Winter wheat growth and development identification method based on satellite remote sensing image

Abstract

The invention relates to the technical field of winter wheat growth and development recognition, in particular to a winter wheat growth and development recognition method based on a satellite remote sensing image, and the method comprises the following steps: S1, carrying out the preprocessing of the satellite remote sensing image; according to the method, satellite remote sensing images are preprocessed, including radiation correction, atmospheric correction, geometric correction and the like, so that noise and distortion in the images are eliminated, image quality is improved, planting and phenological characteristics of winter wheat are investigated and analyzed, specific planting phenological characteristics of winter wheat are obtained, extracted characteristics are classified and identified by using a support vector machine (SVM), and the winter wheat planting phenological characteristics are identified. Winter wheat areas in the images are judged, characteristics related to the wheat development stage can be extracted by analyzing the spectral reflectivity of wheat in different growth stages, the growth condition of winter wheat is evaluated, and the health condition of winter wheat and whether the problems of diseases and insect pests, water stress, nutrient deficiency and the like exist or not are analyzed according to the evaluation result. And corresponding management suggestions are provided accordingly.

Description

Technical Field

[0001] The invention relates to the technical field of winter wheat growth and development identification, and in particular to a method for identifying winter wheat growth and development based on satellite remote sensing images. Background Art

[0002] Winter wheat is the most widely distributed staple food crop in northern my country. The spatial distribution and planting area of ​​winter wheat are important information that agricultural and other relevant departments need to master. Accurately extracting the spatial distribution of winter wheat as soon as possible can provide information support for field management, pest control and yield prediction of winter wheat in winter and in the middle and late growth stages. Traditional monitoring of winter wheat spatial distribution is mainly carried out through field surveys, which requires a lot of manpower, material and financial resources. It is not only labor-intensive, slow, and inefficient, but also has a limited survey scope, is easily interfered by human factors, and has low accuracy. To this end, we propose a method for identifying the growth and development of winter wheat based on satellite remote sensing images to solve the above problems. Summary of the invention

[0003] The purpose of the present invention is to provide a method for identifying the growth and development of winter wheat based on satellite remote sensing images, so as to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a method for identifying the growth and development of winter wheat based on satellite remote sensing images, comprising the following steps:

[0005] S1: Preprocess satellite remote sensing images, including radiation correction, atmospheric correction, geometric correction, etc., to eliminate noise and distortion in the image and improve image quality;

[0006] S2: Investigate and analyze the planting and phenological characteristics of winter wheat to obtain the specific phenological characteristics of winter wheat;

[0007] S3: By continuously monitoring remote sensing images of winter wheat during its growth, we can obtain information on its growth stages, such as sowing period, emergence period, jointing period, heading period, and filling period, and extract winter wheat features, such as texture, color, and shape, from the preprocessed images through image processing techniques, such as edge detection, morphological operations, and histogram equalization.

[0008] S4: Use support vector machine (SVM) to classify and identify the extracted features to determine the winter wheat area in the image. By analyzing the spectral reflectance of wheat at different growth stages, features related to the development stage of wheat can be extracted. These features can be used as input to the SVM to train the model to identify different development stages of wheat.

[0009] S5: SVM can predict wheat yield by analyzing wheat growth data and environmental factors. It can predict wheat yield by analyzing the spectral characteristics of wheat at different growth stages. Combining the growth stage information of winter wheat and other environmental factors such as temperature, humidity, and light, it can evaluate the growth status of winter wheat and determine whether it is healthy and whether it is affected by pests and diseases.

[0010] S6: Based on the evaluation results, analyze the health status of winter wheat to determine whether there are problems such as pests and diseases, water stress, and nutrient deficiency, and make corresponding management recommendations accordingly.

[0011] Further preferably, in S1, through high-resolution remote sensing images, the characteristics of winter wheat leaves, stems, ears, etc. can be more clearly identified, so as to more accurately judge its growth status, and thus formulate more reasonable management measures such as fertilization, irrigation, pest and disease control, etc.

[0012] Further preferably, the SVM model in S4 can handle nonlinear and high-dimensional data, which means that it can adapt to complex agricultural environments and changing climate conditions, so that the SVM model can maintain a high accuracy in wheat harvest prediction in different regions and different years.

[0013] Further preferably, the radiation correction in S1 is to eliminate or reduce the radiation error caused by the sensor, atmosphere and surface characteristics in the image to improve the quality and availability of the image. The purpose of atmospheric correction is to eliminate the influence of factors such as atmosphere and illumination on the reflection of objects, obtain the real physical model parameters such as the reflectivity, emissivity and surface temperature of objects, and determine the interference of effects such as atmospheric scattering and absorption by simulating the transmission process of radiation in the atmosphere, thereby completing the atmospheric correction. The purpose of geometric correction is to eliminate or correct these geometric errors so that the remote sensing image can accurately reflect the geographic coordinates of the surface, thereby improving the quality and availability of the image.

