System and method for interpreting paddy field planting area through remote sensing image
Through the combination of remote sensing image acquisition, identification, change monitoring and interpretation modules, high-precision dynamic monitoring of paddy field areas is achieved, and the problem of low efficiency of paddy field identification and monitoring in the existing technology is solved, and scientific agricultural management and ecological protection tools are provided. .
Patent Information
- Application Number
- CN202411409024.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology is inefficient in the identification and monitoring of paddy field planting areas and cannot adapt to the rapidly changing agricultural environment, resulting in insufficient scientific resource management and ecological protection strategies, affecting the effectiveness of agricultural production efficiency and environmental protection.
The remote sensing image acquisition module is used to screen and time mark, the paddy field remote sensing identification module performs boundary detection and labeling processing, the paddy field change monitoring module calculates pixel differences between images, the remote sensing image interpretation module analyzes micro-terrain and vegetation growth activities, and generates dynamic changes and internal characteristics of paddy fields. Analytical diagram.
It realizes high-precision dynamic monitoring of paddy field areas, supports real-time agricultural strategy adjustment, enhances the ability to evaluate paddy field usage status and vegetation health, provides detailed basis for crop management and resource optimization, and promotes the practical application of ecological protection.
Smart Images

Figure CN118918397A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image interpretation, and in particular to a system and method for interpreting paddy field planting areas using remote sensing images. Background Art
[0002] The field of image interpretation technology involves the use of algorithms and mathematical models to analyze image data in order to identify and classify image content. It is widely used in applications ranging from simple object recognition to complex scene understanding. In the field of remote sensing, image interpretation technology pays special attention to the automatic identification of surface features, such as land cover, vegetation types, and urban layout. It uses methods such as image preprocessing, feature extraction, pattern recognition, and machine learning to not only improve processing efficiency, but also enhance the ability to interpret image data, enabling it to play an important role in many fields such as resource management, environmental monitoring, and agricultural planning.
[0003] Among them, the system of interpreting paddy field planting areas with remote sensing images refers specifically to the system that uses remote sensing technology to analyze and identify the location and scope of paddy field planting areas. The system usually integrates multiple image processing algorithms to identify specific image features of paddy fields. Its main uses include providing accurate agricultural data support, helping agricultural managers make planting strategy decisions, monitoring crop growth conditions and evaluating crop health, thereby optimizing resource allocation and enhancing agricultural production efficiency. It also helps with environmental monitoring and land use planning, and provides important information on water resource utilization and ecological protection.
[0004] Although existing technologies provide a wide range of image analysis applications, they generally lack highly customized processing for specific scenarios such as paddy fields. In the identification and monitoring of paddy field planting areas, traditional methods fail to adapt to the rapidly changing agricultural environment, limiting the precise tracking of paddy field boundaries and their changes, and are inefficient in dynamically monitoring crop growth and health status. At the same time, the lack of targeted analysis tools has also resulted in unscientific strategy formulation in resource management and ecological protection, which in turn affects agricultural production efficiency and environmental protection effectiveness. These technical shortcomings lead to waste of resources, delayed production decisions, and insufficient environmental monitoring in actual operations, exacerbating the fragility of agriculture and ecosystems. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a system and method for interpreting paddy field planting areas using remote sensing images.
[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A system for interpreting paddy field planting areas from remote sensing images comprises: The remote sensing image acquisition module collects remote sensing images through remote sensing satellites, selects images including paddy field areas, time-marks the images, and performs spatial correction simultaneously to form a paddy field remote sensing image set; The paddy field remote sensing recognition module uses the paddy field remote sensing image set to perform boundary detection, highlight the boundary between the paddy field and the non-paddy field area, distinguish the paddy field area from the non-paddy field area, and mark the paddy field area to generate a paddy field area feature map; The paddy field change monitoring module performs image registration based on the paddy field area feature map, accurately aligns the paddy field remote sensing images at different time points, calculates the pixel difference between the images, identifies the changes in the paddy field area and boundaries based on the calculation results, records the newly appeared or disappeared paddy field areas, and obtains the paddy field dynamic change map; The remote sensing image interpretation module uses the paddy field dynamic change map to perform terrain analysis to determine the micro-topography structure of the paddy field area, identify the terrain undulations and water flow direction of the paddy field area, perform surface reflectivity analysis based on the identification results, compare image data at different times, identify changes in vegetation growth activities, reveal the relationship between the paddy field usage status and the vegetation health status, and comprehensively generate an analysis map of the internal characteristics of the paddy field.
