Film mulching farmland identification method and system based on time sequence multispectral remote sensing image
Through the recognition method based on time-series multi-spectral remote sensing image, combined with phenological characteristics, the remote sensing identification index of mulched farmland was constructed, which solved the problem of insufficient recognition efficiency and accuracy of coated farmland in the existing technology, and achieved rapid and high-precision farmland coated farmland Information extraction.
Patent Information
- Application Number
- CN202410914248.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-12
Smart Images

Figure CN118941940A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for identifying film-covered farmland based on time-series multispectral remote sensing images. Background Art
[0002] Farmland film covering technology is a technology widely used in agricultural production. By covering the surface of farmland with a layer of plastic film, it can effectively increase soil temperature and maintain soil moisture, thereby promoting crop growth and increasing yields. Film covering technology can effectively alleviate the adverse effects of the natural environment and create superior growth conditions for agricultural products, thereby quickly achieving high yields and high quality of agricultural products such as fruits and vegetables. However, large-scale film-covered farmland has caused white pollution that cannot be ignored. For example, plastic film remains in the soil and is difficult to degrade, leading to soil pollution and deterioration of the farmland ecological environment. It not only has an adverse impact on water and soil resources and destroys the structure of the soil plow layer, but also hinders the transmission of moisture and nutrients for crops, resulting in reduced agricultural production. These facts show that there is an urgent need for a technology that can quickly obtain information on film-covered farmland.
[0003] Traditional methods mainly rely on manual interpretation and visual inspection. Although this method is intuitive, it is inefficient and highly subjective, making it difficult to promote and apply on a large scale. Remote sensing, as a popular technology for quickly and reliably obtaining comprehensive agricultural information, has made important contributions to agricultural development. Using remote sensing technology to extract information from film-covered farmland can obtain coverage scale and distribution, quickly determine the scale and area of crops, provide effective guidance for agricultural production, avoid agricultural disasters, achieve agricultural production increases, and provide scientific theoretical support for the agricultural sector. At present, many remote sensing index extraction methods for film-covered farmland have been constructed, but the accuracy is still difficult to guarantee. In addition, the spectral characteristics of film-covered farmland will change significantly during the vegetation growth period, and phenological factors should be taken seriously when extracting film-covered farmland. Summary of the invention
[0004] The purpose of the present invention is to provide a method and system for identifying film-covered farmland based on time-series multispectral remote sensing images, so as to solve at least one technical problem existing in the above-mentioned background technology.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions:
[0006] In a first aspect, the present invention provides a method for identifying film-covered farmland based on time-series multispectral remote sensing images, comprising:
[0007] Acquire remote sensing image data to be identified;
[0008] The acquired remote sensing image data to be identified is processed using a pre-trained farmland identification model to obtain the identification results of the film-covered farmland in the remote sensing image; wherein, the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on the visual interpretation method, including typical ground object sample points and film-covered farmland time series sample points; combining the spectral characteristics of typical ground objects and the time series spectral characteristics of film-covered farmland, and calculating the M index spectral separation to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
[0009] Furthermore, a phenology-based remote sensing identification index for film-mulched farmland is constructed, including: analysis of spectral characteristics of typical land objects; analysis of time-series spectral characteristics of film-mulched farmland; analysis of spectral separation of typical land objects; and construction of a phenology-based remote sensing identification index PPMFI for film-mulched farmland.
[0010] Furthermore, the remote sensing index PPMFI is:
[0011]
[0012] Among them, SAVI stands for soil conditioning vegetation index, NDBI stands for normalized building index, and NDVI stands for soil conditioned vegetation index. G represents the normalized difference vegetation index; ρ Coastal is the spectral reflectance of the Coastal surface, ρ Green is the Green surface spectral reflectance, ρ RE-1 is the surface spectral reflectance of RE-1; ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red.
[0013] Furthermore,
[0014] Among them, ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red, L represents a constant, and the default value is 0.5.
[0015] Furthermore,
[0016] Among them, ρ SWIR2 is the surface spectral reflectance of SWIR2, ρ NIR is the surface spectral reflectance in NIR.
[0017] Furthermore,
[0018] Among them, ρ NIRis the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red; NDVI G It is the normalized vegetation index during the greening period of film-mulched farmland.