[0014] Further preferably, the investigation on the planting and phenological characteristics of winter wheat in S2 includes: the need to collect relevant data on the planting and phenological characteristics of winter wheat, including information such as the planting area, planting density, sowing time, growth cycle, harvest time, etc. of winter wheat, and the need to collect meteorological data such as temperature, precipitation, and sunshine duration.

[0015] Further preferably, the data collected in S2 needs to be sorted and analyzed, and statistical software is used to process the data, calculate statistical indicators such as mean value, standard deviation, correlation, etc., and draw charts, such as growth curves, phenological period distribution maps, etc., so as to intuitively display the growth patterns and phenological characteristics of winter wheat.

[0016] Further preferably, the spectral reflectance of winter wheat in S3 will have significant differences in the tillering stage, jointing stage, booting stage and heading stage. By analyzing these differences, the planting area of ​​winter wheat can be identified, and vegetation indices such as the normalized difference vegetation index (NDVI) can be used to enhance the signal of winter wheat and suppress other ground information. By utilizing multi-temporal remote sensing data, the phase feature recognition of winter wheat and the spectral feature recognition are fully combined to accurately identify the planting area of ​​winter wheat.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention pre-processes satellite remote sensing images, including radiation correction, atmospheric correction, geometric correction, etc., to eliminate noise and distortion in the image, improve image quality, investigate and analyze the planting and phenological characteristics of winter wheat, obtain the specific phenological characteristics of winter wheat, use a support vector machine (SVM) to classify and identify the extracted features, judge the winter wheat area in the image, and extract features related to the development stage of wheat by analyzing the spectral reflectance of wheat in different growth periods, evaluate the growth status of winter wheat, analyze the health status of winter wheat according to the evaluation results, and whether there are problems such as pests and diseases, water stress, and nutrient deficiency, and accordingly put forward corresponding management suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the main stereoscopic structure of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example

[0021] See also Figure 1 The present invention provides a technical solution: a method for identifying the growth and development of winter wheat based on satellite remote sensing images, comprising the following steps:

[0022] S1: Preprocess satellite remote sensing images, including radiation correction, atmospheric correction, geometric correction, etc., to eliminate noise and distortion in the image and improve image quality;

[0023] S2: Investigate and analyze the planting and phenological characteristics of winter wheat to obtain the specific phenological characteristics of winter wheat;

[0024] S3: By continuously monitoring remote sensing images of winter wheat during its growth, we can obtain information on its growth stages, such as sowing period, emergence period, jointing period, heading period, and filling period, and extract winter wheat features, such as texture, color, and shape, from the preprocessed images through image processing techniques, such as edge detection, morphological operations, and histogram equalization.

[0025] S4: Use support vector machine (SVM) to classify and identify the extracted features to determine the winter wheat area in the image. By analyzing the spectral reflectance of wheat at different growth stages, features related to the development stage of wheat can be extracted. These features can be used as input to the SVM to train the model to identify different development stages of wheat.

[0026] S5: SVM can predict wheat yield by analyzing wheat growth data and environmental factors. It can predict wheat yield by analyzing the spectral characteristics of wheat at different growth stages. Combining the growth stage information of winter wheat and other environmental factors such as temperature, humidity, and light, it can evaluate the growth status of winter wheat and determine whether it is healthy and whether it is affected by pests and diseases.

[0027] S6: Based on the evaluation results, analyze the health status of winter wheat to determine whether there are problems such as pests and diseases, water stress, and nutrient deficiency, and make corresponding management recommendations accordingly.

[0028] In this embodiment, specifically: in S1, the high-resolution remote sensing images can more clearly identify the characteristics of winter wheat leaves, stems, ears, etc., so as to more accurately judge its growth status, thereby formulating more reasonable management measures such as fertilization, irrigation, and pest control;

[0029] In this embodiment, specifically: the SVM model in S4 can process nonlinear and high-dimensional data, which means that it can adapt to complex agricultural environments and changing climate conditions, so that the SVM model can maintain high accuracy in wheat harvest prediction in different regions and different years;

