A beidou disaster displacement and image video monitoring fusion method and system based on a high-reliability communication link

Abstract

The application provides a Beidou ground disaster displacement and image video monitoring fusion method and system based on a high-reliability communication link, comprising: real-time collection of displacement, inclination and five-direction high-definition video, access to micro-meteorological and wire clip temperature data, unified packaging through a data gateway; APN special line transmission is adopted, and centimeter-level RTK differential service is provided for a UAV; based on a Beidou VRS virtual reference station and a long-baseline monitoring solution technology, a Beidou ground-based enhancement station network is multiplexed to generate virtual observation values for real-time dynamic RTK solution; based on the slant-path tropospheric delay PWV inversion three-dimensional water vapor field, tower-level rainfall prediction is realized, and an AI algorithm is fused to generate a risk assessment report; in a BIM+GIS digital twin scene, a displacement heat map, real-time video and early warning annotation are superimposed, 360-degree panoramic splicing and alarm triggering snapshot are supported, and intelligent early warning decision is realized. Through high-precision Beidou monitoring, multi-modal data fusion and intelligent early warning, the real-time performance, precision and automation level of geological disaster monitoring are significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological disaster monitoring, and in particular to a disaster early warning method combining Beidou high-precision positioning, multi-mode communication link and visual analysis, which is especially suitable for real-time monitoring in complex environments such as mountainous areas and landslide bodies. BACKGROUND

[0002] Geological disasters (such as landslides, collapses, ground subsidence, etc.) have the characteristics of strong suddenness and great destructiveness, which seriously threaten the safety of people's lives and property and the stable operation of major infrastructure. The traditional monitoring methods (such as total station, inclinometer, etc.) have the following technical bottlenecks:

[0003] Insufficient monitoring accuracy: the conventional GNSS single-point positioning accuracy is only meter-level, which is difficult to meet the millimeter-level deformation monitoring demand; manual inspection is low in efficiency and cannot realize all-weather continuous monitoring. Difficulty in multi-source data fusion: displacement, video, weather, etc. Data is scattered and independent, lacks a unified space-time reference, and is difficult to analyze collaboratively; existing systems mostly use single sensors, which cannot fully capture the multi-dimensional precursor characteristics of geological disasters. Insufficient real-time and reliability: poor communication conditions in remote areas, high data backhaul delay, affecting the timeliness of early warning; traditional RTK requires intensive deployment of physical reference stations, with high construction and maintenance costs. Weak intelligent decision-making capability: relying on manual experience to judge risks, with high false positive and false negative rates; early warning and emergency response are disconnected, lacking an automatic disposal mechanism.

[0004] Therefore, there is an urgent need for a high-precision, low-cost monitoring method that realizes real-time early warning and automatic response of geological disasters through Beidou high-precision positioning, multi-modal data fusion and intelligent decision-making. SUMMARY

[0005] Therefore, it is necessary to provide a Beidou geological disaster displacement and image video monitoring fusion method based on high-reliability communication link, which significantly improves the real-time, accuracy and automation level of geological disaster monitoring through high-precision Beidou monitoring, multi-modal data fusion and intelligent early warning, and is suitable for high-risk scenarios such as power transmission towers and slopes.

[0006] The application provides a Beidou disaster displacement and image video monitoring fusion method and system based on a high-reliability communication link, comprising: multi-source data acquisition: real-time acquisition of millimeter-level displacement, inclination and five-direction high-definition video by a Beidou monitoring device, and access to micro-meteorological and clamp temperature data, and unified packaging by a data gateway; high-reliability data transmission: APN special line transmission is adopted, Beidou time stamp is marked to ensure time sequence alignment, and centimeter-level RTK differential service is provided for a UAV; virtual reference station construction: based on a Beidou VRS virtual reference station and a long baseline monitoring solution technology, a Beidou ground-based augmentation station network is multiplexed to generate virtual observation values for real-time dynamic RTK solution; cloud-side intelligent analysis: based on the slant path tropospheric delay PWV, a three-dimensional water vapor field is inversed to realize tower-level rainfall prediction, and an AI algorithm is used to generate a risk assessment report; multi-modal monitoring: in a BIM+GIS digital twin scene, displacement heat maps, real-time videos and early warning labels are superimposed to support 360-degree panoramic splicing and alarm triggering snapshot; intelligent early warning decision: when a threshold value is exceeded or a collapse precursor is identified, an alarm is automatically pushed and a UAV emergency inspection is started. Through high-precision Beidou monitoring, multi-modal data fusion and intelligent early warning, the application significantly improves the real-time performance, precision and automation level of geological disaster monitoring, and is suitable for high-risk scenes such as power transmission towers and slopes.

[0007] In a first aspect, the embodiments of the application provide a Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link, comprising:

[0008] Step 1: multi-source data acquisition, real-time acquisition of millimeter-level displacement, inclination and five-direction high-definition video by a Beidou monitoring device; access to micro-meteorological and clamp temperature data, and unified packaging by a data gateway;

[0009] Step 2: high-reliability data transmission: APN special line transmission is adopted, all data is marked with a Beidou time stamp to ensure time sequence alignment; through a temporary reference station mode, centimeter-level RTK differential service is provided for a UAV;

[0010] Step 3: based on a Beidou VRS virtual reference station and a long baseline monitoring solution technology, a Beidou ground-based augmentation station network that has been completed is multiplexed to construct a virtual reference station instead of a traditional physical reference station, error correction models are established through observation data of multiple reference stations, and virtual observation values are generated for real-time dynamic RTK solution;

[0011] Step 4: cloud-side intelligent analysis, based on the slant path tropospheric delay PWV, a three-dimensional water vapor field is inversed to realize tower-level rainfall prediction; based on an AI algorithm, displacement rate, inclination mutation and video features are fused to generate a risk assessment report;

[0012] Step 5: Multi-modal monitoring: Through the three-dimensional visualization platform, superimpose the displacement heat map, real-time video and warning area annotation in the BIM+GIS digital twin scene, through 360° panoramic splicing, down-view wide-angle monitoring, alarm triggered video automatic snapshot;

[0013] Step 6: Intelligent early warning and decision-making: Through big data analysis and artificial intelligence algorithms, real-time calculation and trend analysis of monitoring data, generate early warning information and automatically trigger alarm mechanism, when the displacement rate exceeds the threshold or AI identifies the collapse precursor characteristics to trigger the emergency response mechanism, automatically push the alarm to the emergency management platform, and synchronously start the unmanned aerial vehicle inspection plan.

[0014] Optionally, in an implementation form of the first aspect of the present application, the step 1: multi-source data acquisition, real-time acquisition of millimeter-level displacement, inclination, five-direction high-definition video through the Beidou monitoring device; access to micro-weather, wire clip temperature data, unified packaging through the data gateway, including:

[0015] Deploying the Beidou disaster monitoring comprehensive device on the tower and slope, real-time acquisition of millimeter-level high-precision displacement settlement, inclination, image video data, wherein the Beidou disaster monitoring comprehensive device is based on GNSS high-precision receiver positioning technology, low-power high-precision GNSS chip and front, back, left and right five-channel cameras, double-channel 180° panoramic high-definition image monitoring splicing, which fuses MEMS sensor technology, narrowband communication technology and embedded system hibernation wake-up technology, can provide millimeter-level high-precision displacement monitoring information and 360° panoramic image video monitoring all day round;

[0016] The Beidou disaster monitoring comprehensive device also has data gateway function, can access micro-weather, wire clip temperature sensor data, and select and apply according to the monitoring scene;

[0017] Through the Internet of Things APN special line, the data is returned to the unified Internet of Things platform, based on the Beidou platform, the positioning and mapping capabilities of the South Grid Sky Platform, multi-source data fusion application is carried out through the system, and digital production application is supported.