[0007] As a further solution of the present invention, the steps of acquiring the paddy field remote sensing image set are: The original data is obtained from the remote sensing satellite, and the original data is preliminarily processed using the formula: Calculate the processed image value , generate the original remote sensing image set, where Represents remote sensing satellite data, represents the extraction efficiency parameter, is the first constant adjustment term, used to correct the model deviation; Based on the original remote sensing image set, images including paddy fields are screened, and time labeling and spatial correction are performed. The formula is used: Calculate normalized image values , generate a screened and corrected paddy field image set, where is the paddy field screening factor, is the normalization coefficient, is the second constant adjustment term, used to correct the result; The screened and corrected paddy field image set is integrated, formatted and outputted, and the formula is used: Calculate the image set integration index , we get a set of paddy field remote sensing images, where Represents the integration efficiency parameter, which is used to adjust the integration effect. is the third constant adjustment term.
[0008] As a further solution of the present invention, the steps of obtaining the paddy field area characteristic map are: Based on the paddy field remote sensing image set, grayscale conversion and noise filtering are performed using the formula: Calculate the gray value after processing , generate the preprocessed paddy field image, where is the channel value of the color image, are the weight coefficients of the red, green and blue channels respectively, is the noise level, is the contrast adjustment parameter, It is the adjustment coefficient of noise and contrast, which is used to balance the effects of noise and contrast; Based on the preprocessed paddy field image, boundary detection and boundary recognition are performed using the formula: Calculate image boundary strength , generate a boundary detection map, where and Respectively represent exist and The gradient of the direction, is the edge enhancement coefficient, is the fine-tuning coefficient; According to the boundary detection map, paddy field and non-paddy field areas are distinguished and marked, using the formula: Calculate image visual effect value , generate the paddy field area characteristic map, where represents the annotation coefficient, is the zone separation precision adjustment factor, and is the adjustment factor used to control the scale and offset of the output results.
[0009] As a further solution of the present invention, the step of calculating the pixel difference between the images is: Based on the paddy field regional characteristic map, standardization processing is performed using the formula: Calculate the normalized pixel value , generate a standardized image, where It is the paddy field area characteristic map image data, is a small amount that prevents the denominator from reaching zero, and are the minimum and maximum pixel values, respectively; Based on the standardized image, key feature points are extracted and image registration is performed using the formula: Calculate the fine-tuned pixel difference after registration , generate the registered image, where is the feature point value, is the adjustment factor, is the regularization coefficient; Based on the registered image, the formula is used: Calculate the pixel difference between two time points , and get the pixel difference map, where It is the image at the reference time point.
[0010] As a further solution of the present invention, the steps for obtaining the paddy field dynamic change map are: Based on the pixel difference map, a difference threshold is set , detect significant changes if > , indicating significant paddy field area or boundary changes, generating a change detection map; According to the change detection map, the changed areas are classified and recorded, using the formula, Calculate the number of new change areas , output the new change area map, where is the coefficient for adjusting the classification sensitivity; Based on the new change area map, all change data are integrated and the formula is used. Calculate composite index , construct a dynamic change diagram of paddy fields, where is the adjustment factor for comprehensive changes.
[0011] As a further solution of the present invention, the steps for identifying the terrain undulation and water flow direction of the paddy field area are: Based on the paddy field dynamic change map, the micro-topography structure is analyzed using the digital elevation model, and the formula is adopted. Calculate weighted mean elevation , generate a micro-topography structure map, where Indicates the target location Elevation data, is the terrain importance weight, is the lateral measure of elevation, represents a data point; According to the micro-topographic structure map, the terrain relief is evaluated using the formula, Calculate the terrain relief index , used to indicate the unevenness of the terrain and obtain terrain relief data, where is the average elevation; Based on the terrain undulation data, the water flow direction is determined using the formula: Calculate the flow direction value , construct a water flow direction map, where is the angle from the horizontal and is used to calculate directivity.
