Rural highway disease monitoring system based on SAR satellite remote sensing technology

Abstract

The invention discloses a rural highway disease monitoring system based on an SAR satellite remote sensing technology. The rural highway disease monitoring system comprises an SAR satellite data acquisition unit, a data receiving unit, a data processing unit, a disease identification unit, a disease evaluation and monitoring unit, an information management unit and a display unit. The SAR satellite data acquisition unit is used for acquiring an SAR image; the data receiving unit is used for receiving SAR image data; the data processing unit is used for processing the received image data; the disease identification unit is used for identifying and monitoring road disease characteristics; the disease assessment and monitoring unit is used for assessing road health conditions and monitoring disease changes; and the information management unit is used for data storage. The system is provided with the information management unit which can store historical data of road disease feature data, so that the disease assessment and monitoring unit can judge a monitoring result in combination with the historical data and real-time data during disease assessment, and road disease analysis is more accurate.

Description

Technical Field

[0001] The invention relates to the technical field of highway disease monitoring, and in particular to a rural highway disease monitoring system based on SAR satellite remote sensing technology. Background Art

[0002] SAR satellite remote sensing technology is a synthetic aperture radar remote sensing technology that acquires surface information by emitting microwave signals and receiving reflected signals. SAR satellite remote sensing technology uses high-resolution SAR images for environmental monitoring, geological surveys, agricultural monitoring, urban development and disaster response.

[0003] The existing monitoring system for rural road disease monitoring uses SAR satellite remote sensing technology. When conducting road disease monitoring, it first regularly obtains road surface photos through the data acquisition unit, and then conducts road disease assessment after data processing, division, machine learning and screening. After that, the road disease is monitored directly based on the assessment data. Although such a system for monitoring road disease can accurately analyze road diseases during the detection period, some roads may have the same problems after repair, and the subsequent effects caused by the same solution method will also be different. Therefore, the existing monitoring system cannot more accurately judge the situation and cause of road diseases, which is not conducive to subsequent road maintenance and treatment. Summary of the invention

[0004] The purpose of the present invention is to provide a rural road disease monitoring system based on SAR satellite remote sensing technology to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solutions: a rural road disease monitoring system based on SAR satellite remote sensing technology, comprising a SAR satellite data acquisition unit, a data receiving unit, a data processing unit, a disease identification unit, a disease assessment and monitoring unit, an information management unit and a display unit;

[0006] The SAR satellite data acquisition unit is used to regularly acquire SAR images of rural road areas, and the SAR images are acquired by using a drone equipped with a SAR radar;

[0007] The data receiving unit is used for receiving SAR image data, and the data reception is performed through a ground receiving station;

[0008] The data processing unit is used for processing the received image data, wherein the data processing first performs image preprocessing and then performs feature extraction;

[0009] The disease recognition unit is used for identifying and monitoring road disease features. The disease recognition classifies the extracted features through a machine learning algorithm and identifies the road disease type.

[0010] The disease assessment and monitoring unit is used to assess the road health status and monitor disease changes. The disease assessment is performed by establishing a disease assessment model and combining historical data and real-time data to determine the monitoring results;

[0011] The information management unit is used for data storage and provides historical data of disease assessment;

[0012] The display unit establishes an interactive interface through a visualization tool for viewing and analyzing monitoring results.

[0013] Preferably, the SAR satellite data acquisition unit includes a data acquisition module, a signal processing module, an image generation module and a data transmission module;

[0014] The data acquisition module is used to receive the original radar signal from the SAR radar and convert it into a digital signal;

[0015] The signal processing module is used to perform gain control and time synchronization processing on the converted digital signal;

[0016] The image generation module uses synthetic aperture radar technology to convert the processed signal into a visual image;

[0017] The data transmission module is used to transmit the acquired data to a ground receiving station.

[0018] Preferably, the ground receiving station is equipped with a gain antenna and a receiving device to transmit the received data to a data processing unit via a high-speed network.

