CN116793256A - Intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling - Google Patents
Intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling Download PDFInfo
- Publication number
- CN116793256A CN116793256A CN202311051354.4A CN202311051354A CN116793256A CN 116793256 A CN116793256 A CN 116793256A CN 202311051354 A CN202311051354 A CN 202311051354A CN 116793256 A CN116793256 A CN 116793256A
- Authority
- CN
- China
- Prior art keywords
- earthwork
- measured
- point cloud
- measurement
- result
- 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.)
- Granted
Links
- 238000000691 measurement method Methods 0.000 title abstract description 17
- 238000005259 measurement Methods 0.000 claims abstract description 79
- 238000004458 analytical method Methods 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 43
- 230000009467 reduction Effects 0.000 claims abstract description 24
- 238000013507 mapping Methods 0.000 claims description 24
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 230000011218 segmentation Effects 0.000 claims description 16
- 238000003066 decision tree Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 14
- 239000000463 material Substances 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012806 monitoring device Methods 0.000 claims description 7
- 230000003746 surface roughness Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 16
- 230000008569 process Effects 0.000 abstract description 7
- 238000012876 topography Methods 0.000 abstract description 6
- 238000012952 Resampling Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004567 concrete Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- 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
- Y02A90/30—Assessment of water resources
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application provides an intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling, which relate to the technical field of intelligent measurement and are used for acquiring basic information of earthwork to be measured, initially setting an image set and locating point distribution coordinates, constructing a control parameter distribution model for analysis, outputting a control set, controlling a three-dimensional scanning device to scan and collect the earthwork to be measured, acquiring scanning point cloud data and performing noise reduction splicing to complete modeling measurement of the earthwork to be measured, and solve the technical problems that in the prior art, when the earthwork is measured in the earthwork engineering, the measurement process is not strict enough due to insufficient intelligence of the measurement method and multidimensional influence factors exist, and the measurement result accuracy is insufficient due to higher measurement difficulty of the topography influence, so that the potential risk of subsequent railway construction is caused. And the three-dimensional laser scanning modeling is carried out on the earthwork to be measured, so that the target consistency point cloud model is determined to measure, the measurement difficulty is weakened, and the accuracy of a measurement result is ensured.
Description
Technical Field
The application relates to the technical field of intelligent measurement, in particular to an intelligent earth measurement method and system based on three-dimensional laser scanning modeling.
Background
The earthwork comprises the steps of digging, filling, transporting and the like of earthwork, is one of main projects in the construction engineering, and particularly aims at the special characteristics of large project quantity and complex construction conditions of railway engineering, and has high construction difficulty due to limited construction process, so that the earthwork measurement planning is needed in advance for guaranteeing the final railway construction energy efficiency.
At present, on-site mapping is performed based on an earthwork measuring instrument, and various measuring methods are assisted to measure the earthwork. The current traditional measurement method mostly depends on professionals, and due to the existing internal and external influence factors, measurement result deviation is easy to cause, and optimization adjustment is needed.
At present, when measurement is carried out in earthwork, the measurement process is not strict enough due to the fact that the measurement method is insufficient in intelligence and multidimensional influence factors exist, and the measurement difficulty is high due to the fact that the topography influence is large, so that the accuracy of a measurement result is insufficient, and potential risks of subsequent railway construction are caused.
Disclosure of Invention
The application provides an intelligent earth measurement method and system based on three-dimensional laser scanning modeling, which are used for solving the technical problems that in the prior art, when measurement is performed in earth works, the measurement process is not strict enough due to insufficient intelligence of the measurement method and multidimensional influence factors exist, and the measurement result accuracy is insufficient due to high difficulty of measurement due to the influence of topography, so that the potential risk of subsequent railway construction is caused.
In view of the problems, the application provides an intelligent earth measurement method and system based on three-dimensional laser scanning modeling.
In a first aspect, the application provides an intelligent earth measurement method based on three-dimensional laser scanning modeling, which comprises the following steps:
acquiring basic information of earthwork to be measured;
the image acquisition device is used for acquiring the image of the earthwork to be measured, and an initial set image set is obtained;
collecting locating points of the earthwork to be measured to obtain locating point distribution coordinates;
inputting the initial set image set and the positioning point distribution coordinates of the basic information into a control parameter distribution model, and outputting a control set, wherein the control parameter distribution model performs neural network training building according to a control parameter decision tree, and the control parameter decision tree is built through hierarchical mapping association of hierarchical identification nodes and hierarchical decision nodes configured by decision processing of sample data;
the three-dimensional scanning device is controlled by the control set to carry out scanning acquisition of the earthwork to be measured, and scanning point cloud data are obtained;
extracting noise characteristics from the characteristics of the earthwork to be measured on the initial set image set, wherein the noise characteristics have position marks;
and carrying out noise reduction splicing on the scanning point cloud data through the noise characteristics, and carrying out modeling measurement on the earthwork to be measured based on a noise reduction splicing result.
