CN118506291B - Infrastructure monitoring method and system based on point cloud - Google Patents
Infrastructure monitoring method and system based on point cloud Download PDFInfo
- Publication number
- CN118506291B CN118506291B CN202410979759.2A CN202410979759A CN118506291B CN 118506291 B CN118506291 B CN 118506291B CN 202410979759 A CN202410979759 A CN 202410979759A CN 118506291 B CN118506291 B CN 118506291B
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring
- terrain
- point cloud
- change
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/945—User interactive design; Environments; Toolboxes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of terrain monitoring, in particular to an infrastructure monitoring method and system based on point cloud, wherein the method comprises the following steps: initializing space positioning of point cloud data based on geographic markers, recording longitude and latitude of each data point, synchronizing by using a time stamp, structuring and arranging data to generate space positioning point cloud data, classifying the space positioning point cloud data in a hierarchical manner, and grouping to obtain grouped topographic point cloud data. According to the invention, the position of a terrain infrastructure is tracked by recording the longitude and latitude of data points, the recording of spatial attributes is optimized, the time correlation of data is synchronously enhanced by using time stamps, the time sequence of terrain change is accurately reflected, the management efficiency and the processing reliability are improved by data structuring, so that the terrain change analysis is more accurate, the pertinence of data processing is improved by hierarchical classification and grouping of point cloud data, and the prospective and early warning capability of monitoring are enhanced by identifying terrain change indexes and calculating change rates.
Description
Technical Field
The invention relates to the technical field of terrain monitoring, in particular to an infrastructure monitoring method and system based on point cloud.
Background
The field of terrain monitoring technology involves the use of various methods and devices to monitor and analyze physical changes in the earth's surface and subsurface, and is primarily used to predict and evaluate the potential risk of natural disasters such as land skis, earthquakes, floods, and the impact of human activities on terrain, such as mining and construction projects. Terrain monitoring techniques, including radar interferometry (InSAR), optical and laser ranging (e.g., liDAR) techniques, and the use of ground and air sensor networks, can provide high resolution terrain variation data, thereby helping engineers and scientists monitor the stability of critical infrastructure and natural topography in real time.
The infrastructure monitoring method is a technical means specially used for evaluating and ensuring the safety of public and private infrastructures, the infrastructures comprise bridges, roads, dams, buildings and the like, the health condition of the infrastructures can be continuously monitored through the implementation of the terrain monitoring technology, and structural weaknesses and potential threats can be found timely, so that necessary maintenance and repair can be carried out.
The existing infrastructure monitoring method is widely applied to prediction of natural disasters and monitoring of infrastructures, but faces challenges of data integration and time correlation processing, especially when large-scale terrain monitoring is carried out, the existing technology cannot effectively synchronize and integrate data points from different time and space, so that accurate terrain change prediction cannot be provided in real time in emergency, the existing method is limited by data processing efficiency when processing high-resolution data, maximum effectiveness is difficult to achieve under the condition that quick response is needed, and critical data cannot be timely identified and classified in the terrain monitoring, so that misreading of the terrain change is caused, and timeliness and effectiveness of disaster response measures are further affected. This lack of data processing and time synchronization in some cases results in neglect or misinterpretation of the terrain threat, thus constituting a potential risk to people's life and property safety.
Disclosure of Invention
The application provides an infrastructure monitoring method and system based on point cloud, wherein the existing infrastructure monitoring method is widely applied to prediction of natural disasters and monitoring of infrastructures, but faces challenges of data integration and time correlation processing, especially when large-scale terrain monitoring is carried out, the prior art cannot effectively synchronize and integrate data points from different time and space, so that accurate terrain change prediction cannot be provided in real time in emergency, the existing method is limited by the efficiency of data processing when high-resolution data are processed, the maximum efficiency is difficult to be exerted under the condition that quick response is required, and if key data cannot be timely identified and classified in the terrain monitoring, misreading of terrain change is caused, and timeliness and effectiveness of disaster response measures are further affected. This lack of data processing and time synchronization in some cases results in neglect or misinterpretation of the terrain threat, thus constituting a potential risk to people's life and property safety.
In view of the above problems, the present application provides a method and a system for monitoring infrastructure based on point cloud.
The application provides a point cloud-based infrastructure monitoring method, which comprises the following steps:
S1: initializing space positioning of point cloud data based on geographic marks, recording longitude and latitude of each data point, synchronizing the data by using a time stamp, structuring the data to generate space positioning point cloud data, classifying the space positioning point cloud data in a hierarchical manner, and grouping the space positioning point cloud data to obtain grouped topographic point cloud data;
S2: based on the grouped terrain point cloud data, a terrain variation analysis algorithm is applied to identify terrain variation indexes in each group of data, the variation rate of each index is calculated, a terrain variation analysis result is obtained, trend prediction is carried out on the terrain variation analysis result, the variation of the terrain in a short period is predicted, and a terrain prediction result is generated;
S3: determining a key area needing to be monitored in an enhanced mode based on the terrain prediction result, setting monitoring frequency and accuracy, generating a monitoring plan, applying the monitoring plan to monitoring equipment, adjusting equipment parameters and matching new monitoring requirements to obtain a monitoring parameter configuration result;
S4: and starting monitoring equipment to collect new point cloud data and analyze in real time based on the monitoring parameter configuration result, identifying new topography variation trend to obtain new periodic topography analysis result, adjusting the monitoring strategy according to the new periodic topography analysis result, optimizing the data collection period and analysis frequency, and establishing the adjusted monitoring strategy.