[0019] In a second aspect, the present invention provides a film-covered farmland identification system based on time-series multispectral remote sensing images, comprising:
[0020] An acquisition module, used for acquiring remote sensing image data to be identified;
[0021] A processing module is used to use a pre-trained farmland identification model to process the acquired remote sensing image data to be identified, so as to obtain the identification results of the film-covered farmland in the remote sensing image; wherein the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on the visual interpretation method, including typical ground object sample points and film-covered farmland time series sample points; combining the spectral characteristics of typical ground objects and the time series spectral characteristics of film-covered farmland, and calculating the spectral separation degree of the M index to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
[0022] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the method for identifying film-covered farmland based on time-series multispectral remote sensing images as described in the first aspect is implemented.
[0023] In a fourth aspect, the present invention provides a computer device comprising a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for identifying film-covered farmland based on time-series multispectral remote sensing images as described in the first aspect.
[0024] In a fifth aspect, the present invention provides an electronic device comprising: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the method for identifying film-covered farmland based on time-series multispectral remote sensing images as described in the first aspect.
[0025] Beneficial effects of the present invention: The provided phenology-based film-mulched farmland remote sensing identification index PPMFI fully considers the phenological characteristics of crop growth and can perform fast and high-precision film-mulched farmland extraction in agricultural areas based on Sentinel-2 remote sensing images.
[0026] Additional advantages of the present invention will be more clearly given in the following description or learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0028] Figure 1 This is a flow chart of the remote sensing extraction method for film-covered farmland described in an embodiment of the present invention.
[0029] Figure 2 It is a schematic diagram of the analysis results of the spectral characteristics of typical ground objects described in an embodiment of the present invention.
[0030] Figure 3 This is a schematic diagram of the time-series spectral feature extraction results of the film-mulched farmland according to an embodiment of the present invention.
[0031] Figure 4 This is a schematic diagram of extracting film-covered farmland results by the film-covered farmland identification method based on time-series multispectral remote sensing images described in an embodiment of the present invention.
[0032] Figure 5 It is a schematic diagram of the comparison results of the details of the extraction method of the film-covered farmland described in the embodiment of the present invention and the existing film-covered farmland extraction method. DETAILED DESCRIPTION
[0033] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below by the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.
[0034] It should be understood by those skilled in the art that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs.
[0035] It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have a meaning consistent with that in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless as defined herein.
[0036] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.
[0037] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. Different embodiments or examples described in this specification and features of different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
[0038] To facilitate understanding of the present invention, the present invention is further explained below with reference to specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation on the embodiments of the present invention.
[0039] Those skilled in the art should understand that the drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily necessary for implementing the present invention.
[0040] Example 1
[0041] In this embodiment 1, a film-covered farmland identification system based on time-series multispectral remote sensing images is first provided, including: an acquisition module for acquiring remote sensing image data to be identified. A processing module is used to process the acquired remote sensing image data to be identified using a pre-trained farmland identification model to obtain the identification result of the film-covered farmland in the remote sensing image; wherein the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on visual interpretation, including typical ground object sample points and film-covered farmland time-series sample points; combining the spectral characteristics of typical ground objects and the time-series spectral characteristics of film-covered farmland, and calculating the spectral separation of the M index to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract film-covered farmland areas and non-film-covered farmland areas.
[0042] In this embodiment, based on the above-mentioned system, a method for identifying film-covered farmland based on time-series multispectral remote sensing images is implemented, including: obtaining remote sensing image data to be identified; using a pre-trained farmland identification model to process the acquired remote sensing image data to be identified, and obtaining the identification results of film-covered farmland in the remote sensing image; wherein the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on visual interpretation, including typical ground object sample points and film-covered farmland time-series sample points; combining the spectral characteristics of typical ground objects and the time-series spectral characteristics of film-covered farmland for analysis, and calculating the M index spectral separation to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract film-covered farmland areas and non-film-covered farmland areas.
[0043] Construct a phenological-based remote sensing identification index for film-mulched farmland, including: analysis of spectral characteristics of typical land objects; analysis of time-series spectral characteristics of film-mulched farmland; analysis of spectral separation of typical land objects; construct a phenological-based remote sensing identification index PPMFI for film-mulched farmland.