[0018] Optionally, in an implementation form of the first aspect of the present application, the step 3: based on the Beidou VRS virtual reference station and long baseline monitoring solution technology, multiplexing the Beidou ground enhancement station network that has been completed, constructing a virtual reference station to replace the traditional physical station, through the observation data of multiple reference stations, establishing an error correction model, thereby generating virtual observation values, for real-time dynamic RTK solution, including:

[0019] Step 3.1: Data acquisition by entity reference station network, multiplexing existing Beidou ground enhancement station needs to meet: station spacing ≤ 30km; equipped with dual-frequency or multi-frequency Beidou receiver; data sampling rate ≥ 1Hz, real-time return of original observation value, PTP protocol is used to realize time synchronization between stations;

[0020] Step 3.2: error modeling through network RTK to obtain error model, wherein the formula of carrier phase observation value is:

[0021] ,

[0022] Wherein, is the carrier phase observation value, is the distance from the receiver to the satellite, is the ionospheric delay, is the tropospheric delay, is the speed of light, and are the clock errors of the receiver and the satellite respectively, is the satellite orbit error, is the multipath effect error, is the carrier phase wavelength, is the integer ambiguity;

[0023] Step 3.3: extraction by Geometry-Free combination, using regional linear interpolation or low-order curved surface fitting to correct the observation value of the reference station, and the formula of the corrected carrier phase observation value is:

[0024] ,

[0025] Wherein, and are the correction values of ionospheric and tropospheric delay respectively, and are the correction values of receiver and satellite clock error respectively;

[0026] Step 3.4: based on the observation value of the main reference station, combined with the geometric correlation term and the atmospheric delay correction, the carrier phase observation value of the virtual reference station is generated, and the formula is as follows:

[0027] ,

[0028] Wherein, is the carrier phase observation value, is the observation value of the main observer station, is the geometric distance error gradient, is the atmospheric delay error gradient.

[0029] Optionally, in an implementation form of the first aspect of the application, the error model is modified using a LAMBDA algorithm, comprising:

[0030] Step 4.1: Error modeling:

[0031] Step 4.1.1: Ionospheric delay, ionospheric delay is extracted by double-frequency geometry-free combination, and a low-order polynomial regional space model is established, wherein the ionospheric delay formula is:

[0032] ,

[0033] wherein, is the ionospheric delay value, and are the frequencies of the two frequency points, respectively, and are carrier phase observations in cycles, and are carrier phase wavelengths corresponding to the carrier phase observations, respectively;

[0034] Step 4.1.2: Tropospheric delay: the dry component is modified by the Saastamoinen model, and the wet component is estimated by a random walk process;

[0035] Step 4.1.3: Orbit / clock bias: using precise ephemeris products or inter-station difference to eliminate;

[0036] Step 4.2: LAMBDA ambiguity fixing;

[0037] Step 4.2.1: Integer Gaussian transformation is performed on to reduce the correlation between ambiguities, and the transformation formula is:

[0038] ,

[0039] wherein, is the initial covariance matrix, is a diagonal matrix, is a decorrelation matrix, ;

[0040] Transformed ambiguity: ;

[0041] Step 4.2.2: Optimal integer solution is searched in the transformed space by integer least squares search : , and a shrinkage search strategy Bootstrapping is adopted to accelerate the calculation;

[0042] Step 4.2.3: Inverse transformation and verification, Inverse transform back to the original space: ; Fixed reliability is verified by ratio test RatioTes

[0043] Step 4.3: Fixed solution error correction, the fixed ambiguity Substitute into the observation equation, and calculate the residual term;

[0044] Step 4.4: Update the covariance matrix by using the residual to correct the ionosphere / troposphere model parameters , into the next epoch solution, error model iteration optimization.

[0045] Optionally, in an implementation form of the first aspect of the application, the step 4: cloud intelligent analysis, based on the slant path tropospheric delay PWV inversion three-dimensional water vapor field, realize the tower level rainfall prediction; Based on AI algorithm fusion displacement rate, angle mutation, video features, generate risk assessment report, including:

[0046] The cloud intelligent analysis is based on Beidou III PPP-B2b precise point positioning service, combined with meteorology and GNSS technology, realizes the tower level rainfall prediction and risk assessment report generation, including:

[0047] Using Beidou III PPP-B2b service, the atmospheric precipitable water PWV is inverted through observation data, and combined with three-dimensional water vapor tomography model, the three-dimensional water vapor field of the monitoring area is reconstructed, the high-precision water vapor prediction is realized, and the surrounding rainfall is finely predicted;

[0048] The Beidou disaster comprehensive monitoring device can be quickly deployed as a temporary reference station, real-time back observation data to Beidou platform, become the supplement of reference station network, improve the availability of differential service, provide centimeter level real-time dynamic positioning service for unmanned aerial vehicle inspection;

[0049] Based on AI algorithm fusion displacement rate, angle mutation, video features multi-dimensional data, generate more accurate risk assessment report.

[0050] Optionally, in an implementation form of the first aspect of the application, the step 5: multi-modal monitoring: through the three-dimensional visualization platform, superimpose displacement heat map, real-time video and warning area annotation in BIM+GIS digital twin scene, through 360° panoramic splicing, downward wide-angle monitoring, alarm trigger video automatic snapshot, including:

[0051] S5.1, Construct a multi-modal data fusion architecture, which includes data layer integration. The data types in the data layer integration include: Beidou displacement data, three-dimensional geological model, geographic space base map, real-time video stream, and meteorological data. The fusion rules include: spatial alignment and time synchronization. The spatial alignment is achieved through seven-parameter conversion between Beidou CGCS2000 coordinate system and BIM local coordinate system to achieve millimeter-level matching. The time synchronization includes using NTP+PTP hybrid protocol to ensure that the timestamp error between video frame and displacement data is less than 10ms;

[0052] S5.2, Displacement trend prediction and target identification: Construct a multi-modal fusion model. The displacement trend prediction uses LSTM neural network to analyze time series data and combines with InSAR historical data to correct model error. Video target identification detects crack expansion and rock mass sliding based on YOLOv7 algorithm and matches and locates with three-dimensional oblique photography model. Risk level assessment generates risk assessment matrix through displacement rate, rainfall and crack width multi-index and outputs red / orange / yellow / blue four-level warning. The multi-modal fusion model evaluates multi-modal data and outputs evaluation results.

[0053] S5.3, Generate displacement heat map: Generate displacement heat map through three-dimensional visualization platform key technology. Use WebGL shader to realize GPU accelerated rendering and support real-time update of multiple monitoring points.

[0054] S5.4, Build BIM+GIS digital twin scene: Engine selection includes Cesium for global terrain and satellite image base, Three.js for loading BIM model and realizing local high-precision rendering. Layered display control is realized through layer display logic. Seamless fusion of three-dimensional scene and video is realized.

[0055] S5.5, Panoramic monitoring integration: Use SIFT feature matching and GPU accelerated stitching technology of OpenCV. Solve camera external parameters through PnP algorithm. Map video pixel coordinates to three-dimensional scene coordinates. Perform panoramic video stitching and real-time monitoring video and three-dimensional model fusion.

[0056] S5.6, Set multi-level warning trigger conditions: When Beidou displacement exceeds threshold and warning level reaches yellow and above, the system will call PTZ camera preset position to capture key frames and store them. At the same time, analyze cracks or collapse through AI and generate report to push to BIM label. Perform multi-modal data linkage and interaction.

[0057] S5.7, Crack / collapse detection model based on YOLOv8+Transformer hybrid architecture: Process complex spatio-temporal relationship through Transformer architecture. Enhance AI analysis and improve detection accuracy.

