CN117238108A - Safety monitoring and early warning system and method for coastline of bedrock of tourist island - Google Patents
Safety monitoring and early warning system and method for coastline of bedrock of tourist island Download PDFInfo
- Publication number
- CN117238108A CN117238108A CN202311107475.6A CN202311107475A CN117238108A CN 117238108 A CN117238108 A CN 117238108A CN 202311107475 A CN202311107475 A CN 202311107475A CN 117238108 A CN117238108 A CN 117238108A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- value
- data
- change
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000008859 change Effects 0.000 claims abstract description 97
- 230000000694 effects Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000006073 displacement reaction Methods 0.000 claims abstract description 13
- 238000011161 development Methods 0.000 claims abstract description 8
- 230000008439 repair process Effects 0.000 claims abstract description 8
- 230000037081 physical activity Effects 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 33
- 238000012360 testing method Methods 0.000 claims description 28
- 238000003066 decision tree Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 239000011435 rock Substances 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 239000013307 optical fiber Substances 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract 1
- 238000004590 computer program Methods 0.000 description 10
- 230000003628 erosive effect Effects 0.000 description 5
- 230000007774 longterm Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006253 efflorescence Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 206010037844 rash Diseases 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
The application belongs to the technical field of safety monitoring of travel routes, and discloses a safety monitoring and early warning system and method for a coastline of a bedrock of a travel island. The system comprises: the data acquisition module is used for acquiring monitoring data information such as fracture activity, spherical weathered body activity, earth surface displacement, stress and strain, rainfall, sea wave power and the like. The data processing module is used for receiving the collected data information, storing and calculating the data. And the dangerous alarm module sets different types of observation value change thresholds according to different monitoring object entities and combining actual conditions. The potential safety hazard prediction module divides the frequently-occurring alarm area into key monitoring areas, predicts the future change condition of the area, combines the actual condition of island bedrock shoreline travel development, and gives out potential safety hazard clearing and protection repair prompts. The application provides real-time monitoring data for island shoreline protection, restoration and island ecological civilization construction.
Description
Technical Field
The application belongs to the technical field of shoreline safety monitoring, and particularly relates to a system and a method for monitoring and early warning of shoreline safety of bedrock of a tourist island.
Background
The island bedrock shoreline has rich tourism resources, comprises various geological remains resources such as rich rock, sea cliffs, sea holes and the like, beautiful coastal zones, human landscapes, fishing leisure fisheries and the like, is a section with highest island tourism development degree and utilization degree, and is also the island tourism line most favored by tourists.
However, island bedrock shorelines are subjected to double influences of sea wave erosion and wind-break action all the year round, so that geological disasters such as shoreline erosion, expansion of fracture scale and rock collapse are easily caused. The development of the travel route of the island-based coastal section requires manual rock drilling and open-circuiting, and the artificial engineering excavation can cause partial rock collapse hidden trouble; the breaking activity can cause spherical efflorescence in the breaking dense development area, the formed spherical efflorescence can be unstable and suddenly roll off to bring unexpected injury to tourists and island residents. Limited monitoring equipment on island travel routes can perform key monitoring on tourist activity areas, but relatively slow changes such as collapse, rolling stones, fracture activities, island land damage, erosion amount of bedrock shorelines and the like are difficult to effectively monitor and predict.
Through the above analysis, the problems and defects existing in the prior art are as follows: the prior art is mainly used for monitoring landslide bodies of slopes and constructing a slope monitoring system, and has poor video monitoring effect; in the prior art, different monitoring modes are not used for monitoring different monitoring, and the aim of early warning in time cannot be achieved; in the prior art, the potential safety hazard prediction effect is poor, so that the potential safety hazard prediction of mutation is inaccurate.
Disclosure of Invention
In order to overcome the problems in the related art, the disclosed embodiment of the application provides a system and a method for monitoring and early warning of the coastline of the bedrock of the tourist island.
The technical scheme is as follows: a travel island bedrock shoreline safety monitoring and early warning system establishes a live-action three-dimensional model by combining an unmanned aerial vehicle oblique photography technology to realize visual potential safety hazard monitoring, early warning and prediction, and specifically comprises the following steps:
the data acquisition module is used for crack activity monitoring, spherical weathered body activity monitoring, earth surface displacement monitoring, stress and strain monitoring, rainfall monitoring, sea wave power monitoring and the like;
the data processing module is used for receiving the acquired data information, storing and calculating the data, and comparing the acquired observation index values of the space coordinate position, the stress value, the deformation value, the rainfall and the like with the initial value to obtain a change value 1; comparing the obtained variable with the last recorded value to obtain a variable value 2, and displaying the obtained two types of variable quantities in a chart form;
the dangerous alarm module is used for setting different types of observed value change thresholds according to different monitoring entities, carrying out dangerous alarm when the monitored value change exceeds the thresholds, feeding back abnormal values and archiving;
the potential safety hazard prediction module divides the frequently-occurring alarm area into a key monitoring area, predicts the future change trend of the area by combining historical monitoring data, and gives out potential safety hazard clearing and protection repair prompts; if the potential safety hazard is cleared, making a prediction again.
Further, in the data acquisition module, the crack activity monitoring is to monitor crack dislocation, width expansion variables and newly formed cracks aiming at cracks developed by a bedrock shoreline and a tour route;
the earth surface displacement monitoring is to install monitoring equipment aiming at a slope, a steep rock exposed surface and a weathered spherical weathered body which are about to collapse on a travel route, and the displacement change information is monitored by combining a positioning system; for a travel road built at sea, carrying out full coverage monitoring by adopting distributed optical fibers;
stress and strain monitoring is carried out aiming at bridges, view platforms and tourist facilities in fracture distribution areas erected on tourist roads, and the stress state and strain condition of each tourist facility are monitored;
the rainfall monitoring is to install monitoring equipment in an exposed slope area and a vegetation coverage area of a travel route to obtain rainfall change information;
the sea wave power monitoring is to erode a bedrock land section developed into a travel route by sea waves, and install monitoring equipment in a fracture dense development area to obtain dynamic change data of sea wave impact force.