[0012] As a further solution of the present invention, the steps for obtaining the internal characteristic analysis diagram of the paddy field are: Collect time series image data, analyze surface reflectivity, and use the formula, Calculate the difference in surface reflectance , and obtain the surface reflectivity change data, where and are the reflectances at two time points, represents the position factor, Indicates the number of locations; Based on the surface reflectivity change data, the vegetation growth activity is determined using the formula: Calculating vegetation growth rate , and obtain paddy field vegetation growth data, where For location The reflectivity change value, is the measurement precision factor; The terrain undulation data, water flow direction map and paddy field vegetation growth data are integrated to construct and output an analytical map of the internal characteristics of the paddy field.
[0013] A method for interpreting paddy field planting areas using remote sensing images comprises the following steps: S1: Obtain raw data based on remote sensing satellites and perform preliminary processing, screen images including paddy fields, perform time tagging and spatial correction, format and output processing, and obtain a remote sensing image set of paddy fields; S2: Based on the paddy field remote sensing image set, graying and noise filtering are performed, boundary detection and boundary recognition are performed, image boundary strength is calculated, paddy field and non-paddy field areas are distinguished, and annotation is performed to generate a paddy field area feature map; S3: Based on the paddy field area feature map, perform standardization processing, extract key feature points and perform image registration, calculate the pixel difference value of the image between two time points, and output a pixel difference map; S4: Based on the pixel difference map, a difference threshold is set to detect significant changes, the changed areas are classified and recorded, all change data are integrated to calculate comprehensive indicators, and a paddy field dynamic change map is constructed; S5: Based on the paddy field dynamic change map, using a digital elevation model, analyzing the micro-topography structure, evaluating the terrain undulation, determining the water flow direction, and constructing a water flow direction map; S6: Use the time series image data to analyze the surface reflectivity, determine the vegetation growth activity, integrate the water flow direction map, and construct and output the paddy field internal feature analysis map.
[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, through meticulous time tagging and spatial correction of remote sensing images, high consistency and accuracy of data are achieved, making dynamic monitoring of paddy field areas more accurate. High-precision boundary detection and regional separation allow accurate tracking of small changes in paddy fields, providing instant updates for agricultural data and supporting timely adjustments to agricultural strategies. Through in-depth analysis of paddy field microtopography and vegetation growth, the ability to assess paddy field usage and vegetation health is enhanced, providing a more detailed basis for crop management and resource optimization, which not only enhances the scientific management of agricultural production, but also provides effective tools for environmental monitoring and land use, and promotes the practical application of ecological protection. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 is a system flow chart of the present invention; Figure 2 The present invention is a flowchart for obtaining a paddy field remote sensing image set; Figure 3 A flow chart for obtaining a paddy field region characteristic map according to the present invention; Figure 4 is a flow chart for calculating pixel differences between images of the present invention; Figure 5 The present invention is a flowchart for obtaining a paddy field dynamic change diagram; Figure 6 The present invention is a flow chart for identifying the terrain undulation and water flow direction of the paddy field area; Figure 7 The present invention is a flow chart for obtaining the internal characteristic analysis diagram of the paddy field. DETAILED DESCRIPTION
[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.
[0018] See also Figure 1 , a system for interpreting paddy field planting areas using remote sensing images comprises: The remote sensing image acquisition module collects remote sensing images through remote sensing satellites, selects images including paddy field areas, time-marks the images, and performs spatial correction simultaneously to form a paddy field remote sensing image set; The paddy field remote sensing identification module uses the paddy field remote sensing image set to perform boundary detection, highlight the boundary between paddy fields and non-paddy fields, distinguish paddy fields from non-paddy fields, and mark the paddy field areas to generate paddy field area feature maps; The paddy field change monitoring module performs image registration based on the paddy field area feature map, accurately aligns the paddy field remote sensing images at different time points, calculates the pixel differences between images, identifies the changes in paddy field area and boundaries based on the calculation results, records the newly appeared or disappeared paddy field areas, and obtains the paddy field dynamic change map; The remote sensing image interpretation module uses the paddy field dynamic change map to conduct terrain analysis to determine the micro-topography structure of the paddy field area, identify the terrain undulations and water flow direction of the paddy field area, and conduct surface reflectivity analysis based on the identification results. It compares image data at different times, identifies changes in vegetation growth activities, reveals the relationship between paddy field usage status and vegetation health status, and comprehensively generates an analysis map of the internal characteristics of the paddy field.