Preferably, the step of acquiring the grouped terrain point cloud data specifically includes:
s111: based on the geographic marks, initializing the space positioning of the point cloud data, recording the longitude and latitude and the time stamp of each data point, and adopting the formula:
calculating the spatial coordinates of each data point, resulting in an initialized set of spatial coordinates, wherein, The spatial coordinates representing the ith data point, a and b are adjustment coefficients for longitude and latitude,Represents a longitude of the person in question,Representing the latitude of the person in question,An exponential growth adjustment representing a timestamp, c being a time decay coefficient;
s112: and carrying out structural arrangement on the initialized space coordinate data set, carrying out space structural arrangement according to geographic information requirements, and adopting the formula:
Integrating the data points to obtain space positioning point cloud data, wherein, Representing the cloud data of the spatial locating points,An exponentially decaying weight factor representing the ith data point,Representing the spatial coordinates of the ith data point, n representing the total number of data points;
S113: performing hierarchical classification on the space positioning point cloud data, classifying the point cloud data according to the topography and landform factors, and adopting the formula:
calculating a representative point cloud for each class, obtaining hierarchical classified point cloud data, wherein, Represents the hierarchical classification point cloud data, m represents the number of point cloud data in the classification,Spatial anchor point cloud data representing the jth data point,A classification weight representing a j-th point;
s114: grouping operation is carried out based on the hierarchical classification point cloud data, and the formula is adopted:
the grouped terrain point cloud data is calculated, wherein, Representing the grouped terrain point cloud data,Is a classification weight given according to geographic features, p represents the number of differential terrain classifications,Hierarchical classification point cloud data representing a kth classification.
Preferably, the step of obtaining the terrain variation analysis result specifically includes:
S211: initializing point cloud data based on the grouped terrain point cloud data, recording longitude and latitude and a time stamp of each data point, and adopting the formula:
Analyzing the position change of each data point corresponding to the initial measurement to obtain an initial indicator of the topography change, wherein, A, b are longitude and latitude adjustment coefficients for the initial index of the terrain change,、To represent the longitude and latitude respectively,C and d are time adjustment coefficients and offset constants;
s212: calculating the change rate of each terrain change initial index, and applying the formula:
The rate of change of the terrain is calculated, wherein, In order to provide a rate of change of the terrain,AndRepresenting the current and previous terrain change indexes respectively, wherein M is the number of the change indexes;
s213: integrating the terrain change rate, evaluating the overall terrain change using a weighted product sum method, using the formula:
generating a topography variation analysis result, wherein, For the result of the terrain variation analysis, K is the number of rates of change,As a weight for the kth rate of change,Is the kth terrain rate of change.
Preferably, the step of obtaining the terrain prediction result specifically includes:
S221: extracting data from the terrain variation analysis result, applying time sequence analysis, and adopting the formula:
calculating a predicted preliminary value by using an exponential smoothing method to obtain preliminary topography trend prediction data, wherein, For the preliminary terrain trend prediction data,In order to smooth the coefficient of the coefficient,In order to adjust the factor(s),As a result of the analysis of the topography change at the previous time point,For the predicted terrain data at the last point in time,Is a normalization factor;
s222: and carrying out error analysis on the preliminary topography trend prediction data, and adopting the formula:
calculating a difference between the real-time terrain data and the predicted terrain data, generating error data, wherein, In order to predict the error of the signal,As a result of the analysis of the topography change at the current time point,For the predicted terrain data at the current point in time,Is a normalization factor;
s223: and adjusting the prediction in the future time period by using the error data, and adopting the formula:
adjusting the current predicted value according to the error, generating a terrain predicted result, wherein, In order to adjust the predicted terrain data,For the purpose of the error adjustment factor,As the predicted terrain data is not adjusted,Is the prediction error of the previous time point.
Preferably, the step of acquiring the monitoring plan specifically includes:
S311: according to the terrain prediction result, calculating a risk factor score of the region, and adopting the formula:
calculating an integrated risk score for each region, resulting in a list of key regions, wherein, Representing the integrated risk score for region i,A score representing the jth predictor,Is a fine-tuning parameter which,Is the weighting coefficient of the j-th factor,Is a regularization parameter which is a function of the data,Is a small constant, n is the total number of predictors;
s312: according to the key region list, differential monitoring frequency and accuracy are set for each region, and the formula is as follows:
a monitored parameter of the critical area is generated, wherein, As a monitoring parameter of the critical area,For the integrated risk score for region i,AndThe maximum and minimum of the region risk scores, respectively.Is the adjustment parameter of the device, which is used for adjusting the parameters,Is an exponential parameter.
S313: and utilizing the monitoring parameters of the key areas to formulate a monitoring strategy and a plan for each key area, wherein the formula is as follows:
a monitoring plan is calculated, wherein, For the monitoring plan of the area i,Is the monitoring parameter setting for region i,Is a conversion factor.
Preferably, the step of obtaining the monitoring parameter configuration result specifically includes:
s321: based on the monitoring plan, evaluating a current configuration of the device, adjusting by a formula:
A preliminary updated device configuration is generated, wherein, Representing the configuration of the device after the preliminary update,Representing the original configuration of the device, P is the monitoring plan,Is the rate of learning to be performed,Is a regularization parameter which is a function of the data,Is a small constant that enhances the stability of the calculation,Is a small constant which is a function of the temperature,Is the power of the power;
S322: and adjusting parameters of the monitoring equipment by utilizing the initially updated equipment configuration, matching new monitoring requirements, and adopting the following formula:
acquiring the adjusted device parameters, wherein, Is the parameters of the device after the adjustment,Is the configuration of the device after the preliminary update,Is an adjustment parameter, T is a threshold;
s323: and carrying out configuration matching according to the adjusted equipment parameters, wherein the formula is as follows:
establishing a configuration result of the monitoring parameters, wherein, Is the result of the configuration of the monitoring parameters,Is the parameters of the device after the adjustment,Is the regulation factor, R is the monitoring requirement that the device should achieve,Is an additional adjustment factor.
Preferably, the step of acquiring the adjusted monitoring policy specifically includes:
S411: based on the monitoring parameter configuration result, calculating the difference between the newly collected point cloud data after the monitoring equipment is started and the previously collected point cloud data, and using the formula:
generating a point cloud data difference, wherein, As the difference value between the new and the old data,Representing the newly collected point cloud data,Representing point cloud data collected before,Is the stability factor of data point i,Is a small increase to avoid zero error, n is the number of data points;
s412: based on the difference value of the new data and the old data, real-time analysis is carried out, the change trend of the terrain infrastructure is identified, and the formula is adopted as follows:
a new trend of the topography is obtained, wherein, For the trend of the new topography change,As the difference value between the new and the old data,Is the weight of each point i, n is the number of points,Is a small constant for balanced weight summation;
s413: according to the new topography variation trend, a monitoring strategy is adjusted, a data collection period and an analysis frequency are optimized, and the formula is adopted as follows:
An adjusted monitoring strategy is obtained, wherein, In order to adjust the monitoring strategy after the adjustment,For new topography trends, C is the current data collection period, F is the current analysis frequency,AndThe greatest historic values of the topography change and analysis frequency respectively,AndIs an adjustment parameter.