Further, the data acquisition site and the monitoring site in the data acquisition module are displayed on the live-action three-dimensional model according to the actual positions.
Another object of the present application is to provide a method for monitoring and early warning of the coastline of tourist island bedrock, the method is operated in the system for monitoring and early warning of the coastline of tourist island bedrock, the method comprises:
s1, collecting monitoring information of crack activity, spherical weathered body activity, earth surface displacement, stress and strain, rainfall and sea wave power;
s2, transmitting the acquired data to a data processing module through an optical fiber, storing and calculating the data, comparing the acquired space coordinate position, stress value and observation index value of rainfall with initial values, and comparing the initial values with the last recorded value to obtain variation and displaying the variation in a chart form;
s3, setting different types of observed value change thresholds according to different monitoring entities, and carrying out dangerous alarm when the monitored value change exceeds the thresholds, and simultaneously feeding back and archiving abnormal values;
s4, dividing the frequently-occurring alarm area into a key monitoring area, and predicting the future change condition of the area by combining historical monitoring data, and carrying out potential safety hazard removal and protection repair prompt; if the potential safety hazard is cleared, making a prediction again.
In step S2, comparing the obtained space coordinate position, stress value, and observation index value of rainfall with initial values, and comparing with the last recorded value, specifically including:
step one: inputting a current observation value X and an initial value T of a current observation index; obtaining the variation X of the relative initial value 1 And the amount of change X relative to the last recorded value 2 ；
Step two: will change the amount X 1 And X 2 Comparing and checking with a set certain observation element threshold Y;
step three: according to the designated number N of stage decision trees in the current stage stage Using label as a fitting threshold value, and sequentially establishing each decision treeFitting a change function change value of the current model;
step four: the model fitting of the current stage is finished, a fitting change value res, res=actual-pred, pred is a predicted value of the current stage on training data X, and the fitting change value res is calculated; the expression is:
where rate is the learning rate,for the i-th decision tree in the current stage +.>The predicted value on the training set X is updated, and the data value actual=res to be fitted is updated; n_evantizers are random forest parameters;
step five: fitting a variation value res to the variation X of the last recorded value, and carrying out Jarque-Bera test;
step six: when the change function of the evaluation function on the given test set T does not descend any more in the designated early_stop stage number, model training is stopped in time to obtain the optimal iteration stage number N of the model, model training is completed, and the step seven is skipped, otherwise, if the change function on the test set T continues to descend, the step four is skipped, and stage iteration is continued;
step seven: and predicting a test set, and obtaining a test set prediction result pred according to the optimal iteration stage number N of the model.
The third step and the seventh step are actually an intermediate calculation process, the threshold value of the variation is obtained through calculation, the variation threshold value of different types of observation values is set according to different monitoring entities for the next step S3, and when the variation of the monitoring values exceeds the threshold value, dangerous alarm is carried out, so that technical support is provided.
In the second step, the original threshold y of the variation X of the last recorded value is checked, and the specific implementation steps are as follows:
(1) Calculating the data distribution skewness S according to the change amount threshold of the last recorded value and the following formula:
wherein actual is a data threshold to be fitted, mean is a sample threshold mean, size is a sample capacity, and std is a sample threshold standard deviation;
(2) Calculating the data distribution kurtosis K according to the change amount threshold value of the last recorded value by the following formula:
(3) The chi-square statistic JB is constructed according to the following formula:
the size is the sample capacity, S is the data distribution skewness, and K is the data distribution kurtosis;
checking the significance of the square statistic JB, and checking the degree of bias of the square statistic JB to determine whether to change the data; entering (4) if the chi-square statistic JB exceeds a set threshold, otherwise entering (5);
(4) Judging whether the data is beyond a preset threshold value, judging whether the upper limit of the change times of the data reaches the preset upper limit of the change times of the data, if the upper limit of the change times is diff, if the diff is less than or equal to 0, jumping to (5), otherwise updating the diff value to be diff-1, performing boxcox change on the data, performing lambda value traversal through the following formula, and generating a change expression by lambda with the maximum data threshold value label likelihood function L after the selection and the change:
wherein actual is a data threshold to be fitted, a new data threshold is obtained, and is used as a first-stage fitting threshold label, and a current-stage judgment variable jud [1] =true is set;
(5) The data bias is not obvious or the data threshold conversion times reach the target upper bound, the original data threshold y is taken as a first stage fitting threshold label, and a current stage judgment variable jud [1] =false is set.