[0019] Preferably, the image preprocessing of the data processing unit is performed by a denoising module, a geometric correction module, an image registration module and a radiation correction module;

[0020] The denoising module uses filters and transform domain denoising to reduce the impact of noise on the image, making the image clearer;

[0021] The geometric correction module is used to ensure that the spatial position of the object in the image is consistent with the actual geographical position;

[0022] The image registration module is used to align images taken at different times, with different sensors or from different viewing angles;

[0023] The radiation correction module is used to correct the radiation value of the image and adjust the radiation intensity of the image to a standardized scale.

[0024] Preferably, the feature extraction of the data processing unit extracts feature information of the highway from the SAR image through image processing and pattern recognition technology, and the feature information of the highway includes boundaries, shapes and textures.

[0025] Preferably, the types of road damage identified by the machine learning algorithm include cracks, subsidence, deformation and water accumulation.

[0026] Preferably, the data division of the disease assessment model includes a training set, a validation set and a test set, and the data division of the training set, the validation set and the test set is performed by an image annotation tool.

[0027] Preferably, the road disease characteristic monitoring is used to analyze the development trend of the disease and provide a basis for maintenance decisions.

[0028] Preferably, the information management unit includes a data storage module and a data calling module, the data storage module is used for storing data, and the data calling module is used for retrieving and viewing historical data stored in the data storage module.

[0029] Preferably, the content viewed by the display unit includes map display and statistical analysis charts.

[0030] Technical effects and advantages of the present invention:

[0031] The system is provided with an information management unit, which is capable of storing data, and thus can store historical data of highway disease characteristic data. In this way, when conducting disease assessment, the disease assessment and monitoring unit can combine historical data and real-time data to judge the monitoring results. By combining historical data for monitoring and judgment, the system can better combine historical data for judgment when conducting highway disease assessment, thereby making highway disease analysis more accurate, and making subsequent operation and repair processing more accurate and stable. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 The figure is a block diagram of the system of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] The present invention provides Figure 1A rural road disease monitoring system based on SAR satellite remote sensing technology is shown, comprising a SAR satellite data acquisition unit, a data receiving unit, a data processing unit, a disease identification unit, a disease assessment and monitoring unit, an information management unit and a display unit;

[0035] The SAR satellite data acquisition unit is used to regularly acquire SAR images of rural road areas. The SAR images are acquired by using a drone equipped with a SAR radar.

[0036] It should be noted that SAR radar obtains SAR images of rural road areas regularly to ensure the timeliness of monitoring. SAR radar obtains surface information by emitting microwave signals and receiving reflected signals. It has the following characteristics: All-weather capability. SAR can work in any weather conditions, including rainy days and nights, because it uses microwave signals, which makes it very effective in monitoring and disaster assessment. High-resolution imaging. SAR can provide high-resolution images that can clearly identify surface features such as buildings, roads and vegetation. Surface change monitoring. SAR technology can monitor surface changes by comparing images taken at different times, such as urban expansion, land use changes, and surface deformation caused by natural disasters such as earthquakes. Interferometry. Through interferometric synthetic aperture radar (InSAR) technology, high-precision height information of the surface can be obtained, which is widely used in geological monitoring, urban subsidence monitoring and other fields. Multi-polarization and multi-band. SAR systems can image in different polarization modes (such as horizontal-horizontal, horizontal-vertical, etc.) and frequency bands, thereby providing rich ground object information and helping to improve classification accuracy and recognition capabilities.

[0037] Specifically, the SAR satellite data acquisition unit includes a data acquisition module, a signal processing module, an image generation module and a data transmission module;

[0038] The data acquisition module is used to receive the original radar signal from the SAR radar and convert it into a digital signal;

[0039] It should be noted that the data collection module first needs to clarify the area of ​​data collection. It determines the specific area that needs to be monitored based on the distribution of rural roads and the needs of disease monitoring. The time frequency is determined based on the usage of the road and the characteristics of the disease occurrence, and determines the time frequency of image acquisition, including monthly, quarterly or annually.

[0040] The signal processing module is used to perform gain control and time synchronization processing on the converted digital signal;

[0041] It should be noted that the signal processing module processes the received raw radar signal, including denoising, gain control and time synchronization, to improve image quality.

[0042] The image generation module uses synthetic aperture radar technology to convert the processed signal into a visual image. This process usually involves pulse compression and imaging reconstruction.

[0043] The data transmission module is used to transmit the acquired data to the ground receiving station through a satellite communication link or other data transmission methods.

[0044] The data receiving unit is used to receive SAR image data, and the data reception is carried out through the ground receiving station;

[0045] Specifically, the ground receiving station is equipped with a gain antenna and a receiving device, and transmits the received data to a data processing unit via a high-speed network.

[0046] The data processing unit is used for processing the received image data. The data processing first performs image preprocessing and then performs feature extraction.

[0047] Specifically, the image preprocessing of the data processing unit is performed by a denoising module, a geometric correction module, an image registration module, and a radiation correction module;

[0048] The denoising module uses filters and transform domains to reduce the impact of noise on the image, making the image clearer;

[0049] It should be noted that the denoising module is to remove noise from the image to improve the image quality. SAR images are usually interfered by various noises, such as speckle noise. Different algorithms (such as filters, transform domain denoising, etc.) are used to reduce the impact of noise on the image. Different types of filters (such as mean filter, median filter, Gaussian filter, etc.) are used to smooth the image, while retaining edge information as much as possible, making the image clearer and the target detection and analysis more accurate. Among them, transform domain denoising uses Fourier transform to convert the image to the frequency domain and process the noise in the frequency domain. The denoising effect is achieved by suppressing low-frequency or high-frequency components.

[0050] The geometric correction module is used to ensure that the spatial position of the objects in the image is consistent with the actual geographical location;

[0051] It should be noted that the geometric correction module corrects the geometric distortion in the image due to factors such as shooting angle and earth curvature; it ensures that the spatial position of the objects in the image is consistent with the actual geographical location, so that the image can be correctly analyzed, measured and compared.

[0052] The geometric correction process usually includes the following steps:

[0053] Image registration: The image to be calibrated is registered with the reference image (usually a high-precision orthophoto or topographic map) to ensure that the two are aligned in space. Registration can use feature point, control point or line feature methods.

[0054] Geometric model establishment: Establish a geometric correction model based on shooting parameters (such as satellite orbit, sensor view, etc.).

[0055] Image transformation: Using the established geometric model, the pixel coordinates in the original image are remapped to the coordinate system. This usually involves an interpolation algorithm to ensure that the pixel values ​​of the new image can transition smoothly.

[0056] Image cropping and resampling: During the correction process, blank areas of the image may occur, so the image needs to be cropped to ensure that the range of the final image is consistent with the requirements.

[0057] The image registration module is used to align images taken at different times, with different sensors or from different viewing angles;

[0058] It should be noted that the image registration module aligns images taken at different times, with different sensors or from different perspectives, thereby matching the features in the images and accurately superimposing the images together, supporting comprehensive analysis of multi-phase and multi-source images, such as change detection and target recognition.

[0059] The radiation correction module is used to correct the radiation value of the image and adjust the radiation intensity of the image to a standardized scale.

[0060] It should be noted that the radiation correction module corrects the radiation value of the image to make it reflect the actual characteristics of the ground objects and eliminate system errors and environmental influences; at the same time, it adjusts the radiation intensity of the image to a standardized scale to facilitate data comparison and analysis at different times and under different conditions.

[0061] Specifically, the feature extraction of the data processing unit extracts feature information of the highway from the SAR image through image processing and pattern recognition technology, and the feature information of the highway includes boundary, shape and texture.

[0062] The disease recognition unit is used to identify and monitor road disease characteristics. Disease recognition classifies the extracted features through machine learning algorithms and identifies the road disease type.

