Data analysis system based on integrated remote sensing data acquisition

Abstract

The application discloses a data analysis system based on integrated remote sensing data collection; including a data analysis system, the data analysis system includes a remote sensing data collection module, a data preprocessing module, a data integration and fusion module, a data feature extraction module, a data time sequence analysis module and a data visualization module; the data analysis system adopts distributed computing, parallel and streaming processing mode to quickly process integrated massive remote sensing data; the application adopts distributed computing, parallel and streaming processing mode, decomposes the computing task into multiple parallel tasks, improves the computing efficiency; when the remote sensing data is preprocessed, the accuracy of the remote sensing data can be maintained, and the computing efficiency is improved; through fusion processing, the multi-source remote sensing image data can form a clear image information; the data time sequence analysis module predicts according to the collected characteristic information and the past historical characteristic information, so that the grazing time length can be accurately controlled.

Description

Technical Field

[0001] This invention belongs to the field of remote sensing data analysis technology, and more specifically, relates to a data analysis system based on integrated remote sensing data acquisition. Background Technology

[0002] A grazing system is an organizational framework for grazing management. It follows the energy flow and material cycle patterns of grassland ecosystems. Based on grassland fencing, livestock watering facilities, vegetation composition regulation, and pasture improvement, it balances the quantity and quality of forage growth with the nutritional needs of livestock by adjusting grazing intensity and frequency in time and space. The initial purpose of grazing systems was to revitalize degraded grasslands through the rational use of seasonal grazing and fallow periods. Extensive scientific research has also shown that a rational grazing system can restore grassland vitality, improve grassland productivity, maintain grassland ecological balance, and enable the sustainable use of grasslands.

[0003] Rotational grazing is a grassland utilization method that typically involves establishing permanent or temporary fences to delineate grazing areas and strictly controlling the grazing time and range of livestock within these areas according to a specific grazing plan. Traditional rotational grazing mainly includes general block rotational grazing (a single herd grazing in a certain order on designated plots), alternating grazing of different livestock (different species of livestock using the same pasture at the same time or at different times), warm-season encampment grazing (rotational grazing with strict order in grazing areas during the pasture growing season), and diurnal grazing (using easily movable point fences or other mobile fences to keep livestock in a small area for concentrated pasture utilization), etc.

[0004] To monitor and predict the growth of pasture grasses, remote sensing technology is used to acquire data from pastures. By monitoring and predicting the growth of pasture grasses based on the data collected by remote sensing, it is possible to effectively and precisely control grazing time, allow pastures sufficient recovery time, improve pasture productivity, maintain grassland ecological balance, and enable the sustainable use of grasslands.

[0005] However, existing technologies have some problems: there are many sources of remote sensing data, and the processing efficiency is slow when processing large amounts of remote sensing image data, which puts a lot of pressure on the computer and cannot improve the computing efficiency. In addition, the processing of remote sensing image data from multiple sources is relatively simple, which makes it impossible to achieve accurate fusion of remote sensing image data, which can easily lead to data loss. It is not convenient to make accurate predictions about pastures, and the predictions about pastures cannot be combined with previous data, and it is not convenient to view the previous data. Therefore, we propose a data analysis system based on integrated remote sensing data acquisition. Summary of the Invention

[0006] To address the problems existing in the prior art, the purpose of this invention is to provide a data analysis system based on integrated remote sensing data acquisition. This system improves the computational processing efficiency of integrated remote sensing image data, enhances the fusion of multi-source remote sensing image data, and enables clear observation and prediction of pastures by performing distributed computing, parallel and streaming processing on remote sensing image data, fine processing and fusion of multi-source remote sensing image data, and monitoring and predicting pasture conditions through time series analysis.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a data analysis system based on integrated remote sensing data acquisition, comprising a data analysis system including a remote sensing data acquisition module, a data preprocessing module, a data integration and fusion module, a data feature extraction module, a data time series analysis module, and a data visualization module;

[0008] The data analysis system employs distributed computing and parallel and streaming processing methods to improve the rapid processing of integrated massive amounts of remote sensing data.

[0009] The distributed computing uses Apache Spark to distribute data and computing tasks across multiple computers for collaborative processing.