[0058] S5.7, Crack / Collapse Detection Model Based on YOLOv8+Transformer Hybrid Architecture: Process complex spatio-temporal relationships through Transformer architecture, enhance AI-enhanced analysis, and improve detection accuracy;

[0059] S5.8, Monitoring Point Density and Adapting to Harsh Environment: When the monitoring point density exceeds 1000 points / km², the system automatically switches to a clustered display mode; in harsh environments, low-light enhancement is performed, and the STARVIS sensor mode is switched to combine with the Retinex algorithm to improve picture quality; in case of communication interruption, the edge node caches the last 15 minutes of data, and when the network is restored, the breakpoint is resumed;

[0060] S5.9, Hololens2 superimposes real-time displacement data, and real-time displacement data is superimposed on the field of view through Hololens2, and key data of early warning events are chained to meet the needs of regulatory audits.

[0061] Optionally, in an implementation manner of the first aspect of the application, the step 6: intelligent early warning and decision making: through big data analysis and artificial intelligence algorithms, real-time calculation and trend analysis are performed on the monitoring data, early warning information is generated and an alarm mechanism is automatically triggered, when the displacement rate exceeds the threshold or the AI identifies the precursory characteristics of collapse, an emergency response mechanism is triggered, and an alarm is automatically pushed to the emergency management platform, and a UAV inspection plan is started simultaneously, including:

[0062] Provide monitoring threshold customization function through Beidou disaster monitoring scene monitoring, and realize accurate control of tower risk through red, orange, yellow and blue level differentiation;

[0063] Provide scene visualization, through South Grid intelligent panoramic map dotting and sensor three-dimensional model erection function, visualize the tower location, risk level, real-time alarm and real-time monitoring data curve information of the tower where the Beidou disaster monitoring terminal is installed, and realize remote real-time monitoring of the tower operation status;

[0064] Provide monitoring report export function, generate special monitoring report for key controlled line towers, and improve the risk control work of power transmission line geological disasters.

[0065] In a second aspect, the embodiments of the present application provide a Beidou disaster displacement and image video monitoring fusion system based on a high-reliability communication link, which is applied to the Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link as described in the first aspect, and includes:

[0066] Sensing layer: real-time collection of millimeter-level displacement, inclination, and five-direction high-definition video through Beidou monitoring devices; access to micro-meteorological and line clip temperature data, and unified packaging through a data gateway;

[0067] Transmission layer: high-reliability data transmission: APN dedicated line transmission is adopted, all data is marked with Beidou timing timestamp to ensure timing alignment; temporary reference station mode is adopted to provide centimeter-level RTK differential service for unmanned aerial vehicles;

[0068] Processing layer: based on Beidou VRS virtual reference station and long baseline monitoring solution technology, multiplexing the Beidou ground enhancement station network that has been completed, constructing a virtual reference station to replace the traditional physical station, through the observation data of multiple reference stations, establishing an error correction model to generate virtual observation values for real-time dynamic RTK solution;

[0069] Analysis layer: cloud intelligent analysis, based on the slant path troposphere delay PWV to retrieve three-dimensional water vapor field, to realize the tower-level rainfall prediction; based on AI algorithm to fuse displacement rate, inclination mutation, video features, to generate risk assessment report;

[0070] Platform layer: multi-modal monitoring: through the three-dimensional visualization platform, superimposing displacement heat map, real-time video and warning area annotation in BIM+GIS digital twin scene, through 360° panoramic splicing, downward wide-angle monitoring, alarm triggering video automatic snapshot;

[0071] Application layer: intelligent early warning and decision-making: through big data analysis and artificial intelligence algorithm, real-time solution and trend analysis of monitoring data, to generate early warning information and automatically trigger alarm mechanism, when the displacement rate exceeds the threshold or the AI identifies the collapse precursor characteristics to trigger the emergency response mechanism, to automatically push the alarm to the emergency management platform, and synchronously start the unmanned aerial vehicle inspection plan.

[0072] In a third aspect, an electronic device is provided, comprising:

[0073] a processor;

[0074] a memory for storing processor-executable instructions;

[0075] wherein the processor is configured to implement the Beidou disaster displacement and image video monitoring fusion method based on high-reliability communication link as described in the first aspect when executing the instructions.

[0076] In a fourth aspect, an electronic device is provided, comprising:

[0077] The application discloses a Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link, and comprises the following steps: multi-source data acquisition: real-time acquisition of millimeter-level displacement, inclination and five-direction high-definition video through a Beidou monitoring device, and access to micro-meteorological and wire clip temperature data, and unified encapsulation through a data gateway; high-reliability data transmission: APN special line transmission is adopted, Beidou time stamp is marked to ensure time sequence alignment, and centimeter-level RTK differential service is provided for a UAV; virtual reference station construction: based on a Beidou VRS virtual reference station and a long baseline monitoring solution technology, a Beidou ground-based enhancement station network is multiplexed to generate virtual observation values for real-time dynamic RTK solution; cloud-side intelligent analysis: based on an oblique path tropospheric delay PWV, a three-dimensional water vapor field is inversed to realize tower-level rainfall prediction, and an AI algorithm is fused to generate a risk assessment report; multi-modal monitoring: in a BIM+GIS digital twin scene, displacement heat maps, real-time videos and early warning labels are superimposed to support 360-degree panoramic splicing and alarm triggering snapshot; intelligent early warning decision: when a threshold value is exceeded or a collapse precursor is identified, an alarm is automatically pushed and a UAV emergency inspection is started through real-time analysis of big data and AI.

[0078] Advantages:

[0079] (1) High-reliability communication architecture: APN special line + Beidou time synchronization, ensuring low-delay and high-faithful data transmission.

[0080] (2) Virtual reference station optimization: multiplexing an existing Beidou ground-based enhancement station network to reduce construction cost and improve long baseline solution accuracy.

[0081] (3) Multi-modal fusion: BIM+GIS three-dimensional visualization platform integrating displacement heat maps, panoramic videos and AI risk analysis to realize digital twin dynamic monitoring.

[0082] (4) Intelligent early warning linkage: based on multi-dimensional AI models such as LSTM displacement prediction and YOLOv8 crack detection to trigger a hierarchical emergency response mechanism.

[0083] (5) UAV cooperative inspection: providing centimeter-level positioning for a UAV through a temporary reference station mode to form a “monitoring-warning-disposal” closed loop. BRIEF DESCRIPTION OF DRAWINGS

[0084] Figure 1 The Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link provided by the embodiment of the application is shown in the flowchart.

[0085] Figure 2The application provides a virtual reference station based on Beidou VRS and a long baseline monitoring solution technology, and a virtual observation value generation process schematic diagram is provided.

[0086] Figure 3 A LAMBDA algorithm based error model correction process schematic diagram is provided.

[0087] Figure 4 A Beidou disaster displacement and image video monitoring fusion system architecture based on a high-reliability communication link is provided.

[0088] Figure 5 An electronic device schematic diagram is provided. DETAILED DESCRIPTION

[0089] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only some of the embodiments of the application, but not all the embodiments of the application.

[0090] It should be noted that the "at least one" in the embodiments of the application means one or more, and the more means two or more than two. Unless otherwise defined, all technical and scientific terms used in the present application have the same meanings as those commonly understood by those skilled in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing the specific embodiments of the application, and are not intended to limit the application.

[0091] It should be noted that the "first", "second" and the like in the embodiments of the application are only used for the purpose of distinguishing description, and cannot be understood as indicating or implying relative importance. The features limited by "first", "second" can explicitly or implicitly include one or more of the features. In the description of the embodiments of the application, the words "exemplary" or "for example" are used to mean serving as an example, instance or illustration. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0092] Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0093] Embodiment one

[0094] The embodiment discloses a Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link, and comprises the following steps: multi-source data acquisition: real-time acquisition of millimeter-level displacement, inclination and five-direction high-definition video by a Beidou monitoring device, and access to micro-meteorological and clamp temperature data, and unified encapsulation through a data gateway; high-reliability data transmission: APN special line transmission is adopted, a Beidou time stamp is marked to ensure time sequence alignment, and centimeter-level RTK differential service is provided for a UAV; virtual reference station construction: based on a Beidou VRS virtual reference station and a long baseline monitoring solution technology, a Beidou ground-based enhancement station network is multiplexed to generate virtual observation values for real-time dynamic RTK solution; cloud-side intelligent analysis: based on a slant-path tropospheric delay PWV, a three-dimensional water vapor field is inversed to realize tower-level rainfall prediction, and an AI algorithm is fused to generate a risk assessment report; multi-modal monitoring: in a BIM+GIS digital twin scene, a displacement heat map, real-time video and early warning labels are superimposed to support 360-degree panoramic splicing and alarm triggering snapshot; intelligent early warning decision: through real-time analysis of big data and AI, an alarm is automatically pushed when a threshold value is exceeded or a collapse precursor is identified, and a UAV emergency inspection is started.

[0095] Figure 1 A Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link is provided for an embodiment of the application. Figure 1 As shown in the figure, a Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link comprises:

[0096] Step 1: multi-source data acquisition, real-time acquisition of millimeter-level displacement, inclination and five-direction high-definition video by a Beidou monitoring device; access to micro-meteorological and clamp temperature data, and unified encapsulation through a data gateway.

[0097] Specifically, the step 1: multi-source data acquisition, real-time acquisition of millimeter-level displacement, inclination and five-direction high-definition video by a Beidou monitoring device; access to micro-meteorological and clamp temperature data, and unified encapsulation through a data gateway, comprises:

[0098] A Beidou disaster monitoring comprehensive device is deployed on a tower and a slope to real-time acquire millimeter-level high-precision displacement settlement, inclination, image video data, wherein the Beidou disaster monitoring comprehensive device is based on GNSS high-precision receiver positioning technology, low-power high-precision GNSS chips and five-channel cameras in front, back, left and right and down, double-path 180-degree panoramic high-definition image monitoring splicing, fuses MEMS sensor technology, narrowband communication technology and embedded system hibernation wake-up technology, and can provide millimeter-level high-precision displacement monitoring information and 360-degree panoramic image video monitoring all day round;

[0099] The Beidou geological disaster monitoring comprehensive device has a data gateway function, can access micro-meteorological, wire clamp temperature measurement and various sensor data, and selects and applies according to the monitoring scene;

[0100] The data is returned to the unified Internet of Things platform through the Internet of Things APN special line, and the positioning and map capabilities based on the Beidou platform and the South Network Sky platform are used to run through the system to develop multi-source data fusion applications and support digital production applications.

[0101] It can be understood that in the present embodiment, the Beidou monitoring device collects millimeter-level displacement, inclination and five-way high-definition video data in real time, simultaneously accesses micro-meteorological and wire clamp temperature data, and returns to the Internet of Things platform after being uniformly packaged by the data gateway. This multi-source data acquisition method can realize comprehensive perception of geological disasters, including key indicators such as deformation and crack expansion. The Beidou monitoring device can realize millimeter-level precision displacement monitoring and support integration of various sensor data. In addition, the Beidou system also has a short message communication function, which can complete data transmission in a network-free environment.

[0102] In the high-risk areas of geological disasters such as towers, slopes, etc., the Beidou geological disaster monitoring comprehensive device (integrating GNSS receiver, multi-channel camera and environmental sensor) is deployed to build an all-weather, multi-dimensional three-dimensional monitoring network. The GNSS high-precision module includes a dual-frequency / multi-frequency low-power GNSS chip (such as and Xintong UB482), which supports BDS-3 full-frequency signal. Combined with MEMS inertial sensors to compensate for high-frequency vibration noise (such as accelerometer + gyroscope), the millimeter-level displacement precision in dynamic environment is improved (horizontal ±2mm+1ppm RMS). At the same time, five cameras (200 million pixel wide-angle lens) are configured in front, back, left, right and down view, supporting: dual 180° panoramic stitching (such as fisheye lens + OpenCV image fusion), wide-angle monitoring (covering the slope foot crack development area), video coding standard H.265 / H.264 + AI edge computing (such as crack recognition algorithm).

[0103] At the same time, according to the application scene, multi-source sensors such as micro-meteorological, wire clamp temperature measurement, rain gauge, crack meter, soil moisture meter, inclinometer, etc. can be accessed, and selected and applied according to the monitoring scene.

[0104] Step 2: High-reliability data transmission: APN special line transmission is adopted, all data is marked with Beidou time stamp, and time sequence alignment is ensured; through the temporary reference station mode, centimeter-level RTK differential service is provided for unmanned aerial vehicles.

[0105] Specifically, all data are transmitted by APN private line, and Beidou time stamp is marked to ensure time alignment. At the same time, the temporary reference station mode is used to provide centimeter-level RTK differential service for the unmanned aerial vehicle. This process highlights the high reliability and real-time performance of the Beidou system, and can meet the monitoring needs in complex geological environments.

[0106] It can be understood that in the embodiment, a customized APN private line (logically isolated from the public network) is used to build a dedicated network channel, and an end-to-end IPSec encrypted tunnel is used to ensure data transmission security. The temporary reference station needs to be equipped with a dual-frequency BDS-3 receiver (such as Huace Navigation i70). It supports 1Hz raw observation value output (including carrier phase, pseudorange, and Doppler frequency shift). Rapid deployment: deploy the temporary reference station 30 minutes before the unmanned aerial vehicle takes off (the site selection requires an open view and stable ground). Differential data generation: the reference station solves satellite orbit / clock error in real time. Broadcast the RTCM3.3 format differential signal through the L-band radio / UHF data transmission radio. Finally, the unmanned aerial vehicle end is solved.

[0107] Step 3: Based on the Beidou VRS virtual reference station and long baseline monitoring solution technology, the existing Beidou ground enhancement station network is reused to build a virtual reference station instead of a traditional physical station. Through the observation data of multiple reference stations, an error correction model is established to generate virtual observation values for real-time dynamic RTK solution.

[0108] It can be understood that in the embodiment, based on the Beidou VRS virtual reference station and long baseline monitoring solution technology, the existing Beidou ground enhancement station network is reused to build a virtual reference station instead of a traditional physical station. Through the observation data of multiple reference stations, an error correction model is established to generate virtual observation values for real-time dynamic RTK solution. This process uses GNSS high-precision positioning technology, and combines regional linear interpolation or low-order curved surface fitting method to correct the observation values, thereby improving the solution accuracy.

[0109] The virtual reference station (VRS) technology generates carrier phase observation values of the virtual reference station through the observation data of multiple reference stations. The core steps include error modeling, ambiguity resolution, and carrier phase observation value synthesis.

[0110] Figure 2 The Beidou VRS virtual reference station and long baseline monitoring solution technology provided in the embodiment of the present application generates a virtual observation value flowchart. Figure 3 The LAMBDA algorithm is used to correct the error model flowchart provided in the embodiment.

[0111] Specifically, in the embodiment, as Figure 2 , 3As shown, the step 3: based on Beidou VRS virtual reference station and long baseline monitoring solution technology, multiplexing the Beidou ground enhancement station network which has been completed, constructing virtual reference station to replace traditional entity base station, through the observation data of multiple reference stations, establishing error correction model, thereby generating virtual observation value, for real-time dynamic RTK solution, including:

[0112] Step 3.1: data acquisition through entity reference station network, multiplexing existing Beidou ground enhancement station needs to meet: station spacing≤30km; equipped with dual-frequency or multi-frequency Beidou receiver; data sampling rate≥1Hz, original observation value real-time backhaul, using PTP protocol to realize time synchronization between stations;

[0113] Step 3.2: error modeling through network RTK to obtain error model, wherein the formula of carrier phase observation value is:

[0114]

[0115] Among them, is the carrier phase observation value, is the distance from the receiver to the satellite, is the ionospheric delay, is the tropospheric delay, is the speed of light, and are the clock errors of the receiver and the satellite respectively, is the satellite orbit error, is the multipath effect error, is the carrier phase wavelength, is the integer ambiguity;

[0116] Step 3.3: through Geometry-Free combination extraction, using regional linear interpolation or low-order curved surface fitting to correct the observation value of the reference station, the corrected carrier phase observation value formula is:

[0117]

[0118] Among them, and are the correction values of ionospheric and tropospheric delay respectively, and are the correction values of receiver and satellite clock error respectively;

[0119] Step 3.4: based on the observation value of the main reference station, combined with the geometric correlation term and the atmospheric delay correction, the carrier phase observation value of the virtual reference station is generated, and the formula is as follows:

[0120]

[0121] Among them,​​​ is the carrier phase observation, is the observer station observation, is the geometric range error gradient, is the atmospheric delay error gradient.

[0122] In Global Navigation Satellite System (GNSS), LAMBDA algorithm is an efficient method for integer ambiguity resolution. The core idea is to reduce the correlation between ambiguities by Z-transformation, thus simplifying the search space of integer ambiguities. Specifically, the error model is modified using LAMBDA algorithm, including:

[0123] Step 4.1: Error modeling:

[0124] Step 4.1.1: Ionospheric delay, extract ionospheric delay by dual-frequency geometry-free combination, and establish a low-order polynomial regional space model, where the ionospheric delay formula is:

[0125] ,

[0126] where, is the ionospheric delay value, and are the frequencies of the two frequency points, and are the carrier phase observations in cycles, and are the carrier phase wavelengths corresponding to the carrier phase observations;

[0127] Step 4.1.2: Tropospheric delay: the dry component is corrected by Saastamoinen model, and the wet component is estimated by random walk process;

[0128] Step 4.1.3: Orbit / clock error: eliminate by using precise ephemeris product or inter-station difference;

[0129] Step 4.2: LAMBDA ambiguity fixing;

[0130] Step 4.2.1: Integer Gaussian transformation is performed on to reduce the correlation between ambiguities, and the transformation formula is:

[0131] ,

[0132] where, is the initial covariance matrix, is a diagonal matrix, is a decorrelation matrix, ;

[0133] Transformed ambiguities: ;

[0134] Step 4.2.2: Search for the optimal integer solution in the transformed space using integer least squares search. : The Bootstrapping strategy is used to accelerate computation.

[0135] Step 4.2.3: Inverse Transformation and Verification, ... Inverse transformation back to the original space: The fixed reliability was verified using the RatioTes test.

[0136] Step 4.3: Fix the solution error correction, and fix the ambiguity. Substitute the observation equations and calculate the residual terms in reverse;

[0137] Step 4.4: Use residuals to correct ionospheric / tropospheric model parameters and update the covariance matrix. Then proceed to the next epoch calculation and perform iterative optimization of the error model.

[0138] Step 4: Cloud-based intelligent analysis, based on the inversion of the three-dimensional water vapor field using oblique path tropospheric delayed PWV, to achieve tower-level rainfall prediction; and based on AI algorithms to fuse displacement rate, tilt angle abrupt change, and video features, to generate a risk assessment report.

[0139] Specifically, step 4: cloud-based intelligent analysis, based on the inversion of the three-dimensional water vapor field using the oblique path tropospheric delayed PWV, to achieve tower-level rainfall prediction; based on AI algorithms fusing displacement rate, tilt angle abrupt changes, and video features, to generate a risk assessment report, including:

[0140] Cloud-based intelligent analysis, based on the BeiDou-3 PPP-B2b precise point positioning service and combined with meteorological and GNSS technologies, enables the generation of pole-level rainfall forecasts and risk assessment reports, including:

[0141] Using the BeiDou-3 PPP-B2b service, atmospheric precipitable water volume (PWV) is retrieved from observation data. Combined with a three-dimensional water vapor tomography model, the three-dimensional water vapor field of the monitoring area is reconstructed to achieve high-precision water vapor prediction and to make refined predictions of surrounding rainfall.

[0142] The BeiDou geological disaster integrated monitoring device can be quickly deployed as a temporary reference station, transmitting observation data back to the BeiDou platform in real time, supplementing the reference station network, improving the availability of differential services, and providing centimeter-level real-time dynamic positioning services for UAV inspections;

[0143] By integrating multi-dimensional data such as displacement rate, tilt angle change, and video features using AI algorithms, a more accurate risk assessment report is generated.

[0144] It can be understood that in the present embodiment, based on Beidou III PPP-B2b precise point positioning service, combined with meteorology and GNSS technology, the tower level rainfall prediction and risk assessment report generation are realized. For example, by inverting atmospheric precipitable water PWV and combining three-dimensional water vapor tomography model, the three-dimensional water vapor field of the monitoring area is reconstructed, and high-precision rainfall prediction is realized. In addition, the AI algorithm fuses displacement rate, angle mutation and video features to generate more accurate risk assessment reports.

[0145] Step 5: Multi-modal monitoring: through the three-dimensional visualization platform, the displacement heat map, real-time video and warning area annotation are superimposed in the BIM+GIS digital twin scene, and through 360° panoramic splicing, downward wide-angle monitoring, the video is automatically captured when the alarm is triggered.

[0146] Specifically, the step 5: multi-modal monitoring: through the three-dimensional visualization platform, the displacement heat map, real-time video and warning area annotation are superimposed in the BIM+GIS digital twin scene, and through 360° panoramic splicing, downward wide-angle monitoring, the video is automatically captured when the alarm is triggered, comprising:

[0147] S5.1, a multi-modal data fusion architecture is constructed, wherein the data layer integration includes data types including Beidou displacement data, three-dimensional geological model, geographic space base map, real-time video stream and meteorological data, wherein the fusion rules include: spatial alignment and time synchronization, the spatial alignment is achieved by seven-parameter conversion of Beidou CGCS2000 coordinate system and BIM local coordinate system to realize millimeter-level matching, the time synchronization includes using NTP+PTP hybrid protocol to ensure that the video frame and displacement data timestamp error is less than 10ms;

[0148] S5.2, displacement trend prediction and target identification: a multi-modal fusion model is constructed, wherein the displacement trend prediction uses LSTM neural network to analyze time series data, and combines InSAR historical data to correct model error; video target identification is based on YOLOv7 algorithm to detect crack expansion and rock mass sliding, and is matched and positioned with three-dimensional oblique photography model; risk level evaluation generates a risk evaluation matrix through multi-indexes of displacement rate, rainfall and crack width, and outputs a red / orange / yellow / blue four-level warning, and the multi-modal fusion model evaluates the multi-modal data to output the evaluation result;

[0149] S5.3, generating displacement heat map: generating displacement heat map through three-dimensional visualization platform key technology, using WebGL shader to realize GPU accelerated rendering, and supporting real-time update of multiple monitoring points;

[0150] S5.4, Building BIM+GIS digital twin scene: Engine selection includes Cesium for global terrain and satellite image base, Three.js for loading BIM models and implementing local high-precision rendering, hierarchical display control is achieved through layer display logic, seamless fusion of three-dimensional scene and video is achieved;