[0019] The paddy field remote sensing image set includes the image set time information and spatial alignment information; the paddy field area feature map includes boundary marking results, area separation results and identification labels; the paddy field dynamic change map includes area change monitoring records, boundary update records and new change area identification results; the paddy field internal feature analysis map includes micro-topography attribute analysis results, water flow analysis results, reflectivity comparison records and vegetation change monitoring results.
[0020] See also Figure 2 , the steps to obtain the paddy field remote sensing image set are: The original data is obtained from the remote sensing satellite, and the original data is preliminarily processed using the formula: Calculate the processed image value , generate the original remote sensing image set, where represents remote sensing satellite data, represents the extraction efficiency parameter, and is the first constant adjustment term used to correct model deviation; Based on the original remote sensing image set, images including paddy fields were screened, and time labeling and spatial correction were performed. The formula was used. Calculate the normalized image value and generate the screened and corrected paddy field image set, where is the paddy field screening factor, is the normalization coefficient, is the second constant adjustment term, used to correct the result; Integrate the screened and corrected paddy field image set, format and output it, and use the formula: Calculate the image set integration index , we get a set of paddy field remote sensing images, where Represents the integration efficiency parameter, which is used to adjust the integration effect. is the third constant adjustment term.
[0021] : Remote sensing satellite data, such as the received pixel value, the data received for a certain pixel is 256.
[0022] : Data extraction efficiency, set to 0.9.
[0023] :The first constant adjustment term is used to correct the model deviation. Through the analysis of previous remote sensing images, .
[0024] Substituting into the formula, we get: The result 245.4 represents the value of the original remote sensing image data after the extraction efficiency is adjusted, which is used for subsequent processing and analysis.
[0025] : Paddy field screening factor, adjusted according to the actual ground conditions, set to 0.7.
[0026] : Normalization coefficient, used to maintain the standardization of data processing, taken as 100.
[0027] : The second constant adjustment term, used to correct the final result, is set to 5.
[0028] Substituting into the formula, we get: result It represents the image data after paddy field screening and normalization, which is the basis for the next step of integration processing.
[0029] : Integration efficiency parameter, used to adjust the integration effect, set to 1.2.
[0030] : The third constant adjustment item, set to 2.
[0031] Substituting into the formula, we get: result It represents the final integration index of the paddy field remote sensing image set, which is used to evaluate the quality of the integrated image set. A higher value indicates a better integration effect, which is suitable for further remote sensing data analysis.
[0032] See also Figure 3 , the steps to obtain the paddy field area characteristic map are: Based on the paddy field remote sensing image set, grayscale conversion and noise filtering are performed using the formula: Calculate the gray value after processing , generate the preprocessed paddy field image, where is the channel value of the color image, are the weight coefficients of the red, green and blue channels respectively, is the noise level, is the contrast adjustment parameter, It is the adjustment coefficient of noise and contrast, which is used to balance the effects of noise and contrast; Based on the preprocessed paddy field image, boundary detection and boundary recognition are performed using the formula: Calculate image boundary strength , generate a boundary detection map, where and Respectively represent exist and The gradient of the direction, is the edge enhancement coefficient, is the fine-tuning coefficient; According to the boundary detection map, paddy field and non-paddy field areas are distinguished and marked, using the formula, Calculate image visual effect value , generate the paddy field area characteristic map, where represents the annotation coefficient, is the zone separation precision adjustment factor, and is the adjustment factor used to control the scale and offset of the output results.
[0033] : The actual pixel values of the red, green and blue channels of a color image: : The weight of the color channel. Since the human eye is more sensitive to green, the weight is set to: and :set up .