[0063] It should be noted that disease identification applies machine learning algorithms to train the extracted features and build models to achieve automatic classification. Commonly used algorithms include support vector machines (SVM), random forests (RF) and convolutional neural networks (CNN), among which;

[0064] Support Vector Machine (SVM) is a supervised learning algorithm used for classification and regression analysis. Its goal is to find an optimal hyperplane that separates data points of different categories and maximizes the boundary distance (i.e., the distance from the support vector to the hyperplane); it performs well in high-dimensional space. For complex boundaries, kernel functions (such as linear kernels, radial basis kernels, etc.) can be used to map data to higher dimensions. It is suitable for small-scale data sets, especially when high accuracy is required in classification problems, such as text classification and image classification;

[0065] Random Forest (RF) is an ensemble learning method that improves the accuracy of classification and regression by building multiple decision trees. Each tree is trained using a random subset of the data and a random subset of the features, and the final result is determined by voting or averaging. It is suitable for large-scale data sets, especially when the feature dimension is high, such as medical diagnosis and financial prediction.

[0066] Convolutional Neural Network (CNN) is a deep learning algorithm that is particularly suitable for processing image data. It extracts image features through convolutional layers and uses pooling layers to reduce the dimensionality of the data. CNN automatically learns hierarchical features in data through a multi-layer structure (including convolutional layers, pooling layers, and fully connected layers). It is mainly used in image and video processing, such as object recognition, facial recognition, and image segmentation.

[0067] Specifically, the types of road damage identified by the machine learning algorithm include cracks, subsidence, deformation, and water accumulation.

[0068] The disease assessment and monitoring unit is used to assess the health status of roads and monitor changes in diseases. Disease assessment is done by establishing a disease assessment model and combining historical data with real-time data to determine the monitoring results.

[0069] Specifically, the data division of the disease assessment model includes a training set, a validation set, and a test set, and the data division of the training set, the validation set, and the test set is performed through an image annotation tool.

[0070] It should be noted that the composition of the training set, validation set, and test set is obtained through data partitioning to facilitate model training and evaluation. During the training process, the model is trained using the training set, and the model parameters are optimized through back propagation. At the same time, the learning rate, batch size, and number of network layers hyperparameters are adjusted to improve model performance. The validation set and test set are used to demonstrate the accuracy and recall of the model test.

[0071] Specifically, road disease characteristic monitoring is used to analyze the development trend of diseases and provide a basis for maintenance decisions.

[0072] The information management unit is used for data storage and provides historical data of disease assessment;

[0073] Specifically, the information management unit includes a data storage module and a data calling module. The data storage module is used for storing data, and the data calling module is used for retrieving and viewing historical data stored in the data storage module.

[0074] It should be noted that the data storage module saves the processed image data, analysis results and disease records, ensuring long-term storage of data and convenient access by the data call module.

[0075] The display unit establishes an interactive interface through visualization tools for viewing and analyzing monitoring results.

[0076] Specifically, the content viewed by the display unit includes map display and statistical analysis charts.

[0077] It should be noted that the map display part can intuitively display the spatial distribution of ground defects, which usually includes the following contents: base map selection, providing different types of base map options, such as satellite images, topographic maps or street maps, and users can choose the appropriate base map according to their needs. Defect annotation, marking the location of ground defects on the map, using different symbols or colors to represent different types of defects (such as cracks, potholes, settlement, etc.), so that users can see at a glance. Heat map, showing the density or severity of defects through heat map, helping to identify high-risk areas or areas of focus. Information pop-up window, users can click on a specific defect mark on the map, and a detailed information window will pop up to display the properties of the defect (such as size, severity and shooting time). Time dynamic display, if there is time series data, it can show the dynamic process of defects changing over time, helping users understand the evolution trend of defects. Layer control, allowing users to select different layers for overlay, such as traffic flow, weather conditions, etc., for multi-dimensional analysis.