[0030] In this embodiment, specifically: the radiation correction in S1 is to eliminate or reduce the radiation error caused by the sensor, atmosphere and surface characteristics in the image to improve the quality and availability of the image; the purpose of atmospheric correction is to eliminate the influence of factors such as atmosphere and illumination on the reflection of objects, obtain the real physical model parameters such as the reflectivity, emissivity and surface temperature of objects, and determine the interference of atmospheric scattering and absorption by simulating the transmission process of radiation in the atmosphere, so as to complete the atmospheric correction; the purpose of geometric correction is to eliminate or correct these geometric errors so that the remote sensing image can accurately reflect the geographic coordinates of the surface, thereby improving the quality and availability of the image;

[0031] In this embodiment, specifically: the investigation of winter wheat planting and phenological characteristics in S2 includes: the need to collect relevant data on winter wheat planting and phenological characteristics, including information such as the planting area, planting density, sowing time, growth cycle, and harvest time of winter wheat, and the need to collect meteorological data such as temperature, precipitation, and sunshine duration;

[0032] In this embodiment, specifically: the data collected in S2 needs to be sorted and analyzed, and statistical software is used to process the data, calculate statistical indicators such as mean value, standard deviation, correlation, etc., and draw charts, such as growth curves, phenological period distribution charts, etc., so as to intuitively display the growth law and phenological characteristics of winter wheat;

[0033] In this embodiment, specifically: in S3, the spectral reflectance of winter wheat will have significant differences in the tillering stage, jointing stage, booting stage and heading stage. By analyzing these differences, the planting area of ​​winter wheat can be identified, and vegetation indices such as the Normalized Difference Vegetation Index (NDVI) are used to enhance the signal of winter wheat and suppress other ground information. By using multi-temporal remote sensing data, the phase feature recognition of winter wheat is fully combined with the spectral feature recognition to accurately identify the planting area of ​​winter wheat.

[0034] In this embodiment, specifically: the satellite remote sensing image is preprocessed, including radiation correction, atmospheric correction, geometric correction, etc. The radiation correction is to eliminate or reduce the radiation error caused by the sensor, atmosphere and surface characteristics in the image, so as to improve the quality and availability of the image. The purpose of atmospheric correction is to eliminate the influence of factors such as atmosphere and illumination on the reflection of the object, obtain the real physical model parameters such as the reflectivity, emissivity and surface temperature of the object, and determine the interference of the effects such as atmospheric scattering and absorption by simulating the transmission process of radiation in the atmosphere, so as to complete the atmospheric correction. The purpose of geometric correction is to eliminate or correct these geometric errors so that the remote sensing image can accurately reflect the geographic coordinates of the surface, thereby improving the quality and availability of the image, and eliminating the noise and Distortion, improve image quality, through high-resolution remote sensing images, the leaves, stems, ears and other characteristics of winter wheat can be more clearly identified, so as to more accurately judge its growth status, and thus formulate more reasonable management measures such as fertilization, irrigation, pest and disease control, and investigate and analyze the planting and phenological characteristics of winter wheat. The investigation of the planting and phenological characteristics of winter wheat includes: the need to collect relevant data on the planting and phenological characteristics of winter wheat, including the planting area, planting density, sowing time, growth cycle, harvest time and other information of winter wheat, and the need to collect meteorological data, such as temperature, precipitation, sunshine duration, and the investigation of the planting and phenological characteristics of winter wheat includes: the need to collect relevant data on the planting and phenological characteristics of winter wheat, including the planting area, planting density, sowing time, growth cycle, harvest time and other information of winter wheat. In order to obtain information such as planting area, planting density, sowing time, growth cycle, and harvest time, it is necessary to collect meteorological data such as temperature, precipitation, and sunshine duration to obtain the specific phenological characteristics of winter wheat. By continuously monitoring the remote sensing images of winter wheat during its growth, it is possible to obtain information on the growth stages of winter wheat, such as sowing period, emergence period, jointing period, heading period, and filling period. The features of winter wheat, such as texture, color, and shape, are extracted from the preprocessed images through image processing techniques such as edge detection, morphological operations, and histogram equalization. The extracted features are classified and identified using support vector machines (SVMs). The SVM model can handle nonlinear and high-dimensional data, which means it can adapt to complex agricultural environments and variable The climatic conditions make the SVM model maintain a high accuracy in wheat harvest prediction in different regions and years. The winter wheat area in the image can be judged. By analyzing the spectral reflectance of wheat in different growth periods, the features related to the wheat development stage can be extracted. These features can be used as the input of SVM to train the model to identify the different development stages of wheat. SVM can predict wheat yield by analyzing wheat growth data and environmental factors. By analyzing the spectral characteristics of wheat at different growth stages, wheat yield can be predicted. Combined with the growth stage information of winter wheat and other environmental factors such as temperature, humidity, light, etc., the growth status of winter wheat can be evaluated to determine whether it is healthy and whether it is affected by pests and diseases.According to the evaluation results, the health status of winter wheat is analyzed to see whether there are problems such as pests and diseases, water stress, and nutrient deficiency, and corresponding management suggestions are put forward accordingly.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for identifying winter wheat growth and development based on satellite remote sensing images, characterized in that: The following steps are involved: S1: Preprocess satellite remote sensing images, including radiation correction, atmospheric correction, geometric correction, etc., to eliminate noise and distortion in the image and improve image quality; S2: Investigate and analyze the planting and phenological characteristics of winter wheat to obtain the specific phenological characteristics of winter wheat; S3: By continuously monitoring remote sensing images of winter wheat during its growth, we can obtain information on its growth stages, such as sowing period, emergence period, jointing period, heading period, and filling period, and extract winter wheat features, such as texture, color, and shape, from the preprocessed images through image processing techniques, such as edge detection, morphological operations, and histogram equalization. S4: Use support vector machine (SVM) to classify and identify the extracted features to determine the winter wheat area in the image. By analyzing the spectral reflectance of wheat at different growth stages, features related to the development stage of wheat can be extracted. These features can be used as input to the SVM to train the model to identify different development stages of wheat. S5: SVM can predict wheat yield by analyzing wheat growth data and environmental factors. It can predict wheat yield by analyzing the spectral characteristics of wheat at different growth stages. Combining the growth stage information of winter wheat and other environmental factors such as temperature, humidity, and light, it can evaluate the growth status of winter wheat and determine whether it is healthy and whether it is affected by pests and diseases. S6: Based on the evaluation results, analyze the health status of winter wheat to determine whether there are problems such as pests and diseases, water stress, and nutrient deficiency, and make corresponding management recommendations accordingly.

