A highway survey intelligent design method and system based on satellite imagery

Abstract

The present invention discloses a method and system for intelligent highway survey design based on satellite imagery, which relates to the field of remote sensing technology. By geometrically calibrating and atmospherically correcting satellite image data Ir, errors caused by atmospheric, lighting, and satellite orbital factors are corrected to form a corrected impact data set Ip, effectively eliminating the impact of environmental factors on data accuracy. The anomaly rate S is corrected in combination with different geological information to generate a corrected anomaly rate Sadj, which is then combined with the structural sensitivity function fstruct to calculate the risk assessment value R for different regions. On this basis, the overall highway safety score Rtotal is obtained through statistical analysis. This provides a practical reference for the later construction and maintenance of highways, and ensures early identification and early warning of safety hazards during highway construction through abnormal trend analysis, dynamic monitoring, and geological correction methods.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing technology, and in particular to a method and system for intelligent design of highway survey based on satellite images. Background Art

[0002] Satellite imagery is widely used in fields such as land resources, environmental monitoring, and urban planning. During highway construction, geological surveys, route selection, and construction quality monitoring are key tasks for ensuring project safety and quality. With the continuous expansion of project scale and technological advancements, remote sensing technology based on satellite imagery has been gradually introduced into the entire highway survey and design process, playing an increasingly important role. Especially when faced with complex factors such as geological disasters, ecological impacts, and the construction environment, remote sensing imagery-based technologies can provide accurate data support and decision-making basis for survey and design. Specifically, in the later stages of highway construction, especially in terms of roadbed stability and bridge bearing capacity, dynamic monitoring technology has become an important research area.

[0003] Although remote sensing technology has been introduced into the field of modern highway construction for environmental monitoring and geological surveys, there are still many limitations in the dynamic monitoring after highway construction, especially in the long-term tracking of surface subsidence. Existing monitoring methods mostly rely on ground field surveys and measuring instruments. Although they can accurately obtain settlement data, there are certain timeliness issues. Generally, ground monitoring requires more frequent on-site surveys, and it is difficult to monitor a large area. It is impossible to grasp the trend of settlement changes in real time, especially for complex terrain and difficult-to-reach areas. Monitoring is more difficult. In addition, traditional settlement monitoring methods are not sensitive enough to detect early settlement, and are prone to miss some minor deformations, causing safety hazards in the later stages of construction.

[0004] The inefficiencies and inaccuracies of this traditional monitoring method have led to significant pressure on highway construction projects during their operational phase, particularly for bridges, tunnels, and other facilities in high-risk areas. The gradual accumulation of subsidence can lead to unnecessary safety issues and, in extreme cases, even structural damage. Therefore, relying on ground-based monitoring methods cannot fully capture geological changes or respond promptly to subsidence changes, limiting the ability to accurately predict and adjust structural safety during highway construction. Summary of the Invention

[0005] In view of the deficiencies of the existing technology, the present invention provides a method and system for intelligent design of highway survey based on satellite images, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for intelligent design of highway survey based on satellite images, comprising the following steps:

[0007] S1, by performing geometric calibration and atmospheric correction on the collected satellite image data Ir, the errors caused by atmospheric, illumination and satellite orbit factors are corrected to form the corrected impact dataset Ip;

[0008] S2. Extracting surface subsidence features from the corrected impact dataset Ip, including cracks and elevation changes, and integrating the extracted features to form a surface anomaly feature set F;

[0009] S3. Perform an anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation is based on the feature set F of surface settlement at different time points to calculate the change amount and rate of the surface anomaly and obtain the anomaly rate S.

[0010] S4. Correct the abnormal rate S according to different geological information, obtain the influence of different geological factors on the abnormal rate S, and mark it as the corrected abnormal rate Sadj;

[0011] S5. Based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, the settlement impact assessment is performed, the risk assessment value R of different areas is calculated, and the risk warning is triggered according to the risk assessment value R. When the risk warning is triggered, the overall highway safety score Rtotal is obtained through statistical analysis of the risk assessment values R of different areas, and compared with the preset overall abnormal assessment threshold Tsafe to obtain the overall abnormal assessment result of the highway, and trigger the execution measures according to the overall abnormal assessment result of the highway.

[0012] Preferably, said S1 includes S11 and S12;

[0013] S11. Correcting spatial errors in the satellite image data Ir caused by satellite orbit error, image tilt, and ground undulation by geometrically calibrating the collected satellite image data Ir so that the geographic coordinates in the satellite image data Ir are consistent with the actual ground coordinates. Specifically, the geometric calibration is performed by matching ground control points with corresponding points in the satellite image data Ir to obtain calibrated target geographic coordinates (xt, yt). The target geographic coordinates (xt, yt) are then integrated to obtain a geometrically calibrated output image dataset Ig.

[0014] The target geographic coordinates (xt, yt) are obtained by the following calibration formula:

[0015] (xt, yt)=Mgeo*(xr, yr)+b;

[0016] Where (xr, yr) represents the coordinate position in the satellite image data Ir, specifically the horizontal and vertical axis values of the coordinate position, Mgeo represents the geometric transformation matrix, and b represents the translation variable.

[0017] Preferably, S12, performing atmospheric correction on the obtained output image dataset Ig to correct the optical signal received by the satellite sensor affected by atmospheric, lighting, dust, and water vapor factors, and correcting each target geographic coordinate (xt, yt) in the output image dataset Ig to obtain a corrected impact dataset Ip;

[0018] The calculation formula for correcting the target geographic coordinates (xt, yt) in the output image dataset Ig is as follows:

[0019]

[0020] Where Padj(xt, yt) represents the corrected target geographic coordinates, Pgeo represents the reflectivity after geometric correction, and Tatm represents the atmospheric effect correction coefficient, which indicates the degree of influence of the atmosphere on light propagation.