[0034] : Noise and contrast adjustment coefficient, set to .
[0035] Calculate the grayscale part: Calculate the negative effect of noise and contrast: The final result of synthesis: result It is the gray value after preprocessing, which simplifies the image data. This gray value reflects the brightness of the image after removing some noise, which helps to improve the accuracy and efficiency of the subsequent boundary detection algorithm.
[0036] and :set up and .
[0037] : Edge enhancement coefficient, set to .
[0038] : Fine-tuning coefficient, used to fine-tune the sensitivity of boundary detection, set to .
[0039] Calculate the magnitude of the boundary gradient: Apply enhancement and adjustment factors: result It indicates the boundary strength of each point in the image. The purpose is to identify the significant boundaries in the image, specifically the boundary between paddy fields and non-paddy fields. A higher boundary detection value indicates that there is a more obvious boundary at this point because the pixel value of this point has a greater change in space.
[0040] :Marking coefficient, take .
[0041] : Area separation precision adjustment coefficient, set to .
[0042] and : Adjustment coefficient, set to .
[0043] Substituting into the formula, we get: result It represents the image visual effect value, showing the paddy field area after annotation processing, enhancing the visual effect and making the paddy field area more prominent and easy to identify in the final image.
[0044] See also Figure 4 , the calculation steps of pixel differences between images are: Based on the paddy field regional characteristic map, standardization is performed using the formula: Calculate the normalized pixel value , generate a standardized image, where It is the paddy field area characteristic map image data, is a small amount that prevents the denominator from reaching zero, and are the minimum and maximum pixel values, respectively; Based on the standardized image, key feature points are extracted and image registration is performed using the formula: Calculate the fine-tuned pixel difference after registration , generate the registered image, where is the feature point value, is the adjustment factor, is the regularization coefficient; Based on the registered images, the formula is used: Calculate the pixel difference between two time points , and get the pixel difference map, where It is the image at the reference time point.
[0045] : Paddy field area feature map image data, collecting the original pixel value of a small area is 180.
[0046] and : The minimum and maximum pixel values of the region, collected as 100 and 200.
[0047] : A small constant to prevent the denominator from being zero, set to 1.
[0048] Substituting into the formula, we get: What you get Represents the pixel value normalized within a given range. The normalized value is more conducive to the consistency of subsequent processing.
[0049] : Feature point value, set to 0.780.
[0050] : Adjustment coefficient, set to 1.0 and 1.0.
[0051] : Regularization parameter, set to 2.
[0052] Substituting into the formula, we get: What you get Represents the fine-tuned pixel difference after registration, indicating the level of precise alignment between the two images after registration.
[0053] : The pixel value at the reference time point is set to 0, then: Calculated Indicates the amount of pixel difference between two time points. This value reflects the intensity of change in the area.
[0054] See also Figure 5, the steps to obtain the paddy field dynamic change map are: Based on the pixel difference map, set the difference threshold , detect significant changes if > , indicating significant paddy field area or boundary changes, generating a change detection map; According to the change detection map, the changed areas are classified and recorded, using the formula, Calculate the number of new change areas , output the new change area map, where is the coefficient for adjusting the classification sensitivity; Based on the new change area map, all change data are integrated and the formula is used. Calculate composite index , construct a dynamic change diagram of paddy fields, where is the adjustment factor for comprehensive changes.
[0055] Difference threshold , set to 0.05, combined with the above calculation results = 0.077, for comparison: 0.077>0.05 Indicates significant changes in paddy field area or boundaries.
[0056] : Classification sensitivity adjustment parameter, set to 1.2, aims to fine-tune the sensitivity of changes to adapt to different environmental conditions or monitoring needs.
[0057] Substituting into the formula, we get: Calculated Indicating the number of newly appeared or disappeared paddy field areas reflects the changes in paddy fields and is used for further analysis and decision making.
[0058] : Adjustment coefficient, set to 1.1, to further emphasize the change area and ensure visibility in the dynamic change graph.