In the seventh step, according to the optimal iteration stage number N of the model, a test set prediction result pred is obtained, which specifically includes:
(1) Calculating a predicted value pred of the stage model in the current stage on a test set T, wherein the expression is as follows:
where pred is the test set prediction result, rate is the learning rate,decision tree for phase j->Is predicted by->The inverse of the pre-transformation for the phase j threshold is shown in the following specific expression:
wherein F is stage -1 Jud [ j ] as an inverse transform function of the current stage model]Determining a variable, sigmod, for the current phase j -1 Inverse transformation for sigmoid (& gt) transformation, boxcos -1 (. Cndot.) is the inverse of the boxcos (-) transform;
prediction result of stage jboxcos -1 The (-) expression is as follows:
sigmod -1 the (-) expression is as follows:
(2) Calculating the current-stage change function value loss=l (pred, y T )，y T For the test set Tprimitive threshold, L (·) is the change function used by the system, and for the regression problem is the square change function, where loss= (pred-y) T ) 2 。
In step S4, the frequent occurrence alarm area is divided into important monitoring areas, and the future change condition of the areas is predicted by combining the history monitoring data, including:
acquiring image sequences acquired at different angles in a frequently-occurring alarm region as an input set, and acquiring feature matching point pairs of images through feature extraction and matching, wherein the feature matching point pairs are subjected to evolution processing;
according to the geological evolution and the security threat model, selecting characteristic points of the candidate images as seed points to carry out matching evolution on surrounding neighborhood of the candidate images and filtering the candidate images to obtain evolution matching point pairs;
calibrating an image acquisition instrument, and combining the matching point pairs to obtain the internal and external parameters of the image acquisition instrument; obtaining instrument parameters and matching point pairs according to the images, and recovering three-dimensional model points;
reconstructing by adopting geological evolution and a security threat model, selecting seed model points to generate an initial point, and evolving in a grid neighborhood of the initial point;
and filtering the error according to the constraint condition to obtain an accurate evolution three-dimensional point cloud model.
Further, the geological evolution and security threat model specifically comprises:
for each feature point f of the reference image, finding a corresponding candidate matching point f' in the candidate image according to epipolar constraint; using geological evolution and a security threat model, selecting zero-mean normalized cross-correlation coefficient ZNCC as an objective function, calculating ZNCC values of matching point pairs, and sorting according to the sizes of the ZNCC values:
wherein x is the correspondence of the image feature point f in the imageCoordinate information, x 'is coordinate information corresponding to the image feature point f' in the image; i (x) and I (x ') represent pixel intensities at the x-coordinate and the x' -coordinate;and->Representing the average pixel brightness of an image window centered at x and an image window centered at x';
selecting a characteristic point larger than a threshold value mu 1 as a seed point to carry out neighborhood evolution, and selecting a characteristic point larger than a threshold value mu 2 as a reserve matching point mu 1> mu 2; for all matching points of the reference image, establishing one-to-many matching in the size of a fixed window in the center of the candidate image; for the points of the reference image, matching the points of other images, and establishing mixed matching of all the points in the window; on the premise of meeting parallax gradient constraint and confidence constraint, ZNCC of an evolution matching point pair is calculated, evolution points larger than a threshold value mu 3 are screened to be used as seed points for secondary evolution, evolution points larger than a threshold value mu 4 are screened to be used as reserve matching points, and mu 3 is larger than mu 4;
assuming u 'and u are a pair of image matching point pairs, x' and x are another adjacent image matching point pair, the parallax gradient constraint formula is:
||(u′-u)-(x′-x)|| ∞ ≤ε
where ε is the threshold of parallax gradient; parallax gradient constraints reduce image matching ambiguity;
the formula of the confidence constraint is:
s(x)＝max{|I(x+Δ)-I(x)l，Δ∈{(1，0)，(-1，0)，(0，1)，(0，-1)}}
the confidence constraint is adopted to improve the reliability of the matching evolution and obtain the evolution matching point pair.
Further, the process of calibrating the image acquisition instrument label is to calculate the internal parameters of the image acquisition instrument according to the imaging principle of the image acquisition instrument; according to the characteristic points and matching of the image sequence, selecting two input images as reference, and calculating a basic matrix F of a reference image point pair, wherein F satisfies the equation x 'fx=0, and x' and x are a pair of image matching points; estimating initial values K' and K of internal reference matrixes of the reference image pair, calculating an essential matrix of the image point pair and extracting rotation and translation components; the internal and external parameters and feature matching point pairs of the image acquisition instrument are known, and three-dimensional model points corresponding to the feature points are obtained by using triangulation.
By combining all the technical schemes, the application has the advantages and positive effects that: the application provides a safety monitoring and early warning system for a coastline of a tourist island bedrock, which combines actual conditions of the coastline of the island bedrock for the tourist, so as to effectively ensure the safety of passengers and residents of the island and provide real-time monitoring data for the protection of the coastline.
Innovations in safety monitoring systems: in the past, the safety monitoring of the island is focused on the side slope after artificial quarrying, and mainly monitors the landslide body of the side slope and constructs a side slope monitoring system. The monitoring and early warning system provided by the application mainly aims at the tour route developed by the tour island bedrock shoreline, and has a prediction function besides real-time monitoring. Meanwhile, the defect that many tourist islands only use video monitoring as a monitoring means can be well made up.
Improvement of a data acquisition module: (1) the monitoring content is more comprehensive. The monitoring content is added with factors such as fracture activity, sea wave power and the like, so that the monitoring content is more systematic. The fracture activity and the sea wave dynamic environment are key influencing factors for erosion of bedrock shoreline. Particularly monitors the stability of tourist facilities and viewing platforms with larger influence of fracture; the stability of the spherical weathered body under the dual influence of fracture and weathering was monitored. And (2) combining the data acquisition point surfaces. Aiming at key landslide areas, rock collapse areas, spherical weathered rock blocks, tourist facilities and the like, point-shaped monitoring stations are arranged; for the broken dense distribution areas and the tourist roads, distributed optical fibers are adopted for continuous layout, so that the purpose of timely early warning is achieved.