[0044] The remote sensing index PPMFI is:
[0045]
[0046] Among them, SAVI stands for soil conditioning vegetation index, NDBI stands for normalized building index, and NDVI stands for soil conditioned vegetation index. G represents the normalized difference vegetation index; ρ Coastal is the spectral reflectance of the Coastal surface, ρ Green is the Green surface spectral reflectance, ρ RE-1 is the surface spectral reflectance of RE-1; ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red.
[0047]
[0048] Among them, ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red, L represents a constant, and the default value is 0.5.
[0049]
[0050] Among them, ρ SWIR2 is the surface spectral reflectance of SWIR2, ρ NIR is the surface spectral reflectance in NIR.
[0051]
[0052] Among them, ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red; NDVI G It is the normalized vegetation index during the greening period of film-mulched farmland.
[0053] Example 2
[0054] like Figures 1 to 5 As shown, in this embodiment 2, a method for identifying film-covered farmland based on time-series multispectral remote sensing images is provided to overcome the shortcomings of the existing film-covered farmland methods and fully consider the vegetation phenological characteristic information. The method includes the following steps:
[0055] Step 1: Collect Sentinel-2 remote sensing image data covering the study area;
[0056] Step 2: Preprocess the data based on ENVI5.6 and SNAP software platforms, including geometric correction, resampling to 10m, format conversion, etc.
[0057] Step 3: Select sample points by visual interpretation, including typical landform sample points and time series sample points of film-mulched farmland.
[0058] Step 4: Combine the spectral characteristics of typical objects and the time series spectral characteristics of mulched farmland, and calculate the spectral separation of the M index. In this embodiment, a phenology-based plastic-mulched farmland remote sensing identification index (PPMFI) is provided, and the remote sensing index PPMFI calculation formula is as follows:
[0059]
[0060] Where SAVI represents the soil conditioning vegetation index, NDBI represents the normalized building index, and NDVI represents the G Represents the normalized difference vegetation index. Coastal is the spectral reflectance of the Coastal surface, ρ Green is the Green surface spectral reflectance, ρ RE-1 is the surface spectral reflectance of RE-1. NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red.
[0061] Among them, SAVI, NDBI, NDVI G The calculation principle of , is as follows:
[0062]
[0063] In the formula, ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red, L represents a constant, and the default value is 0.5.
[0064]
[0065] In the formula, ρ SWIR2 is the surface spectral reflectance of SWIR2, ρ NIR is the surface spectral reflectance in NIR.
[0066]
[0067] In the formula, ρ NIR is the NIR surface spectral reflectance, ρ Red NDVI is the surface spectral reflectance of Red. G It is the normalized vegetation index during the greening period of film-mulched farmland.
[0068] Furthermore, the steps of constructing the remote sensing index PPMFI are as follows:
[0069] S1: Analysis of spectral characteristics of typical objects;
[0070] S2: Time series spectral characteristics analysis of film-mulched farmland;
[0071] S3: Analysis of spectral separation of typical objects;
[0072] S4: Construct the remote sensing identification index PPMFI based on phenology of mulched farmland;
[0073] The phenology-based film-mulched farmland remote sensing identification index PPMFI is used for remote sensing extraction of film-mulched farmland.
[0074] Step 4: Segment the result by setting the threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
[0075] Step 5: Process the remote sensing image based on the constructed film-covered farmland remote sensing identification index, and obtain the film-covered farmland extraction result through post-processing such as threshold segmentation. Randomly generate test points based on Python software programming for accuracy verification, mainly calculating the overall classification accuracy, user accuracy, producer accuracy and F1 score, and conducting comprehensive accuracy evaluation;
[0076]
[0077] Wherein, True Positive (TP): predicting the positive class as the positive class number, that is, the film-covered farmland is identified as the film-covered farmland; True Negative (TN): predicting the negative class as the negative class number, that is, the non-film-covered farmland is identified as the non-film-covered farmland; False Positive (FP): predicting the negative class as the positive class number (Type I error), that is, the non-film-covered farmland is identified as the film-covered farmland; False Negative (FN): predicting the positive class as the negative class number → missing (Type II error), that is, the film-covered farmland is identified as the non-film-covered farmland.
[0078] In this embodiment, a typical agricultural area in a certain province and city in China is used as the study area. First, Sentinel-2 remote sensing image data within the study area is collected, and the remote sensing image data is preprocessed, mainly including radiation correction, resampling, band synthesis and format conversion. Various typical ground object sample points are selected in the study area by visual interpretation method to draw the typical ground object spectral characteristic curve and analyze the typical ground object spectral characteristics; the film-covered farmland area sample points are selected in the study area by visual interpretation method to draw the time series spectral characteristic curve of the film-covered farmland and determine the best phase for index construction; the spectral separation is calculated by combining the M index method to analyze the best extraction band of the film-covered farmland; and then the PPMFI index is constructed; the spatial distribution results of the film-covered farmland are obtained by post-processing the extraction results; finally, random sample points are selected based on python programming for accuracy verification and evaluation.
[0079] Specifically, the method of this embodiment is as follows:
[0080] Step 1: Collect Sentinel-2 remote sensing image data covering the study area;
[0081] This embodiment combines the crop phenological characteristics of the study area and collects monthly remote sensing images from the start of film covering to crop harvest, mainly Sentinel-2MSI multispectral image data.
[0082] Step 2: Preprocess the data based on ENVI5.6 and SNAP software platforms, including geometric correction, resampling to 10m, format conversion, etc.
[0083] For the Sentinel-2MSI products that have not been atmospherically corrected, additional atmospheric correction processing is required to obtain Level-2A products. All bands are resampled to 10m to unify the data resolution. All bands are synthesized into one image and exported to tif format for subsequent processing and calculation.
[0084] Step 3: Select sample points by visual interpretation, including typical ground feature sample points and time series sample points of film-covered farmland;
[0085] The sample points are mainly obtained through visual interpretation, and the pixel DN values of the sample points are obtained based on Python programming. This example considers typical landforms such as film-mulched farmland (PMF), greenhouse (PCG), blue building (Bbuild), red building (Rbuild), dry bare soil (SBS), wet bare soil (WBS), water body (WB), and vegetation (VEG). When acquiring the time series sample points of film-mulched farmland, this example considers the crop growth law and phenological information, and obtains monthly images from October to June of the following year for processing.
[0086] Step 4: Combine the spectral characteristics of typical objects and the time series spectral characteristics of mulched farmland, calculate the spectral separation of the M index, and provide a phenology-based Plastic-Mulched Farmland Remote Sensing Identification Index (PPMFI);
[0087] The PPMFI index is constructed by analyzing the spectral characteristic curves of typical ground objects and the time-series spectral characteristic analysis curves of mulched farmland, and analyzing the spectral separation of ground object bands.
[0088] Step 5: Process the remote sensing image based on the constructed film-covered farmland remote sensing identification index, and obtain the film-covered farmland extraction result through post-processing such as threshold segmentation. Randomly generate test points based on Python software programming for accuracy verification, mainly calculating the overall classification accuracy, user accuracy, producer accuracy and F1 score for comprehensive accuracy evaluation.
[0089] In this example, the overall accuracy of the PPMFI index in the four selected typical areas reached more than 90%, the user accuracy reached more than 88%, the producer accuracy reached more than 70%, and the overall F1-score was more than 80%. The extraction of film-covered farmland had high accuracy and good overall effect.
[0090] Example 3
[0091] This embodiment 3 provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the above-mentioned method for identifying film-covered farmland based on time-series multispectral remote sensing images is implemented. The method includes:
[0092] Acquire remote sensing image data to be identified;
[0093] The acquired remote sensing image data to be identified is processed using a pre-trained farmland identification model to obtain the identification results of the film-covered farmland in the remote sensing image; wherein, the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on the visual interpretation method, including typical ground object sample points and film-covered farmland time series sample points; combining the spectral characteristics of typical ground objects and the time series spectral characteristics of film-covered farmland, and calculating the M index spectral separation to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
[0094] Example 4
[0095] This embodiment 4 provides a computer device, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the above-mentioned method for identifying film-covered farmland based on time-series multispectral remote sensing images, the method comprising:
[0096] Acquire remote sensing image data to be identified;
[0097] The acquired remote sensing image data to be identified is processed using a pre-trained farmland identification model to obtain the identification results of the film-covered farmland in the remote sensing image; wherein, the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on the visual interpretation method, including typical ground object sample points and film-covered farmland time series sample points; combining the spectral characteristics of typical ground objects and the time series spectral characteristics of film-covered farmland, and calculating the M index spectral separation to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
[0098] Example 5
[0099] This embodiment 5 provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions for implementing the above-mentioned method for identifying film-covered farmland based on time-series multispectral remote sensing images, the method comprising:
[0100] Acquire remote sensing image data to be identified;
[0101] The acquired remote sensing image data to be identified is processed using a pre-trained farmland identification model to obtain the identification results of the film-covered farmland in the remote sensing image; wherein, the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on the visual interpretation method, including typical ground object sample points and film-covered farmland time series sample points; combining the spectral characteristics of typical ground objects and the time series spectral characteristics of film-covered farmland, and calculating the M index spectral separation to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
[0102] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0106] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative work on the basis of the technical solution disclosed in the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for identifying film-covered farmland based on time-series multispectral remote sensing images, characterized in that: include: Acquire remote sensing image data to be identified; The acquired remote sensing image data to be identified is processed using a pre-trained farmland identification model to obtain the identification results of the film-covered farmland in the remote sensing image; wherein, the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on the visual interpretation method, including typical ground object sample points and film-covered farmland time series sample points; combining the spectral characteristics of typical ground objects and the time series spectral characteristics of film-covered farmland, and calculating the M index spectral separation to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
2. The method for identifying film-covered farmland based on time-series multispectral remote sensing images according to claim 1, characterized in that: Construct a phenological-based remote sensing identification index for film-mulched farmland, including: analysis of spectral characteristics of typical land objects; analysis of time-series spectral characteristics of film-mulched farmland; analysis of spectral separation of typical land objects; construct a phenological-based remote sensing identification index PPMFI for film-mulched farmland.
3. The method for identifying film-covered farmland based on time-series multispectral remote sensing images according to claim 2, characterized in that: The remote sensing index PPMFI is: Among them, SAVI stands for soil conditioning vegetation index, NDBI stands for normalized building index, and NDVI stands for soil conditioned vegetation index. G represents the normalized difference vegetation index; ρ Coastal is the spectral reflectance of the Coastal surface, ρ Green is the Green surface spectral reflectance, ρ RE-1 is the surface spectral reflectance of RE-1; ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red.
4. The method for identifying film-covered farmland based on time-series multispectral remote sensing images according to claim 3 is characterized in that: Among them, ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red, L represents a constant, and the default value is 0.
5.
5. The method for identifying film-covered farmland based on time-series multispectral remote sensing images according to claim 3 is characterized in that: Among them, ρ SWIR2 is the surface spectral reflectance of SWIR2, ρ NIR is the surface spectral reflectance in NIR.
6. The method for identifying film-covered farmland based on time-series multispectral remote sensing images according to claim 3, characterized in that: Among them, ρ NIR is the NIR surface spectral reflectance, ρ Red is the surface spectral reflectance of Red; NDVI G It is the normalized vegetation index during the greening period of film-mulched farmland.
7. A film-covered farmland identification system based on time-series multispectral remote sensing images, characterized in that: include: An acquisition module, used for acquiring remote sensing image data to be identified; A processing module is used to use a pre-trained farmland identification model to process the acquired remote sensing image data to be identified, so as to obtain the identification results of the film-covered farmland in the remote sensing image; wherein the training of the farmland identification model includes: collecting remote sensing image data covering the study area and performing preprocessing; selecting sample points based on the visual interpretation method, including typical ground object sample points and film-covered farmland time series sample points; combining the spectral characteristics of typical ground objects and the time series spectral characteristics of film-covered farmland, and calculating the spectral separation degree of the M index to construct a phenological-based film-covered farmland remote sensing identification index for film-covered farmland remote sensing extraction; segmenting the results by setting a threshold T to extract the film-covered farmland area and the non-film-covered farmland area.
8. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method for identifying film-covered farmland based on time-series multispectral remote sensing images as described in any one of claims 1-6 is implemented.
9. A computer device, characterized in that: It includes a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method for identifying covered farmland based on time-series multispectral remote sensing images as described in any one of claims 1-6.
10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the method for identifying film-covered farmland based on time-series multispectral remote sensing images as described in any one of claims 1-6.
Citation Information
Cited By
Mulching film monitoring method and device, computer equipment and medium
CN120009208A
Remote sensing identification method and equipment for plastic film mulching cultivated land based on time sequence spectral characteristics
CN121330518A
Multispectral remote sensing avalanche identification method
CN121767872A
Water body abnormity monitoring method and system based on remote sensing big data
CN121954853A