2. The method for identifying winter wheat growth and development based on satellite remote sensing images according to claim 1, characterized in that: Through high-resolution remote sensing images, S1 can more clearly identify the leaves, stems, ears and other characteristics of winter wheat, so as to more accurately judge its growth status and formulate more reasonable management measures such as fertilization, irrigation, pest and disease control.

3. The method for identifying winter wheat growth and development based on satellite remote sensing images according to claim 2, characterized in that: The SVM model in S4 can handle nonlinear and high-dimensional data, which means that it can adapt to complex agricultural environments and changing climate conditions, allowing the SVM model to maintain a high degree of accuracy in wheat harvest predictions in different regions and years.

4. The method for identifying winter wheat growth and development based on satellite remote sensing images according to claim 3, characterized in that: The radiation correction in S1 is to eliminate or reduce the radiation errors caused by sensors, atmosphere and surface characteristics in the image to improve the quality and availability of the image. The purpose of atmospheric correction is to eliminate the influence of factors such as atmosphere and illumination on the reflection of objects, obtain the real physical model parameters such as object reflectivity, emissivity, surface temperature, etc., and complete the atmospheric correction by simulating the transmission process of radiation in the atmosphere and determining the interference of effects such as atmospheric scattering and absorption. The purpose of geometric correction is to eliminate or correct these geometric errors so that the remote sensing image can accurately reflect the geographic coordinates of the surface, thereby improving the quality and availability of the image.

5. The method for identifying winter wheat growth and development based on satellite remote sensing images according to claim 4, characterized in that: The investigation of winter wheat planting and phenological characteristics in S2 includes: the need to collect relevant data on winter wheat planting and phenological characteristics, including information such as winter wheat planting area, planting density, sowing time, growth cycle, harvest time, etc., and the need to collect meteorological data such as temperature, precipitation, and sunshine duration.

6. The method for identifying winter wheat growth and development based on satellite remote sensing images according to claim 5, characterized in that: The data collected in S2 need to be sorted and analyzed, and statistical software should be used to process the data, calculate statistical indicators such as mean, standard deviation, and correlation, and draw charts, such as growth curves and phenological period distribution maps, in order to intuitively display the growth patterns and phenological characteristics of winter wheat.

7. The method for identifying winter wheat growth and development based on satellite remote sensing images according to claim 6, characterized in that: In S3, the spectral reflectance of winter wheat will have significant differences during the tillering stage, jointing stage, booting stage and heading stage. By analyzing these differences, the planting area of ​​winter wheat can be identified. Vegetation indices such as the Normalized Difference Vegetation Index (NDVI) are used to enhance the signal of winter wheat and suppress other ground information. Multi-temporal remote sensing data are used to fully combine the temporal feature recognition of winter wheat with the spectral feature recognition to accurately identify the planting area of ​​winter wheat.

Images