Improvement of a potential safety hazard prediction module and a data processing module: most monitoring and early warning systems do not have embedded safety hazard prediction functions. Spherical weathered bodies, fissure activity and bedrock shoreline erosion are long-term acting processes, and the amount is a long-term accumulated process, but abrupt changes are sudden, so that prediction of potential safety hazards based on long-term monitoring data is very important. To realize the process, on one hand, accurate data is required, and long-term data accumulation is required, so that the data processing module is high in requirement; on the other hand, a process model for the occurrence and development of potential safety hazards needs to be built. The application constructs a geological evolution and safety threat model of the spherical weathered body. According to the method, the coordinate position and the relative initial value obtained by calculating data and the change quantity relative to the last recorded value are calculated, a frequently-occurring alarm area is divided into key monitoring areas, and future change conditions of the areas are predicted by combining historical monitoring data to obtain an accurate evolution three-dimensional point cloud model.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure;
FIG. 1 is a schematic diagram of a safety monitoring and early warning system for a coastline of a bedrock of a tourist island, which is provided by the embodiment of the application;
FIG. 2 is a schematic diagram of a safety monitoring and early warning system for a coastline of a bedrock of a tourist island, which is provided by the embodiment of the application;
FIG. 3 is a flow chart of a method for monitoring and early warning of the coastline safety of the bedrock of the tourist island, which is provided by the embodiment of the application;
in the figure: 1. a data acquisition module; 2. a data processing module; 3. a hazard alarm module; 4. and a potential safety hazard prediction module.
Detailed Description
In order that the above objects, features and advantages of the application will be readily understood, a more particular description of the application will be rendered by reference to the appended drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The application may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit or scope of the application, which is therefore not limited to the specific embodiments disclosed below.
In embodiment 1, as shown in fig. 1, the embodiment of the application provides a safety monitoring and early warning system for a coastline of a bedrock of a tourist island, which comprises a data acquisition module 1, a data processing module 2, a danger alarm module 3 and a potential safety hazard prediction module 4. And combining a live-action three-dimensional model established by the unmanned aerial vehicle oblique photography technology to develop visual potential safety hazard monitoring and early warning work.
The data acquisition module 1: the method is used for crack activity monitoring, spherical weathered body activity monitoring, earth surface displacement monitoring, stress and strain monitoring, rainfall monitoring, sea wave power monitoring and the like; and displaying all the data acquisition sites on the live-action three-dimensional model according to the actual positions.
(1) Fracture activity monitoring: the method is mainly used for monitoring crack dislocation and width expansion variables aiming at cracks with larger development scale of a bedrock shoreline;
(2) Monitoring surface displacement: the method is mainly used for installing monitoring equipment and combining a high-precision positioning system to monitor displacement change information of spherical weathered bodies which possibly collapse slopes, steeper rock exposed surfaces and have higher weathering degrees but are not easy to clear on a travel route. And carrying out full coverage monitoring on the tourist roads built at the sea by adopting distributed optical fibers.
(3) Stress and strain monitoring: the method is mainly used for monitoring bridges, viewing platforms, tourist facilities in fracture distribution areas and the like erected on tourist roads, and monitoring the stress state and the strain condition of the bridges.
(4) And (3) rainfall monitoring: the rainfall has a great influence on the island travel route, particularly on a green belt and an exposed slope of a newly-built route, and monitoring equipment is installed in a vegetation slope area of the travel route to acquire rainfall change information.
(5) Wave power monitoring: and installing monitoring equipment in a sunken area of the bedrock shoreline eroded by sea waves to obtain dynamic change data of the sea wave impact force.
The data processing module 2: the method comprises the steps of receiving collected data information, storing and calculating the data, and comparing the obtained observation index values of space coordinate positions, stress values, deformation values, rainfall and the like with initial values to obtain a change value 1; comparing the obtained variable with the last recorded value to obtain a variable value 2, and displaying the obtained two types of variable quantities in a chart form;
the hazard warning module 3: setting different types of observed value change thresholds according to different monitoring entities, and carrying out dangerous alarm when the monitored value change exceeds the thresholds, and simultaneously feeding back and archiving abnormal values; relevant management personnel check on site in time according to the alarm information, and carry out necessary disposal work such as protection repair or potential safety hazard removal. After the treatment is finished, the monitoring work initial value of the next stage is set.
The potential safety hazard prediction module 4: dividing a frequently-occurring alarm area into a key monitoring area, predicting the future change trend of the area by combining historical monitoring data, and giving out potential safety hazard clearing and protection repair prompts; if the potential safety hazard is cleared, making a prediction again.
Fig. 2 shows the principle of the system for monitoring and early warning of the coastline safety of the bedrock of the tourist island according to the embodiment of the application.
In embodiment 2, as shown in fig. 3, the method for monitoring and early warning of the coastline of the tourist island bedrock according to the embodiment of the application includes:
s1, collecting monitoring information of crack activity, earth surface displacement, stress and strain, rainfall and sea wave power;
s2, transmitting the acquired data to a data processing terminal through an optical fiber, storing the data, calculating, and comparing the obtained values of all the observation indexes such as the space coordinate position, the stress value, the rainfall and the like with the initial observation value and the change quantity of the last observation record value; and displaying the variation in a graph form;
s3, setting different types of numerical value change thresholds according to different monitoring entities; when the monitored numerical variation exceeds a threshold value, dangerous alarms are carried out;
s4, dividing the frequently-occurring alarm area into a key monitoring area, and predicting the future change condition of the area by combining historical monitoring data, and carrying out potential safety hazard removal and protection repair prompt.
In the embodiment of the present application, in step S2, calculating the coordinate position and the relative initial value of the data acquisition and the variation amount relative to the last recorded value includes:
step one: inputting a current observation value X and an initial value T of a current observation index; obtaining the variation X of the relative initial value 1 And the amount of change X relative to the last recorded value 2 ；
Step two: will change the amount X 1 And X 2 Comparing and checking with a set certain observation element threshold Y;
step three: according to the designated number N of stage decision trees in the current stage stage Using label as a fitting threshold value, and sequentially establishing each decision treeFitting a change function change value of the current model;
step four: the model fitting of the current stage is finished, a fitting change value res, res=actual-pred, pred is a predicted value of the current stage on training data X, and the fitting change value res is calculated;
where rate is the learning rate,for the i-th decision tree in the current stage +.>The predicted value on the training set X is updated, and the data value actual=res to be fitted is updated; n_evantizers are random forest parameters;
step five: fitting a variation value res to the variation X of the last recorded value, and carrying out Jarque-Bera test;
step six: when the change function of the evaluation function on the given test set T does not descend any more in the designated early_stop stage number, model training is stopped in time to obtain the optimal iteration stage number N of the model, model training is completed, and the step seven is skipped, otherwise, if the change function on the test set T continues to descend, the step four is skipped, and stage iteration is continued;
step seven: and predicting a test set, and obtaining a test set prediction result pred according to the optimal iteration stage number N of the model.
In the embodiment of the present application, the test implementation step of the second step is as follows:
(1) Calculating the data distribution skewness S according to the change amount threshold of the last recorded value and the following formula:
wherein actual is a data threshold to be fitted, mean is a sample threshold mean, size is a sample capacity, and std is a sample threshold standard deviation;
(2) Calculating the data distribution kurtosis K according to the change amount threshold value of the last recorded value by the following formula:
(3) The chi-square statistic JB is constructed according to the following formula:
the size is the sample capacity, S is the data distribution skewness, and K is the data distribution kurtosis;
checking the significance of the square statistic JB, and checking the degree of bias of the square statistic JB to determine whether to change the data; if the chi-square statistic JB exceeds the set threshold, entering the step (4), otherwise, entering the step (5);
(4) Judging whether the data is beyond a preset threshold value, judging whether the upper limit of the change times of the data reaches the preset upper limit of the change times of the data, if the upper limit of the change times is diff, if the diff is less than or equal to 0, jumping to (5), otherwise updating the diff value to be diff-1, performing boxcox change on the data, performing lambda value traversal through the following formula, and generating a change expression by lambda with the maximum data threshold value label likelihood function L after the selection and the change:
wherein actual is a data threshold to be fitted, a new data threshold is obtained, and is used as a first-stage fitting threshold label, and a current-stage judgment variable jud [1] =true is set;
(5) The data bias is not obvious or the data threshold conversion times reach the target upper bound, the original data threshold y is taken as a first stage fitting threshold label, and a current stage judgment variable jud [1] =false is set.
In the seventh step, according to the optimal iteration stage number N of the model, a test set prediction result pred is obtained, which specifically includes:
(1) Calculating a predicted value pred of the stage model in the current stage on a test set T, wherein the expression is as follows:
where pred is the test set prediction result, rate is the learning rate,decision tree for phase j->Is predicted by->The inverse of the pre-transformation for the phase j threshold is shown in the following specific expression:
wherein F is stage -1 For the inversion of the stage model of the current stageFunction change, jud [ j ]]Determining a variable, sigmod, for the current phase j -1 Inverse transformation, boxcos, for sigmod (& gt) transformation -1 (. Cndot.) is the inverse of the boxcos (-) transform;
prediction result of stage jboxcos -1 The (-) expression is as follows:
sigmod -1 the (-) expression is as follows:
(2) Calculating the current-stage change function value loss=l (pred, y T )，y T For the test set Tprimitive threshold, L (·) is the change function used by the system, and for the regression problem is the square change function, where loss= (pred-y) T ) 2 。
In the embodiment of the present application, in step S4, the area where the alarm frequently occurs is divided into the key monitoring area, and the prediction of the future change condition of the area by combining the history monitoring data includes:
acquiring image sequences acquired by frequently-occurring alarm areas at different angles as an input set; obtaining a feature matching point pair of the image through feature extraction and matching, and carrying out evolution processing on the feature matching point pair; according to the geological evolution and the security threat model, selecting characteristic points of the candidate images as seed points to carry out matching evolution on surrounding neighborhood of the candidate images and filtering the candidate images to obtain evolution matching point pairs; calibrating an image acquisition instrument, and combining the matching point pairs to obtain the internal and external parameters of the image acquisition instrument; obtaining instrument parameters and matching point pairs according to the images, and recovering three-dimensional model points; reconstructing by adopting geological evolution and a security threat model, selecting seed model points to generate an initial point, and evolving in a grid neighborhood of the initial point; and filtering the error according to the constraint condition to obtain an accurate evolution three-dimensional point cloud model.
In one embodiment, the geological evolution and security threat model specifically includes:
for each feature point f of the reference image, finding a corresponding candidate matching point f' in the candidate image according to epipolar constraint; then, using geological evolution and a security threat model, selecting zero-mean normalized cross-correlation coefficient ZNCC as an objective function, calculating ZNCC values of matching point pairs, and sequencing according to the size of the ZNCC values:
wherein x is the corresponding coordinate information of the image feature point f in the image, and x 'is the corresponding coordinate information of the image feature point f' in the image; i (x) and I (x ') represent pixel intensities at the x-coordinate and the x' -coordinate;and->Representing the average pixel brightness of an image window centered at x and an image window centered at x';
selecting a characteristic point larger than a threshold value mu 1 as a seed point to carry out neighborhood evolution, and selecting a characteristic point larger than a threshold value mu 2 as a reserve matching point mu 1> mu 2; for all matching points of the reference image, establishing one-to-many matching in the size of a fixed window in the center of the candidate image; for the points of the reference image, matching the points of other images, and establishing mixed matching of all the points in the window; on the premise of meeting parallax gradient constraint and confidence constraint, ZNCC of an evolution matching point pair is calculated, evolution points larger than a threshold value mu 3 are screened to be used as seed points for secondary evolution, the evolution points larger than the threshold value mu 4 are screened to be used as reserve matching points, and mu 3 is larger than mu 4;
assuming u 'and u are a pair of image matching point pairs, x' and x are another adjacent image matching point pair, the parallax gradient constraint formula is:
||(u′-u)-(x′-x)|| ∞ ≤ε
where ε is the threshold of parallax gradient; parallax gradient constraints reduce image matching ambiguity;
the formula of the confidence constraint is:
s(x)＝max{|I(x+Δ)-I(x)|,Δ∈{(1,0),(-1,0),(0,1),(0,-1)}}
the confidence constraint is adopted to improve the reliability of the matching evolution and obtain the evolution matching point pair.