[0078] The statistical analysis chart section is used to conduct quantitative analysis of ground defects, and usually includes the following content: Defect quantity statistics, using bar charts or pie charts to show the quantity distribution of different types of defects, so that users can understand the relative proportion and total number of each type of defects. Defect severity analysis, you can use box plots or bar charts to show the severity distribution of defects, to help identify the types of defects that need the most attention and treatment. Trend analysis, line charts can be used to show the trend of the number or severity of defects over time, to help users understand the increase or decrease of defects. Regional analysis, grouping statistics according to geographical regions, showing the number and type distribution of defects in each region, to facilitate regional management and decision-making. Statistical summary, provides basic statistical information about the defect data set, such as mean, standard deviation, minimum value, maximum value, etc., to help users quickly understand the overall situation of defects.

[0079] Finally, it should be noted that the above 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 aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A rural road disease monitoring system based on SAR satellite remote sensing technology, characterized in that: It includes SAR satellite data acquisition unit, data receiving unit, data processing unit, disease identification unit, disease assessment and monitoring unit, information management unit and display unit; The SAR satellite data acquisition unit is used to regularly acquire SAR images of rural road areas, and the SAR images are acquired by using a drone equipped with a SAR radar; The data receiving unit is used for receiving SAR image data, and the data reception is performed through a ground receiving station; The data processing unit is used for processing the received image data, wherein the data processing first performs image preprocessing and then performs feature extraction; The disease recognition unit is used for identifying and monitoring road disease features. The disease recognition classifies the extracted features through a machine learning algorithm and identifies the road disease type. The disease assessment and monitoring unit is used to assess the road health status and monitor disease changes. The disease assessment is performed by establishing a disease assessment model and combining historical data and real-time data to determine the monitoring results; The information management unit is used for data storage and provides historical data of disease assessment; The display unit establishes an interactive interface through a visualization tool for viewing and analyzing monitoring results.

2. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The SAR satellite data acquisition unit includes a data acquisition module, a signal processing module, an image generation module and a data transmission module; The data acquisition module is used to receive the original radar signal from the SAR radar and convert it into a digital signal; The signal processing module is used to perform gain control and time synchronization processing on the converted digital signal; The image generation module uses synthetic aperture radar technology to convert the processed signal into a visual image; The data transmission module is used to transmit the acquired data to a ground receiving station.

3. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The ground receiving station is equipped with a gain antenna and a receiving device, and transmits the received data to a data processing unit via a high-speed network.

4. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The image preprocessing of the data processing unit is performed by a denoising module, a geometric correction module, an image registration module and a radiation correction module; The denoising module uses filters and transform domain denoising to reduce the impact of noise on the image, making the image clearer; The geometric correction module is used to ensure that the spatial position of the object in the image is consistent with the actual geographical position; The image registration module is used to align images taken at different times, with different sensors or from different viewing angles; The radiation correction module is used to correct the radiation value of the image and adjust the radiation intensity of the image to a standardized scale.

5. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The feature extraction of the data processing unit extracts feature information of the highway from the SAR image through image processing and pattern recognition technology, and the feature information of the highway includes boundary, shape and texture.

6. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The types of road damage identified by the machine learning algorithm include cracks, subsidence, deformation, and water accumulation.

7. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The data division of the disease assessment model includes a training set, a validation set and a test set, and the data division of the training set, the validation set and the test set is performed by an image annotation tool, and the image annotation tool includes LabelMe and Labelbox.

8. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The road disease characteristic monitoring is used to analyze the development trend of the disease and provide a basis for maintenance decisions.

9. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The information management unit includes a data storage module and a data calling module. The data storage module is used for storing data, and the data calling module is used for retrieving and viewing historical data stored in the data storage module.

10. The rural road disease monitoring system based on SAR satellite remote sensing technology according to claim 1 is characterized in that: The content viewed by the display unit includes map display and statistical analysis charts.

Images