[0010] The parallel and streaming processing uses Apache Kafka to process multiple data streams or tasks simultaneously to improve processing efficiency; the computational task is decomposed into multiple parallel tasks to improve computational efficiency.

[0011] The remote sensing data acquisition module is used to receive and acquire remote sensing data monitored by the remote sensing platform. The remote sensing platform includes satellites, aircraft and drones. The remote sensing platform monitors and acquires data through onboard sensors, including optical sensors, radar sensors and lidar.

[0012] Optical sensors capture information from the visible and near-infrared spectra;

[0013] Radar sensors acquire information about the Earth's surface by actively emitting electromagnetic waves and receiving reflected signals.

[0014] LiDAR acquires high-precision terrain data and three-dimensional information by scanning the earth's surface with lasers;

[0015] The data preprocessing module preprocesses the acquired remote sensing data, including geometric correction, atmospheric correction, radiometric correction, noise removal, image enhancement, and image fusion.

[0016] Geometric correction is the process of converting pixel coordinates in remote sensing images into actual geographic coordinates on the Earth's surface.

[0017] Atmospheric correction is the process of adjusting the radiometric values ​​in remote sensing images caused by atmospheric scattering and absorption effects, in order to extract true surface information from the images.

[0018] Radiometric correction adjusts the raw radiometric values ​​of remote sensing data to eliminate errors caused by the sensor and data acquisition process.

[0019] Noise removal addresses noise or artifacts in remote sensing data, improving data quality.

[0020] Image enhancement helps to better extract information by improving the visualization of images;

[0021] Image fusion combines image data from different sensors or at different times to obtain richer information;

[0022] The data integration and fusion module is used to integrate data from different sensors and remote sensing platforms to ensure the spatial and temporal consistency of data from different sources;

[0023] The data feature extraction module is used to extract features from the fused remote sensing data, which facilitates subsequent analysis and processing based on the extracted features.

[0024] The data time series analysis module applies statistical models to model and predict time series data, and combines remote sensing data acquired at different times to perform time series analysis and change monitoring.

[0025] The data visualization module is used to visualize the prediction and monitoring data of the data time series analysis module to facilitate understanding and analysis. It includes an integrated map and a dynamic display. The integrated map overlays the analysis results of different datasets onto a map for spatial visualization. The dynamic display shows the changes and dynamic processes of the land surface through time series animation.

[0026] Optionally, the noise removal is performed by processing the remote sensing data using Gaussian filtering, and the calculation formula for Gaussian filtering is as follows:

[0027] ,in, It is at point Gaussian function value, It is the standard deviation of the Gaussian function, which controls the strength of smoothing; and These are coordinates relative to the center of the Gaussian function;

[0028] Standard deviation The calculation formula is as follows:

[0029] ,in, It is the value of each remote sensing data point, and the value is... Two-dimensional values, This represents the mean of the remote sensing data points. Let N be the mean error of the remote sensing data points, and N be the number of remote sensing data points.

[0030] The mean error The calculation formula is as follows:

[0031] ,in, This is the actual calculated mean. This is the predicted mean.

[0032] Optionally, the Gaussian filtering separation separates the two-dimensional Gaussian function into a one-dimensional Gaussian function, improving computational efficiency. The separation formula for the Gaussian filtering is as follows:

[0033] ,in, It is a one-dimensional Gaussian function on the X-axis. It is a one-dimensional Gaussian function on the Y-axis;

[0034] The one-dimensional Gaussian function on the X-axis is shown below:

[0035] ;

[0036] The one-dimensional Gaussian function on the Y-axis is shown below:

[0037] Where x and y are the values ​​of the Gaussian function, respectively. Values ​​on the X and Y axes;

[0038] Next, convolution is performed on the one-dimensional Gaussian functions on the X and Y axes. The processing procedure is as follows:

[0039] ;

[0040] ;

[0041] in, and These are the convolution results of remote sensing data points on the X and Y axes, respectively. and These are the values ​​of remote sensing data points on the X and Y axes, respectively. and These are the convolution kernels on the X and Y axes, respectively, and L is the length of the convolution kernel.

[0042] Optionally, the data integration and fusion module performs fusion processing on remote sensing images acquired by different remote sensing platforms or different sensors, and the calculation process of the fusion processing is as follows:

[0043] ,

[0044] in, These are the pixel values ​​of the merged image. These are the pixel values ​​of the original images that need to be merged. It is a weighting coefficient, and its value is between 0 and 1.