[0151] S5.5, panoramic monitoring integration: Using OpenCV's SIFT feature matching and GPU-accelerated stitching technology, the camera's external parameters are calculated through the PnP algorithm, the video pixel coordinates are mapped to three-dimensional scene coordinates, panoramic video stitching and real-time monitoring video and three-dimensional model fusion are performed;

[0152] S5.6, set multi-level warning trigger condition: When the Beidou displacement exceeds the threshold and the warning level reaches yellow and above, the system will call the PTZ camera preset position to capture key frames and store them, while analyzing cracks or collapses through AI and generating reports to push to BIM labels, for multi-modal data linkage and interaction;

[0153] S5.7, crack / collapse detection model based on YOLOv8+Transformer hybrid architecture: Through the Transformer architecture to handle complex spatio-temporal relationships, AI-enhanced analysis to improve detection accuracy;

[0154] S5.7, crack / collapse detection model based on YOLOv8+Transformer hybrid architecture: Through the Transformer architecture to handle complex spatio-temporal relationships, AI-enhanced analysis to improve detection accuracy;

[0155] S5.8, monitoring point density and harsh environment adaptation: When the monitoring point density exceeds 1000 points / km², the system automatically switches to clustering display mode; In harsh environments, low-light enhancement is performed, and switching to STARVIS sensor mode combined with Retinex algorithm to improve picture quality; In case of communication interruption, the edge node caches the last 15 minutes of data, and when the network is restored, the data is transmitted continuously;

[0156] S5.9, Hololens2 superimposes real-time displacement data, and real-time displacement data is superimposed on the field of view through Hololens2, and key data of warning events are chained to meet regulatory audit requirements.

[0157] It can be understood that in the present embodiment, through the three-dimensional visualization platform, the displacement heat map, real-time video and warning area annotation are superimposed in the BIM+GIS digital twin scene. For example, GPU accelerated rendering is achieved using WebGL shaders, and real-time updates of multiple monitoring points are supported. At the same time, when the alarm is triggered, the video is automatically captured to record the disaster development process.

[0158] Step 6: Intelligent early warning and decision-making: through big data analysis and artificial intelligence algorithms, real-time calculation and trend analysis are performed on the monitoring data to generate early warning information and automatically trigger the alarm mechanism. When the displacement rate exceeds the threshold or the AI identifies the collapse precursor characteristics, the emergency response mechanism is triggered, and the warning is automatically pushed to the emergency management platform, and the UAV inspection plan is started simultaneously.

[0159] Specifically, the step 6: intelligent early warning and decision-making: through big data analysis and artificial intelligence algorithms, real-time calculation and trend analysis are performed on the monitoring data to generate early warning information and automatically trigger the alarm mechanism. When the displacement rate exceeds the threshold or the AI identifies the collapse precursor characteristics, the emergency response mechanism is triggered, and the warning is automatically pushed to the emergency management platform, and the UAV inspection plan is started simultaneously, including:

[0160] Provide monitoring threshold customization function through Beidou disaster monitoring scene monitoring, realize accurate control of tower risk through red, orange, yellow and blue level division;

[0161] Provide scene visualization, through South Grid intelligent map dotting, sensor three-dimensional model erection function, visualize the tower position, risk level, real-time alarm and real-time monitoring data curve information of the installed Beidou disaster monitoring terminal, realize remote real-time monitoring of tower operation status;

[0162] Provide monitoring report export function, generate special monitoring report for key controlled line towers, and improve the geological disaster risk control work of transmission lines.

[0163] It can be understood that in the present embodiment, the high-precision positioning capability of the Beidou system, the Internet of Things technology and the AI algorithm are fully utilized to realize the intelligent management of the whole chain of geological disaster monitoring. This not only improves the efficiency and accuracy of disaster warning, but also provides strong support for disaster emergency response, and achieves remarkable results in the application of landslide, debris flow and other geological disaster monitoring.

[0164] Embodiment two

[0165] As shown in Figure 4 The present application provides a Beidou disaster displacement and image video monitoring fusion system based on a high-reliability communication link, which is applied to the Beidou disaster displacement and image video monitoring fusion method based on a high-reliability communication link as described in embodiment one, and includes a perception layer, a transmission layer, a processing layer, an analysis layer, a platform layer and an application.

[0166] It can be understood that in the present embodiment, the perception layer is used to collect millimeter-level displacement, inclination, five-direction high-definition video in real time through the Beidou monitoring device; access micro-meteorological and wire clip temperature data, and uniformly package through the data gateway.

[0167] It can be understood that in the embodiment, the transmission layer is used for high-reliability data transmission: adopts APN private line transmission, all data are marked with Beidou time stamp to ensure timing alignment; and provides centimeter-level RTK differential service for the unmanned aerial vehicle through a temporary reference station mode.

[0168] It can be understood that in the embodiment, the processing layer is used for multiplexing the Beidou ground enhancement station network that has been constructed based on the Beidou VRS virtual reference station and the long baseline monitoring solution technology, constructing a virtual reference station to replace a traditional physical reference station, establishing an error correction model through observation data of multiple reference stations to generate virtual observation values for real-time dynamic RTK solution.

[0169] It can be understood that in the embodiment, the analysis layer is used for cloud intelligent analysis, PWV inversion of three-dimensional water vapor field based on slant path tropospheric delay, and realization of tower-level rainfall prediction; and risk assessment report generation based on AI algorithm fusion of displacement rate, inclination mutation and video features.

[0170] It can be understood that in the embodiment, the platform layer is used for multi-modal monitoring: through a three-dimensional visualization platform, superimposing displacement heat map, real-time video and warning area annotation in a BIM+GIS digital twin scene, through 360° panoramic splicing and downward wide-angle monitoring, alarm triggering video automatic snapshot.

[0171] It can be understood that in the embodiment, the application layer is used for intelligent early warning and decision making: through big data analysis and artificial intelligence algorithm, real-time solution and trend analysis of monitoring data, generation of early warning information and automatic triggering of alarm mechanism, automatic pushing of alarm to an emergency management platform when the displacement rate exceeds a threshold value or AI identifies collapse precursor features to trigger an emergency response mechanism, and synchronous starting of an unmanned aerial vehicle inspection plan.

[0172] Figure 5 The electronic device provided in an embodiment of the present application. As shown in Figure 5 , the electronic device at least includes the following parts: a processor 101 and a memory 100, a communication interface 103, and a bus 102.

[0173] In the embodiment of the present application, the memory 100 is used to store processor 101 executable instructions, and the processor 101 is configured to execute instructions to implement the device module for Beidou disaster displacement and image video monitoring fusion based on high-reliability communication link as shown in Figure 5 .

[0174] In the embodiment of the present application, a computer readable storage medium includes instructions, and the instructions instruct the device to execute the method as in the first aspect. For example, the instructions instruct the device to execute the method as shown in the flow steps in Figure 1 .

[0175] The program that works in the electronic device according to the embodiment of the present application can be a program that controls a central processing unit (CPU) or the like to realize the functions of the above-described embodiments according to one aspect of the present application (a program that causes a computer to function). Then, the information processed by these devices is temporarily stored in a random access memory (RAM) when it is processed, and then stored in various ROMs such as a read only memory (Flash ROM), a hard disk drive (HDD), and the like, and read out, corrected, and written by the CPU as needed.

[0176] Note that a part of the electronic device according to the above-described embodiments can also be realized by a computer. In this case, a program for realizing the control function can be recorded in a computer-readable recording medium, and realized by reading the program recorded in the recording medium into a computer and executing it.

[0177] Note that the "computer" referred to here means a computer built in the electronic device, and a computer including hardware such as an OS and a peripheral device. Further, the "computer-readable recording medium" means a removable medium such as a floppy disk, a magneto-optical disk, a ROM, a CD-ROM, and the like, a storage device such as a hard disk built in the computer.

[0178] Further, the "computer-readable recording medium" can include a medium that dynamically stores a program for a short period of time, such as a communication line in the case of transmitting a program via a network such as the Internet or a communication line such as a telephone line, and a medium that stores a program for a fixed period of time, such as a volatile memory inside a computer that is a server or a client in this case. Further, the above-described program can be a program for realizing a part of the above-described functions, and can also be a program that can realize the above-described functions by being combined with a program already recorded in a computer.

[0179] Further, the electronic device according to the above-described embodiments can also be realized as an assembly (device group) constituted by a plurality of devices. Each device constituting the device group can have a part or all of each function or each function block of the electronic device according to the above-described embodiments. As the device group, all of each function or each function block of the electronic device can be possessed.

[0180] Those skilled in the art will recognize that the above embodiments are merely illustrative of the present application and should not be taken as limiting. Rather, all changes and variations that are within the spirit of the present application will be considered as falling within the scope of the present application.

Claims

1. A Beidou earthquake displacement and image video monitoring fusion method based on a high-reliability communication link, characterized in that, The method comprises: Step 1: Multi-source data acquisition, real-time acquisition of millimeter-level displacement, inclination, five-direction high-definition video by Beidou monitoring device; access to microclimate, clip temperature data, unified packaging through data gateway; Step 2: High-reliability data transmission: adopt APN special line transmission, all data are marked with Beidou time stamp to ensure time sequence alignment; provide centimeter-level RTK differential service for unmanned aerial vehicle through temporary reference station mode; Step 3: Based on Beidou VRS virtual reference station and long baseline monitoring solution technology, reuse the Beidou ground enhancement station network which has been completed, build virtual reference station instead of traditional physical station, through the observation data of multiple reference stations, establish error correction model to generate virtual observation value for real-time dynamic RTK solution; Step 4: Cloud intelligent analysis, based on the slant path tropospheric delay PWV inversion three-dimensional water vapor field, realize the tower level rainfall prediction; based on AI algorithm fusion displacement rate, inclination mutation, video features, generate risk assessment report; Step 5: Multi-modal monitoring: through three-dimensional visualization platform, superimpose displacement heat map, real-time video and warning area label in BIM+GIS digital twin scene, through 360° panoramic splicing, downward wide-angle monitoring, alarm triggered video automatic snapshot; Step 6: Intelligent early warning and decision-making: through big data analysis and artificial intelligence algorithm, real-time solution and trend analysis of monitoring data, generate early warning information and automatically trigger alarm mechanism, when displacement rate exceeds threshold or AI identifies collapse precursor characteristics to trigger emergency response mechanism, automatically push alarm to emergency management platform, synchronously start unmanned aerial vehicle inspection plan.

2. The Beidou earthquake displacement and image video monitoring fusion method based on a high-reliability communication link according to claim 1, characterized in that, The step 1: multi-source data acquisition, real-time acquisition of millimeter-level displacement, inclination, five-direction high-definition video by Beidou monitoring device; Access to microclimate, clip temperature data, unified packaging through data gateway, including: Deploy Beidou disaster monitoring comprehensive device on tower and slope, real-time acquisition of millimeter-level high-precision displacement settlement, inclination, image video data, wherein the Beidou disaster monitoring comprehensive device is based on GNSS high-precision receiver positioning technology, low-power high-precision GNSS chip and front, rear, left and right five-channel camera, double-channel 180° panoramic high-definition image monitoring splicing, which integrates MEMS sensor technology, narrowband communication technology and embedded system hibernation wake-up technology, can provide millimeter-level high-precision displacement monitoring information and 360° panoramic image video monitoring all day round; The Beidou disaster monitoring comprehensive device also has data gateway function, can access microclimate, clip temperature sensor data, and select and apply according to monitoring scene; Through Internet of Things APN special line, return data to unified Internet of Things platform, based on Beidou platform, Nanwang Zhi Kan platform positioning and mapping capability, carry out multi-source data fusion application through system, support digital production application. 3.The Beidou earthquake displacement and image video monitoring fusion method based on high reliability communication link according to claim 1, characterized in that, The step 3: based on Beidou VRS virtual reference station and long baseline monitoring solution technology, multiplexing the Beidou ground enhancement station network that has been completed, constructing virtual reference station to replace traditional physical base station, through the observation data of multiple reference stations, establishing error correction model to generate virtual observation value, which is used for real-time dynamic RTK solution, including: Step 3.1: data acquisition through physical reference station network, multiplexing existing Beidou ground enhancement station needs to meet: station spacing ≤ 30 km; equipped with dual-frequency or multi-frequency Beidou receiver; data sampling rate ≥ 1 Hz, real-time backhaul of original observation value, time synchronization between stations is realized by PTP protocol; Step 3.2: error model is obtained by network RTK error modeling, wherein the formula of carrier phase observation value is: ， wherein, is a carrier phase observation, is a receiver-to-satellite range, is an ionospheric delay, is a tropospheric delay, is a speed of light, and are clock errors of the receiver and satellite, respectively, is a satellite orbit error, is a multipath effect error, is a carrier phase wavelength, is an integer ambiguity; Step 3.3: through Geometry-Free combination extraction, regional linear interpolation or low-order curved surface fitting is used to correct the observation value of reference station, and the formula of corrected carrier phase observation value is: ， wherein, and are the corrections for ionospheric and tropospheric delays, respectively, and are the corrections for receiver and satellite clock errors, respectively; Step 3.4: based on the observation value of the main reference station, combined with the geometric correlation term and the atmospheric delay correction, the carrier phase observation value of the virtual reference station is generated, and the formula is as follows: ， wherein is a carrier phase observation, is an observer station observation, is a geometric range error gradient, is an atmospheric delay error gradient.

4. The Beidou earthquake displacement and image video monitoring fusion method based on a high-reliability communication link according to claim 3, characterized in that The error model is corrected using LAMBDA algorithm, including: Step 4.1: error modeling: Step 4.1.1: ionospheric delay, ionospheric delay is extracted by dual-frequency geometry-free combination, and a low-order polynomial regional space model is established, wherein the ionospheric delay formula is: ， wherein, is an ionospheric delay value, and are the frequencies of the two frequencies, respectively, and are the carrier phase observations in cycles, and are the carrier phase wavelengths corresponding to the carrier phase observations, respectively. Step 4.1.2: tropospheric delay: dry component is corrected by Saastamoinen model, and wet component is estimated by random walk process; Step 4.1.3: orbit / clock difference: precise ephemeris product or inter-station difference is used for elimination; Step 4.2: LAMBDA ambiguity fixing; Step 4.2.1: Integer Gauss transform on the reducing the correlation between ambiguities, the transform formula is: ， wherein is an initial covariance matrix, is a diagonal matrix, is a decorrelation matrix, ; Transformed ambiguities: ; Step 4.2.2: Search for the optimal integer solution in the transformed space by integer least square search : , Bootstrapping is used to accelerate the computation with a shrinking search strategy. Step 4.2.3: Inverse transform and validation, transform back to original space: Inverse transform back to original space: ; Validate fixed reliability by ratio test Ratio Tes Step 4.3: Fixing the ambiguity error correction, fixing the ambiguity Substitute the observation equation, and calculate the residual term. Step 4.4: Update the covariance matrix with the ionospheric / tropospheric model parameter corrections from the residuals and proceed to the next epoch solution for error model iteration optimization.

5. The Beidou earthquake displacement and image video monitoring fusion method based on a high-reliability communication link according to claim 1, characterized in that, The step 4: cloud intelligent analysis, based on slant path tropospheric delay PWV inversion three-dimensional water vapor field, realizing tower level rainfall prediction; Based on AI algorithm fusion displacement rate, angle mutation, video features, risk assessment report is generated, including: Cloud intelligent analysis based on Beidou No.3 PPP-B2b precise point positioning service, combined with meteorology and GNSS technology, realizes tower level rainfall prediction and risk assessment report generation, including: Using Beidou No.3 PPP-B2b service, atmospheric precipitable water PWV is inverted through observation data, and three-dimensional water vapor field of the monitoring area is reconstructed by combining three-dimensional water vapor tomography model, realizing high-precision water vapor prediction and fine prediction of surrounding rainfall; Beidou disaster comprehensive monitoring device can be quickly deployed as a temporary reference station, real-time backhaul of observation data to Beidou platform, becoming a supplement to the reference station network, improving the availability of differential service, providing centimeter-level real-time dynamic positioning service for unmanned aerial vehicle inspection; Based on AI algorithm fusion displacement rate, angle mutation, video features multi-dimensional data, more accurate risk assessment report is generated.

6. The Beidou earthquake displacement and image video monitoring fusion method based on a high-reliability communication link according to claim 1, characterized in that, The step 5: multi-modal monitoring: through three-dimensional visualization platform, displacement heat map, real-time video and warning area annotation are superimposed in BIM+GIS digital twin scene, through 360° panorama splicing, downward wide-angle monitoring, alarm triggering video automatic snapshot, including: S5.1, Construct a multi-modal data fusion architecture, which includes data layer integration. The data types in the data layer integration include: Beidou displacement data, three-dimensional geological model, geographic space base map, real-time video stream, and meteorological data. The fusion rules include: spatial alignment and time synchronization. The spatial alignment is achieved through seven-parameter conversion between Beidou CGCS2000 coordinate system and BIM local coordinate system to achieve millimeter-level matching. The time synchronization includes using NTP+PTP hybrid protocol to ensure that the timestamp error between video frame and displacement data is less than 10ms; S5.2, Displacement trend prediction and target identification: Construct a multi-modal fusion model, in which the displacement trend prediction uses LSTM neural network to analyze time series data and combines with InSAR historical data to correct model error. Video target identification is based on YOLOv7 algorithm to detect crack expansion and rock mass sliding, and matches with three-dimensional oblique photography model for positioning. Risk level assessment generates risk assessment matrix through displacement rate, rainfall and crack width multi-index, and outputs red / orange / yellow / blue four-level warning. The multi-modal fusion model evaluates multi-modal data and outputs the evaluation results; S5.3, Generate displacement heat map: Generate displacement heat map through three-dimensional visualization platform key technology, use WebGL shader to realize GPU accelerated rendering, and support real-time update of multiple monitoring points; S5.4, Build BIM+GIS digital twin scene: Engine selection includes Cesium for global terrain and satellite image base, Three.js for loading BIM model and realizing local high-precision rendering, hierarchical display control is realized through layer display logic, and seamless fusion of three-dimensional scene and video is realized; S5.5, Panoramic monitoring integration: Use SIFT feature matching and GPU accelerated stitching technology of OpenCV, solve camera external parameters through PnP algorithm, map video pixel coordinates to three-dimensional scene coordinates, and realize panoramic video stitching and real-time monitoring video and three-dimensional model fusion; S5.6, Set multi-level warning trigger conditions: When Beidou displacement exceeds the threshold and warning level reaches yellow and above, the system will call PTZ camera preset position to capture key frames and store them, and at the same time, analyze cracks or collapse through AI and generate reports to push to BIM label, realize multi-modal data linkage and interaction; S5.7, Crack / collapse detection model based on YOLOv8+Transformer hybrid architecture: Process complex spatio-temporal relationship through Transformer architecture, enhance AI analysis, and improve detection accuracy; S5.8, Monitor point density and harsh environment adaptation: When the monitoring point density exceeds 1000 points / km², the system automatically switches to clustering display mode; In harsh environment, low light enhancement is carried out, and STARVIS sensor mode is switched to improve picture quality combined with Retinex algorithm; In case of communication interruption, edge node caches the latest 15 minutes of data, and resumes transmission when network is restored; S5.9, Hololens2 superimposes real-time displacement data, superimposes real-time displacement data into the field of view through Hololens2, and chains key data of early warning events to meet regulatory audit requirements.

7. The Beidou earthquake displacement and image video monitoring fusion method based on a high-reliability communication link according to claim 1, characterized in that, The step 6: intelligent early warning and decision: through big data analysis and artificial intelligence algorithm, the monitoring data is solved and trend analyzed in real time, the early warning information is generated and the alarm mechanism is automatically triggered, when the displacement rate exceeds the threshold or the AI identifies the collapse precursor characteristics, the emergency response mechanism is triggered, the alarm is automatically pushed to the emergency management platform, and the unmanned aerial vehicle inspection plan is started synchronously. Provide monitoring threshold customization function through Beidou disaster monitoring scene monitoring, realize accurate control of tower risk through red, orange, yellow and blue level differentiation; Provide scene visualization through NGS panoramic map dotting and sensor three-dimensional model erection function, visualize the tower location, risk level, real-time alarm and real-time monitoring data curve information of the tower where the Beidou disaster monitoring terminal is installed, and realize remote real-time monitoring of the tower operation status; Provide monitoring report export function, generate special monitoring report for key controlled line towers, and improve the risk control work of power transmission line geological disasters.

8. A Beidou earthquake displacement and image video monitoring fusion system based on a high-reliability communication link, applied to the Beidou earthquake displacement and image video monitoring fusion method based on a high-reliability communication link according to any one of claims 1 to 7, characterized in that, Including: Sensing layer: real-time collection of millimeter-level displacement, inclination, and five-direction high-definition video through Beidou monitoring devices; Access microclimate and wire clip temperature data, and unify encapsulation through data gateway; Transmission layer: high-reliability data transmission: APN dedicated line transmission is adopted, all data is marked with Beidou time stamp to ensure time sequence alignment; Provide centimeter-level RTK differential service for unmanned aerial vehicles through temporary reference station mode; Processing layer: based on Beidou VRS virtual reference station and long baseline monitoring solution technology, reuse the Beidou ground enhancement station network that has been completed, build virtual reference station instead of traditional physical station, through the observation data of multiple reference stations, establish error correction model, and generate virtual observation value for real-time dynamic RTK solution; Analysis layer: cloud intelligent analysis, based on slant path troposphere delay PWV inversion three-dimensional water vapor field, realize tower level rainfall prediction; based on AI algorithm fusion displacement rate, inclination mutation, video features, generate risk assessment report; Platform layer: multi-modal monitoring: through three-dimensional visualization platform, superimpose displacement heat map, real-time video and warning area annotation in BIM+GIS digital twin scene, through 360° panorama splicing, downward wide-angle monitoring, alarm triggered video automatic snapshot; Application layer: intelligent early warning and decision: through big data analysis and artificial intelligence algorithm, the monitoring data is solved and trend analyzed in real time, the early warning information is generated and the alarm mechanism is automatically triggered, when the displacement rate exceeds the threshold or the AI identifies the collapse precursor characteristics, the emergency response mechanism is triggered, the alarm is automatically pushed to the emergency management platform, and the unmanned aerial vehicle inspection plan is started synchronously.

9. An electronic device, comprising: Including: A processor; A memory for storing processor-executable instructions; Wherein the processor is configured to implement the Beidou disaster displacement and image video monitoring fusion method based on high-reliability communication link as claimed in any one of claims 1 to 7 when executing the instructions.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program, and the program instructs the device to perform the Beidou disaster displacement and image video monitoring fusion method based on the high-reliability communication link according to any one of claims 1 to 7.

Images