A point cloud based infrastructure monitoring system, the system comprising:
The point cloud data initialization module is used for associating the space position of each point with a time stamp in the point cloud data collection process based on the geographic mark, positioning and matching the space data through longitude and latitude, and determining the time sequence of the data points by using the time stamp to obtain a space time stamp set;
The point cloud data grouping module adopts the space time stamp set, performs space interval division on data through geographic information, performs partition management on the data points, and acquires a grouping geographic data set through space definition standards;
The terrain change analysis module processes the grouped geographic data set, applies terrain change detection logic to the grouped data set, determines the change amount of the terrain height and the position offset, and extracts the terrain dynamic change characteristics by utilizing time sequence comparison analysis to construct a terrain change index set;
The monitoring scheme design module evaluates the monitoring requirements of the key change areas based on the terrain change index set, sets monitoring frequency and precision parameters according to the change indexes, adjusts configuration parameters of monitoring equipment and generates monitoring strategy configuration;
And the real-time monitoring and adjusting module is used for configuring and starting monitoring equipment according to the monitoring strategy, collecting new point cloud data in real time, identifying the change trend of the infrastructure in the new terrain, adjusting the monitoring strategy and the data analysis frequency, and obtaining the updated monitoring strategy.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method has the advantages that the position of an infrastructure data point in each terrain can be accurately tracked by initializing the space positioning of the point cloud data and recording the longitude and latitude of each data point, the space attribute record of the data is optimized by the aid of the refined data acquisition strategy, the time correlation of the data is enhanced by the synchronous use of time stamps, the time sequence of the terrain change can be accurately reflected in the analysis process, the data management efficiency is improved by the aid of the data structuring mode, the reliability of data processing is enhanced, and the follow-up terrain change analysis is more accurate. By hierarchically classifying and grouping the spatial anchor point cloud data, pertinence of data processing and feasibility of operation are improved, and more detailed observation and analysis of changes of a specific area are allowed. The strategy of identifying the terrain change index and calculating the change rate effectively reveals the change trend of the terrain, the prospective and early warning capability of terrain monitoring are further enhanced, and the structured and layered data processing logic improves the accuracy and efficiency of the terrain monitoring, so that the safety monitoring and disaster prevention of the infrastructure are better served.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a general flow chart of an infrastructure monitoring method based on point cloud according to the present invention;
FIG. 2 is a flow chart of grouped terrain point cloud data for providing a point cloud based infrastructure monitoring method in accordance with the present invention;
FIG. 3 is a flow chart showing the results of analysis of terrain variations for a point cloud based infrastructure monitoring method in accordance with the present invention;
FIG. 4 is a flow chart of a terrain prediction result of the point cloud based infrastructure monitoring method of the present invention;
FIG. 5 is a flow chart of a monitoring plan of the present invention for providing a point cloud based infrastructure monitoring method;
FIG. 6 is a flow chart showing the configuration results of monitoring parameters of the infrastructure monitoring method based on point cloud according to the present invention;
Fig. 7 is a flowchart of an adjusted monitoring strategy of the present invention for providing a point cloud based infrastructure monitoring method.
Detailed Description
The application provides an infrastructure monitoring method and system based on point cloud.
Summary of the application
The infrastructure monitoring method in the prior art is widely applied to prediction of natural disasters and monitoring of infrastructures, but faces challenges of data integration and time correlation processing, especially when large-scale terrain monitoring is carried out, the prior art cannot effectively synchronize and integrate data points from different time and space, so that accurate terrain change prediction cannot be provided in real time in emergency, the existing method is limited by data processing efficiency when processing high-resolution data, so that maximum effectiveness is difficult to develop under the condition of quick response, and if key data cannot be timely identified and classified in the terrain monitoring, misreading of terrain change is caused, and timeliness and effectiveness of disaster response measures are further affected. This lack of data processing and time synchronization in some cases results in neglect or misinterpretation of the terrain threat, thus constituting a potential risk to people's life and property safety.
Aiming at the technical problems, the technical scheme provided by the application has the following overall thought:
examples
As shown in fig. 1, the present application provides a point cloud-based infrastructure monitoring method, wherein the method comprises:
S1: initializing space positioning of point cloud data based on geographic markers, recording longitude and latitude of each data point, synchronizing the data by using a time stamp, structuring the data to generate space positioning point cloud data, classifying the space positioning point cloud data in a hierarchical manner, and grouping the space positioning point cloud data to obtain grouped terrain point cloud data;
S2: based on the grouped terrain point cloud data, a terrain change analysis algorithm is applied to identify terrain change indexes in each group of data, the change rate of each index is calculated to obtain a terrain change analysis result, trend prediction is carried out on the terrain change analysis result, the terrain change in a short period is predicted, and a terrain prediction result is generated;
S3: determining a key area needing to be monitored in an enhanced mode based on a terrain prediction result, setting monitoring frequency and accuracy, generating a monitoring plan, applying the monitoring plan to monitoring equipment, adjusting equipment parameters and matching new monitoring requirements to obtain a monitoring parameter configuration result;
s4: based on the monitoring parameter configuration result, starting the monitoring equipment to collect new point cloud data and conduct real-time analysis, identifying new topography change trend, obtaining new periodic topography analysis result, adjusting the monitoring strategy according to the new periodic topography analysis result, optimizing the data collection period and analysis frequency, and establishing the adjusted monitoring strategy.
The space positioning point cloud data comprises longitude and latitude coordinates, time marks and data index serial numbers, the grouping terrain point cloud data comprises layering elevation distribution, gradient classification and region division, the terrain change analysis results comprise change rates, key change indexes and change point positions, the terrain prediction results comprise future change trends, potential influence areas and change prediction intervals, the monitoring plan comprises monitoring region selection, monitoring frequency setting and monitoring precision requirements, the monitoring parameter configuration results comprise parameter setting values, adjustment areas and time configuration, the new periodic terrain analysis results comprise change trends, stability assessment and risk point identification, and the adjusted monitoring strategies comprise collection period adjustment, analysis frequency change and execution strategy timetables.