[0045] Optionally, the data feature extraction module accelerates the construction of the integral image using a fast algorithm, and the construction process is calculated as follows:

[0046] ;

[0047] in, Is the image in position The original pixel values; In position The integral image value represents the sum of all pixel values ​​within the region from the top-left corner (0,0) to (x,y) of the image; the formula quickly calculates the integral image value at the current position using previously calculated integral image values; and the integral image value in the formula... These represent the integral values ​​at the left, top, and top-left corners, respectively.

[0048] Optionally, the integral image detects key points using the determinant of the Hessian matrix; and the formula for calculating the determinant of the Hessian matrix is ​​as follows:

[0049] ;

[0050] in, It is the second derivative of the image along the X-axis, representing the curvature of the image;

[0051] It is the second derivative of the image along the Y-axis, representing the curvature of the image;

[0052] It is the mixed second derivative of the image in the X and Y axis directions, describing the interaction between the image in the two directions;

[0053] For each keypoint, the local region is used to generate a feature descriptor using the Haar wavelet response; and the formula for calculating the Haar wavelet response is as follows:

[0054] ;

[0055] Where d is the size of the Haar feature, used to calculate the response within a local region; These are integral map values, used to accelerate the calculation of the response in local regions.

[0056] Optionally, the data time series analysis module performs time series analysis on the acquired and processed remote sensing images using the SARIMA model, and calculates the features of the remote sensing images using the integral map established by the data feature extraction module, thereby realizing time series analysis and processing of the remote sensing images and improving the prediction of remote sensing impacts.

[0057] The SARIMA model's calculation formula for seasonal time series data processing is as follows:

[0058] ;

[0059] Where p is the order of the autoregressive term, indicating how many lags are used in the SARIMA model to predict the current value; q is the order of the moving average term, indicating how many lag error terms are used in the SARIMA model to predict the current value; P is the order of the seasonal autoregressive term, indicating how many seasonal lags are used in the SARIMA model; Q is the order of the seasonal moving average term, indicating how many seasonal lag error terms are used in the SARIMA model; s is the seasonal period, i.e., the length of a complete season; here s is chosen as 12, indicating that there are 12 months in a year; Φ1, Φ2, ..., Φ p These are the coefficients of the seasonal autoregressive term, representing the relationship between the current value and the previous P seasonally lagged values, Θ1, Θ2, ..., Θ q It is the coefficient of the seasonal moving average term, representing the relationship between the current value and the previous Q seasonal lag error terms.

[0060] Optionally, when calculating the SARIMA model, exogenous variables are introduced to perform calculations on the time series data, and the calculation formula is as follows:

[0061] ;

[0062] in, It is an exogenous variable, and These are the coefficients of exogenous variables, and exogenous variables are used as explanatory variables to eliminate the sudden changes in remote sensing images caused by external factors.

[0063] Optionally, the specific steps for dynamically updating the parameters of the SARIMA model using the Bayesian method are as follows:

[0064] Assuming model parameters The prior distribution is ;

[0065] Given observation data and model parameters Calculate the likelihood function The likelihood function of a SARIMA model typically involves calculating the residuals of the time series:

[0066] ,

[0067] in, Based on current parameters The model's predicted values, It is the variance of the error;

[0068] By combining the prior distribution and the likelihood function, the posterior distribution is calculated using Bayes' theorem. ;

[0069] ,

[0070] in, It is the marginal likelihood;

[0071] With new data Upon arrival, update the posterior distribution of the parameters to the new prior distribution, and repeat the above steps:

[0072]

[0073] Here, It is based on the posterior distribution of the first t observations.

[0074] Optionally, the data visualization module displays changes in remote sensing images through dynamic display, that is, it displays the changes and dynamic processes of grassland turf through time-series animation. The dynamic display steps of the data visualization module are as follows:

[0075] Data loading: Import or link processed remote sensing image data to ensure the accuracy and integrity of the remote sensing image data;

[0076] Configure the display: Set the chart type, style, and dynamic characteristics, and configure real-time updates and interactivity;

[0077] Enables dynamic functionality: Configures real-time updates and interactive operations for remote sensing image data, and achieves real-time updates, interactivity, and dynamic display through time-series data;

[0078] Operation and monitoring: Start the display module to monitor the updates of remote sensing image data and user interaction in real time;

[0079] Adjustments and optimizations: Adjustments will be made based on actual usage to optimize performance and user experience.

