of the red light band B4, and the central wavelength of the near - infrared band B8A within a first preset time period includes: According to the surface red light reflectivity ρ within the first preset time period B4 , the surface near-infrared reflectivity ρ B8A , the central wavelength λ of the red light band B4 B4 , the central wavelength λ of the near-infrared band B8A B8A and calculate the first classification index LASCI of the area to be recognized.
3. The method according to claim 2, wherein The method for determining the preset index threshold includes: Obtaining fish - crab spectral imaging data of the fish - crab aquaculture area and non - fish - crab spectral imaging data of the non - fish - crab aquaculture area; wherein, the fish - crab spectral imaging data includes: the fish - crab surface red light reflectivity of the fish - crab aquaculture area for the red light band B4 and the fish - crab surface near - infrared reflectivity for the near - infrared band B8A; the non - fish - crab spectral imaging data includes: the non - fish - crab surface red light reflectivity of the non - fish - crab aquaculture area for the red light band B4 and the non - fish - crab surface near - infrared reflectivity for the near - infrared band B8A; Calculating a fish - crab classification index of the fish - crab aquaculture area according to the fish - crab surface red light reflectivity, the fish - crab surface near - infrared reflectivity, the central wavelength of the red light band B4, and the central wavelength of the near - infrared band B8A within the first preset time period; Calculating a non - fish - crab classification index of the non - fish - crab aquaculture area according to the non - fish - crab surface red light reflectivity, the non - fish - crab surface near - infrared reflectivity, the central wavelength of the red light band B4, and the central wavelength of the near - infrared band B8A within the first preset time period; Determining the training classification results of the fish - crab aquaculture area and the non - fish - crab aquaculture area according to the fish - crab classification index, the non - fish - crab classification index, and the current index threshold; Calculating the current classification accuracy corresponding to the current index threshold according to the training classification results; When the current classification accuracy meets the accuracy requirement, determining the current index threshold as the preset index threshold; When the current classification accuracy does not meet the accuracy requirement, updating the current index threshold until the classification accuracy corresponding to the updated current index threshold meets the accuracy requirement.
4. The method according to claim 1, wherein The multi - spectral imaging data further includes: the surface red - edge reflectivity of the non - fish - crab aquaculture area for the red - edge band B5; The method further includes: Calculating a second classification index of the non - fish - crab aquaculture area according to the surface red light reflectivity, the surface red - edge reflectivity, the central wavelength of the red light band B4, and the central wavelength of the red - edge band B5; Determine the aquaculture type of the non-fish and crab aquaculture area according to the change rate of the second classification index within the second preset time period; wherein, the aquaculture types of the non-fish and crab aquaculture area include sea cucumber aquaculture and shrimp aquaculture.
5. The method according to claim 4, characterized in that, The calculating of the second classification index of the non-fish and crab aquaculture area according to the surface red light reflectivity, the surface red edge reflectivity, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5 includes: According to the surface red light reflectivity ρ B4 、the surface red edge reflectivity ρ h5 、the central wavelength λ of the red light band B4 B4 、the central wavelength λ of the red edge band B5 55 and calculate the second classification index SPCI of the non - fish and crab farming area.
6. The method according to claim 5, wherein The second preset time period includes: two second preset sub-time periods when the area to be recognized is in a non-frozen state; The determining of the aquaculture type of the non-fish and crab aquaculture area according to the change rate of the second classification index within the second preset time period includes: Determine the aquaculture type of the non-fish and crab aquaculture area according to the change rate of the second classification index, the second change threshold, and the third change threshold within each second preset sub-time period.
7. The method according to claim 6, wherein The determining method of the second change threshold and the third change threshold includes: Obtain the sea cucumber spectral imaging data of the sea cucumber aquaculture area and the shrimp spectral imaging data of the shrimp aquaculture area; wherein, the sea cucumber spectral imaging data includes: the sea cucumber surface red light reflectivity of the sea cucumber aquaculture area for the red light band B4, and the sea cucumber surface red edge reflectivity for the red edge band B5; the shrimp spectral imaging data includes: the shrimp surface red light reflectivity of the shrimp aquaculture area for the red light band B4, and the shrimp surface red edge reflectivity for the red edge band B5; Calculate the sea cucumber classification index of the sea cucumber aquaculture area according to the sea cucumber surface red light reflectivity, the sea cucumber surface red edge reflectivity, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; Calculate the shrimp classification index of the shrimp aquaculture area according to the shrimp surface red light reflectivity, the shrimp surface red edge reflectivity, the central wavelength of the red light band B4, and the central wavelength of the red edge band B5; Determine the training aquaculture type of the non-fish and crab aquaculture area according to the change rate of the sea cucumber classification index, the change rate of the shrimp classification index, the second current change threshold, and the third current change threshold within each second preset sub-time period; Calculate the current classification accuracy corresponding to the second current change threshold and the third current change threshold according to the training aquaculture type; When the current classification accuracy meets the accuracy requirement, determine the second current change threshold as the second change threshold, and determine the third current change threshold as the third change threshold; When the current classification accuracy does not meet the accuracy requirement, update the second current change threshold and / or the third current change threshold until the classification accuracy corresponding to the updated second current change threshold and third current change threshold meets the accuracy requirement.
8. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, the method described in any one of claims 1-7 is implemented.
9. An electronic device, characterized in that, The electronic device includes: A memory; A processor; A computer program executable by the processor is stored on the memory. When the computer program is executed by the processor, the method according to any one of claims 1-7 is performed.
10. A computer-readable storage medium, characterized in that, Computer program instructions are stored in the computer-readable storage medium. When the computer program instructions are run by a processor, the method according to any one of claims 1-7 is performed.