In the embodiment of the application, the process of calibrating the image acquisition instrument mark is to calculate the internal parameters of the image acquisition instrument according to the imaging principle of the image acquisition instrument; according to the characteristic points and matching of the image sequence, selecting two input images as reference, and calculating a basic matrix F of a reference image point pair, wherein F satisfies the equation x 'fx=0, and x' and x are a pair of image matching points; estimating initial values K' and K of internal reference matrixes of the reference image pair, calculating an essential matrix of the image point pair and extracting rotation and translation components; the internal and external parameters and feature matching point pairs of the image acquisition instrument are known, and three-dimensional model points corresponding to the feature points are obtained by using triangulation.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The content of the information interaction and the execution process between the devices/units and the like is based on the same conception as the method embodiment of the present application, and specific functions and technical effects brought by the content can be referred to in the method embodiment section, and will not be described herein.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the functions described above. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. For specific working processes of the units and modules in the system, reference may be made to corresponding processes in the foregoing method embodiments.
Based on the technical solutions described in the embodiments of the present application, the following application examples may be further proposed.
According to an embodiment of the present application, there is also provided a computer apparatus including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor performs the steps of any of the various method embodiments described above.
Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of the respective method embodiments described above.
The embodiment of the application also provides an information data processing terminal, which is used for providing a user input interface to implement the steps in the method embodiments when being implemented on an electronic device, and the information data processing terminal is not limited to a mobile phone, a computer and a switch.
The embodiment of the application also provides a server, which is used for realizing the steps in the method embodiments when being executed on the electronic device and providing a user input interface.
Embodiments of the present application also provide a computer program product which, when run on an electronic device, causes the electronic device to perform the steps of the method embodiments described above.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc.
While the application has been described with respect to what is presently considered to be the most practical and preferred embodiments, it is to be understood that the application is not limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications, equivalents, and alternatives falling within the spirit and scope of the application.
Claims (10)
1. A travel island bedrock shoreline safety monitoring and early warning system is characterized in that the system establishes a live-action three-dimensional model by combining an unmanned aerial vehicle oblique photography technology to realize visual potential safety hazard monitoring, early warning and prediction, and specifically comprises the following steps:
the data acquisition module (1) is used for crack activity monitoring, spherical weathered body activity monitoring, earth surface displacement monitoring, stress and strain monitoring, rainfall monitoring, sea wave power monitoring and the like;
the data processing module (2) is used for receiving the acquired data information, storing and calculating the data, and comparing the acquired observation index values of the space coordinate position, the stress value, the deformation value, the rainfall and the like with the initial values to obtain a change value 1; comparing the obtained variable with the last recorded value to obtain a variable value 2, and displaying the obtained two types of variable quantities in a chart form;
the dangerous alarm module (3) is used for setting different types of observed value change thresholds according to different monitoring entities, carrying out dangerous alarm when the monitored value change exceeds the thresholds, feeding back abnormal values and archiving;
the potential safety hazard prediction module (4) divides the frequently-occurring alarm area into a key monitoring area, predicts the future change trend of the area by combining historical monitoring data, and gives out potential safety hazard clearing and protection repair prompts; if the potential safety hazard is cleared, making a prediction again.
2. The tourist island bedrock shoreline safety monitoring and early warning system according to claim 1, wherein in the data acquisition module (1), the crack activity monitoring comprises: monitoring crack dislocation, width expansion variable and the condition of newly formed cracks aiming at cracks developed on a bedrock shoreline and a tour route;
the surface displacement monitoring comprises: aiming at a slope, a steep rock exposed surface and a weathered spherical weathered body which are about to collapse on a travel route, monitoring equipment is installed, and displacement change information is monitored by combining a positioning system; for a travel road built at sea, carrying out full coverage monitoring by adopting distributed optical fibers;
the stress and strain monitoring includes: monitoring bridge, view platform and tourist facilities in fracture distribution area, and monitoring stress state and strain of each tourist facility;
the rainfall monitoring includes: installing monitoring equipment in an exposed slope area and a vegetation coverage area of the travel route to acquire rainfall variation information;
the sea wave power monitoring comprises the following steps: and (3) the bedrock shore section developed into the travel route is corroded by sea waves, monitoring equipment is installed in a fracture dense development area, and dynamic change data of the sea wave impact force are obtained.
3. The system for monitoring and early warning of the coastline safety of the tourist island bedrock according to claim 1 is characterized in that a data acquisition site and a monitoring site in the data acquisition module (1) are displayed on a live-action three-dimensional model according to actual positions.
4. A method for monitoring and early warning of the coastline of a tourist island bedrock, which is characterized in that the method is operated in the system for monitoring and early warning of the coastline of the tourist island bedrock according to any one of claims 1 to 3, and the method comprises the following steps:
s1, collecting monitoring information of crack activity, spherical weathered body activity, earth surface displacement, stress and strain, rainfall and sea wave power;
s2, transmitting the acquired data to a data processing module (2) through an optical fiber, storing and calculating the data, comparing the acquired space coordinate position, stress value and observation index value of rainfall with initial values, and comparing the initial values with the last recorded value to obtain variation and displaying the variation in a chart form;
s3, setting different types of observed value change thresholds according to different monitoring entities, and carrying out dangerous alarm when the monitored value change exceeds the thresholds, and simultaneously feeding back and archiving abnormal values;
s4, dividing the frequently-occurring alarm area into a key monitoring area, and predicting the future change condition of the area by combining historical monitoring data, and carrying out potential safety hazard removal and protection repair prompt; if the potential safety hazard is cleared, making a prediction again.