In a second aspect, the present application provides an intelligent earth measurement system based on three-dimensional laser scanning modeling, the system comprising:
the information acquisition module is used for acquiring basic information of earthwork to be measured;
the image acquisition module is used for acquiring the image of the earthwork to be measured through the image acquisition device to obtain an initial set image set;
the positioning point acquisition module is used for acquiring positioning points of the earthwork to be measured to obtain positioning point distribution coordinates;
the control analysis module is used for inputting the initial set image set and the positioning point distribution coordinates of the basic information into a control parameter distribution model and outputting a control set, wherein the control parameter distribution model performs neural network training building according to a control parameter decision tree, and the control parameter decision tree is built through the hierarchical mapping association between hierarchical identification nodes configured by the decision processing of sample data and hierarchical decision nodes;
the point cloud data acquisition module is used for controlling the three-dimensional scanning device to perform scanning acquisition of the earthwork to be measured through the control set to obtain scanning point cloud data;
the feature extraction module is used for extracting noise features from the features of the earthwork to be measured on the initial set image set, wherein the noise features have position marks;
and the modeling measurement module is used for carrying out noise reduction splicing on the scanning point cloud data through the noise characteristics and carrying out modeling measurement on the earthwork to be measured based on a noise reduction splicing result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
according to the intelligent earthwork measuring method based on three-dimensional laser scanning modeling, basic information of earthwork to be measured and an initial set image set are acquired, positioning point acquisition is carried out on the earthwork to be measured, and positioning point distribution coordinates are obtained; constructing a control parameter distribution model for analysis, outputting a control set, and controlling the three-dimensional scanning device to perform scanning acquisition of the earthwork to be measured to obtain scanning point cloud data; noise characteristics are extracted to carry out noise reduction splicing on the scanning point cloud data, modeling measurement of earthwork to be measured is carried out based on noise reduction splicing results, and the technical problems that in the prior art, when measurement is carried out in earthwork, due to the fact that the measurement method is insufficient in intelligence and multidimensional influence factors exist, a measurement flow is not strict enough, and due to the fact that the measurement difficulty is high due to the fact that the influence of topography is large, accuracy of the measurement results is insufficient, and potential risks of subsequent railway construction are caused are solved. And the three-dimensional laser scanning modeling is carried out on the earthwork to be measured, so that the target consistency point cloud model is determined to measure, the measurement difficulty is weakened, and the accuracy of a measurement result is ensured.
Drawings
FIG. 1 is a schematic flow chart of an intelligent earth measurement method based on three-dimensional laser scanning modeling;
FIG. 2 is a schematic diagram of a process for obtaining noise characteristics in an intelligent earth measurement method based on three-dimensional laser scanning modeling;
FIG. 3 is a schematic diagram of a screening flow of an earthwork metering method in an intelligent earthwork measuring method based on three-dimensional laser scanning modeling;
fig. 4 is a schematic diagram of an intelligent earth measurement structure based on three-dimensional laser scanning modeling.
Reference numerals illustrate: the system comprises an information acquisition module 11, an image acquisition module 12, a positioning point acquisition module 13, a control analysis module 14, a point cloud data acquisition module 15, a feature extraction module 16 and a modeling measurement module 17.
Detailed Description
The application provides an intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling, which are used for acquiring basic information of earthwork to be measured, an initial set image set and locating point distribution coordinates, constructing a control parameter distribution model for analysis, outputting a control set, controlling a three-dimensional scanning device to scan and collect the earthwork to be measured, obtaining scanning point cloud data and performing noise reduction splicing, and performing modeling measurement of the earthwork to be measured based on a noise reduction splicing result.
Example 1
As shown in fig. 1, the application provides an intelligent earth measurement method based on three-dimensional laser scanning modeling, the method is applied to an intelligent earth measurement system, the intelligent earth measurement system is in communication connection with an image acquisition device and a three-dimensional scanning device, and the method comprises the following steps:
step S100: acquiring basic information of earthwork to be measured;
specifically, the earthwork comprises the steps of digging, filling, transporting and the like of earthwork, and is one of main projects in the construction engineering, particularly for railway engineering, due to the characteristics of large project quantity and complex construction conditions, construction difficulty is high due to limited construction progress. Specifically, the earthwork to be measured is a target earthwork to be subjected to engineering construction, information such as coverage area, landform information, soil volume weight, barrier distribution and the like of the earthwork to be measured is collected and used as basic information of the earthwork to be measured, and the basic information is a basic basis for carrying out earthwork measurement.
Step S200: the image acquisition device is used for acquiring the image of the earthwork to be measured, and an initial set image set is obtained;
step S300: collecting locating points of the earthwork to be measured to obtain locating point distribution coordinates;
specifically, the image acquisition device is arranged in the coverage area of the earthwork to be measured, the omnibearing multi-angle image acquisition is carried out on the earthwork to be measured based on the image acquisition device, the acquired images are sequentially adjusted based on the transition of the acquisition angles, and the initial set image set is generated. Preferably, the image acquisition distance can be set and adjusted, and the global image and the local image are acquired respectively, so that the completeness of image acquisition is ensured, and the completeness of image coverage information is ensured.