Specifically, as shown in fig. 2, the step of acquiring the grouped terrain point cloud data specifically includes:
s111: based on the geographic marks, initializing the space positioning of the point cloud data, recording the longitude and latitude and the time stamp of each data point, and adopting the formula:
calculating the spatial coordinates of each data point, resulting in an initialized set of spatial coordinates, wherein, The spatial coordinates representing the ith data point, a and b are adjustment coefficients for longitude and latitude,Represents a longitude of the person in question,Representing the latitude of the person in question,An exponential growth adjustment representing a timestamp, c being a time decay coefficient;
S112: carrying out structural arrangement on the initialized space coordinate data set, carrying out space structural arrangement according to geographic information requirements, and adopting the formula:
Integrating the data points to obtain space positioning point cloud data, wherein, Representing the cloud data of the spatial locating points,An exponentially decaying weight factor representing the ith data point,Representing the spatial coordinates of the ith data point, n representing the total number of data points;
S113: carrying out hierarchical classification on the space positioning point cloud data, classifying the point cloud data according to the topography and landform factors, and adopting the formula:
calculating a representative point cloud for each class, obtaining hierarchical classified point cloud data, wherein, Represents the hierarchical classification point cloud data, m represents the number of point cloud data in the classification,Spatial anchor point cloud data representing the jth data point,A classification weight representing a j-th point;
s114: grouping operation is carried out based on hierarchical classification point cloud data, and a formula is adopted:
the grouped terrain point cloud data is calculated, wherein, Representing the grouped terrain point cloud data,Is a classification weight given according to geographic features, p represents the number of differential terrain classifications,Hierarchical classification point cloud data representing a kth classification.
Spatial coordinate formula of data points:
: longitude of the i-th data point;
: latitude of the ith data point;
: timestamp of the i-th data point.
Longitude [ (longitude ]) And latitude [ ]) Directly obtain from the data set, the time stamp @, the) Also acquired from the dataset, representing the specific time of the data point record;
components in the calculation formula:
Calculating the sum of squares of longitude and latitude contributions: ；
The square root function is applied to adjust the scale of the position data and the effect of the time stamp is adjusted using the exponential function so that more recent time stamps have a greater effect on the result.
Assume thatA specific value of a data point is，
。
The calculation formula of the space positioning point cloud data:
: the weight factor of the ith data point;
Weighting factor May be determined based on the importance or criteria of the data points, such as data quality or reliability;
performing exponential decay processing on the position influence of each data point to reflect the distance or time, wherein the larger the weight is, the smaller the contribution of the data point is;
Assume that The data point L values were 599.90, 450.00, 500.00, weight W0.05,
The calculation formula of the hierarchical classification point cloud data comprises the following steps:
: classification weights for the jth data point;
Classification weight The importance assignment may be based on the category to which the data point belongs;
Will be Is brought into a cosine function to smooth the range of values, making it suitable for further analysis;
Assuming m=3, the weights V are 1,2,1.5, respectively, the last step As a result of (a)
The calculation formula of the grouped terrain point cloud data comprises the following steps:
: the weight of the kth class;
Category weight Depending on geography or other characteristics;
for each class Taking square root of the value, enhancing sensitivity to small values, and carrying out weighted average according to the weight;
Assuming p=2, weight Respectively, is 2 and 3, respectively,Values 1.5 and 2.0, respectively:
specifically, as shown in fig. 3, the step of obtaining the topography change analysis result specifically includes:
S211: based on grouped terrain point cloud data, initializing point cloud data, recording longitude and latitude and time stamps of each data point, and adopting the formula:
Analyzing the position change of each data point corresponding to the initial measurement to obtain an initial indicator of the topography change, wherein, A, b are longitude and latitude adjustment coefficients for the initial index of the terrain change,、To represent the longitude and latitude respectively,C and d are time adjustment coefficients and offset constants;
s212: calculating the change rate of each terrain change initial index, and applying the formula:
The rate of change of the terrain is calculated, wherein, In order to provide a rate of change of the terrain,AndRepresenting the current and previous terrain change indexes respectively, wherein M is the number of the change indexes;
s213: the global terrain change rate is estimated using a weighted product sum method, using the formula:
generating a topography variation analysis result, wherein, For the result of the terrain variation analysis, K is the number of rates of change,As a weight for the kth rate of change,Is the kth terrain rate of change.
The calculation formula of the initial index of the terrain change is deduced:
a. b: longitude and latitude adjustment coefficients are set by a geographic information system according to the terrain characteristics;
， : longitude and latitude of the data point;
: a time stamp;
c. d: the coefficients and offsets of the timestamp effect are adjusted.
For a data point, its longitude is set=100, Latitude=40, Timestamp=1609459200；
Let a=0.5, b=1.5, c=0.0001, d=100;
Calculating longitude and latitude adjustment values: adjustedValue = ；
Calculating a time adjustment value:
；
calculating initial index of topographic variation ：。
And (3) deriving a topographic change rate calculation formula:
、 : current and previous terrain variation indicators;
assuming a variation index of three data points, And=[62995，62998，62999]，
Calculating a change value of each point:
，
，
，
calculating the rate of change using a sine function:
And (3) deriving a calculation formula of a topographic variation analysis result:
: a weight factor for measuring the influence of each rate of change;
: kth terrain rate of change.
Assume three rates of changeAnd corresponding weight factors=[1，1.5，2]，
Calculating a weighted sum:
。
Specifically, as shown in fig. 4, the step of obtaining the terrain prediction result specifically includes:
s221: extracting data from the terrain variation analysis result, applying time sequence analysis, and adopting the formula:
calculating a predicted preliminary value by using an exponential smoothing method to obtain preliminary topography trend prediction data, wherein, For the preliminary terrain trend prediction data,In order to smooth the coefficient of the coefficient,In order to adjust the factor(s),As a result of the analysis of the topography change at the previous time point,For the predicted terrain data at the last point in time,Is a normalization factor;
s222: error analysis is carried out on the preliminary topography trend prediction data, and the formula is adopted:
calculating a difference between the real-time terrain data and the predicted terrain data, generating error data, wherein, In order to predict the error of the signal,As a result of the analysis of the topography change at the current time point,For the predicted terrain data at the current point in time,Is a normalization factor;
s223: using the error data to adjust the predictions in the future time period, using the formula:
adjusting the current predicted value according to the error, generating a terrain predicted result, wherein, In order to adjust the predicted terrain data,For the purpose of the error adjustment factor,As the predicted terrain data is not adjusted,Is the prediction error of the previous time point.
Calculating a predicted preliminary value formula by an exponential smoothing method:
: smoothing coefficients, e.g. selecting a value based on the volatility of the historical data ；
: Adjusting factors, enhancing or reducing the influence of historical predictors, depending on the trending of the data, e.g.；
: Normalization factors for balancing denominators, avoiding denominators being zero, e.g.。
Acquisition from historical dataThe result of the terrain change at the last time point is assumed to be 150;
Deriving from previous predictions Assume that the previous prediction was 140;
application formula calculation ：
Error data formula:
: normalization factors, e.g. ；
Obtaining the topographic variation result of the current time pointAssuming 160, useI.e. 12900.
Application formula calculation：
Terrain prediction result formula:
: error adjustment coefficients, e.g. =0.4；
UsingAssume that57686;
application formula calculation ：
。
Specifically, as shown in fig. 5, the acquisition steps of the monitoring plan are specifically:
S311: according to the terrain prediction result, calculating the risk factor score of the region, and adopting the formula:
calculating an integrated risk score for each region, resulting in a list of key regions, wherein, Representing the integrated risk score for region i,A score representing the jth predictor,Is a fine-tuning parameter which,Is the weighting coefficient of the j-th factor,Is a regularization parameter which is a function of the data,Is a small constant, n is the total number of predictors;
S312: according to the key region list, differential monitoring frequency and accuracy are set for each region, and the formula is as follows:
a monitored parameter of the critical area is generated, wherein, As a monitoring parameter of the critical area,For the integrated risk score for region i,AndThe maximum and minimum of the region risk scores, respectively.Is the adjustment parameter of the device, which is used for adjusting the parameters,Is an exponential parameter.
S313: and (3) utilizing the monitoring parameters of the key areas to formulate a monitoring strategy and a plan for each key area, wherein the formula is as follows:
a monitoring plan is calculated, wherein, For the monitoring plan of the area i,Is the monitoring parameter setting for region i,Is a conversion factor.
The calculation process of the integrated risk score comprises the following steps:
and (3) data collection: collecting the prediction factor corresponding to each region i Wherein j represents an index of a factor, from 1 to n;
factor adjustment: adding a trimming parameter to each predictor This may be a bias adjustment based on previous data;
square factor: the adjusted prediction factor Performing squaring operation to enhance the influence of factor change on the final risk score;
the weights are applied: multiplying the squared result by the weight of the factor The weight determines the importance of each factor in the overall risk score;
Regularization: using regularization parameters And a very small constantAvoiding zero errors while balancing the computation;
and (3) summing: summing the weighted scores of all factors to obtain a total risk score for region i
Assuming a region with three factors, the scoring of each factorAdjusting parametersWeighting ofRegularization parametersSum constant of，
，
，
，
。
Calculating a monitoring parameter formula of the key area:
determining an extremum: first determining the maximum in risk scores for all regions And minimum value；
Calculating a difference value: for each region i, calculate its risk scoreAnd maximum value ofTaking the square root of the difference between them helps to narrow the range of fractional changes, making the frequency adjustment more sensitive;
standardization: dividing the result obtained in the last step by the square root of the difference between the maximum and minimum risk scores, and carrying out normalization treatment to ensure that all values are between 0 and 1;
Application of adjustment parameters: multiplying the normalized result by the adjustment parameter The flexibility of monitoring the frequency can be adjusted as desired.
Nonlinear conversion is applied: indexing the above resultsThe processing further adjusts the nonlinear characteristic of the frequency so that the adjustment of the monitoring frequency is more sensitive to the change in the risk score.
Assume thatThe risk score extremum of the region is，Adjusting parametersNonlinear index，
，
。
Formulation of monitoring plan formula
Square root is calculated: monitoring frequencyCalculating the square root thereof to adjust the sensitivity of the frequency;
adjusting the planned intensity: by conversion factors To adjust the implementation strength of the monitoring plan, and the factor can be set according to actual needs;
calculating a final monitoring plan value: converting the factor Dividing the calculated square root value to obtain the specific monitoring plan intensity of each area.
Assuming conversion factorsIt is known that，
。
Specifically, as shown in fig. 6, the step of acquiring the monitoring parameter configuration result specifically includes:
S321: based on the monitoring plan, the current configuration of the device is evaluated, adjusted by the formula:
A preliminary updated device configuration is generated, wherein, Representing the configuration of the device after the preliminary update,Representing the original configuration of the device, P is the monitoring plan,Is the rate of learning to be performed,Is a regularization parameter which is a function of the data,Is a small constant that enhances the stability of the calculation,Is a small constant which is a function of the temperature,Is the power of the power;
s322: and adjusting parameters of the monitoring equipment by utilizing the initially updated equipment configuration, matching new monitoring requirements, and adopting the formula:
acquiring the adjusted device parameters, wherein, Is the parameters of the device after the adjustment,Is the configuration of the device after the preliminary update,Is an adjustment parameter, T is a threshold;
s323: according to the adjusted equipment parameters, configuration matching is carried out, and the formula is adopted as follows:
establishing a configuration result of the monitoring parameters, wherein, Is the result of the configuration of the monitoring parameters,Is the parameters of the device after the adjustment,Is the regulation factor, R is the monitoring requirement that the device should achieve,Is an additional adjustment factor.
Deducing a device configuration formula after preliminary updating:
Device original configuration : Assume thatObtained by the last detection of the device, here assumed to be；
Monitoring plan P: p represents a target configuration value adjusted according to new monitoring requirements, assuming p=70
Learning rate：Is a preset constant, controls the speed of configuration update, assuming=0.1；
Regularization parametersAnd a small constant：AndFor ensuring that the denominator is non-zero and for smoothing the adjustment process, it is assumed that=2 Sum=1；
Tuning constantAnd the power of：For further adjusting the value of the denominator, improving the accuracy of the adjustment, provided，Adjusting for nonlinear effects of updates, assuming=2。
Hypothesis calculationIs the difference of (a):；
raising the difference to a power ；
Calculating denominator:；
application formula calculation 。
The adjusted device parameters derive the formula:
Adjusted device parameters : Obtained from equation 1, used herein=62.41；
Adjusting parametersAnd threshold T: Control the steepness of the curve, assuming =0.5, T is the adjusted center point, assuming t=60;
Assume that the calculation of the index part: ；
application formula calculation 。
Monitoring parameter configuration result deduction formula:
Adjusted device parameters : From equation 2, here used=48；
Regulatory factorAdditional adjustment coefficients：Determining the sensitivity of configuration adjustments, assuming=0.2，For fine tuning the final result, assuming=0.1；
Monitoring requirement R that the device should reach: let r=75;
Calculating denominator: ；
Calculation of And apply the formula to calculate the difference of (C)：
。
Specifically, as shown in fig. 7, the step of acquiring the adjusted monitoring policy specifically includes:
S411: based on the monitoring parameter configuration result, calculating the difference between the newly collected point cloud data after the monitoring equipment is started and the previously collected point cloud data, and using the formula:
generating a point cloud data difference, wherein, As the difference value between the new and the old data,Representing the newly collected point cloud data,Representing point cloud data collected before,Is the stability factor of data point i,Is a small increase to avoid zero error, n is the number of data points;
S412: based on the difference value of the new data and the old data, real-time analysis is carried out, the change trend of the terrain infrastructure is identified, and the formula is adopted as follows:
a new trend of the topography is obtained, wherein, For the trend of the new topography change,As the difference value between the new and the old data,Is the weight of each point i, n is the number of points,Is a small constant for balanced weight summation;
S413: according to the new topography change trend, a monitoring strategy is adjusted, the data collection period and the analysis frequency are optimized, and the formula is adopted as follows:
An adjusted monitoring strategy is obtained, wherein, In order to adjust the monitoring strategy after the adjustment,For new topography trends, C is the current data collection period, F is the current analysis frequency,AndThe greatest historic values of the topography change and analysis frequency respectively,AndIs an adjustment parameter.
The difference value formula of new and old data:
assume new point cloud data collected from a monitoring device Is a vector:=[10，12，15]；
suppose previously collected point cloud data Is a vector:；
For each point i, the absolute difference between the new and old data is calculated: ；
Assuming a stability factor for each point i The method comprises the following steps:；
setting a small constant 0.01 To avoid divide by zero errors;
calculating the point cloud data difference by applying a formula: 。
Analyzing a new terrain variation trend formula in real time:
The weights are applied:
assume weights for each data point The method comprises the following steps:；
calculating the difference and the weight sum of the weight adjustment:
Calculating the difference of weight adjustment: ；
calculating the sum of the weights plus a small constant ；
Calculating new topography change trend：
The formula applies:。
and according to a monitoring strategy formula after the new periodic topography analysis result is adjusted:
Basic parameters assume:
current data collection period c=5, current analysis frequency f=2, maximum historic terrain variation =30, Maximum analysis frequency=5, Adjusting parameters=0.05 Sum=0.02；
Calculating a monitoring strategy adjustment factor:
Adjustment factor: ；
Frequency adjustment factor: ；
calculating an adjusted monitoring strategy ：
The formula applies:。
A point cloud based infrastructure monitoring system, the system comprising:
The point cloud data initialization module is used for associating the space position of each point with a time stamp in the point cloud data collection process based on the geographic mark, positioning and matching the space data through longitude and latitude, and determining the time sequence of the data points by using the time stamp to obtain a space time stamp set;
The point cloud data grouping module adopts a space time stamp set, performs space interval division on data through geographic information, performs partition management on the data points, and acquires a grouping geographic data set through space definition standards;
The terrain change analysis module processes the grouped geographic data set, applies terrain change detection logic to the grouped data set, determines the change amount of the terrain height and the position offset, and extracts the terrain dynamic change characteristics by utilizing time sequence comparison analysis to construct a terrain change index set;
the monitoring scheme design module evaluates the monitoring requirements of the key change areas based on the terrain change index set, sets monitoring frequency and precision parameters according to the change indexes, adjusts configuration parameters of monitoring equipment and generates monitoring strategy configuration;
the real-time monitoring and adjusting module is used for starting the monitoring equipment according to the monitoring strategy configuration, collecting new point cloud data in real time, identifying the change trend of the infrastructure in the new terrain, adjusting the monitoring strategy and the data analysis frequency, and obtaining the updated monitoring strategy.
Although the application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, it is intended that the present application cover the modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.
Claims (7)
1. A method of point cloud based infrastructure monitoring, the method comprising:
Initializing space positioning of point cloud data based on geographic marks, recording longitude and latitude of each data point, synchronizing the data by using a time stamp, structuring the data to generate space positioning point cloud data, classifying the space positioning point cloud data in a hierarchical manner, and grouping the space positioning point cloud data to obtain grouped topographic point cloud data;
Based on the grouped terrain point cloud data, a terrain variation analysis algorithm is applied to identify terrain variation indexes in each group of data, the variation rate of each index is calculated, a terrain variation analysis result is obtained, trend prediction is carried out on the terrain variation analysis result, the variation of the terrain in a short period is predicted, and a terrain prediction result is generated;
the step of obtaining the terrain variation analysis result comprises the following steps:
initializing point cloud data based on the grouped terrain point cloud data, recording longitude and latitude and a time stamp of each data point, and adopting the formula:
；
Analyzing the position change of each data point corresponding to the initial measurement to obtain an initial indicator of the topography change, wherein, A, b are longitude and latitude adjustment coefficients for the initial index of the terrain change,、To represent the longitude and latitude respectively,C and d are time adjustment coefficients and offset constants;
calculating the change rate of each terrain change initial index, and applying the formula:
；
The rate of change of the terrain is calculated, wherein, In order to provide a rate of change of the terrain,AndRepresenting the current and previous terrain change indexes respectively, wherein M is the number of the change indexes;
Integrating the terrain change rate, evaluating the overall terrain change using a weighted product sum method, using the formula:
；
generating a topography variation analysis result, wherein, For the result of the terrain variation analysis, K is the number of rates of change,As a weight for the kth rate of change,Is the kth terrain change rate;
Determining a key area needing to be monitored in an enhanced mode based on the terrain prediction result, setting monitoring frequency and accuracy, generating a monitoring plan, applying the monitoring plan to monitoring equipment, adjusting equipment parameters and matching new monitoring requirements to obtain a monitoring parameter configuration result;
And starting monitoring equipment to collect new point cloud data and analyze in real time based on the monitoring parameter configuration result, identifying new topography variation trend to obtain new periodic topography analysis result, adjusting the monitoring strategy according to the new periodic topography analysis result, optimizing the data collection period and analysis frequency, and establishing the adjusted monitoring strategy.
2. The method for monitoring point cloud based infrastructure according to claim 1, wherein the step of acquiring the group terrain point cloud data specifically comprises:
based on the geographic marks, initializing the space positioning of the point cloud data, recording the longitude and latitude and the time stamp of each data point, and adopting the formula:
；
calculating the spatial coordinates of each data point, resulting in an initialized set of spatial coordinates, wherein, The spatial coordinates representing the ith data point, a and b are adjustment coefficients for longitude and latitude,Represents a longitude of the person in question,Representing the latitude of the person in question,An exponential growth adjustment representing a timestamp, c being a time decay coefficient;
and carrying out structural arrangement on the initialized space coordinate data set, carrying out space structural arrangement according to geographic information requirements, and adopting the formula:
；
Integrating the data points to obtain space positioning point cloud data, wherein, Representing the cloud data of the spatial locating points,Represents the firstThe exponential decay weight factor of a data point,Representing the spatial coordinates of the ith data point, n representing the total number of data points;
Performing hierarchical classification on the space positioning point cloud data, classifying the point cloud data according to the topography and landform factors, and adopting the formula:
；
calculating a representative point cloud for each class, obtaining hierarchical classified point cloud data, wherein, Represents the hierarchical classification point cloud data, m represents the number of point cloud data in the classification,Spatial anchor point cloud data representing the jth data point,A classification weight representing a j-th point;
Grouping operation is carried out based on the hierarchical classification point cloud data, and the formula is adopted:
；
the grouped terrain point cloud data is calculated, wherein, Representing the grouped terrain point cloud data,Is a classification weight given according to geographic features, p represents the number of differential terrain classifications,Hierarchical classification point cloud data representing a kth classification.
3. The method for monitoring point cloud based infrastructure according to claim 1, wherein the step of obtaining the terrain prediction result specifically comprises:
Extracting data from the terrain variation analysis result, applying time sequence analysis, and adopting the formula:
；
calculating a predicted preliminary value by using an exponential smoothing method to obtain preliminary topography trend prediction data, wherein, For the preliminary terrain trend prediction data,In order to smooth the coefficient of the coefficient,In order to adjust the factor(s),As a result of the analysis of the topography change at the previous time point,For the predicted terrain data at the last point in time,Is a normalization factor;
And carrying out error analysis on the preliminary topography trend prediction data, and adopting the formula:
；
calculating a difference between the real-time terrain data and the predicted terrain data, generating error data, wherein, In order to predict the error of the signal,As a result of the analysis of the topography change at the current time point,For the predicted terrain data at the current point in time,Is a normalization factor;
and adjusting the prediction in the future time period by using the error data, and adopting the formula:
；
adjusting the current predicted value according to the error, generating a terrain predicted result, wherein, In order to adjust the predicted terrain data,For the purpose of the error adjustment factor,As the predicted terrain data is not adjusted,Is the prediction error of the previous time point.
4. A point cloud based infrastructure monitoring method according to claim 3, wherein the step of obtaining the monitoring plan is specifically:
According to the terrain prediction result, calculating a risk factor score of the region, and adopting the formula:
；
calculating an integrated risk score for each region, resulting in a list of key regions, wherein, Representing the integrated risk score for region i,A score representing the jth predictor,Is a fine-tuning parameter which,Is the weighting coefficient of the j-th factor,Is a regularization parameter which is a function of the data,Is a small constant, n is the total number of predictors;
According to the key region list, differential monitoring frequency and accuracy are set for each region, and the formula is as follows:
；
a monitored parameter of the critical area is generated, wherein, As a monitoring parameter of the critical area,For the integrated risk score for region i,AndThe maximum value and the minimum value of the regional risk score are respectively; Is the adjustment parameter of the device, which is used for adjusting the parameters, Is an exponential parameter;
And utilizing the monitoring parameters of the key areas to formulate a monitoring strategy and a plan for each key area, wherein the formula is as follows:
；
a monitoring plan is calculated, wherein, For the monitoring plan of the area i,Is the monitoring parameter setting for region i,Is a conversion factor.
5. The method for monitoring point cloud based infrastructure according to claim 4, wherein the step of obtaining the configuration result of the monitoring parameter specifically comprises:
based on the monitoring plan, evaluating a current configuration of the device, adjusting by a formula:
；
A preliminary updated device configuration is generated, wherein, Representing the configuration of the device after the preliminary update,Representing the original configuration of the device, P is the monitoring plan,Is the rate of learning to be performed,Is a regularization parameter which is a function of the data,Is a small constant that enhances the stability of the calculation,Is a small constant which is a function of the temperature,Is the power of the power;
And adjusting parameters of the monitoring equipment by utilizing the initially updated equipment configuration, matching new monitoring requirements, and adopting the following formula:
；
acquiring the adjusted device parameters, wherein, Is the parameters of the device after the adjustment,Is the configuration of the device after the preliminary update,Is an adjustment parameter, T is a threshold;
and carrying out configuration matching according to the adjusted equipment parameters, wherein the formula is as follows:
；
establishing a configuration result of the monitoring parameters, wherein, Is the result of the configuration of the monitoring parameters,Is the parameters of the device after the adjustment,Is the regulation factor, R is the monitoring requirement that the device should achieve,Is an additional adjustment factor.
6. The method for monitoring point cloud based infrastructure according to claim 5, wherein the step of obtaining the adjusted monitoring policy specifically comprises:
Based on the monitoring parameter configuration result, calculating the difference between the newly collected point cloud data after the monitoring equipment is started and the previously collected point cloud data, and using the formula:
；
generating a point cloud data difference, wherein, As the difference value between the new and the old data,Representing the newly collected point cloud data,Representing point cloud data collected before,Is the stability factor of data point i,Is a small increase to avoid zero error, n is the number of data points;
based on the difference value of the new data and the old data, real-time analysis is carried out, the change trend of the terrain infrastructure is identified, and the formula is adopted as follows:
；
a new trend of the topography is obtained, wherein, For the trend of the new topography change,As the difference value between the new and the old data,Is the weight of each point i, n is the number of points,Is a small constant for balanced weight summation;
According to the new topography variation trend, a monitoring strategy is adjusted, a data collection period and an analysis frequency are optimized, and the formula is adopted as follows:
；
An adjusted monitoring strategy is obtained, wherein, In order to adjust the monitoring strategy after the adjustment,For new topography trends, C is the current data collection period, F is the current analysis frequency,AndThe greatest historic values of the topography change and analysis frequency respectively,AndIs an adjustment parameter.
7. A point cloud based infrastructure monitoring system, characterized in that the point cloud based infrastructure monitoring method according to any of claims 1-6 is performed, the system comprising:
The point cloud data initialization module is used for associating the space position of each point with a time stamp in the point cloud data collection process based on the geographic mark, positioning and matching the space data through longitude and latitude, and determining the time sequence of the data points by using the time stamp to obtain a space time stamp set;
The point cloud data grouping module adopts the space time stamp set, performs space interval division on data through geographic information, performs partition management on the data points, and acquires a grouping geographic data set through space definition standards;
The terrain change analysis module processes the grouped geographic data set, applies terrain change detection logic to the grouped data set, determines the change amount of the terrain height and the position offset, and extracts the terrain dynamic change characteristics by utilizing time sequence comparison analysis to construct a terrain change index set;
The monitoring scheme design module evaluates the monitoring requirements of the key change areas based on the terrain change index set, sets monitoring frequency and precision parameters according to the change indexes, adjusts configuration parameters of monitoring equipment and generates monitoring strategy configuration;
And the real-time monitoring and adjusting module is used for configuring and starting monitoring equipment according to the monitoring strategy, collecting new point cloud data in real time, identifying the change trend of the infrastructure in the new terrain, adjusting the monitoring strategy and the data analysis frequency, and obtaining the updated monitoring strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410979759.2A CN118506291B (en) | 2024-07-22 | 2024-07-22 | Infrastructure monitoring method and system based on point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410979759.2A CN118506291B (en) | 2024-07-22 | 2024-07-22 | Infrastructure monitoring method and system based on point cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118506291A CN118506291A (en) | 2024-08-16 |
| CN118506291B true CN118506291B (en) | 2024-10-18 |
Family
ID=92234953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410979759.2A Active CN118506291B (en) | 2024-07-22 | 2024-07-22 | Infrastructure monitoring method and system based on point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118506291B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118365005A (en) * | 2024-06-18 | 2024-07-19 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Pollution and carbon reduction coupling index analysis method and system based on big data |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10151839B2 (en) * | 2012-06-01 | 2018-12-11 | Agerpoint, Inc. | Systems and methods for determining crop yields with high resolution geo-referenced sensors |
| EP3157322A4 (en) * | 2015-07-13 | 2017-11-15 | Agerpoint, Inc. | Modular systems and methods for determining crop yields with high resolution geo-referenced sensors |
| US11841439B2 (en) * | 2020-11-02 | 2023-12-12 | Waymo Llc | Point cloud segmentation using a coherent lidar for autonomous vehicle applications |
-
2024
- 2024-07-22 CN CN202410979759.2A patent/CN118506291B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118365005A (en) * | 2024-06-18 | 2024-07-19 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Pollution and carbon reduction coupling index analysis method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118506291A (en) | 2024-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guo et al. | Air pollution forecasting using artificial and wavelet neural networks with meteorological conditions | |
| CN104142142B (en) | Whole world vegetation fraction estimation method | |
| US20240242289A1 (en) | Spatial simulation method for assessment of direct economic losses of typhoon flood based on remote sensing | |
| Song et al. | Prediction of landslides using ASTER imagery and data mining models | |
| CN111401602B (en) | Assimilation method for satellite and ground rainfall measurement values based on neural network | |
| Simanjuntak et al. | Object-based image analysis to map local climate zones: The case of Bandung, Indonesia | |
| Libertino et al. | Regional-scale analysis of extreme precipitation from short and fragmented records | |
| US20190228223A1 (en) | Identification and localization of anomalous crop health patterns | |
| Karimzadeh et al. | A deep learning model for road damage detection after an earthquake based on synthetic aperture radar (SAR) and field datasets | |
| CN103529189A (en) | Soil organic matter space distribution predication method based on qualitative and quantitative auxiliary variables | |
| CN113610301B (en) | A Prediction Algorithm for Characterizing the Time Series Evolution of Land Subsidence | |
| CN105426587A (en) | Method for completing pavement condition acquisition and monitoring based on smart phone | |
| WO2024152865A1 (en) | Meteorological-station-based ecosystem carbon-water flux calculation method and system | |
| CN115356732B (en) | InSAR deformation result-oriented potential landslide risk area identification method | |
| CN116595121A (en) | Data display monitoring system based on remote sensing technology | |
| CN113011372A (en) | Automatic monitoring and identifying method for saline-alkali soil | |
| CN118505702B (en) | A fast calculation method for sandy coastal erosion based on multi-period remote sensing images | |
| CN118211481A (en) | Hydrologic information prediction method and system based on regional drainage basin | |
| Hofer et al. | A statistical downscaling method for daily air temperature in data-sparse, glaciated mountain environments | |
| CN118506291B (en) | Infrastructure monitoring method and system based on point cloud | |
| CN119131514A (en) | A method for detecting open-pit mine disasters based on drones | |
| CN116110210B (en) | Data-driven landslide hazard auxiliary decision-making method in complex environment | |
| Hiester et al. | A topological approach for quantitative comparisons of ocean model fields to satellite ocean color data | |
| CN118365165A (en) | Carbon emission measuring and calculating method and system for regional atmosphere treatment | |
| ESLAMINEZHAD et al. | DEVELOPMENT OF A DATA-DRIVEN MODEL TO PREDICT LANDSLIDE SENSITIVE AREAS. |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |