CN109828284B - Actual measurement method and device based on artificial intelligence - Google Patents
Actual measurement method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN109828284B CN109828284B CN201910201649.2A CN201910201649A CN109828284B CN 109828284 B CN109828284 B CN 109828284B CN 201910201649 A CN201910201649 A CN 201910201649A CN 109828284 B CN109828284 B CN 109828284B
- Authority
- CN
- China
- Prior art keywords
- model
- data
- sub
- target
- initial
- 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
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method and a device for actually measuring actual quantity based on artificial intelligence, wherein the method for actually measuring the actual quantity comprises the following steps: acquiring a 3D initial model of a target space through a laser radar; acquiring parameters of at least one target sub-model in the 3D initial model; generating a building information model according to the parameters; fitting the building information model with a preset model of a target space; and obtaining comparison data of the building information model and the preset model according to the fitting result. The method and the device can perform semantic segmentation on the indoor scene, and automatically identify objects from the scanned scene of the solid building; the method comprises the steps of automatically classifying planes obtained by analyzing scene semantics based on a core algorithm for solving 3D actual measurement based on artificial intelligence, determining the type of a measurement dimension, carrying out real-time fitting scanning on the entity building 3D modeling to form BIM data and designed BIM, and providing real-time data support for BIM quality management of a full life cycle.
Description
Technical Field
The invention relates to a method and a device for actually measuring actual measurement based on artificial intelligence.
Background
The laser radar is a radar system that detects a characteristic quantity such as a position and a velocity of a target by emitting a laser beam. The working principle is that a detection signal is transmitted to a target, then the received signal reflected from the target is compared with the transmitted signal, and after appropriate processing, relevant information of the target, such as target distance, azimuth, height, speed, attitude, even shape and other parameters, can be obtained, and the method can be applied to military, buildings and other aspects.
In the prior art, a laser radar comprises a laser transmitter, an optical receiver, a rotary table, an information processing system and the like, wherein a laser device converts electric pulses into optical pulses to be transmitted out, and the optical receiver restores the optical pulses reflected from a target into the electric pulses to be transmitted to a display.
The current building industry does not achieve fully automated measurements because of the technical bottlenecks, both in hardware and software.
In the aspect of hardware, an expensive laser radar scanner needs an IPAD (internet protocol ad) for operation control and data recording during scanning, then a professional technician is required to convert the IPAD into a computer, the original data is imported to process the original point cloud data, a universal 3D point cloud format is output, various third-party software is used, and rendering is manually confirmed and each index is clicked one by one to obtain required data. The price, efficiency and use cost are too high to be popularized and applied.
The difficulty in software is that no mature solution can measure in real time, intelligently and reliably.
Disclosure of Invention
The invention aims to overcome the defects that a laser radar scanner in the prior art is high in price, complex in operation, slow in operation, low in working efficiency and incapable of carrying out real-time, intelligent and reliable measurement without a mature solution, and provides a method and a device for carrying out artificial intelligence-based actual measurement, wherein the method and the device can be used for segmenting indoor scene semantics, automatically identifying objects from a scanned scene of an entity building, automatically classifying planes obtained by analyzing scene semantics, determining the type of a measured dimension, fitting the scanned entity building 3D in real time to form BIM (building information model) data and designed BIM, and providing real-time data support for BIM quality management of a full life cycle.
The invention solves the technical problems through the following technical scheme:
a method for actually measuring actual quantity based on artificial intelligence is characterized in that the method for actually measuring actual quantity passes through the following steps:
acquiring a 3D initial model of a target space through a laser radar;
obtaining parameters of at least one target sub-model in the 3D initial model;
generating a 3D data model according to the parameters, wherein the 3D data model comprises building data of a target sub-model;
fitting the 3D data model with a preset model of a target space;
and obtaining comparison data of the 3D data model and the preset model according to the fitting result.
Preferably, the obtaining parameters of at least one target sub-model in the 3D initial model includes:
identifying semantic information of a sub-region in the 3D initial model according to an artificial intelligence technology;
dividing the 3D initial model into a plurality of initial sub-models according to semantic information;
and recombining the initial submodels matched with each other according to the geometric characteristics and the relative position relationship of the initial submodels to obtain a target submodel and semantic information of the target submodel.