5. The method for monitoring and early warning of the coastline of the tourist island bedrock according to claim 4, wherein in step S2, the obtained space coordinate position, stress value and observed index value of rainfall are compared with initial values and compared with the last recorded value, and the method specifically comprises the following steps:
step one: inputting a current observation value X and an initial value T of a current observation index; obtaining the variation X of the relative initial value 1 And the amount of change X relative to the last recorded value 2 ；
Step two: will change the amount X 1 And X 2 Comparing and checking with a set certain observation element threshold Y;
step three: according to the designated number N of stage decision trees in the current stage stage Using label as a fitting threshold value, and sequentially establishing each decision treeFitting a change function change value of the current model;
step four: the model fitting of the current stage is finished, a fitting change value res, res=actual-pred, pred is a predicted value of the current stage on training data X, and the fitting change value res is calculated; the expression is:
where rate is the learning rate,for the i-th decision tree in the current stage +.>The predicted value on the training set X is updated, and the data value actual=res to be fitted is updated; n_evantizers are random forest parameters;
step five: fitting a variation value res to the variation X of the last recorded value, and carrying out Jarque-Bera test;
step six: when the change function of the evaluation function on the given test set T does not descend any more in the designated early_stop stage number, model training is stopped in time to obtain the optimal iteration stage number N of the model, model training is completed, and the step seven is skipped, otherwise, if the change function on the test set T continues to descend, the step four is skipped, and stage iteration is continued;
step seven: and predicting a test set, and obtaining a test set prediction result pred according to the optimal iteration stage number N of the model.
6. The method for monitoring and early warning of the coastline of the tourist island bedrock according to claim 5, wherein in the second step, the original threshold value y of the variation X of the last recorded value is checked, and the specific implementation steps are as follows:
(1) Calculating the data distribution skewness S according to the change amount threshold of the last recorded value and the following formula:
wherein actual is a data threshold to be fitted, mean is a sample threshold mean, size is a sample capacity, and std is a sample threshold standard deviation;
(2) Calculating the data distribution kurtosis K according to the change amount threshold value of the last recorded value by the following formula:
(3) The chi-square statistic JB is constructed according to the following formula:
the size is the sample capacity, S is the data distribution skewness, and K is the data distribution kurtosis;
checking the significance of the square statistic JB, and checking the degree of bias of the square statistic JB to determine whether to change the data; if the chi-square statistic JB exceeds the set threshold, entering the step (4), otherwise, entering the step (5);
(4) Judging whether the data is beyond a preset threshold value, judging whether the upper limit of the change times of the data reaches the preset upper limit of the change times of the data, if the upper limit of the change times is diff, if the diff is less than or equal to 0, jumping to (5), otherwise updating the diff value to be diff-1, performing boxcox change on the data, performing lambda value traversal through the following formula, and generating a change expression by lambda with the maximum data threshold value label likelihood function L after the selection and the change:
wherein actual is a data threshold to be fitted, a new data threshold is obtained, and is used as a first-stage fitting threshold label, and a current-stage judgment variable jud [1] =true is set;
(5) The data bias is not obvious or the data threshold conversion times reach the target upper bound, the original data threshold y is taken as a first stage fitting threshold label, and a current stage judgment variable jud [1] =false is set.
7. The method for monitoring and early warning of the coastline of the tourist island bedrock according to claim 5, wherein in the seventh step, according to the optimal iteration stage number N of the model, a test set prediction result pred is obtained, which specifically comprises:
(1) Calculating a predicted value pred of the stage model in the current stage on a test set T, wherein the expression is as follows:
where pred is the test set prediction result, rate is the learning rate,decision tree for phase j->Is predicted by->The inverse of the pre-transformation for the phase j threshold is shown in the following specific expression:
wherein F is stage -1 Jud [ j ] as an inverse transform function of the current stage model]Determining a variable, sigmod, for the current phase j -1 Inverse transformation, boxcos, for sigmod (& gt) transformation -1 (. Cndot.) is the inverse of the boxcos (-) transform;
prediction result of stage jboxcos -1 The (-) expression is as follows:
sigmod -1 the (-) expression is as follows:
(2) Calculating the current-stage change function value loss=l (pred, y T )，y T For the test set Tprimitive threshold, L (·) is the change function used by the system, and for the regression problem is the square change function, where loss= (pred-y) T ) 2 。
8. The method for monitoring and early warning of coastline safety of tourist island bedrock according to claim 4, wherein in step S4, the frequent occurrence warning area is divided into important monitoring areas, and the future change condition of the areas is predicted by combining the historical monitoring data, comprising:
acquiring image sequences acquired at different angles in a frequently-occurring alarm region as an input set, and acquiring feature matching point pairs of images through feature extraction and matching, wherein the feature matching point pairs are subjected to evolution processing;
according to the geological evolution and the security threat model, selecting characteristic points of the candidate images as seed points to carry out matching evolution on surrounding neighborhood of the candidate images and filtering the candidate images to obtain evolution matching point pairs;
calibrating an image acquisition instrument, and combining the matching point pairs to obtain the internal and external parameters of the image acquisition instrument; obtaining instrument parameters and matching point pairs according to the images, and recovering three-dimensional model points;
reconstructing by adopting geological evolution and a security threat model, selecting seed model points to generate an initial point, and evolving in a grid neighborhood of the initial point;
and filtering the error according to the constraint condition to obtain an accurate evolution three-dimensional point cloud model.