[0059] Substituting into the formula, we get: Generated It is a quantitative indicator of the dynamic change map that comprehensively reflects all identified paddy field changes, ensuring significance and visibility in the dynamic change map, and is used to show the changing trend of the paddy field area over time.
[0060] See also Figure 6 , the steps for identifying the terrain undulation and water flow direction in the paddy field area are: Based on the dynamic change map of paddy fields, the micro-topography structure is analyzed using the digital elevation model and the formula is adopted. Calculate weighted mean elevation , generate a micro-topography structure map, where Indicates the target location Elevation data, is the terrain importance weight, is the lateral measure of elevation, represents a data point; According to the micro-topographic structure map, the terrain undulation is evaluated using the formula: Calculate the terrain relief index , used to indicate the unevenness of the terrain and obtain terrain relief data, where is the average elevation; Based on the terrain data, the water flow direction is determined using the formula: Calculate the flow direction value , construct a water flow direction map, where is the angle from the horizontal and is used to calculate directivity.
[0061] Collect three data points, elevation values rice.
[0062] Weight .
[0063] Horizontal measurement factor .
[0064] Substitute into the formula to calculate : Meters represent the weighted average elevation after considering topographic importance and elevation lateral measurement factors, reflecting the comprehensive structure of microtopography.
[0065] Combining the above data, calculate the average elevation: Substitute into the formula and calculate: result Meters reflects the root mean square value of terrain undulation, indicating that the terrain has certain undulations in elevation.
[0066] Collect three sets of data [4.08, 4.08, 4.08], angle =[0°, 45°, 90°].
[0067] Substituting into the formula, we get: Represents the weighted average flow direction value, which uses terrain relief data and the cosine of the angle to determine the dominant flow direction.
[0068] See also Figure 7 , the steps to obtain the internal characteristic analysis map of the paddy field are: Collect time series image data, analyze surface reflectivity, and use the formula, Calculate the difference in surface reflectance , and obtain the surface reflectivity change data, where and are the reflectances at two time points, represents the position factor, Indicates the number of locations; Based on the surface reflectivity change data, the vegetation growth activity is determined using the formula: Calculating vegetation growth rate , and obtain paddy field vegetation growth data, where For location The reflectivity change value, is the measurement precision factor; Based on the terrain undulation data, water flow direction map and paddy field vegetation growth data, an analytical map of the internal characteristics of the paddy field is constructed and output.
[0069] Collect reflectivity data at three locations , , location factor .
[0070] Substituting into the formula, we get: It represents the difference in surface reflectance calculated by weighted average, which is used to reflect the degree of change of surface conditions at different times.
[0071] Collecting reflectivity difference data , measurement accuracy .
[0072] Substituting into the formula, we get: It represents the comprehensive changes in paddy field vegetation growth activities at various locations, reflecting the overall trend of paddy field vegetation activities.
[0073] A method for interpreting paddy field planting areas using remote sensing images comprises the following steps: S1: Obtain raw data based on remote sensing satellites and perform preliminary processing, screen images including paddy fields, perform time tagging and spatial correction, format and output processing, and obtain a remote sensing image set of paddy fields; S2: Based on the paddy field remote sensing image set, grayscale and noise filtering are performed, boundary detection and boundary recognition are performed, image boundary strength is calculated, paddy field and non-paddy field areas are distinguished, and annotation is performed to generate paddy field area feature maps; S3: Based on the paddy field area feature map, standardization processing is performed, key feature points are extracted and image registration is performed, the pixel difference value of the image between two time points is calculated, and the pixel difference map is output; S4: Based on the pixel difference map, set the difference threshold to detect significant changes, classify and record the changed areas, integrate all the change data to calculate the comprehensive index, and construct the dynamic change map of the paddy field; S5: Based on the paddy field dynamic change map, the digital elevation model is used to analyze the micro-topography structure, evaluate the terrain undulation, determine the water flow direction, and construct the water flow direction map; S6: Use time series image data to analyze surface reflectivity, determine vegetation growth activities, integrate water flow direction maps, and construct and output analysis maps of paddy field internal characteristics.
[0074] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A system for interpreting paddy field planting areas using remote sensing images, characterized in that: The system comprises: The remote sensing image acquisition module collects remote sensing images through remote sensing satellites, selects images including paddy field areas, time-marks the images, and performs spatial correction simultaneously to form a paddy field remote sensing image set; The paddy field remote sensing recognition module uses the paddy field remote sensing image set to perform boundary detection, highlight the boundary between the paddy field and the non-paddy field area, distinguish the paddy field area from the non-paddy field area, and mark the paddy field area to generate a paddy field area feature map; The paddy field change monitoring module performs image registration based on the paddy field area feature map, accurately aligns the paddy field remote sensing images at different time points, calculates the pixel difference between the images, identifies the changes in the paddy field area and boundaries based on the calculation results, records the newly appeared or disappeared paddy field areas, and obtains the paddy field dynamic change map; The remote sensing image interpretation module uses the paddy field dynamic change map to perform terrain analysis to determine the micro-topography structure of the paddy field area, identify the terrain undulations and water flow direction of the paddy field area, perform surface reflectivity analysis based on the identification results, compare image data at different times, identify changes in vegetation growth activities, reveal the relationship between the paddy field usage status and the vegetation health status, and comprehensively generate an analysis map of the internal characteristics of the paddy field.
2. The system for interpreting paddy field planting areas from remote sensing images according to claim 1, characterized in that: The steps for obtaining the paddy field remote sensing image set are: The original data is obtained from the remote sensing satellite, and the original data is preliminarily processed using the formula: Calculate the processed image value , generate the original remote sensing image set, where, Represents remote sensing satellite data, represents the extraction efficiency parameter, is the first constant adjustment term, used to correct the model deviation; Based on the original remote sensing image set, images including paddy fields are screened, and time labeling and spatial correction are performed. The formula is used: Calculate normalized image values , generate a screened and corrected paddy field image set, where is the paddy field screening factor, is the normalization coefficient, is the second constant adjustment term, used to correct the result; The screened and corrected paddy field image set is integrated, formatted and outputted, and the formula is used: Calculate the image set integration index , we get a set of paddy field remote sensing images, where Represents the integration efficiency parameter, which is used to adjust the integration effect. is the third constant adjustment term.
3. The system for interpreting paddy field planting areas from remote sensing images according to claim 2, characterized in that: The steps for obtaining the paddy field area characteristic map are: Based on the paddy field remote sensing image set, grayscale conversion and noise filtering are performed using the formula: Calculate the gray value after processing , generate the preprocessed paddy field image, where is the channel value of the color image, are the weight coefficients of the red, green and blue channels respectively, is the noise level, is the contrast adjustment parameter, It is the adjustment coefficient of noise and contrast, which is used to balance the effects of noise and contrast; Based on the preprocessed paddy field image, boundary detection and boundary recognition are performed using the formula: Calculate image boundary strength , generate a boundary detection map, where and Respectively represent exist and The gradient of the direction, is the edge enhancement coefficient, is the fine-tuning coefficient; According to the boundary detection map, paddy field and non-paddy field areas are distinguished and marked, using the formula: Calculate image visual effect value , generate the paddy field area characteristic map, where represents the annotation coefficient, is the zone separation precision adjustment factor, and is the adjustment factor used to control the scale and offset of the output results.
4. The system for interpreting paddy field planting areas from remote sensing images according to claim 3, characterized in that: The steps for calculating the pixel difference between the images are: Based on the paddy field regional characteristic map, standardization processing is performed using the formula: Calculate the normalized pixel value , generate a standardized image, where It is the paddy field area characteristic map image data, is a small amount that prevents the denominator from reaching zero, and are the minimum and maximum pixel values, respectively; Based on the standardized image, key feature points are extracted and image registration is performed using the formula: Calculate the fine-tuned pixel difference after registration , generate the registered image, where is the feature point value, is the adjustment factor, is the regularization coefficient; Based on the registered image, the formula is used: Calculate the pixel difference between two time points , and get the pixel difference map, where It is the image at the reference time point.
5. The system for interpreting paddy field planting areas from remote sensing images according to claim 4, characterized in that: The steps for obtaining the paddy field dynamic change diagram are as follows: Based on the pixel difference map, a difference threshold is set , detect significant changes if > , indicating significant paddy field area or boundary changes, generating a change detection map; According to the change detection map, the changed areas are classified and recorded, using the formula, Calculate the number of new change areas , output the new change area map, where is the coefficient for adjusting the classification sensitivity; Based on the new change area map, all change data are integrated and the formula is used. Calculate composite index , construct a dynamic change diagram of paddy fields, where is the adjustment factor for comprehensive changes.
6. The system for interpreting paddy field planting areas from remote sensing images according to claim 5, characterized in that: The steps for identifying the terrain undulation and water flow direction of the paddy field area are as follows: Based on the paddy field dynamic change map, the micro-topography structure is analyzed using the digital elevation model, and the formula is adopted. Calculate weighted mean elevation , generate a micro-topography structure map, where Indicates the target location Elevation data, is the terrain importance weight, is the lateral measure of elevation, represents a data point; According to the micro-topographic structure map, the terrain relief is evaluated using the formula, Calculate the terrain relief index , used to indicate the unevenness of the terrain and obtain terrain relief data, where is the average elevation; Based on the terrain undulation data, the water flow direction is determined using the formula: Calculate the flow direction value , construct a water flow direction map, where is the angle from the horizontal and is used to calculate directivity.
7. The system for interpreting paddy field planting areas from remote sensing images according to claim 6, characterized in that: The steps for obtaining the paddy field internal feature analysis map are as follows: Collect time series image data, analyze surface reflectivity, and use the formula, Calculate the difference in surface reflectance , and obtain the surface reflectivity change data, where and are the reflectances at two time points, represents the position factor, Indicates the number of locations; Based on the surface reflectivity change data, the vegetation growth activity is determined using the formula: Calculating vegetation growth rate , and obtain paddy field vegetation growth data, where For location The reflectivity change value, is the measurement precision factor; The terrain undulation data, water flow direction map and paddy field vegetation growth data are integrated to construct and output an analytical map of paddy field internal characteristics.
8. A method for interpreting paddy field planting areas from remote sensing images, characterized in that: The system for interpreting paddy field planting areas from remote sensing images according to any one of claims 1 to 7 comprises the following steps: Based on the acquisition of raw data from remote sensing satellites and preliminary processing, images including paddy fields are screened, time-stamping and spatial correction are performed, formatting and output processing are performed, and a paddy field remote sensing image set is obtained; Based on the paddy field remote sensing image set, graying and noise filtering are performed, boundary detection and boundary recognition are performed, image boundary strength is calculated, paddy field and non-paddy field areas are distinguished, and annotation is performed to generate a paddy field area feature map; Based on the paddy field area feature map, standardization processing is performed, key feature points are extracted and image registration is performed, pixel difference values of images between two time points are calculated, and a pixel difference map is output; Based on the pixel difference map, a difference threshold is set to detect significant changes, the changed areas are classified and recorded, all change data are integrated to calculate comprehensive indicators, and a paddy field dynamic change map is constructed; Based on the paddy field dynamic change map, a digital elevation model is used to analyze the micro-topography structure, evaluate the terrain undulation, determine the water flow direction, and construct a water flow direction map; Using time series image data, the surface reflectivity is analyzed to determine vegetation growth activities, and the water flow direction map is integrated to construct and output an analytical map of the internal characteristics of the paddy field.
Citation Information
Patent Citations
Object-oriented specific area full-automatic change monitoring method
CN106991424A
Land utilization monitoring method and device based on remote sensing image data
CN110263764A
Farmland weed accurate identification method and device based on satellite remote sensing
CN116805396A
Surface vegetation analysis system and method based on remote sensing image
CN116958817A
Straw field leaving satellite remote sensing dynamic supervision method in combination with video monitoring
CN117197678A
Cited By
Herbaceous plant planting monitoring system and use method thereof
CN119722369A
Remote sensing monitoring method and system for cultivated land protection
CN120279484A
Unmanned aerial vehicle-based concave green land vegetation management system
CN122157029A
Unmanned aerial vehicle based sunken greenery vegetation management system
CN122157029B