Preferably, the reconstructing the mutually matched initial sub-models according to the geometric features and the relative position relationship of the initial sub-models to obtain the target sub-models and the semantic information of the target sub-models comprises:
establishing a plane database according to the house type graph of the target space, wherein the plane database comprises plane geometric characteristics and a plane relative position relation;
matching the initial sub-model with a plane in a plane database by using random forest technology according to the geometrical characteristics of the plane and the relative position relationship of the plane;
and fusing the preset sub-model and the matched plane to obtain the target sub-model and the semantic information of the target sub-model.
Preferably, the obtaining parameters of at least one target sub-model in the 3D initial model includes:
acquiring a data type corresponding to the target sub-model according to the semantic information of the target sub-model;
and acquiring data in the data type according to the comparison relation between the size and the actual size of the target sub-model as building data corresponding to the target sub-model in the 3D data model.
Preferably, the obtaining the data type corresponding to the target sub-model according to the semantic information of the target sub-model includes:
acquiring a house type corresponding to the 3D initial model through a neural network algorithm;
and acquiring a data type corresponding to the target sub-model according to the house model and the semantic information.
Preferably, the obtaining of the comparison data between the 3D data model and the preset model according to the fitting result includes;
and obtaining the distance between a target voxel on the 3D data model and a preset model, wherein the comparison data comprises the sum of the distances of all target voxels.
Preferably, the 3D data model is fitted to a preset model of the target space;
extracting key voxels on data points of the 3D data model;
the spatial positions of the key voxels are recorded sequentially.
Preferably, the sequentially recording the spatial positions of the key voxels comprises:
generating a sub-plane according to the spatial position of the key voxel;
acquiring a normal vector of the sub-plane;
and fitting the 3D data model with a preset model of a target space according to the normal vector.
The application discloses real quantity actually measured device based on artificial intelligence, its special electricity lies in, the real quantity actually measured device is used for realizing the method of real quantity actually measured as described above.
Preferably, the actual measurement device comprises a housing, a lidar, a power assembly, a power supply assembly, a hardware acceleration assembly and an embedded platform assembly, wherein the lidar is mounted on the upper portion of the actual measurement device; the power assembly comprises a rotating unit, a stepping motor and a stepping motor controller which are arranged in the shell; the laser radar is arranged on the rotating unit, and the rotating unit provides power for the rotation of the laser radar; the power supply assembly is electrically connected with the laser radar, the stepping motor controller, the hardware acceleration assembly and the embedded platform assembly; the laser radar transmits a scanning signal to the embedded platform assembly; the embedded platform assembly is electrically connected with the hardware acceleration assembly.
On the basis of the common knowledge in the field, the above preferred conditions can be combined randomly to obtain the preferred embodiments of the invention.
The positive progress effects of the invention are as follows:
the method and the device can perform semantic segmentation on the indoor scene, and automatically identify the object from the scanned scene of the solid building; the method comprises the steps of automatically classifying planes obtained by analyzing scene semantics based on a core algorithm for solving 3D actual measurement based on artificial intelligence, determining the type of a measurement dimension, carrying out real-time fitting scanning on the entity building 3D modeling to form BIM data and designed BIM, and providing real-time data support for BIM quality management of a full life cycle.
Drawings
Fig. 1 is a schematic structural diagram of an actual measurement apparatus in embodiment 1 of the present invention.
Fig. 2 is a flowchart of a method for actually measuring actual quantities according to embodiment 1 of the present invention.
Fig. 3 is another flowchart of the method for actually measuring the actual measurement quantity according to embodiment 1 of the present invention.
Fig. 4 is another flowchart of the method for actually measuring the actual measurement quantity according to embodiment 1 of the present invention.
Fig. 5 is another flowchart of the method for actually measuring the actual measurement quantity according to embodiment 1 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
Referring to fig. 1, the present embodiment provides an artificial intelligence based actual measurement device, which includes a housing 11, a lidar 12, a power module 13, a power module 14, a hardware acceleration module, and an embedded platform module 15.
And the laser radar is arranged on the upper part of the actual measurement device.
The power assembly comprises a rotating unit arranged in the shell, a stepping motor and a stepping motor controller.
The laser radar is installed on the rotating unit, and the rotating unit provides power for the rotation of the laser radar.
The power supply assembly is electrically connected with the laser radar, the stepping motor controller, the hardware acceleration assembly and the embedded platform assembly.
The laser radar transmits a scanning signal to the embedded platform assembly; the embedded platform assembly is electrically connected with the hardware acceleration assembly.
The device for actually measuring the actual measurement further comprises an acquisition module, a calculation module, a generation module, a fitting module and a processing module.
The acquisition module is used for acquiring a 3D initial model of a target space through a laser radar;
the calculation module is used for acquiring parameters of at least one target sub-model in the 3D initial model;
the generation module is used for generating a 3D data model according to the parameters, and the 3D data model comprises building data of a target sub-model;
the fitting module is used for fitting the 3D data model with a preset model of a target space;
and the processing module is used for acquiring comparison data of the 3D data model and the preset model according to a fitting result.
Referring to fig. 2 to 5, the present embodiment provides a method for measuring actual quantities by using the apparatus for measuring actual quantities, including:
101, acquiring parameters of at least one target sub-model in the 3D initial model;
102, generating a 3D data model according to the parameters, wherein the 3D data model comprises building data of a target sub-model;
and 104, acquiring comparison data of the 3D data model and the preset model according to the fitting result.
In this embodiment, the preset model may be a designed building information model.
A model obtained by the laser radar can be used for obtaining 3D scanning data containing various building information through segmentation and recombination, and the construction condition of a building can be judged by using the building model.
The present embodiment can manage measured data. Firstly, the measured data is filed, the coordinate systems of the 3D scanning data of the solid building and the design BIM are aligned by adopting a fitting mode of the 3D scanning data of the solid building and the design BIM, and then the corresponding relation between the design BIM and the 3D model of the solid building is known, for example, the levelness range of the ceiling is measured in the 3D model of the solid building, and the measured levelness range of the ceiling of which house type is very poor is also known. In the case where a building has many rooms therein, each room may correspond to a respective solid building 3D model, and the actual measured dimensions in each room are stored.
Furthermore, in order to obtain semantic information in the model, the sub-models of the object and the wall are obtained according to the semantic information. Step 101 comprises:
and 1013, recombining the initial sub-models matched with each other according to the geometric characteristics and the relative position relationship of the initial sub-models to obtain the target sub-models and the semantic information of the target sub-models.
From the scanned 3D scene, the complete wall of the ceiling, floor, wall with door opening/window opening, edge of door opening/window opening that needs to be measured are identified. There are the following problems: 1. some interference factors such as stacked sundries, pre-installed air conditioners, water pipes and the like exist in the 3D scene; 2. the sensors need to be acquired at a plurality of sites/positions, data needs to be fused and spliced, and splicing errors can be introduced; 3. the sensor may scan for noise outside the scene. These problems can lead to the problem of over-partitioning of the identified planes, i.e., the physically same plane, into several planes. There may also be situations where noise outside the scene is treated as a plane.
The embodiment can recombine the planes segmented from the original scene.
establishing a plane database according to the house type graph of the target space, wherein the plane database comprises plane geometric characteristics and a plane relative position relation;
matching the initial sub-model with a plane in a plane database by using a random forest technology according to the geometrical characteristics of the plane and the relative position relationship of the plane;
and fusing the preset sub-model and the matched plane to obtain the target sub-model and the semantic information of the target sub-model.
By using the above steps, the present embodiment can form a complete plane, and then output the complete plane to the measurement module for measurement.
With respect to the measurements, step 102 includes:
and 1022, acquiring data in the data type according to the comparison relation between the size of the target sub-model and the actual size, and using the data as building data corresponding to the target sub-model in the 3D data model.
The data types comprise indexes such as wall surface flatness, wall surface verticality, ceiling levelness, floor flatness, room + room squareness, room size, internal and external angles and the like. But also what data to measure on what plane, e.g. flatness on walls without door/window openings, flatness on walls with door openings, perpendicularity of the walls, inside and outside corners of two walls intersecting perpendicularly, distance measurement of two main walls parallel to the room for calculating the depth of the room, on two main walls perpendicular to the room for measuring the squareness of the room, etc.
Specifically, step 1021 comprises:
acquiring a house type corresponding to the 3D initial model through a neural network algorithm;
and acquiring a data type corresponding to the target sub-model according to the house model and the semantic information.
The present embodiment also considers the problem of diversity of house types. In the case of a square house, it is relatively simple, for example, when measuring a ceiling and a floor, the measuring area is a closed rectangular area surrounded by four walls. In the case of an irregular house, such as a diamond hall, it is more intelligent to divide a rectangular area as large as possible into measurement areas. In the real measurement, more complex situations need to be faced, so in order that the algorithm has certain universality, different house types are classified by constructing a neural network, the scanned 3D scene is input into the network, and the output result is the corresponding house type. The corresponding house type, measured area, data, and measurement location will guide the subsequent measurement.
Step 104 is specifically to obtain a distance between a target voxel on the building information model and a preset model, and the comparison data includes a sum of the distances of all the target voxels.
The difference between the 3D data model and the preset model can be obtained through the sum of the distances.
To align the two models, step 103 includes:
and step 1031, extracting key voxels from data points of the building information model.
And 1032, recording the spatial positions of the key voxels in sequence.
And 1034, acquiring a normal vector of the sub-plane.
And 1035, fitting the building information model with a preset model of the target space according to the normal vector.
Multiple key voxels can be paralleled by using multiple cores of a CPU or a processor, and real-time calculation of normal vector and feature extraction can be realized.
In this embodiment, the key voxels implement multi-sum parallel computation with the hardware acceleration component via an embedded platform component.
The actual measurement device and method of the embodiment have the advantages that:
introduce the building segmentation trade with highly intelligent, highly automatic, the highly information-based 3D measurement for the first time, solved the pain point problem of building trade, include: manpower and time are consumed; the measurement is greatly and inaccurately influenced by human; rechecking the irreproducible scene; it is difficult to electronically manage measurement data.
Specifically, 1, based on semantic segmentation of an artificial intelligence indoor scene, automatically identifying each wall surface/ceiling/floor, door and window from a scanned scene of an entity building; 2. based on a core algorithm for solving the 3D actual measurement based on artificial intelligence, automatically classifying planes obtained by analyzing scene semantics, and determining the types of measurement sizes, including indexes such as wall surface flatness, wall surface verticality, ceiling levelness, floor flatness, room squareness, room size, internal and external angles and the like; 3. the real-time fitting scanning entity building 3D modeling forms BIM data and designed BIM, and provides real-time data support for BIM quality management of the whole life cycle.
While specific embodiments of the invention have been described above, it will be understood by those skilled in the art that these are by way of example only, and that the scope of the invention is defined by the appended claims. Various changes or modifications to these embodiments may be made by those skilled in the art without departing from the principle and spirit of this invention, and these changes and modifications are within the scope of this invention.
Claims (8)
1. A method for actually measuring actual quantity based on artificial intelligence is characterized in that the method for actually measuring actual quantity comprises the following steps:
acquiring a 3D initial model of a target space through a laser radar;
obtaining parameters of at least one target sub-model in the 3D initial model;
generating a 3D data model according to the parameters, wherein the 3D data model comprises building data of a target sub-model;
fitting the 3D data model with a preset model of a target space;
acquiring comparison data of the 3D data model and the preset model according to a fitting result;
wherein, the obtaining of the parameter of at least one target sub-model in the 3D initial model comprises:
identifying semantic information of a sub-region in the 3D initial model according to an artificial intelligence technology;
dividing the 3D initial model into a plurality of initial sub-models according to semantic information;
recombining the initial sub-models matched with each other according to the geometric characteristics and the relative position relationship of the initial sub-models to obtain a target sub-model and semantic information of the target sub-model;
the method for obtaining the semantic information of the target sub-model and the target sub-model by recombining the initial sub-models matched with each other according to the geometric characteristics and the relative position relationship of the initial sub-models comprises the following steps:
establishing a plane database according to the house type graph of the target space, wherein the plane database comprises plane geometric characteristics and a plane relative position relation;
matching the initial sub-model with a plane in a plane database by using a random forest technology according to the geometrical characteristics of the plane and the relative position relationship of the plane;
and fusing the preset sub-model and the matched plane to obtain the target sub-model and the semantic information of the target sub-model.
2. The method of actual measurement according to claim 1, wherein the generating of the 3D data model from the parameters, the 3D data model including building data of a target sub-model, comprises:
acquiring a data type corresponding to the target sub-model according to the semantic information of the target sub-model;
and acquiring data in the data type according to the comparison relation between the size of the target sub-model and the actual size as building data corresponding to the target sub-model in the 3D data model.
3. The method for actually measuring the actual measurement quantity according to claim 2, wherein the obtaining the data type corresponding to the target sub-model according to the semantic information of the target sub-model comprises:
acquiring a house type corresponding to the 3D initial model through a neural network algorithm;
and acquiring a data type corresponding to the target sub-model according to the house model and the semantic information.
4. The method for actually measuring actual quantity according to claim 1, wherein the obtaining of the comparison data between the 3D data model and the preset model according to the fitting result comprises;
and obtaining the distance between a target voxel on the 3D data model and a preset model, wherein the comparison data comprises the sum of the distances of all target voxels.
5. The method of actual measurement according to claim 1, wherein the 3D data model is fitted to a predetermined model of the target space;
extracting key voxels on data points of the 3D data model;
the spatial positions of the key voxels are recorded sequentially.
6. The method of actual measurement of claim 5, wherein the sequentially recording the spatial locations of the key voxels comprises:
generating a sub-plane according to the spatial position of the key voxel;
acquiring a normal vector of the sub-plane;
and fitting the 3D data model with a preset model of a target space according to the normal vector.
7. An apparatus for actual measurement based on artificial intelligence, characterized in that the apparatus for actual measurement is used for implementing a method for actual measurement according to any of claims 1 to 6.
8. The actual measurement device of claim 7, wherein the actual measurement device comprises a housing, a lidar, a power module, a hardware acceleration module, and an embedded platform module, the lidar being mounted on top of the actual measurement device; the power assembly comprises a rotating unit, a stepping motor and a stepping motor controller which are arranged in the shell; the laser radar is arranged on the rotating unit, and the rotating unit provides power for the rotation of the laser radar; the power supply assembly is electrically connected with the laser radar, the stepping motor controller, the hardware acceleration assembly and the embedded platform assembly; the laser radar transmits a scanning signal to the embedded platform assembly; the embedded platform assembly is electrically connected with the hardware acceleration assembly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201649.2A CN109828284B (en) | 2019-03-18 | 2019-03-18 | Actual measurement method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910201649.2A CN109828284B (en) | 2019-03-18 | 2019-03-18 | Actual measurement method and device based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109828284A CN109828284A (en) | 2019-05-31 |
| CN109828284B true CN109828284B (en) | 2023-02-10 |
Family
ID=66870240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910201649.2A Active CN109828284B (en) | 2019-03-18 | 2019-03-18 | Actual measurement method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109828284B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111197979B (en) * | 2019-06-20 | 2022-07-26 | 广东领慧建筑科技有限公司 | Point cloud data analysis-based building detection method and device |
| CN110595446B (en) * | 2019-08-19 | 2021-12-24 | 广东领盛装配式建筑科技有限公司 | Building actual measurement method and device based on virtual guiding rule |
| CN111027118B (en) * | 2019-11-19 | 2024-01-19 | 广东博智林机器人有限公司 | Actual measurement real-quantity task point searching and task dispatching method and system |
| CN111277967A (en) * | 2020-01-20 | 2020-06-12 | 中国十七冶集团有限公司 | Actual measurement real quantity information conduction scanner based on BIM modeling |
| CN111308495B (en) * | 2020-03-13 | 2022-03-08 | 厦门知本家科技有限公司 | Method for generating indoor house type 3D data through radar ranging |
| CN112669364A (en) * | 2020-12-07 | 2021-04-16 | 盎锐（上海）信息科技有限公司 | Display method and measurement system for actual measurement |
| CN112833777B (en) * | 2020-12-07 | 2023-09-22 | 盎锐（上海）信息科技有限公司 | Measuring method and measuring system for actual measurement |
| CN113252015A (en) * | 2021-05-10 | 2021-08-13 | 中建三局集团华南有限公司 | Actual measurement real-size robot device based on point cloud and AI processing |
| CN113375556B (en) * | 2021-06-18 | 2024-06-04 | 盎锐(杭州)信息科技有限公司 | Full stack type actual measurement real quantity system, measurement method and laser radar |
| CN113362461B (en) * | 2021-06-18 | 2024-04-02 | 盎锐(杭州)信息科技有限公司 | Point cloud matching method and system based on semantic segmentation and scanning terminal |
| CN113670234B (en) * | 2021-06-21 | 2024-06-04 | 盎锐(杭州)信息科技有限公司 | Display method, measurement system and laser radar for actual measurement |
| CN113313761B (en) * | 2021-07-28 | 2022-04-01 | 盎锐(常州)信息科技有限公司 | Site acquisition method, scanning device and system for actual measurement |
| CN113436244B (en) * | 2021-08-25 | 2021-12-17 | 盎锐(常州)信息科技有限公司 | Model processing method and system for actual measurement actual quantity and laser radar |
| CN114049444B (en) * | 2022-01-13 | 2022-04-15 | 深圳市其域创新科技有限公司 | 3D scene generation method and device |
| CN115130191A (en) * | 2022-07-28 | 2022-09-30 | 盎维云(深圳)计算有限公司 | Positive and reverse BIM fusion modeling engine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065355A (en) * | 2012-12-26 | 2013-04-24 | 安科智慧城市技术（中国）有限公司 | Method and device of achieving three-dimensional modeling of wisdom building |
| CN106127857A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | Synthetic data drives the on-board LiDAR data modeling method with model-driven |
| CN106524920A (en) * | 2016-10-25 | 2017-03-22 | 上海建科工程咨询有限公司 | Application of field measurement in construction project based on three-dimensional laser scanning |
| CN107909645A (en) * | 2017-11-16 | 2018-04-13 | 青岛市光电工程技术研究院 | Building view generation method, apparatus and system |
| CN107978017A (en) * | 2017-10-17 | 2018-05-01 | 厦门大学 | Doors structure fast modeling method based on wire extraction |
| CN108038908A (en) * | 2017-11-21 | 2018-05-15 | 泰瑞数创科技(北京)有限公司 | Spatial object identification and modeling method and system based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9251433B2 (en) * | 2012-12-10 | 2016-02-02 | International Business Machines Corporation | Techniques for spatial semantic attribute matching for location identification |
-
2019
- 2019-03-18 CN CN201910201649.2A patent/CN109828284B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065355A (en) * | 2012-12-26 | 2013-04-24 | 安科智慧城市技术（中国）有限公司 | Method and device of achieving three-dimensional modeling of wisdom building |
| CN106127857A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | Synthetic data drives the on-board LiDAR data modeling method with model-driven |
| CN106524920A (en) * | 2016-10-25 | 2017-03-22 | 上海建科工程咨询有限公司 | Application of field measurement in construction project based on three-dimensional laser scanning |
| CN107978017A (en) * | 2017-10-17 | 2018-05-01 | 厦门大学 | Doors structure fast modeling method based on wire extraction |
| CN107909645A (en) * | 2017-11-16 | 2018-04-13 | 青岛市光电工程技术研究院 | Building view generation method, apparatus and system |
| CN108038908A (en) * | 2017-11-21 | 2018-05-15 | 泰瑞数创科技(北京)有限公司 | Spatial object identification and modeling method and system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109828284A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109828284B (en) | Actual measurement method and device based on artificial intelligence | |
| Rebolj et al. | Point cloud quality requirements for Scan-vs-BIM based automated construction progress monitoring | |
| Guo et al. | Geometric quality inspection of prefabricated MEP modules with 3D laser scanning | |
| CN108763685B (en) | Construction method of space special-shaped curved surface curtain wall system | |
| US9761015B2 (en) | Method for determining dimensions in an indoor scene from a single depth image | |
| CN110287519A (en) | A kind of the building engineering construction progress monitoring method and system of integrated BIM | |
| US20190164445A1 (en) | Method and system for simulating a radar image | |
| CN110595446B (en) | Building actual measurement method and device based on virtual guiding rule | |
| Huang et al. | Active image-based modeling with a toy drone | |
| Kawashima et al. | Finding the next-best scanner position for as-built modeling of piping systems | |
| CN116993923B (en) | Three-dimensional model making method, system, computer equipment and storage medium for converter station | |
| JP6781432B2 (en) | Radio wave propagation simulation model creation method, creation system, creation device and creation program | |
| Hu et al. | An automatic 3D registration method for rock mass point clouds based on plane detection and polygon matching | |
| JP2020009326A (en) | Radio wave propagation simulation model creation method, creation system, creation device, and creation program | |
| CN113362461A (en) | Point cloud matching method and system based on semantic segmentation and scanning terminal | |
| CN113654538B (en) | Room square finding method, laser radar and measuring system for actual measurement | |
| CN113935946B (en) | Method and device for detecting underground obstacle in real time | |
| CN113436244B (en) | Model processing method and system for actual measurement actual quantity and laser radar | |
| Dierenbach et al. | Next-Best-View method based on consecutive evaluation of topological relations | |
| Pexman et al. | Registration And Feature Extraction From Terrestrial Laser Scanner Point Clouds For Aerospace Manufacturing | |
| Wiemann et al. | Optimizing triangle mesh reconstructions of planar environments | |
| CN115600395B (en) | Indoor engineering quality acceptance evaluation method and device | |
| CN113569856B (en) | Model semantic segmentation method for actual measurement and laser radar | |
| Hu et al. | PriSeg: IFC-Supported Primitive Instance Geometry Segmentation with Unsupervised Clustering | |
| Low | View planning for range acquisition of indoor environments |
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 |