[0021] 5. Preferably, S2 includes S21 and S22;

[0022] S21. Extracting surface subsidence features from the corrected impact dataset Ip, including cracks and elevation changes, and analyzing the differences in cracks and elevation changes by comparing the impact datasets Ip at different time periods;

[0023] Among them, the elevation change extraction obtains the elevation change value △H of the area by affecting the lifting and settlement information of the corrected target geographic coordinates Padj (xt, yt) in the dataset Ip in different time periods, and compares it with the preset settlement uplift threshold Thigh to obtain the extraction result of the corrected target geographic coordinates Padj (xt, yt). The corrected target geographic coordinates Padj (xt, yt) are marked according to the extraction result to form the settlement geographic coordinate set Cjj and the uplift geographic coordinate set Lqj;

[0024] The elevation change value ΔH is obtained by the following calculation formula:

[0025] ΔH=Padj(xt,yt,Hc)-Padj(xt,yt,Hr);

[0026] Where Padj(xt, yt, Hc) and Padj(xt, yt, Hr) represent the elevation values of the corrected target geographic coordinates Padj(xt, yt) before and after the fixed period, respectively;

[0027] When the elevation change value △H>1.5 times the settlement uplift threshold Thigh, the extraction result of the corrected target geographic coordinate Padj (xt, yt) is obtained as the settlement result, indicating that the corrected target geographic coordinate Padj (xt, yt) is a settlement geographic coordinate point and is added to the settlement geographic coordinate set Cjj;

[0028] When the elevation change value △H is less than 0.5 times of the subsidence uplift threshold Thigh, the extraction result of the corrected target geographic coordinate Padj (xt, yt) is obtained as an uplift result, indicating that the corrected target geographic coordinate Padj (xt, yt) is an uplift geographic coordinate point and is added to the uplift geographic coordinate set Lqj;

[0029] Among them, crack extraction extracts crack information through the height difference map, obtains the gradient fluctuation value △I of the image gradient by comparing the impact data set Ip of different time periods, and compares it with the preset gradient fluctuation threshold Tcrack to obtain the extraction result of the corrected target geographic coordinate Padj(xt, yt), and marks the corrected target geographic coordinate Padj(xt, yt) according to the extraction result to form the crack geographic coordinate set Lfj;

[0030] The gradient fluctuation value ΔI is obtained by the following calculation formula:

[0031]

[0032] Where, and They represent the local change rates of the corrected target geographic coordinates Padj(xt, yt) in the xt horizontal axis direction and the yt vertical axis direction, respectively. Indicates the gradient value calculated at the corrected target geographic coordinate Padj(xt, yt) by combining the local rate of change in the xt horizontal axis direction and the yt vertical axis direction;

[0033] When the gradient fluctuation value △I> the gradient fluctuation threshold Tcrack, the corrected target geographic coordinate Padj (xt, yt) is extracted as the crack result, indicating that the corrected target geographic coordinate Padj (xt, yt) is the crack geographic coordinate point and is added to the crack geographic coordinate set Lfj.

[0034] Preferably, S22, according to the obtained settlement geographic coordinate set Cjj, uplift geographic coordinate set Lqj and fracture geographic coordinate set Lfj, the same corrected target geographic coordinate Padj (xt, yt) in the corrected impact data set Ip is replaced, and the surface anomaly feature set F is obtained by integrating the settlement geographic coordinate set Cjj, uplift geographic coordinate set Lqj, fracture geographic coordinate set Lfj and impact data set Ip.

[0035] Preferably, said S3 includes S31;

[0036] S31. Perform an anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation calculates the change amount and rate of the surface anomaly based on the feature set F of surface settlement at different time points to obtain an anomaly rate S.

[0037] The abnormal change rate S is obtained by the following calculation formula:

[0038]

[0039] Where △Cj represents the amount of settlement change, △Lq represents the amount of uplift change, △Lf represents the amount of crack change, △t represents the time interval, β represents the adjustment coefficient, SCj represents the rate of settlement change, SLq represents the rate of uplift change, and SLf represents the rate of crack change.

[0040] Preferably, the settlement change ΔCj is obtained by the calculation formula ΔCj=F(Cjj, t+1)-F(Cjj, t), wherein t represents time, and F(Cjj, t+1) represents the settlement geographic coordinate set in the surface anomaly feature set F at time t+1;

[0041] The uplift variation ΔLq is obtained by the calculation formula ΔLq=F(Lqj, t+1)-F(Lqj, t), where F(Lqj, t+1) represents the uplift geographic coordinate set in the surface anomaly feature set F at time t+1;

[0042] The crack change amount ΔLf is obtained by the calculation formula ΔLf=F(Lfj, t+1)-F(Lfj, t), where F(Lfj, t+1) represents the crack geographic coordinate set in the surface anomaly feature set F at time t+1;

[0043] The sedimentation change rate SCj is expressed by Obtain calculation formula;

[0044] The elevation change rate SLq is expressed by Obtain calculation formula;

[0045] The crack change rate SLf is expressed by Obtain the calculation formula.

[0046] Preferably, the S4 includes S41;

[0047] S41, correcting the abnormal rate S according to different geological information, obtaining the influence of different geological factors on the abnormal rate S, and marking it as the corrected abnormal rate Sadj;

[0048] The corrected abnormal rate Sadj is obtained by the following calculation formula:

[0049]

[0050] Where n represents the total number of geological factors, λ(i) represents the correction coefficient of the i-th geological factor, and G(i) represents the influence degree of the i-th geological factor.

[0051] Preferably, the S5 includes S51;

[0052] S51, based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, perform settlement impact assessment, calculate risk assessment values R of different areas, and determine whether to trigger risk warning according to the risk assessment values R;

[0053] The risk assessment value R is obtained by the following calculation formula:

[0054]

[0055] Where R(t) represents the risk assessment value at time t, γ represents the scaling factor, exp represents the exponential function, Sadj(t) represents the corrected anomaly rate at time t, f(m) represents the sensitivity of highway facilities in region m to ground changes, L represents the total length of highway in region m, and dm represents the integral variable, specifically representing a small change in region m.

[0056] When the risk assessment value R>1, a risk warning is triggered, the overall highway survey mechanism is executed, the current area m is marked as a maintenance area, and a notification is sent to the relevant road maintenance department for processing;

[0057] S52. When executing the overall highway survey mechanism, the overall highway safety score Rtotal is obtained by statistically analyzing the risk assessment values R of different areas, and is compared with the preset overall abnormality assessment threshold Tsafe to obtain the overall highway abnormality assessment result, and the execution measures are triggered according to the overall highway abnormality assessment result;

[0058] The overall highway safety score Rtotal The calculation formula is obtained, where Q represents the total number of assessment areas, and R(t, m) represents the risk assessment value of area m at time t;

[0059] The overall abnormality assessment results of the highway are obtained by the following comparison method:

[0060] When the highway overall safety score Rtotal is less than the overall abnormality assessment threshold Tsafe, the highway overall abnormality assessment result is obtained as a normal result;

[0061] When the highway overall safety score Rtotal ≥ the overall abnormality assessment threshold Tsafe, the highway overall abnormality assessment result is obtained as an abnormal result, triggering execution measures, including prompting the current area m to be abnormal, and replanning and diverting the current highway.

[0062] A highway survey and intelligent design system based on satellite images, including a satellite data calibration module, a data feature extraction module, a data analysis module, a correction module and an evaluation and decision module;

[0063] The satellite data calibration module performs geometric calibration and atmospheric correction on the collected satellite image data Ir to correct errors caused by atmospheric, illumination and satellite orbit factors, thereby forming a corrected impact dataset Ip.

[0064] The data feature extraction module extracts surface subsidence features, including cracks and elevation changes, from the corrected impact dataset Ip, and integrates the extracted features to form a surface anomaly feature set F;

[0065] The data analysis module performs anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation calculates the change amount and rate of surface anomalies based on the feature set F of surface settlement at different time points to obtain the anomaly rate S.

[0066] The correction module corrects the abnormal rate S according to different geological information, obtains the influence of different geological factors on the abnormal rate S, and marks it as the corrected abnormal rate Sadj;

[0067] The evaluation and decision module evaluates the impact of settlement based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, calculates the risk assessment value R of different areas, and determines whether to trigger a risk warning based on the risk assessment value R. When a risk warning is triggered, the overall safety score Rtotal of the highway is obtained through statistical analysis of the risk assessment values R of different areas, and is compared with the preset overall abnormality assessment threshold Tsafe to obtain the overall abnormality assessment result of the highway, and trigger execution measures based on the overall abnormality assessment result of the highway.

[0068] The present invention provides a method and system for intelligent highway survey and design based on satellite imagery, which has the following beneficial effects:

[0069] (1) Through geometric calibration and atmospheric correction of satellite image data Ir, the errors caused by atmospheric, illumination, and satellite orbit factors were corrected to form the corrected impact data set Ip, effectively eliminating the impact of environmental factors on data accuracy. The anomaly rate S was corrected by combining different geological information to generate the corrected anomaly rate Sadj. This was combined with the structural sensitivity function fstruct to calculate the risk assessment value R for different regions. On this basis, the overall highway safety score Rtotal was obtained through statistical analysis. This provides a practical reference for the later construction and maintenance of the highway, helping relevant departments to make accurate decisions. It also ensures the early identification and early warning of safety hazards during highway construction through abnormal trend analysis, dynamic monitoring, and geological correction. Through precise calculation and analysis, it is possible to predict subsidence risks in the early stages of highway construction, provide data support for subsequent design, avoid the lag in the discovery of hidden geological problems in traditional survey methods, and significantly improve design efficiency and safety.

[0070] (2) By calculating the change in settlement △Cj, uplift △Lq, and crack △Lf, the change rates of various types of surface changes are obtained. By adjusting and integrating these rates, the method can comprehensively evaluate the changing trends of the highway geological environment and promptly discover potential safety hazards. It not only improves the accuracy and real-time performance of highway settlement monitoring, but also can make scientific assessments based on different types of surface changes. Compared with traditional survey methods, the method can capture the evolution of complex geological phenomena such as settlement, uplift, and cracks in real time, providing a more reliable, data-driven decision-making basis for highway design and safety monitoring, further improving the safety and emergency response capabilities of highway construction.

[0071] (3) The risk assessment value R(t) of different areas is calculated, and the set threshold is used to determine whether a risk warning is triggered. The sensitivity of the highway facilities in the area is also combined to make the risk assessment more comprehensive and precise. The overall safety score Rtotal of the highway is obtained and compared with the preset safety threshold Tsafe to ensure the accuracy of the overall abnormality assessment results of the highway. If the overall safety score exceeds the threshold, the system will automatically trigger further measures, including marking the abnormal area and replanning the highway route. This multi-level and multi-dimensional assessment system not only improves the safety of the highway, but also enhances the flexibility and response speed of emergency management, provides an effective decision-making support tool for road maintenance departments, and greatly improves the accuracy and timeliness of highway maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a schematic diagram of the steps of a method for intelligent highway survey and design based on satellite images according to the present invention;

[0073] Figure 2 The figure is a schematic diagram of a highway survey and intelligent design system based on satellite images according to the present invention. DETAILED DESCRIPTION

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0075] Example 1

[0076] The present invention provides a method for intelligent highway survey and design based on satellite images. Figure 1 , including the following steps:

[0077] S1, by performing geometric calibration and atmospheric correction on the collected satellite image data Ir, the errors caused by atmospheric, illumination and satellite orbit factors are corrected to form the corrected impact dataset Ip;

[0078] S2. Extracting surface subsidence features from the corrected impact dataset Ip, including cracks and elevation changes, and integrating the extracted features to form a surface anomaly feature set F;

[0079] S3. Perform an anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation is based on the feature set F of surface settlement at different time points to calculate the change amount and rate of the surface anomaly and obtain the anomaly rate S.

[0080] S4. Correct the abnormal rate S according to different geological information, obtain the influence of different geological factors on the abnormal rate S, and mark it as the corrected abnormal rate Sadj;

[0081] S5. Based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, the settlement impact assessment is performed, the risk assessment value R of different areas is calculated, and the risk warning is triggered according to the risk assessment value R. When the risk warning is triggered, the overall highway safety score Rtotal is obtained through statistical analysis of the risk assessment values R of different areas, and compared with the preset overall abnormal assessment threshold Tsafe to obtain the overall abnormal assessment result of the highway, and trigger the execution measures according to the overall abnormal assessment result of the highway.

[0082] In this embodiment, intelligent improvement in the highway survey and design process is achieved through precise satellite image data processing and multi-level analysis. First, through geometric calibration and atmospheric correction of the satellite image data Ir, the errors caused by atmospheric, lighting and satellite orbit factors are corrected to form a corrected impact data set Ip, effectively eliminating the impact of environmental factors on data accuracy. Next, surface settlement features are extracted, including cracks and elevation changes. By integrating these features, a surface anomaly feature set F is constructed, providing a reliable data basis for further analysis. Through abnormal trend analysis and change rate calculation, based on time series analysis and surface settlement data at different time points, the change amount and rate of surface anomalies are calculated, and the anomaly rate S is obtained. The calculation of this anomaly rate combines the data changes at different time nodes, which can timely reflect the abnormal dynamics in the highway construction process and provide a scientific basis for predicting potential risks. To further improve prediction accuracy, the anomaly rate S was modified based on various geological information to generate a modified anomaly rate Sadj. This was then combined with the structural sensitivity function fstruct to calculate the risk assessment value R for each region. Based on this, statistical analysis was performed to derive the overall highway safety score Rtotal. Comparing this value with the preset overall anomaly assessment threshold Tsafe effectively identifies potential highway risks and triggers a timely warning. This process provides a practical reference for subsequent highway construction and maintenance, helping relevant departments make accurate decisions. Furthermore, through anomaly trend analysis, dynamic monitoring, and geological corrections, it ensures early identification and early warning of safety hazards during highway construction. Through precise calculation and analysis, settlement risks can be predicted early in the highway construction process, providing data support for subsequent design. This avoids the delay in identifying hidden geological issues associated with traditional survey methods, significantly improving design efficiency and safety.

[0083] Example 2

[0084] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the S1 includes S11 and S12;

[0085] S11. Correcting spatial errors in the satellite image data Ir caused by satellite orbit error, image tilt, and ground undulation by geometrically calibrating the collected satellite image data Ir so that the geographic coordinates in the satellite image data Ir are consistent with the actual ground coordinates. Specifically, the geometric calibration is performed by matching ground control points with corresponding points in the satellite image data Ir to obtain calibrated target geographic coordinates (xt, yt). The target geographic coordinates (xt, yt) are then integrated to obtain a geometrically calibrated output image dataset Ig.

[0086] The target geographic coordinates (xt, yt) are obtained by the following calibration formula:

[0087] (xt, yt)=Mgeo*(xr, yr)+b;

[0088] Where (xr, yr) represents the coordinate position in the satellite image data Ir, specifically the horizontal and vertical axis values of the coordinate position; Mgeo represents the geometric transformation matrix, specifically the spatial transformation from the satellite image data Ir to the actual ground coordinates, including the use of the affine transformation matrix for spatial transformation; b represents the translation variable, specifically the displacement in the coordinate transformation.

[0089] S12. Perform atmospheric correction on the acquired output image dataset Ig to correct the optical signals received by the satellite sensor that are affected by atmospheric, lighting, dust, and water vapor factors. Correct the geographic coordinates (xt, yt) of each target in the output image dataset Ig to obtain a corrected impact dataset Ip.

[0090] The calculation formula for correcting the target geographic coordinates (xt, yt) in the output image dataset Ig is as follows:

[0091]

[0092] Where Padj(xt, yt) represents the corrected target geographic coordinates after correction, Pgeo represents the reflectivity after geometric correction, which is usually calculated by the spectral reflectivity collected by the sensor and obtained through geometric transformation. Tatm represents the atmospheric effect correction coefficient, which indicates the degree of influence of the atmosphere on light propagation. Specifically, different components in the atmosphere will absorb or scatter the light signal received by the satellite sensor, thereby affecting the measured value of the reflectivity. The atmospheric effect correction coefficient Tatm can be calculated through the atmospheric transmission model MODTRAN and the atmospheric transmission model 6S to compensate for the influence of the atmosphere on light propagation.

[0093] 6. S2 includes S21 and S22;

[0094] S21. Extracting surface subsidence features from the corrected impact dataset Ip, including cracks and elevation changes, and analyzing the differences in cracks and elevation changes by comparing the impact datasets Ip at different time periods;

[0095] Among them, the elevation change extraction obtains the elevation change value △H of the area by affecting the lifting and settlement information of the corrected target geographic coordinates Padj (xt, yt) in the dataset Ip in different time periods, and compares it with the preset settlement uplift threshold Thigh to obtain the extraction result of the corrected target geographic coordinates Padj (xt, yt). The corrected target geographic coordinates Padj (xt, yt) are marked according to the extraction result to form the settlement geographic coordinate set Cjj and the uplift geographic coordinate set Lqj;

[0096] The elevation change value ΔH is obtained by the following calculation formula:

[0097] ΔH=Padj(xt,yt,Hc)-Padj(xt,yt,Hr);

[0098] Where Padj(xt, yt, Hc) and Padj(xt, yt, Hr) represent the elevation values of the corrected target geographic coordinates Padj(xt, yt) before and after the fixed period, respectively;

[0099] When the elevation change value △H>1.5 times the settlement uplift threshold Thigh, the extraction result of the corrected target geographic coordinate Padj (xt, yt) is obtained as the settlement result, indicating that the corrected target geographic coordinate Padj (xt, yt) is a settlement geographic coordinate point and is added to the settlement geographic coordinate set Cjj;

[0100] When the elevation change value △H is less than 0.5 times of the subsidence uplift threshold Thigh, the extraction result of the corrected target geographic coordinate Padj (xt, yt) is obtained as an uplift result, indicating that the corrected target geographic coordinate Padj (xt, yt) is an uplift geographic coordinate point and is added to the uplift geographic coordinate set Lqj;

[0101] Among them, crack extraction extracts crack information through the height difference map. Specifically, after atmospheric correction, the morphology and deformation of the settlement area will be more prominent. By comparing the impact data sets Ip of different time periods, the gradient fluctuation value △I of the image gradient is obtained, and compared with the preset gradient fluctuation threshold Tcrack, the extraction result of the corrected target geographic coordinates Padj(xt, yt) is obtained. The corrected target geographic coordinates Padj(xt, yt) are marked according to the extraction results to form the crack geographic coordinate set Lfj;

[0102] The gradient fluctuation value ΔI is obtained by the following calculation formula:

[0103]

[0104] Where, and They represent the local change rates of the corrected target geographic coordinates Padj(xt, yt) in the xt horizontal axis direction and the yt vertical axis direction, respectively. Specifically, it represents the partial derivative of the corrected target geographic coordinate Padj (xt, yt) with respect to the horizontal axis of xt, which reflects the rate of change of the pixel value in the image in the horizontal direction. In most cases, the edge or significant structural change of the image will lead to The value of becomes larger, Specifically, it represents the partial derivative of the corrected target geographic coordinate Padj (xt, yt) with respect to the vertical axis, which reflects the rate of change of the pixel value in the image in the vertical direction. The edge and important structural changes of the image usually lead to The changes are large, It represents the gradient value of the corrected target geographic coordinate Padj(xt, yt) calculated by combining the local change rate in the xt horizontal axis direction and the yt vertical axis direction, reflecting the overall change degree of the point;

[0105] When the gradient fluctuation value △I> the gradient fluctuation threshold Tcrack, the corrected target geographic coordinate Padj (xt, yt) is extracted as the crack result, indicating that the corrected target geographic coordinate Padj (xt, yt) is the crack geographic coordinate point and is added to the crack geographic coordinate set Lfj.

[0106] In this embodiment, geometric calibration of the collected satellite image data Ir corrects for spatial errors caused by factors such as satellite orbit error, image tilt, and ground undulation, ensuring consistency between the (xt, yt) coordinates in the image data and the actual ground coordinates, providing accurate geographic data for subsequent analysis. Furthermore, the method uses atmospheric correction to correct for the effects of atmospheric, lighting, and environmental factors on the satellite sensor's optical signal, generating a corrected impact dataset Ip. This further improves the reliability and accuracy of the data. By extracting surface subsidence features from the corrected impact dataset Ip, the method accurately identifies anomalies such as subsidence, uplift, and cracks, ensuring timely detection of different types of geological changes. In elevation change analysis, by comparing the elevation changes of coordinates at different time points, the method accurately identifies subsidence and uplift areas, generating a subsidence geographic coordinate set Cjj and an uplift geographic coordinate set Lqj, respectively, effectively identifying surface anomalies during highway construction. Crack extraction is determined by the fluctuation of image gradients, generating a crack geographic coordinate set Lfj. This ensures comprehensive monitoring of surface deformation details and provides a more reliable basis for highway design and safety assessment. Especially in the identification of potential risk areas such as surface subsidence and cracks, the method not only improves the timeliness of monitoring, but also provides data support for the adjustment of design plans and safety warnings, avoiding engineering accidents caused by geological changes, and effectively improving the safety and sustainability of highway construction.

[0107] Example 3

[0108] This embodiment is explained in Example 2, please refer to Figure 1 Specifically: S22, replace the same corrected target geographic coordinates Padj (xt, yt) in the corrected impact data set Ip according to the obtained settlement geographic coordinate set Cjj, uplift geographic coordinate set Lqj and fracture geographic coordinate set Lfj, and obtain the surface anomaly feature set F by integrating the settlement geographic coordinate set Cjj, uplift geographic coordinate set Lqj, fracture geographic coordinate set Lfj and impact data set Ip.

[0109] Said S3 includes S31;

[0110] S31. Perform an anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation calculates the change amount and rate of the surface anomaly based on the feature set F of surface settlement at different time points to obtain an anomaly rate S.

[0111] The abnormal change rate S is obtained by the following calculation formula:

[0112]

[0113] Where △Cj represents the amount of settlement change, △Lq represents the amount of uplift change, △Lf represents the amount of crack change, △t represents the time interval, β represents the adjustment coefficient, SCj represents the rate of settlement change, SLq represents the rate of uplift change, and SLf represents the rate of crack change.

[0114] The settlement change ΔCj is obtained by the calculation formula ΔCj=F(Cjj, t+1)-F(Cjj, t), where t represents time, and F(Cjj, t+1) represents the settlement geographic coordinate set in the surface anomaly feature set F at time t+1;

[0115] The uplift variation ΔLq is obtained by the calculation formula ΔLq=F(Lqj, t+1)-F(Lqj, t), where F(Lqj, t+1) represents the uplift geographic coordinate set in the surface anomaly feature set F at time t+1;

[0116] The crack change amount ΔLf is obtained by the calculation formula ΔLf=F(Lfj, t+1)-F(Lfj, t), where F(Lfj, t+1) represents the crack geographic coordinate set in the surface anomaly feature set F at time t+1;

[0117] The sedimentation change rate SCj is expressed by Obtain calculation formula;

[0118] The elevation change rate SLq is expressed by Obtain calculation formula;

[0119] The crack change rate SLf is expressed by Obtain the calculation formula.

[0120] This embodiment provides a comprehensive and systematic highway survey and safety assessment solution through precise surface anomaly feature extraction and change rate calculation. By extracting surface anomaly features such as settlement, uplift, and cracks from the calibrated impact dataset Ip, the method can identify different types of geological changes. These features are then replaced by the corrected target geographic coordinates Padj(xt, yt) to form a surface anomaly feature set F, laying a solid foundation for subsequent anomaly trend analysis and change rate calculation. In the calculation of the anomaly change rate S, by comparing the surface settlement feature set F at different time points, the method dynamically monitors the changes in settlement, uplift, and cracks, and calculates the settlement change ΔCj, uplift change ΔLq, and crack change ΔLf, respectively, to obtain the change rates of various types of surface changes. By adjusting and integrating these rates, the method can comprehensively assess the changing trends of the highway geological environment and promptly identify potential safety hazards. This not only improves the accuracy and real-time performance of highway settlement monitoring but also enables scientific assessments based on different types of surface changes. Compared with traditional survey methods, this method can capture the evolution process of complex geological phenomena such as subsidence, uplift and cracks in real time, providing a more reliable, data-driven decision-making basis for highway design and safety monitoring, and further improving the safety of highway construction and emergency response capabilities.

[0121] Example 4

[0122] This embodiment is explained in Example 3, please refer to Figure 1 Specifically: the S4 includes S41;

[0123] S41, correcting the abnormal rate S according to different geological information, obtaining the influence of different geological factors on the abnormal rate S, and marking it as the corrected abnormal rate Sadj;

[0124] The corrected abnormal rate Sadj is obtained by the following calculation formula:

[0125]

[0126] Where n represents the total number of geological factors, which specifically reflects the diversity of the geological factors we consider, such as soil type, rock type and groundwater. λ(i) represents the correction coefficient of the i-th geological factor, which specifically indicates the degree of influence of the geological factor on the anomaly rate. This correction coefficient is used to quantify the contribution of each geological factor to the overall change rate. G(i) represents the degree of influence of the i-th geological factor, which specifically represents the specific impact of the i-th geological factor on the surface anomaly change. For example, soil type may have a greater impact on settlement, so its impact G1 may be relatively large; groundwater flow may have a greater impact on uplift, so the impact of G2 on uplift will be quantified to a certain extent.

[0127] Said S5 includes S51;

[0128] S51, based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, perform settlement impact assessment, calculate risk assessment values R of different areas, and determine whether to trigger risk warning according to the risk assessment values R;

[0129] The risk assessment value R is obtained by the following calculation formula:

[0130]

[0131] Where R(t) represents the risk assessment value at time t, γ represents the scaling factor, exp represents the exponential function, Sadj(t) represents the corrected anomaly rate at time t, f(m) represents the sensitivity of the highway facilities in region m to ground changes, and f(m) close to 1 indicates that the infrastructure at this location is very sensitive to surface deformation; if f(m) is much less than 1, it means that the infrastructure at this location is not very sensitive, L represents the total length of highway in region m, and dm represents the integral variable, which specifically represents the response to small changes in region m.

[0132] When the risk assessment value R>1, a risk warning is triggered, the overall highway survey mechanism is executed, the current area m is marked as a maintenance area, and a notification is sent to the relevant road maintenance department for processing;

[0133] S52. When executing the overall highway survey mechanism, the overall highway safety score Rtotal is obtained by statistically analyzing the risk assessment values R of different areas, and is compared with the preset overall abnormality assessment threshold Tsafe to obtain the overall highway abnormality assessment result, and the execution measures are triggered according to the overall highway abnormality assessment result;

[0134] The overall highway safety score Rtotal The calculation formula is obtained, where Q represents the total number of assessment areas, and R(t, m) represents the risk assessment value of area m at time t;

[0135] The overall abnormality assessment results of the highway are obtained by the following comparison method:

[0136] When the highway overall safety score Rtotal is less than the overall abnormality assessment threshold Tsafe, the highway overall abnormality assessment result is obtained as a normal result;

[0137] When the highway overall safety score Rtotal ≥ the overall abnormality assessment threshold Tsafe, the highway overall abnormality assessment result is obtained as an abnormal result, triggering execution measures, including prompting the current area m to be abnormal, and replanning and rerouting the current highway;

[0138] Replanning existing highways involves re-determining the optimal route or designing detours based on current anomaly characteristics and risk assessments to ensure smooth traffic flow and avoid risk areas. For example, different highway design options can be proposed for areas with significant settlement or cracks, including measures such as improving road structural strength, adding supports, or changing pavement materials to enhance road deformation resistance.

[0139] At the same time, based on geological assessments and settlement impacts, it may be necessary to reconstruct or reinforce the roadbed in the affected sections, including strengthening the base soil layer and adding a drainage layer, so as to improve the road's bearing capacity and reduce the risk of future settlement or deformation;

[0140] Rerouting tips include temporary detour route planning: providing temporary rerouting guidance on the current road, especially in areas with severe subsidence, cracks or other geological changes, calculating the safest temporary detour route based on the impact range, and publishing relevant information on the traffic monitoring platform; traffic diversion measures: taking different traffic diversion measures according to the different degrees of abnormalities, such as restricting the passage of heavy vehicles, partially closing traffic, setting up warning signs, etc., to reduce the impact of abnormal sections on traffic flow.

[0141] In this embodiment, by combining the correction of the abnormal rate S with the assessment of settlement impacts based on different geological factors, accurate and comprehensive decision-making support is provided for highway safety assessments. By correcting the geological factors to obtain the corrected abnormal rate Sadj, the impact of diverse geological factors such as soil type, rock type, and groundwater on surface fluctuations is considered. The correction coefficient λ(i) and the degree of influence G(i) for each factor are quantified, making the calculation of the abnormal rate more accurate and effectively reflecting the changing trends under different geological conditions. By combining the corrected abnormal rate Sadj with the structural sensitivity function f(m), a settlement impact assessment is performed, and risk assessment values R(t) for different regions are calculated. A set threshold is then used to determine whether a risk warning is triggered. This step not only considers the geological characteristics of the region but also incorporates the sensitivity of the highway facilities within the region, making the risk assessment more comprehensive and detailed. When the risk assessment value exceeds a predetermined threshold, the system triggers the corresponding overall highway survey mechanism and simultaneously initiates maintenance procedures, ensuring the timeliness and effectiveness of highway safety management. By statistically analyzing the risk assessment values of different areas, the overall highway safety score Rtotal is obtained. By comparing this score with the preset safety threshold Tsafe, the accuracy of the overall highway anomaly assessment results is ensured. If the overall safety score exceeds the threshold, the system automatically triggers further measures, including marking abnormal areas and rerouting the highway. This multi-level, multi-dimensional assessment system not only improves highway safety, but also enhances the flexibility and responsiveness of emergency management. It provides road maintenance departments with effective decision-making support tools and greatly improves the accuracy and timeliness of highway maintenance.

[0142] Example 5

[0143] A highway survey intelligent design system based on satellite images, please refer to Figure 2 ,Specifically: including satellite data calibration module, data feature extraction module, data analysis module, ,correction module and evaluation and decision module;

[0144] The satellite data calibration module performs geometric calibration and atmospheric correction on the collected satellite image data Ir to correct errors caused by atmospheric, illumination and satellite orbit factors, thereby forming a corrected impact dataset Ip.

[0145] The data feature extraction module extracts surface subsidence features, including cracks and elevation changes, from the corrected impact dataset Ip, and integrates the extracted features to form a surface anomaly feature set F;

[0146] The data analysis module performs anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation calculates the change amount and rate of surface anomalies based on the feature set F of surface settlement at different time points to obtain the anomaly rate S.

[0147] The correction module corrects the abnormal rate S according to different geological information, obtains the influence of different geological factors on the abnormal rate S, and marks it as the corrected abnormal rate Sadj;

[0148] The evaluation and decision module evaluates the impact of settlement based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, calculates the risk assessment value R of different areas, and determines whether to trigger a risk warning based on the risk assessment value R. When a risk warning is triggered, the overall safety score Rtotal of the highway is obtained through statistical analysis of the risk assessment values R of different areas, and is compared with the preset overall abnormality assessment threshold Tsafe to obtain the overall abnormality assessment result of the highway, and trigger execution measures based on the overall abnormality assessment result of the highway.

[0149] In this embodiment,

[0150] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent highway survey and design based on satellite imagery, characterized by: The following steps are involved: S1, by performing geometric calibration and atmospheric correction on the collected satellite image data Ir, the errors caused by atmospheric, illumination and satellite orbit factors are corrected to form the corrected impact dataset Ip; S2. Extracting surface subsidence features from the corrected impact dataset Ip, including cracks and elevation changes, and integrating the extracted features to form a surface anomaly feature set F; Said S2 includes S21 and S22; S21. Extracting surface subsidence features from the corrected impact dataset Ip, including cracks and elevation changes, and analyzing the differences in cracks and elevation changes by comparing the impact datasets Ip at different time periods; Among them, the elevation change extraction obtains the elevation change value △H of the area by affecting the lifting and settlement information of the corrected target geographic coordinates Padj (xt, yt) in the dataset Ip in different time periods, and compares it with the preset settlement uplift threshold Thigh to obtain the extraction result of the corrected target geographic coordinates Padj (xt, yt). The corrected target geographic coordinates Padj (xt, yt) are marked according to the extraction result to form the settlement geographic coordinate set Cjj and the uplift geographic coordinate set Lqj; The elevation change value ΔH is obtained by the following calculation formula: ΔH=Padj(xt,yt,Hc)-Padj(xt,yt,Hr); Where Padj(xt, yt, Hc) and Padj(xt, yt, Hr) represent the elevation values of the corrected target geographic coordinates Padj(xt, yt) before and after the fixed period, respectively; When the elevation change value △H>1.5 times the settlement uplift threshold Thigh, the extraction result of the corrected target geographic coordinate Padj (xt, yt) is obtained as the settlement result, indicating that the corrected target geographic coordinate Padj (xt, yt) is a settlement geographic coordinate point and is added to the settlement geographic coordinate set Cjj; When the elevation change value △H is less than 0.5 times of the subsidence uplift threshold Thigh, the extraction result of the corrected target geographic coordinate Padj (xt, yt) is obtained as an uplift result, indicating that the corrected target geographic coordinate Padj (xt, yt) is an uplift geographic coordinate point and is added to the uplift geographic coordinate set Lqj; Among them, crack extraction extracts crack information through the height difference map, obtains the gradient fluctuation value △I of the image gradient by comparing the impact data set Ip of different time periods, and compares it with the preset gradient fluctuation threshold Tcrack to obtain the extraction result of the corrected target geographic coordinate Padj(xt, yt), and marks the corrected target geographic coordinate Padj(xt, yt) according to the extraction result to form the crack geographic coordinate set Lfj; The gradient fluctuation value ΔI is obtained by the following calculation formula: Where, and They represent the local change rates of the corrected target geographic coordinates Padj(xt, yt) in the xt horizontal axis direction and the yt vertical axis direction, respectively. Indicates the gradient value calculated at the corrected target geographic coordinate Padj(xt, yt) by combining the local rate of change in the xt horizontal axis direction and the yt vertical axis direction; When the gradient fluctuation value △I> the gradient fluctuation threshold Tcrack, the corrected target geographic coordinate Padj (xt, yt) is extracted as the crack result, indicating that the corrected target geographic coordinate Padj (xt, yt) is the crack geographic coordinate point and is added to the crack geographic coordinate set Lfj; S3. Perform an anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation is based on the feature set F of surface settlement at different time points to calculate the change amount and rate of the surface anomaly and obtain the anomaly rate S. S4. Correct the abnormal rate S according to different geological information, obtain the influence of different geological factors on the abnormal rate S, and mark it as the corrected abnormal rate Sadj; S5. Based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, the settlement impact assessment is performed, the risk assessment value R of different areas is calculated, and the risk warning is triggered according to the risk assessment value R. When the risk warning is triggered, the overall highway safety score Rtotal is obtained through statistical analysis of the risk assessment values R of different areas, and compared with the preset overall abnormal assessment threshold Tsafe to obtain the overall abnormal assessment result of the highway, and trigger the execution measures according to the overall abnormal assessment result of the highway.

2. The method for intelligent highway survey and design based on satellite imagery according to claim 1, characterized in that: Said S1 includes S11 and S12; S11. Correcting spatial errors in the satellite image data Ir caused by satellite orbit error, image tilt, and ground undulation by geometrically calibrating the collected satellite image data Ir so that the geographic coordinates in the satellite image data Ir are consistent with the actual ground coordinates. Specifically, the geometric calibration is performed by matching ground control points with corresponding points in the satellite image data Ir to obtain calibrated target geographic coordinates (xt, yt). The target geographic coordinates (xt, yt) are then integrated to obtain a geometrically calibrated output image dataset Ig. The target geographic coordinates (xt, yt) are obtained by the following calibration formula: (xt, yt)=Mgeo*(xr, yr)+b; Where (xr, yr) represents the coordinate position in the satellite image data Ir, specifically the horizontal and vertical axis values of the coordinate position, Mgeo represents the geometric transformation matrix, and b represents the translation variable.

3. The method for intelligent highway survey and design based on satellite imagery according to claim 2, characterized in that: S12. Perform atmospheric correction on the acquired output image dataset Ig to correct the optical signal received by the satellite sensor affected by atmospheric, lighting, dust, and water vapor factors, and obtain the corrected impact dataset Ip by correcting each target geographic coordinate (xt, yt) in the output image dataset Ig.

4. The method for intelligent highway survey and design based on satellite imagery according to claim 1, characterized in that: S22. Replace the same corrected target geographic coordinates Padj (xt, yt) in the corrected impact data set Ip according to the acquired settlement geographic coordinate set Cjj, uplift geographic coordinate set Lqj and fracture geographic coordinate set Lfj, and obtain the surface anomaly feature set F by integrating the settlement geographic coordinate set Cjj, uplift geographic coordinate set Lqj, fracture geographic coordinate set Lfj and impact data set Ip.

5. The method for intelligent highway survey and design based on satellite images according to claim 4, characterized in that: Said S3 includes S31; S31. Perform an anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation calculates the change amount and rate of the surface anomaly based on the feature set F of surface settlement at different time points to obtain an anomaly rate S. The abnormal rate S is obtained by the following calculation formula: Where △Cj represents the amount of settlement change, △Lq represents the amount of uplift change, △Lf represents the amount of crack change, △t represents the time interval, β represents the adjustment coefficient, SCj represents the rate of settlement change, SLq represents the rate of uplift change, and SLf represents the rate of crack change.

6. The method for intelligent highway survey and design based on satellite imagery according to claim 1, characterized in that: Said S4 includes S41; S41, correcting the abnormal rate S according to different geological information, obtaining the influence of different geological factors on the abnormal rate S, and marking it as the corrected abnormal rate Sadj; The corrected abnormal rate Sadj is obtained by the following calculation formula: Where n represents the total number of geological factors, λ(i) represents the correction coefficient of the i-th geological factor, and G(i) represents the influence degree of the i-th geological factor.

7. The method for intelligent highway survey and design based on satellite images according to claim 1, characterized in that: The S5 includes S51; S51, based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, perform settlement impact assessment, calculate risk assessment values R of different areas, and determine whether to trigger risk warning according to the risk assessment values R; The risk assessment value R is obtained by the following calculation formula: Where R(t) represents the risk assessment value at time t, γ represents the scaling factor, exp represents the exponential function, Sadj(t) represents the corrected anomaly rate at time t, f(m) represents the sensitivity of highway facilities in region m to ground changes, L represents the total length of highway in region m, and dm represents the integral variable, specifically representing a small change in region m. When the risk assessment value R>1, a risk warning is triggered, the overall highway survey mechanism is executed, the current area m is marked as a maintenance area, and a notification is sent to the relevant road maintenance department for processing; S52. When executing the overall highway survey mechanism, the overall highway safety score Rtotal is obtained by statistically analyzing the risk assessment values R of different areas, and is compared with the preset overall abnormality assessment threshold Tsafe to obtain the overall highway abnormality assessment result, and the execution measures are triggered according to the overall highway abnormality assessment result; The overall abnormality assessment results of the highway are obtained by the following comparison method: When the highway overall safety score Rtotal is less than the overall abnormality assessment threshold Tsafe, the highway overall abnormality assessment result is obtained as a normal result; When the highway overall safety score Rtotal ≥ the overall abnormality assessment threshold Tsafe, the highway overall abnormality assessment result is obtained as an abnormal result, triggering execution measures, including prompting the current area m to be abnormal, and replanning and diverting the current highway.

8. A satellite image-based highway survey and intelligent design system, applied to the satellite image-based highway survey and intelligent design method according to any one of claims 1 to 7, characterized in that: It includes satellite data calibration module, data feature extraction module, data analysis module, correction module and evaluation and decision module; The satellite data calibration module performs geometric calibration and atmospheric correction on the collected satellite image data Ir to correct errors caused by atmospheric, illumination and satellite orbit factors, thereby forming a corrected impact dataset Ip. The data feature extraction module extracts surface subsidence features, including cracks and elevation changes, from the corrected impact dataset Ip, and integrates the extracted features to form a surface anomaly feature set F; The data analysis module performs anomaly trend analysis and change rate calculation based on the formed surface anomaly feature set F. The anomaly trend analysis includes time series analysis. The change rate calculation calculates the change amount and rate of surface anomalies based on the feature set F of surface settlement at different time points to obtain the anomaly rate S. The correction module corrects the abnormal rate S according to different geological information, obtains the influence of different geological factors on the abnormal rate S, and marks it as the corrected abnormal rate Sadj; The evaluation and decision module evaluates the impact of settlement based on the obtained corrected abnormal rate Sadj and the structural sensitivity function F, calculates the risk assessment value R of different areas, and determines whether to trigger a risk warning based on the risk assessment value R. When a risk warning is triggered, the overall safety score Rtotal of the highway is obtained through statistical analysis of the risk assessment values R of different areas, and is compared with the preset overall abnormality assessment threshold Tsafe to obtain the overall abnormality assessment result of the highway, and trigger execution measures based on the overall abnormality assessment result of the highway.

Images