Further, based on the coverage area of the earthwork to be measured, a coordinate axis is determined based on the spatial position, and a spatial coordinate system is further constructed. And carrying out structure recognition on the earthwork to be measured, and recognizing and extracting a plurality of positioning points which can represent the structural condition of the earthwork to be measured, such as corner positioning, edge positioning and the like. The distribution density of specific positioning points is determined according to the structural complexity of different positions. And carrying out position mapping correspondence on the determined positioning points based on the space coordinate system, and determining positioning coordinates in the space coordinate system to form the positioning point distribution coordinates. Based on the distribution coordinates of the positioning points, the main body framework of the earthwork to be measured can be determined.
Step S400: inputting the initial set image set and the positioning point distribution coordinates of the basic information into a control parameter distribution model, and outputting a control set, wherein the control parameter distribution model performs neural network training building according to a control parameter decision tree, and the control parameter decision tree is built through hierarchical mapping association of hierarchical identification nodes and hierarchical decision nodes configured by decision processing of sample data;
specifically, the control parameter distribution model is constructed, and the control parameter distribution model is an analysis model for performing point cloud scanning control parameters of the three-dimensional scanning device. Illustratively, one way of modeling the feasibility is as follows: carrying out big data investigation and statistics to determine engineering data of a plurality of earthworks, including sample image sets and sample basic information, carrying out positioning point analysis on the basis, determining sample positioning point distribution coordinates, extracting control parameters corresponding to each sample, and directly obtaining the parameter data because the engineering data are constructed engineering. And taking the sample image set, the sample basic information and the sample positioning point distribution coordinates as identification information, determining a hierarchy identification node, taking corresponding sample control parameters as hierarchy decision nodes, carrying out mapping connection on the hierarchy identification node and the hierarchy decision nodes, generating a control parameter decision tree, and generating the control parameter distribution model by carrying out neural network training based on the control parameter decision tree. Inputting the initial set image set, the basic information and the positioning point distribution coordinates into the control parameter distribution model, and directly determining corresponding control parameters by performing data matching mapping to serve as the control set for output. And the control parameter distribution model is constructed to determine the control set, so that the analysis rate can be ensured, and the objectivity and accuracy of an analysis result are improved.
Step S500: the three-dimensional scanning device is controlled by the control set to carry out scanning acquisition of the earthwork to be measured, and scanning point cloud data are obtained;
specifically, the control set is a control parameter for performing target scanning on the three-dimensional scanning device, such as a scanning range, a point cloud interval density, and the like. And controlling the three-dimensional scanning device based on the control set, and emitting laser to the earthwork to be measured based on a certain scanning density, wherein the three-dimensional scanning device can be a three-dimensional laser scanner for recording laser echo signals and laser flight time. Determining the distance between the earthwork to be measured and the three-dimensional scanning device based on the laser flight time; and determining the point cloud position, color information, reflection intensity information and the like of the earthwork to be measured based on the laser echo signals, performing attribution integration on each point cloud data, and generating the scanning point cloud data. And the scanning point cloud data are source data for carrying out the earth modeling to be measured.
Further, the intelligent earth measurement system is communicatively connected to the shake monitoring device, and step S500 of the present application further includes:
step S510-1: the three-dimensional scanning device is subjected to jitter monitoring through the jitter monitoring device, and a mapping relation between jitter data and scanning point cloud data is established according to jitter monitoring time and three-dimensional acquisition parameters;
step S520-1: performing jitter feature analysis on the jitter data to extract jitter features;
step S530-1: and according to the established mapping relation, denoising compensation of the scanning point cloud data is carried out based on the jitter characteristics.
Further, the step S500 of the present application further includes:
step S510-2: performing outlier analysis on the scanning point cloud data to obtain outlier analysis results;
step S520-2: and when the point abnormal value of the abnormal point analysis result cannot meet the preset point threshold value, executing a re-acquisition instruction, and re-acquiring the point cloud data of the node at the position corresponding to the abnormal point.
Specifically, in the target scanning process of the three-dimensional scanning device, due to the systematic error existing in the device, for example, jitter caused by rotation of a laser radar, deviation exists in the point cloud data acquisition result, and deviation compensation is performed by performing jitter characteristic analysis. Specifically, the shake monitoring device is a functional device for collecting live shake monitoring, and based on the shake monitoring device, the shake data is obtained by performing real-time shake monitoring of the three-dimensional scanner. The jitter data is provided with the jitter monitoring time identifier, the three-dimensional acquisition parameters are spatial position parameters corresponding to the acquired point cloud data, and mapping and corresponding the dithering data and the scanning point cloud data by taking the dithering monitoring time and the three-dimensional sub-surface and parameters as mapping association reference bases, and determining the mapping relation. And further carrying out jitter characteristic analysis on prime number jitter data, wherein the jitter characteristic analysis comprises jitter directions and jitter amplitudes, and the jitter characteristics corresponding to different scanning point cloud data are different as the jitter characteristics. And based on the mapping relation, matching and corresponding the jitter characteristics and the scanning point cloud data to adjust and correct the spatial position of the scanning point cloud data so as to finish denoising compensation of the point cloud data and further improve the data accuracy.
Further, the scan point cloud data is subjected to outlier analysis, that is, abnormal data determination, for example, data deviating from the overall trend of the same type of data, and then can be regarded as outlier data, and outliers in the scan point cloud data are identified, so that an outlier analysis result is generated, for example, identification is performed based on a specific identifier. And setting the preset point threshold, namely judging critical limiting data of abnormal degree of the point abnormal value, for example, the point abnormal value is less than 10%. When the point abnormal value of the abnormal point analysis result does not meet the preset point threshold value, the data abnormal degree is higher, the resampling necessity exists to ensure the follow-up modeling accuracy, the resampling instruction is generated, namely, the starting instruction of the abnormal point scanning point cloud data acquisition is performed again, along with the receiving of the resampling instruction, the point cloud data is acquired again for the position node corresponding to the abnormal point, the abnormal point data is covered, and the accuracy of the data is ensured.
Step S600: extracting noise characteristics from the characteristics of the earthwork to be measured on the initial set image set, wherein the noise characteristics have position marks;
further, as shown in fig. 2, step S600 of the present application further includes:
step S610: performing scene aggregation in the image on the initial set image set, and generating a scene segmentation area based on a scene aggregation result;
step S620: respectively carrying out material identification based on the scene segmentation areas to obtain material identification results, wherein the material identification results are used as first earthwork surface features;
step S630: carrying out earth surface roughness recognition on the scene segmentation area to obtain a roughness recognition result;
step S640: taking the roughness identification result as a second earthwork surface characteristic;
step S650: the noise feature is extracted based on the first and second earthwork surface features.
Specifically, in the process of scanning the earthwork to be measured, the three-dimensional scanning device generates redundant data, namely noise points, which are different from the entity of the earthwork to be measured to a certain extent due to the influence of factors such as surface roughness, surface materials and the like, so as to influence the precision and efficiency of subsequent three-dimensional modeling, and noise feature extraction is performed on the earthwork to be measured, so that noise reduction processing is performed subsequently.
Specifically, scene recognition is performed based on the initial set image set, and multidimensional scene features, such as geographic features, obstacles and the like, are determined. And combining the areas with the same characteristic attribute by taking the multi-dimensional scene characteristics as scene aggregation basis, dividing the areas with different characteristic attributes, and dividing the earthwork coverage area to be measured into a plurality of subareas serving as the scene division areas. And respectively carrying out material identification on each scene area, such as wood, stone, concrete and the like, aiming at the scene segmentation areas, and mapping and corresponding the material identification result and the scene segmentation areas to obtain the first earthwork surface characteristics. And further respectively carrying out earth surface roughness recognition on the scene segmentation areas, for example, directly measuring the surface roughness according to an optical instrument, mapping and corresponding the measurement result and the scene segmentation areas, and generating the roughness recognition result. And taking the roughness identification result as the second earthwork surface characteristic. And determining corresponding noise characteristics, such as phase deviation of laser echo signals, and the like, based on the first earthwork surface characteristics and the second earthwork surface characteristics, positioning noise points, and further performing position identification on the noise characteristics. And determining the noise characteristics through accurate recognition so as to carry out targeted noise positioning removal later.
Step S700: and carrying out noise reduction splicing on the scanning point cloud data through the noise characteristics, and carrying out modeling measurement on the earthwork to be measured based on a noise reduction splicing result.
Further, step S700 of the present application further includes:
step S710-1: after the noise reduction of the scanned point cloud data is completed, obtaining a point cloud initial positioning distribution result through the positioning point distribution coordinates;
step S720-1: performing first clustering of the point cloud based on the initial positioning distribution result of the point cloud;
step S730-1: and performing characteristic point cloud splicing on the similar point clouds after the first clustering is completed, performing inter-point cloud clustering splicing after the splicing is completed, and performing modeling measurement of the earthwork to be measured based on a clustering splicing result.
Specifically, based on the noise characteristics, the scanned point cloud data is subjected to characteristic recognition, data corresponding to the identification position is determined, noise reduction processing is performed, the noise reduction processing method is not particularly limited, for example, a mean value filtering method and the like, and the scanned point cloud data with noise reduction completed is determined. And matching the locating point distribution coordinates with the scanned point cloud with the noise reduced, and carrying out locating distribution on the scanned point cloud data with the noise reduced at the locating point distribution coordinates to serve as an initial locating distribution result of the point cloud. And clustering the scanned point clouds based on the distribution position based on the initial positioning distribution result of the point clouds, for example, based on the scene segmentation area, performing splicing processing of the scanned point clouds in the area, and executing first clustering of the point clouds.
Furthermore, the scanning point clouds in the same scene area are used as the same kind of scanning point clouds to carry out characteristic point cloud splicing. The specific implementation mode of the characteristic point cloud coordinate is that geographic coordinate conversion is carried out based on an indirect method, a plurality of characteristic points are determined to be common points, namely relative reference characteristics, the similar scanning point clouds are converted into a unified coordinate system, point cloud splicing is completed, and a point cloud splicing result corresponds to the scene segmentation area. Further, after the splicing is completed, the point cloud splicing is executed again on the basis, the specific splicing mode is the same, coordinate conversion is carried out again on a plurality of different coordinate system data acquired by primary splicing, integral point cloud coordinate data with regional completeness is generated, the cluster splicing result is used as the cluster splicing result and is matched with earthwork to be measured, the cluster splicing result is a built point cloud model and is used as earthwork modeling, and the earthwork to be measured is carried out based on the earthwork modeling, so that the measurement difficulty can be effectively weakened.
Further, as shown in fig. 3, step S700 of the present application further includes:
step S710-2: performing terrain feature evaluation based on the initial set image set and the earth modeling to obtain terrain evaluation features and feature values;
step S720-2: constructing an earthwork metering database;
step S730-2: screening the earthwork metering database by a metering method based on the terrain evaluation characteristics and the characteristic values to obtain screening results;
step S740-2: and finishing the measurement of the earthwork to be measured through the screening result and the earthwork modeling.
Specifically, the calculation of the earthwork amount is performed based on the earthwork modeling, the metering efficiency and the effect of different metering methods are different due to the difference of specific terrains, and the optimal metering mode is determined in a matching mode based on the terrains of the earthwork to be measured. Specifically, based on the initial set image set and the earthwork modeling, performing terrain feature recognition extraction, such as terrain relief, terrain rule degree and the like, on the earthwork to be measured, wherein the terrain feature value is used as the terrain evaluation feature, and the specific feature value is used as the feature value, such as specific amplitude of the terrain relief and the like. And acquiring big data to obtain a plurality of executable metering modes, determining a specific metering method and suitable earthwork characteristics, and correspondingly integrating the specific metering method and the suitable earthwork characteristics to generate the earthwork metering database, wherein a section method is suitable for a section with large topography fluctuation and irregularity. Traversing the earthwork metering database, and screening and determining a characteristic fit metering method based on the terrain evaluation characteristic and the characteristic value to serve as the screening result. The screening result is a measurement mode to be executed, the earthwork measurement of the earthwork to be measured is carried out in the earthwork modeling, the consistency of the measurement result and the earthwork to be measured is guaranteed, preferably, the earthwork to be measured can be divided according to the situation distribution condition of the earthwork to be measured, the matching of the preferable measurement modes is carried out respectively according to different situation conditions, and the measurement effect can be further improved.
Further, the present application also includes step S800, including:
step S810: performing measurement result verification on the earthwork to be measured to obtain a measurement result deviation value;
step S820: judging whether the measured result deviation value is within an expected deviation threshold range or not;
step S830: when the measured result deviation value is not in the expected deviation threshold range, carrying out error source analysis of modeling measurement on the earthwork to be measured to obtain an error source analysis result;
step S840: and constructing an earthwork modeling metering compensation database based on the error source analysis result.
Specifically, the earthwork to be measured is measured in a matching preference metering mode, and the measurement result is obtained. And verifying the measurement result to judge the measurement accuracy, and acquiring the deviation value of the measurement result. For example, a plurality of verification points are determined for the earthwork to be measured, setting can be randomly performed, actual measurement is performed, mapping and checking are performed with corresponding measurement results in the earthwork modeling, and the measurement result deviation value is determined. Setting the threshold value of the expected deviation value, namely, critical data for judging the deviation degree of the measurement result, such as the deviation amplitude of 5%, further judging whether the deviation value of the measurement result is in the range of the expected deviation value, and if so, indicating that the deviation degree is smaller and can be properly ignored; when the measured data is not in the range, the deviation degree of the measured data is larger, data compensation is needed to ensure the data accuracy, error source analysis of modeling measurement is carried out on the earthwork to be measured, and the data deviation direction and the deviation amplitude are determined to carry out specific judgment. Specifically, the data acquisition and processing flow is subjected to inspection so as to perform error source positioning, and an error source, an error direction and an error scale are determined and used as the error source analysis result, wherein the error source analysis result is the complete coverage analysis result of the earthwork to be measured. Determining the error source analysis result. And determining adjustment data of different error positions based on the error source analysis result, and integrally generating the earthwork modeling metering compensation database. And adjusting the measurement result based on the earthwork modeling metering compensation database, and further improving the accuracy of the measurement result.
Example two
Based on the same inventive concept as the intelligent earth measurement method based on three-dimensional laser scanning modeling in the foregoing embodiments, as shown in fig. 4, the present application provides an intelligent earth measurement system based on three-dimensional laser scanning modeling, the system comprising:
the information acquisition module 11 is used for acquiring basic information of earthwork to be measured;
the image acquisition module 12 is used for acquiring the image of the earthwork to be measured through the image acquisition device, so as to obtain an initial set image set;
the positioning point acquisition module 13 is used for acquiring positioning points of the earthwork to be measured, and acquiring positioning point distribution coordinates;
the control analysis module 14 is configured to input the initial set image set and the positioning point distribution coordinates of the basic information into a control parameter distribution model, and output the control set, where the control parameter distribution model performs neural network training building according to a control parameter decision tree, and the control parameter decision tree is built in association with hierarchical mapping of hierarchical identification nodes and hierarchical decision nodes, which are configured by decision processing of sample data;
the point cloud data acquisition module 15 is used for controlling the three-dimensional scanning device to perform scanning acquisition of the earthwork to be measured through the control set, so as to obtain scanning point cloud data;
the feature extraction module 16 is configured to perform feature extraction of noise features of the earthwork to be measured on the initial set image set, where the noise features have a location identifier;
the modeling measurement module 17 is configured to perform noise reduction stitching on the scan point cloud data according to the noise characteristics, and perform modeling measurement on the earthwork to be measured based on a noise reduction stitching result.
Further, the system further comprises:
the scene segmentation module is used for carrying out intra-image scene aggregation on the initial set image set and generating scene segmentation areas based on scene aggregation results;
the material identification module is used for respectively carrying out material identification based on the scene segmentation areas to obtain material identification results, and the material identification results are used as first earthwork surface characteristics;
the surface roughness recognition module is used for recognizing the earth surface roughness of the scene segmentation area and obtaining a roughness recognition result;
the characteristic determining module is used for taking the roughness recognition result as a second earthwork surface characteristic;
and the noise feature extraction module is used for extracting and obtaining the noise feature based on the first earthwork surface feature and the second earthwork surface feature.
Further, the system further comprises:
the distribution result determining module is used for obtaining a point cloud initial positioning distribution result through the positioning point distribution coordinates after the scanning point cloud data is subjected to noise reduction;
the point cloud clustering module is used for carrying out first clustering on the point cloud based on the point cloud initial positioning distribution result;
and the point cloud splicing module is used for carrying out characteristic point cloud splicing on the similar point clouds after the first clustering is completed, and after the splicing is completed, carrying out inter-point cloud clustering splicing, and carrying out modeling measurement of the earthwork to be measured based on a clustering splicing result.
Further, the system further comprises:
the mapping relation establishing module is used for carrying out jitter monitoring on the three-dimensional scanning device through the jitter monitoring device and establishing a mapping relation between jitter data and scanning point cloud data according to jitter monitoring time and three-dimensional acquisition parameters;
the jitter feature extraction module is used for carrying out jitter feature analysis on the jitter data and extracting jitter features;
and the data compensation module is used for carrying out denoising compensation on the scanning point cloud data based on the jitter characteristics according to the established mapping relation.
Further, the system further comprises:
the topographic feature evaluation module is used for evaluating topographic features based on the initial set image set and the earthwork modeling to obtain topographic evaluation features and feature values;
the database construction module is used for constructing an earthwork metering database;
the metering method screening module is used for screening the earthwork metering database by a metering method based on the topography evaluation characteristics and the characteristic values to obtain screening results;
and the earthwork metering module is used for finishing the metering of the earthwork to be measured through the screening result and the earthwork modeling.
Further, the system further comprises:
the result verification module is used for verifying the measurement result of the earthwork to be measured to obtain a measurement result deviation value;
the deviation value judging module is used for judging whether the deviation value of the measurement result is within an expected deviation threshold value range or not;
the error source analysis module is used for carrying out error source analysis of modeling measurement on the earthwork to be measured when the deviation value of the measurement result is not in the range of the expected deviation threshold value, so as to obtain an error source analysis result;
and the compensation database construction module is used for constructing an earthwork modeling metering compensation database based on the error source analysis result.
Further, the system further comprises:
the abnormal point analysis module is used for carrying out abnormal point analysis on the scanning point cloud data to obtain an abnormal point analysis result;
and the re-acquisition module is used for executing a re-acquisition instruction when the point abnormal value of the abnormal point analysis result cannot meet the preset point threshold value, and re-acquiring the point cloud data of the position node corresponding to the abnormal point.
In the present disclosure, through the foregoing detailed description of an intelligent method for measuring earthwork based on three-dimensional laser scanning modeling, those skilled in the art can clearly understand that the method and the system for intelligent method for measuring earthwork based on three-dimensional laser scanning modeling in this embodiment, for the device disclosed in the embodiment, since the device corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The method is characterized by being applied to an intelligent earth measuring system, wherein the intelligent earth measuring system is in communication connection with an image acquisition device and a three-dimensional scanning device, and the method comprises the following steps:
acquiring basic information of earthwork to be measured;
the image acquisition device is used for acquiring the image of the earthwork to be measured, and an initial set image set is obtained;
collecting locating points of the earthwork to be measured to obtain locating point distribution coordinates;
inputting the initial set image set and the positioning point distribution coordinates of the basic information into a control parameter distribution model, and outputting a control set, wherein the control parameter distribution model performs neural network training building according to a control parameter decision tree, and the control parameter decision tree is built through hierarchical mapping association of hierarchical identification nodes and hierarchical decision nodes configured by decision processing of sample data;
the three-dimensional scanning device is controlled by the control set to carry out scanning acquisition of the earthwork to be measured, and scanning point cloud data are obtained;
extracting noise characteristics from the characteristics of the earthwork to be measured on the initial set image set, wherein the noise characteristics have position marks;
and carrying out noise reduction splicing on the scanning point cloud data through the noise characteristics, and carrying out modeling measurement on the earthwork to be measured based on a noise reduction splicing result.
2. The method of claim 1, wherein the method comprises:
performing scene aggregation in the image on the initial set image set, and generating a scene segmentation area based on a scene aggregation result;
respectively carrying out material identification based on the scene segmentation areas to obtain material identification results, wherein the material identification results are used as first earthwork surface features;
carrying out earth surface roughness recognition on the scene segmentation area to obtain a roughness recognition result;
taking the roughness identification result as a second earthwork surface characteristic;
the noise feature is extracted based on the first and second earthwork surface features.
3. The method of claim 1, wherein the method comprises:
after the noise reduction of the scanned point cloud data is completed, obtaining a point cloud initial positioning distribution result through the positioning point distribution coordinates;
performing first clustering of the point cloud based on the initial positioning distribution result of the point cloud;
and performing characteristic point cloud splicing on the similar point clouds after the first clustering is completed, performing inter-point cloud clustering splicing after the splicing is completed, and performing modeling measurement of the earthwork to be measured based on a clustering splicing result.
4. The method of claim 1, wherein the intelligent earth measurement system is communicatively coupled to a shake monitoring device, the method comprising:
the three-dimensional scanning device is subjected to jitter monitoring through the jitter monitoring device, and a mapping relation between jitter data and scanning point cloud data is established according to jitter monitoring time and three-dimensional acquisition parameters;
performing jitter feature analysis on the jitter data to extract jitter features;
and according to the established mapping relation, denoising compensation of the scanning point cloud data is carried out based on the jitter characteristics.
5. The method of claim 1, wherein the method comprises:
performing terrain feature evaluation based on the initial set image set and the earth modeling to obtain terrain evaluation features and feature values;
constructing an earthwork metering database;
screening the earthwork metering database by a metering method based on the terrain evaluation characteristics and the characteristic values to obtain screening results;
and finishing the measurement of the earthwork to be measured through the screening result and the earthwork modeling.
6. The method of claim 1, wherein the method comprises:
performing measurement result verification on the earthwork to be measured to obtain a measurement result deviation value;
judging whether the measured result deviation value is within an expected deviation threshold range or not;
when the measured result deviation value is not in the expected deviation threshold range, carrying out error source analysis of modeling measurement on the earthwork to be measured to obtain an error source analysis result;
and constructing an earthwork modeling metering compensation database based on the error source analysis result.
7. The method of claim 1, wherein the method comprises:
performing outlier analysis on the scanning point cloud data to obtain outlier analysis results;
and when the point abnormal value of the abnormal point analysis result cannot meet the preset point threshold value, executing a re-acquisition instruction, and re-acquiring the point cloud data of the node at the position corresponding to the abnormal point.
8. An intelligent earth measuring system based on three-dimensional laser scanning modeling, which is characterized in that the system is in communication connection with an image acquisition device and a three-dimensional scanning device, and comprises:
the information acquisition module is used for acquiring basic information of earthwork to be measured;
the image acquisition module is used for acquiring the image of the earthwork to be measured through the image acquisition device to obtain an initial set image set;
the positioning point acquisition module is used for acquiring positioning points of the earthwork to be measured to obtain positioning point distribution coordinates;
the control analysis module is used for inputting the initial set image set and the positioning point distribution coordinates of the basic information into a control parameter distribution model and outputting a control set, wherein the control parameter distribution model performs neural network training building according to a control parameter decision tree, and the control parameter decision tree is built through the hierarchical mapping association between hierarchical identification nodes configured by the decision processing of sample data and hierarchical decision nodes;
the point cloud data acquisition module is used for controlling the three-dimensional scanning device to perform scanning acquisition of the earthwork to be measured through the control set to obtain scanning point cloud data;
the feature extraction module is used for extracting noise features from the features of the earthwork to be measured on the initial set image set, wherein the noise features have position marks;
and the modeling measurement module is used for carrying out noise reduction splicing on the scanning point cloud data through the noise characteristics and carrying out modeling measurement on the earthwork to be measured based on a noise reduction splicing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311051354.4A CN116793256B (en) | 2023-08-21 | 2023-08-21 | Intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311051354.4A CN116793256B (en) | 2023-08-21 | 2023-08-21 | Intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116793256A true CN116793256A (en) | 2023-09-22 |
| CN116793256B CN116793256B (en) | 2023-10-27 |
Family
ID=88046195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311051354.4A Active CN116793256B (en) | 2023-08-21 | 2023-08-21 | Intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116793256B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013105447A (en) * | 2011-11-16 | 2013-05-30 | Olympus Corp | Image processing device, image processing method, and image processing program |
| CN108090284A (en) * | 2017-12-19 | 2018-05-29 | 建基工程咨询有限公司 | Application based on laser scanning modeling reverse Engineering Technology in construction Supervision |
| CN113792457A (en) * | 2021-08-28 | 2021-12-14 | 中铁十九局集团第六工程有限公司 | Improved prism method based earth volume calculation method |
| CN113917483A (en) * | 2021-10-13 | 2022-01-11 | 国网山西省电力公司输电检修分公司 | Robot drilling space model construction method and system and electronic equipment |
| WO2023001251A1 (en) * | 2021-07-22 | 2023-01-26 | 梅卡曼德（北京）机器人科技有限公司 | Dynamic picture-based 3d point cloud processing method and apparatus, device and medium |
| CN116448080A (en) * | 2023-06-16 | 2023-07-18 | 西安玖安科技有限公司 | Unmanned aerial vehicle-based oblique photography-assisted earth excavation construction method |
-
2023
- 2023-08-21 CN CN202311051354.4A patent/CN116793256B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013105447A (en) * | 2011-11-16 | 2013-05-30 | Olympus Corp | Image processing device, image processing method, and image processing program |
| CN108090284A (en) * | 2017-12-19 | 2018-05-29 | 建基工程咨询有限公司 | Application based on laser scanning modeling reverse Engineering Technology in construction Supervision |
| WO2023001251A1 (en) * | 2021-07-22 | 2023-01-26 | 梅卡曼德（北京）机器人科技有限公司 | Dynamic picture-based 3d point cloud processing method and apparatus, device and medium |
| CN113792457A (en) * | 2021-08-28 | 2021-12-14 | 中铁十九局集团第六工程有限公司 | Improved prism method based earth volume calculation method |
| CN113917483A (en) * | 2021-10-13 | 2022-01-11 | 国网山西省电力公司输电检修分公司 | Robot drilling space model construction method and system and electronic equipment |
| CN116448080A (en) * | 2023-06-16 | 2023-07-18 | 西安玖安科技有限公司 | Unmanned aerial vehicle-based oblique photography-assisted earth excavation construction method |
Non-Patent Citations (1)
| Title |
|---|
| 关喜彬: "基于无人机三维激光点云数据的DTM法 边界自动提取及土方量计算分析", 《市政技术》, vol. 40, no. 10, pages 198 - 202 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116793256B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109101709A (en) | The site construction management system that 3D laser scanner technique is combined with BIM technology | |
| CN102506824B (en) | Method for generating digital orthophoto map (DOM) by urban low altitude unmanned aerial vehicle | |
| KR102104304B1 (en) | Real-Time Modeling System and Method for Geo-Spatial Information Using 3D Scanner of Excavator | |
| CN111709981A (en) | Registration method of laser point cloud and analog image with characteristic line fusion | |
| CN113906414A (en) | Distributed processing for generating pose maps for high definition maps for navigating autonomous vehicles | |
| CN109544691B (en) | MF (multi-frequency) method for automatically fusing multi-source heterogeneous water depth data to construct high-resolution DBM (database management system) | |
| CN111765867A (en) | Road effective earth volume calculation method based on oblique photography technology | |
| Rieger et al. | Roads and buildings from laser scanner data within a forest enterprise | |
| CN112446844B (en) | Point cloud feature extraction and registration fusion method | |
| Bergelt et al. | Improving the intrinsic calibration of a Velodyne LiDAR sensor | |
| CN111765869A (en) | Different-gradient road earthwork measurement method based on oblique photography technology | |
| KR101265746B1 (en) | Method for automatic registration of 3-dimensional scan data for intelligent excavation system | |
| Perera et al. | An automated method for 3D roof outline generation and regularization in airbone laser scanner data | |
| WO2011085435A1 (en) | Classification process for an extracted object or terrain feature | |
| CN111256730A (en) | Earth mass balance correction calculation method for low-altitude oblique photogrammetry technology | |
| CN111964599A (en) | Highway high slope surface deformation monitoring and analyzing method based on oblique photogrammetry technology | |
| Jiang et al. | Determination of construction site elevations using drone technology | |
| CN117433513B (en) | Map construction method and system for topographic mapping | |
| CN116793256B (en) | Intelligent earthwork measurement method and system based on three-dimensional laser scanning modeling | |
| CN116448080B (en) | Unmanned aerial vehicle-based oblique photography-assisted earth excavation construction method | |
| WO2011085433A1 (en) | Acceptation/rejection of a classification of an object or terrain feature | |
| CN111783191A (en) | Mountain road earth volume calculation method based on oblique photography technology | |
| Zhang et al. | Primitive-based building reconstruction by integration of Lidar data and optical imagery | |
| CN115962755A (en) | Earth and stone calculation method based on unmanned aerial vehicle oblique photography technology | |
| CN113532424B (en) | Integrated equipment for acquiring multidimensional information and cooperative measurement method |
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 |