[0080] The technical effects and advantages of this invention are as follows:

[0081] In order to improve the speed and efficiency of remote sensing data processing, this invention adopts distributed computing and parallel and streaming processing methods to distribute remote sensing data and computing tasks to multiple computers for collaborative processing, thereby processing multiple remote sensing data streams or tasks simultaneously to improve processing efficiency; and decomposes computing tasks into multiple parallel tasks to improve computing efficiency.

[0082] When preprocessing remote sensing data, Gaussian filtering is used for denoising. During Gaussian filtering, the standard deviation of the Gaussian function is reduced to control the smoothing intensity. The standard deviation of the Gaussian function is reduced by using the mean and error, which can maintain the accuracy of remote sensing data and reduce the smoothing intensity of the denoising process. In addition, to reduce the computational burden, the two-dimensional function of the remote sensing image is decomposed into a one-dimensional function to improve computational efficiency.

[0083] For remote sensing image data from multiple sources, fusion processing is used to fuse the remote sensing images, so that the remote sensing image data from multiple sources can form a clear image information. During the fusion processing, the maximum and minimum values ​​in the remote sensing images are weighted and processed to achieve the fusion processing of remote sensing image data from multiple sources.

[0084] Furthermore, after fusing remote sensing image data from multiple sources, feature extraction is performed to facilitate the acquisition of pasture changes. This allows the data time series analysis module to make predictions based on the collected feature information and historical feature information. In addition, the pasture needs to be harvested and stored. By calculating the time series data through exogenous variables, it is possible to accurately control the grazing time, give the pasture a certain recovery time, improve the pasture's production efficiency, maintain the ecological balance of the grassland, and enable the sustainable use of the grassland. In addition, the introduction of Bayesian methods to dynamically update parameters facilitates the real-time updating of remote sensing image data during the display of grassland turf changes and dynamics, enabling timely observation and prediction.

[0085] Other features and advantages of the invention will become clear from the following detailed description of exemplary embodiments of the invention with reference to the accompanying drawings. Attached Figure Description

[0086] Figure 1 This is a schematic diagram of the integrated remote sensing data acquisition and data analysis system provided by the present invention. Detailed Implementation

[0087] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0088] like Figure 1 As shown in the figure, the data analysis system based on integrated remote sensing data acquisition provided in this embodiment of the invention is characterized by including a data analysis system, which includes a remote sensing data acquisition module, a data preprocessing module, a data integration and fusion module, a data feature extraction module, a data time series analysis module, and a data visualization module.

[0089] The data analysis system employs distributed computing and parallel and streaming processing methods to improve the rapid processing of integrated massive amounts of remote sensing data;

[0090] Distributed computing uses Apache Spark to distribute data and computing tasks across multiple computers for collaborative processing.

[0091] Parallel and streaming processing utilizes Apache Kafka to process multiple data streams or tasks simultaneously, thereby improving processing efficiency; it also decomposes computational tasks into multiple parallel tasks to improve computational efficiency.

[0092] The remote sensing data acquisition module is used to receive and collect remote sensing data monitored by the remote sensing platform. The remote sensing platform includes satellites, aircraft and drones. The remote sensing platform monitors and collects data through onboard sensors, including optical sensors, radar sensors and lidar.

[0093] Optical sensors capture information from the visible and near-infrared spectra;

[0094] Radar sensors acquire information about the Earth's surface by actively emitting electromagnetic waves and receiving reflected signals.

[0095] LiDAR acquires high-precision terrain data and three-dimensional information by scanning the earth's surface with lasers;

[0096] The data preprocessing module preprocesses the acquired remote sensing data, including geometric correction, atmospheric correction, radiometric correction, noise removal, image enhancement, and image fusion.

[0097] Geometric correction is the process of converting pixel coordinates in remote sensing images into actual geographic coordinates on the Earth's surface.

[0098] Atmospheric correction is the process of adjusting the radiometric values ​​in remote sensing images caused by atmospheric scattering and absorption effects, in order to extract true surface information from the images.

[0099] Radiometric correction adjusts the raw radiometric values ​​of remote sensing data to eliminate errors caused by the sensor and data acquisition process.

[0100] Noise removal addresses noise or artifacts in remote sensing data, improving data quality.

[0101] Image enhancement helps to better extract information by improving the visualization of images;

[0102] Image fusion combines image data from different sensors or at different times to obtain richer information;

[0103] The data integration and fusion module is used to integrate data from different sensors and remote sensing platforms to ensure the spatial and temporal consistency of data from different sources;

[0104] The data feature extraction module is used to extract features from the fused remote sensing data, which facilitates subsequent analysis and processing based on the extracted features;

[0105] The data time series analysis module applies statistical models to model and predict time series data, combining remote sensing data acquired at different times to perform time series analysis and change monitoring;

[0106] The data visualization module is used to visualize the prediction and monitoring data from the data time series analysis module to facilitate understanding and analysis. It includes integrated maps and dynamic displays. The integrated map overlays the analysis results of different datasets onto a map for spatial visualization. The dynamic display shows the changes and dynamic processes of the land surface through time series animations.

[0107] In this embodiment, preferably, noise removal is performed by calculating and processing the remote sensing data using Gaussian filtering, and the calculation formula for Gaussian filtering is as follows:

[0108] ,in, It is at point Gaussian function value, It is the standard deviation of the Gaussian function, which controls the strength of smoothing; and These are coordinates relative to the center of the Gaussian function;

[0109] Standard deviation The calculation formula is as follows:

[0110] ,in, It is the value of each remote sensing data point, and the value is... Two-dimensional values, This represents the mean of the remote sensing data points. Let N be the mean error of the remote sensing data points, and N be the number of remote sensing data points.

[0111] Mean error The calculation formula is as follows:

[0112] ,in, This is the actual calculated mean. This is the predicted mean;

[0113] Gaussian filtering is used to filter the acquired remote sensing image data, improving the accuracy of the data. To maintain the smoothness of the denoising process, the standard deviation of the Gaussian function is calculated at a low value. The standard deviation is calculated using the mean and error of the remote sensing image data to maintain its stability, facilitating smooth denoising.

[0114] Furthermore, Gaussian filtering separates the two-dimensional Gaussian function into a one-dimensional Gaussian function, improving computational efficiency. The separation formula for Gaussian filtering is shown below:

[0115] ,in, It is a one-dimensional Gaussian function on the X-axis. It is a one-dimensional Gaussian function on the Y-axis;

[0116] The one-dimensional Gaussian function on the X-axis is shown below:

[0117] ;

[0118] The one-dimensional Gaussian function on the Y-axis is shown below:

[0119] Where x and y are the values ​​of the Gaussian function, respectively. Values ​​on the X and Y axes;

[0120] Next, convolution is performed on the one-dimensional Gaussian functions on the X and Y axes. The processing procedure is as follows:

[0121] ;

[0122] ;

[0123] in, and These are the convolution results of remote sensing data points on the X and Y axes, respectively. and These are the values ​​of remote sensing data points on the X and Y axes, respectively. and These are the convolution kernels on the X and Y axes, respectively, and L is the length of the convolution kernel;

[0124] To reduce the complexity of Gaussian filtering and improve computational efficiency and workload, converting the two-dimensional Gaussian function into a one-dimensional Gaussian function can improve computational efficiency.

[0125] In this embodiment, preferably, the data integration and fusion module performs fusion processing on remote sensing images acquired by different remote sensing platforms or different sensors, and the calculation process of the fusion processing is as follows:

[0126] ,

[0127] in, These are the pixel values ​​of the merged image. These are the pixel values ​​of the original images that need to be merged. It is a weighting coefficient, and its value is between 0 and 1;

[0128] By fusing remote sensing image data from different sources, the maximum and minimum values ​​of the remote sensing image data are used for calculation, and weights are assigned to the maximum and minimum values ​​to achieve the fusion of remote sensing image data from different sources and form a clear remote sensing image information.

[0129] In this embodiment, preferably, the data feature extraction module accelerates the construction of the integral image using a fast algorithm, and the construction process is calculated as follows:

[0130] ;

[0131] in, Is the image in position The original pixel values; In position The integral image value represents the sum of all pixel values ​​within the region from the top-left corner (0,0) to (x,y) of the image; the formula quickly calculates the integral image value at the current position using previously calculated integral image values; and the integral image value in the formula... These represent the integral values ​​at the left, top, and top-left corners, respectively.

[0132] A fast algorithm is used to construct an accelerated integral map for feature extraction. The algorithm calculates the integral map value of the original pixel value and uses the calculated integral map value to quickly calculate the integral map value of the current position, thereby achieving fast calculation and processing of integral map values ​​and improving the feature extraction rate.

[0133] Furthermore, the feature is that the integral image detects key points using the determinant of the Hessian matrix; and the formula for calculating the determinant of the Hessian matrix is ​​as follows:

[0134] ;

[0135] in, It is the second derivative of the image along the X-axis, representing the curvature of the image;

[0136] It is the second derivative of the image along the Y-axis, representing the curvature of the image;

[0137] It is the mixed second derivative of the image in the X and Y axis directions, describing the interaction between the image in the two directions;

[0138] For each keypoint, the local region is used to generate a feature descriptor using the Haar wavelet response; and the formula for calculating the Haar wavelet response is as follows:

[0139] ;

[0140] Where d is the size of the Haar feature, used to calculate the response within a local region; These are integral map values, used to accelerate the calculation of the response in local regions;

[0141] For integral images, key points are detected by using the determinant of the Hessian matrix, which facilitates the generation of feature descriptors for the local region of each key point, enabling the calculation of features within the local region and accelerating the calculation of the local region's response.

[0142] In this embodiment, preferably, the data time series analysis module performs time series analysis on the acquired and processed remote sensing images using the SARIMA model, and calculates the features of the remote sensing images using the integral map established by the data feature extraction module, and performs time series analysis processing on the remote sensing images to improve the prediction processing of remote sensing impacts.

[0143] The SARIMA model's calculation formula for seasonal time series data processing is as follows:

[0144] ;

[0145] Where p is the order of the autoregressive term, indicating how many lags are used in the SARIMA model to predict the current value; q is the order of the moving average term, indicating how many lag error terms are used in the SARIMA model to predict the current value; P is the order of the seasonal autoregressive term, indicating how many seasonal lags are used in the SARIMA model; Q is the order of the seasonal moving average term, indicating how many seasonal lag error terms are used in the SARIMA model; s is the seasonal period, i.e., the length of a complete season; here s is chosen as 12, indicating that there are 12 months in a year; Φ1, Φ2, ..., Φ pThese are the coefficients of the seasonal autoregressive term, representing the relationship between the current value and the previous P seasonally lagged values, Θ1, Θ2, ..., Θ q It is the coefficient of the seasonal moving average term, representing the relationship between the current value and the previous Q seasonal lag error terms;

[0146] By combining historical data with remote sensing imagery, it is possible to make predictions about the future, which facilitates the prediction of pasture growth and the control and regulation of grazing.

[0147] Furthermore, when calculating the time series data, the SARIMA model incorporates exogenous variables, and the calculation formula is as follows:

[0148] ;

[0149] in, It is an exogenous variable, and These are the coefficients of exogenous variables, and exogenous variables are used as explanatory variables to eliminate the sudden changes in remote sensing images caused by external factors.

[0150] To mitigate the impact of large-scale harvesting and storage of forage in autumn, the harvesting process is calculated to facilitate precise control of grazing time, allowing pastures sufficient recovery time, improving pasture productivity, maintaining grassland ecological balance, and enabling sustainable grassland utilization.

[0151] Furthermore, the specific steps for dynamically updating the parameters of the SARIMA model using the Bayesian method are as follows:

[0152] Assuming model parameters The prior distribution is ;

[0153] Given observation data and model parameters Calculate the likelihood function The likelihood function of a SARIMA model typically involves calculating the residuals of the time series:

[0154] ,

[0155] in, Based on current parameters The model's predicted values, It is the variance of the error;

[0156] By combining the prior distribution and the likelihood function, the posterior distribution is calculated using Bayes' theorem. ;

[0157] ,

[0158] in, It is the marginal likelihood;

[0159] With new data Upon arrival, update the posterior distribution of the parameters to the new prior distribution, and repeat the above steps:

[0160]

[0161] Here, It is based on the posterior distribution of the first t observations;

[0162] To update remote sensing image data and enable real-time updates of the dynamically displayed pasture conditions, facilitating clear observation of pasture changes, a Bayesian method is used to dynamically update parameters, thereby improving the effectiveness and accuracy of the dynamic display.

[0163] In this embodiment, preferably, the data visualization module displays changes in remote sensing images through dynamic display, that is, it displays the changes and dynamic processes of grassland turf through time-series animation. The dynamic display steps of the data visualization module are as follows:

[0164] Data loading: Import or link processed remote sensing image data to ensure the accuracy and integrity of the remote sensing image data;

[0165] Configure the display: Set the chart type, style, and dynamic characteristics, and configure real-time updates and interactivity;

[0166] Enables dynamic functionality: Configures real-time updates and interactive operations for remote sensing image data, and achieves real-time updates, interactivity, and dynamic display through time-series data;

[0167] Operation and monitoring: Start the display module to monitor the updates of remote sensing image data and user interaction in real time;

[0168] Adjustments and optimizations: Adjustments will be made based on actual usage to optimize performance and user experience;

[0169] To enable dynamic display of changes in pasture grass and to allow for selective adjustment of parameters, thereby improving the effectiveness and accuracy of the dynamic display, users can adjust the parameters themselves based on their actual usage experience.

[0170] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A data analysis system based on integrated remote sensing data acquisition, characterized in that, The system includes a data analysis system, which comprises a remote sensing data acquisition module, a data preprocessing module, a data integration and fusion module, a data feature extraction module, a data time series analysis module, and a data visualization module. The data analysis system employs distributed computing and parallel and streaming processing methods to improve the rapid processing of integrated massive amounts of remote sensing data. The distributed computing uses Apache Spark to distribute remote sensing data and computing tasks across multiple computers for collaborative processing. The parallel and streaming processing uses Apache Kafka to process multiple remote sensing data streams or tasks simultaneously to improve processing efficiency; the computational task is decomposed into multiple parallel tasks to improve computational efficiency. The remote sensing data acquisition module is used to receive and acquire remote sensing data monitored by the remote sensing platform. The remote sensing platform includes satellites, aircraft and drones. The remote sensing platform monitors and acquires data through onboard sensors, including optical sensors, radar sensors and lidar. Optical sensors capture information from the visible and near-infrared spectra; Radar sensors acquire information about the Earth's surface by actively emitting electromagnetic waves and receiving reflected signals. LiDAR acquires high-precision terrain data and three-dimensional information by scanning the earth's surface with lasers; The data preprocessing module preprocesses the acquired remote sensing data, including geometric correction, atmospheric correction, radiometric correction, noise removal, image enhancement, and image fusion. Geometric correction is the process of converting pixel coordinates in remote sensing images into actual geographic coordinates on the Earth's surface. Atmospheric correction is the process of adjusting the radiometric values ​​in remote sensing images caused by atmospheric scattering and absorption effects, in order to extract true surface information from the images. Radiometric correction adjusts the raw radiometric values ​​of remote sensing data to eliminate errors caused by the sensor and data acquisition process. Noise removal addresses noise or artifacts in remote sensing data, improving data quality. Image enhancement helps to better extract information by improving the visualization of images; Image fusion combines image data from different sensors or at different times to obtain richer information; The data integration and fusion module is used to integrate data from different sensors and remote sensing platforms to ensure the spatial and temporal consistency of data from different sources; The data feature extraction module is used to extract features from the fused remote sensing data, which facilitates subsequent analysis and processing based on the extracted features. The data time series analysis module applies statistical models to model and predict time series data, and combines remote sensing data acquired at different times to perform time series analysis and change monitoring. The data visualization module is used to visualize the prediction and monitoring data of the data time series analysis module to facilitate understanding and analysis; it includes an integrated map and a dynamic display. The integrated map overlays the analysis results of different datasets onto a map for spatial visualization; the dynamic display shows surface changes and dynamic processes through time series animations. The data time series analysis module performs time series analysis on the acquired and processed remote sensing images using the SARIMA model. Through the integral map established by the data feature extraction module, it calculates the features of the remote sensing images and performs time series analysis on the remote sensing images, thereby improving the prediction of remote sensing impacts.

2. The data analysis system based on integrated remote sensing data acquisition according to claim 1, characterized in that: The noise removal process involves calculating and processing the remote sensing data using Gaussian filtering, and the calculation formula for Gaussian filtering is shown below: ,in, It is at point Gaussian function value, It is the standard deviation of the Gaussian function, which controls the strength of smoothing; and These are coordinates relative to the center of the Gaussian function; Standard deviation The calculation formula is as follows: ,in, It is the value of each remote sensing data point, and the value is... Two-dimensional values, This represents the mean of the remote sensing data points. Let N be the mean error of the remote sensing data points, and N be the number of remote sensing data points. The mean error The calculation formula is as follows: ,in, This is the actual calculated mean. This is the predicted mean.

3. The data analysis system based on integrated remote sensing data acquisition according to claim 2, characterized in that: The Gaussian filtering separation process divides the two-dimensional Gaussian function into a one-dimensional Gaussian function, improving computational efficiency. The separation formula for the Gaussian filtering is shown below: ,in, It is a one-dimensional Gaussian function on the X-axis. It is a one-dimensional Gaussian function on the Y-axis; The one-dimensional Gaussian function on the X-axis is shown below: ； The one-dimensional Gaussian function on the Y-axis is shown below: Where x and y are the values ​​of the Gaussian function, respectively. Values ​​on the X and Y axes; Next, convolution is performed on the one-dimensional Gaussian functions on the X and Y axes. The processing procedure is as follows: ； ； in, and These are the convolution results of remote sensing data points on the X and Y axes, respectively. and These are the values ​​of remote sensing data points on the X and Y axes, respectively. and These are the convolution kernels on the X and Y axes, respectively, and L is the length of the convolution kernel.

4. The data analysis system based on integrated remote sensing data acquisition according to claim 1, characterized in that: The data integration and fusion module performs fusion processing on remote sensing images acquired by different remote sensing platforms or different sensors, and the calculation process of the fusion processing is as follows: ， in, These are the pixel values ​​of the merged image. These are the pixel values ​​of the original images that need to be merged. It is a weighting coefficient, and its value is between 0 and 1.

5. The data analysis system based on integrated remote sensing data acquisition according to claim 1, characterized in that: The data feature extraction module accelerates the construction of the integral image through a fast algorithm, and the construction process is calculated as follows: ； in, Is the image in position The original pixel values; In position The integral image value represents the sum of all pixel values ​​within the region from the top-left corner (0,0) to (x,y) of the image; the formula quickly calculates the integral image value at the current position using previously calculated integral image values; and the integral image value in the formula... These represent the integral values ​​at the left, top, and top-left corners, respectively.

6. The data analysis system based on integrated remote sensing data acquisition according to claim 5, characterized in that: The integral image detects key points using the determinant of the Hessian matrix; and the formula for calculating the determinant of the Hessian matrix is ​​as follows: ； in, It is the second derivative of the image along the X-axis, representing the curvature of the image; It is the second derivative of the image along the Y-axis, representing the curvature of the image; It is the mixed second derivative of the image in the X and Y axis directions, describing the interaction between the image in the two directions; For each keypoint, the local region is used to generate a feature descriptor using the Haar wavelet response; and the formula for calculating the Haar wavelet response is as follows: ； Where d is the size of the Haar feature, used to calculate the response within a local region; These are integral map values, used to accelerate the calculation of the response in local regions.

7. The data analysis system based on integrated remote sensing data acquisition according to claim 1, characterized in that: The data visualization module displays changes in remote sensing images through dynamic presentation, specifically by showcasing the changes and dynamic processes of grassland turf through time-series animation. The dynamic presentation steps of the data visualization module are as follows: Data loading: Import or link processed remote sensing image data to ensure the accuracy and integrity of the remote sensing image data; Configure the display: Set the chart type, style, and dynamic characteristics, and configure real-time updates and interactivity; Enables dynamic functionality: Configures real-time updates and interactive operations for remote sensing image data, and achieves real-time updates, interactivity, and dynamic display through time-series data; Operation and monitoring: Start the display module to monitor the updates of remote sensing image data and user interaction in real time; Adjustments and optimizations: Adjustments will be made based on actual usage to optimize performance and user experience.

Images