9. The method for monitoring and early warning of the coastline of the tourist island bedrock according to claim 8, wherein the geological evolution and security threat model specifically comprises:
for each feature point f of the reference image, finding a corresponding candidate matching point f' in the candidate image according to epipolar constraint; using geological evolution and a security threat model, selecting zero-mean normalized cross-correlation coefficient ZNCC as an objective function, calculating ZNCC values of matching point pairs, and sorting according to the sizes of the ZNCC values:
wherein x is the corresponding coordinate information of the image feature point f in the image, and x 'is the corresponding coordinate information of the image feature point f' in the image; i (x) and I (x ') represent pixel intensities at the x-coordinate and the x' -coordinate;and->Representing the average pixel brightness of an image window centered at x and an image window centered at x';
selecting a characteristic point larger than a threshold value mu 1 as a seed point to carry out neighborhood evolution, and selecting a characteristic point larger than a threshold value mu 2 as a reserve matching point mu 1> mu 2; for all matching points of the reference image, establishing one-to-many matching in the size of a fixed window in the center of the candidate image; for the points of the reference image, matching the points of other images, and establishing mixed matching of all the points in the window; on the premise of meeting parallax gradient constraint and confidence constraint, ZNCC of an evolution matching point pair is calculated, evolution points larger than a threshold value mu 3 are screened to be used as seed points for secondary evolution, the evolution points larger than the threshold value mu 4 are screened to be used as reserve matching points, and mu 3 is larger than mu 4;
assuming u 'and u are a pair of image matching point pairs, x' and x are another adjacent image matching point pair, the parallax gradient constraint formula is:
||(u′-u)-(x′-x)|| ∞ ≤ε
where ε is the threshold of parallax gradient; parallax gradient constraints reduce image matching ambiguity;
the formula of the confidence constraint is:
s(x)＝max}|I(x+Δ)-I(x)|,△∈{(1,0),(-1,0),(0,1),(0,-1)}}
the confidence constraint is adopted to improve the reliability of the matching evolution and obtain the evolution matching point pair.
10. The method for monitoring and early warning of the coastline safety of the tourist island bedrock of claim 8, wherein the process of calibrating the image acquisition instrument mark is to calculate the internal parameters of the image acquisition instrument according to the imaging principle of the image acquisition instrument; according to the characteristic points and matching of the image sequence, selecting two input images as reference, and calculating a basic matrix F of a reference image point pair, wherein F satisfies the equation x 'fx=0, and x' and x are a pair of image matching points; estimating initial values K' and K of internal reference matrixes of the reference image pair, calculating an essential matrix of the image point pair and extracting rotation and translation components; the internal and external parameters and feature matching point pairs of the image acquisition instrument are known, and three-dimensional model points corresponding to the feature points are obtained by using triangulation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311107475.6A CN117238108A (en) | 2023-08-31 | 2023-08-31 | Safety monitoring and early warning system and method for coastline of bedrock of tourist island |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311107475.6A CN117238108A (en) | 2023-08-31 | 2023-08-31 | Safety monitoring and early warning system and method for coastline of bedrock of tourist island |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117238108A true CN117238108A (en) | 2023-12-15 |
Family
ID=89083587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311107475.6A Pending CN117238108A (en) | 2023-08-31 | 2023-08-31 | Safety monitoring and early warning system and method for coastline of bedrock of tourist island |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117238108A (en) |
-
2023
- 2023-08-31 CN CN202311107475.6A patent/CN117238108A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113611085B (en) | Monitoring and early warning method and system for geological disasters in geotechnical engineering | |
| KR102112046B1 (en) | Method for maintenance and safety diagnosis of facilities | |
| JP7261816B2 (en) | Structure repair method selection system, repair method selection method, and repair method selection server | |
| CN114021487B (en) | Early warning method, device and equipment for landslide collapse and readable storage medium | |
| JP6960168B2 (en) | Local information assimilation equipment and methods and programs for real-time flood hazard mapping | |
| Liu et al. | A state-of-the-practice review of three-dimensional laser scanning technology for tunnel distress monitoring | |
| CN116975576B (en) | Mountain road geological disaster risk evaluation method based on key information statistics | |
| CN116202432A (en) | Intelligent regional landslide monitoring and management method | |
| Soleymani et al. | Damage detection and monitoring in heritage masonry structures: Systematic review | |
| CN116580532A (en) | Geological disaster early warning system based on radar remote sensing technology | |
| CN116378123A (en) | BIM-based foundation pit health monitoring system | |
| CN116543114A (en) | Lifting three-dimensional visual underground engineering sand table demonstration system | |
| Wang et al. | Automatic identification of rock discontinuity and stability analysis of tunnel rock blocks using terrestrial laser scanning | |
| CN117113830B (en) | Mountain restoration evaluation prediction system based on data analysis | |
| CN113656868A (en) | BIM technology-based hospital construction collaborative management platform | |
| CN117238108A (en) | Safety monitoring and early warning system and method for coastline of bedrock of tourist island | |
| CN115457739B (en) | Geological disaster early warning method and device, electronic equipment and storage medium | |
| CN114493295B (en) | Method for determining tunnel monitoring project under salt rock geology and monitoring system | |
| CN116579214A (en) | Digital twinning-based three-dimensional visual bridge pier monitoring system and method | |
| CN112802307B (en) | Geological monitoring and early warning method and system for geological investigation | |
| Sampaleanu | The role of intact rock fracture in rockfall initiation | |
| CN115345511A (en) | Dynamic evaluation method, evaluation system and equipment for landslide risk of highway corridor | |
| CN112907567A (en) | SAR image ordered artificial structure extraction method based on spatial reasoning method | |
| CN115761174B (en) | Laser radar-based embankment service life monitoring method and system and electronic equipment | |
| CN117589120B (en) | BIM-based foundation pit deformation automatic monitoring and early warning method, system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |