CN109523105A - A kind of visualization Risk Identification and equipment based on bim Yu ar technology - Google Patents
A kind of visualization Risk Identification and equipment based on bim Yu ar technology Download PDFInfo
- Publication number
- CN109523105A CN109523105A CN201810981440.8A CN201810981440A CN109523105A CN 109523105 A CN109523105 A CN 109523105A CN 201810981440 A CN201810981440 A CN 201810981440A CN 109523105 A CN109523105 A CN 109523105A
- Authority
- CN
- China
- Prior art keywords
- risk
- bim
- feature
- visualization
- user location
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 40
- 238000012800 visualization Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 4
- 238000010224 classification analysis Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000000611 regression analysis Methods 0.000 claims description 4
- 230000002045 lasting effect Effects 0.000 claims 1
- 230000003190 augmentative effect Effects 0.000 description 6
- 230000009466 transformation Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 241000282693 Cercopithecidae Species 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/01—Indexing scheme relating to G06F3/01
- G06F2203/012—Walk-in-place systems for allowing a user to walk in a virtual environment while constraining him to a given position in the physical environment
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Pure & Applied Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to engineering-built technical fields, a kind of specifically visualization Risk Identification and equipment based on bim Yu ar technology, the reality imagery at user location and user location is acquired to be uploaded to background client terminal in real time by mobile terminal, and receives the feedback information that client is issued.The reality imagery at BIM modeling and real-time reception mobile terminal user location collected and user location is carried out to scene by background client terminal, feature identification is carried out to carry out characteristic similarity matching with preset risk classifications library to reality imagery, and issues the feedback information including BIM model image to mobile terminal.The present invention is compared with the existing technology, the advantage is that: providing visualization Risk Identification scheme using BIM and AR technology, intuitively quickly feature of risk is recognized, risk information and the default counter-measure suggested are fed back into user, user is informed at the first time, strong decision support is provided, engineering site level of security is promoted.
Description
Technical field
The present invention relates to engineering-built technical field, a kind of specifically visualization risk based on bim Yu ar technology
Discrimination method and equipment.
Background technique
AR technology (Augmented Reality, augmented reality) is a kind of position for calculating camera image in real time
Set and angle and plus respective image, video, 3D model technology, the target of this technology is to realize virtual world on the screen
Interacting between real world.This technology is most proposed early in nineteen ninety, with mentioning for accompanied electronic products C PU operational capability
It rises, it is expected that the purposes of augmented reality will be increasingly wider.In AR equipment, helmet-mounted display (Head-mounted
Displays, abbreviation HMD) it is widely used in virtual reality system, to enhance the visual immersion of user.
AR technology is mainly used in mobile application interaction at present, and the exploratory stage is still in practical implementation.This Shen
Please inventors have found that risk identification work in, AR has natural complementary effect in conjunction with BIM technology, utilizes the three of BIM
Dimension visualize and model structure data feature, AR can provide bring into sense feedback interaction be overlapped, it is possible to provide compared with
Good Risk Identification effect of visualization and early warning is shown.In consideration of it, present inventor devises one kind based on bim and ar technology
Visualization Risk Identification and equipment.
Summary of the invention
It is an object of the invention to solve the deficiencies in the prior art, the visualization risk based on bim and ar technology is provided and is distinguished
Know method and apparatus, the risk source of one line of engineering is recognized, and is fed back using effect of visualization in user, to reach risk
Warning against danger, the effect that risk information is shown and prompt takes measures, so that it is guaranteed that engineering one are issued after source Fast Identification, identification
Personal safety of the informant person under construction environment.
To achieve the goals above, a kind of visualization Risk Identification based on bim Yu ar technology is designed, feature exists
Include the following steps: in the visualization Risk Identification
The reality imagery at user location and user location is acquired by mobile terminal to be uploaded to background client terminal in real time, and
Receive the feedback information that client is issued.
BIM modeling and real-time reception mobile terminal user location collected and user are carried out to scene by background client terminal
Reality imagery at position carries out feature identification to reality imagery to carry out characteristic similarity with preset risk classifications library
Match, if characteristic similarity reaches preset threshold value, background client terminal identifies such risk in BIM model, and to movement
End issues the feedback information including BIM model image.
The present invention also has following preferred technical solution and implementation steps:
Step a. uses true absolute coordinate, and the BIM model at scene is established by background client terminal.
Step b. learns preset feature of risk using machine learning module, using risk source picture as training
Data source, using the geometrical characteristic of risk source picture, color, behavior state and physical attribute as feature of risk, and correspondence will be defeated
Variable is set as the type of risk source out, carries out classification and regression analysis to data in entirety training library using CNN neural network, obtains
The correlation models of preset feature of risk and output variable out, and by the correlation mould of preset feature of risk and output variable
Type is stored in the risk classifications library of background client terminal.
Step c. acquires the reality imagery at user location, posture and user location by mobile terminal and is uploaded to backstage visitor
Family end carries out Object identifying and edge extracting to reality imagery by client, and will extract obtained feature and risk classifications library
In preset risk classifications matched, if match degree is greater than the preset threshold, determining that identification object in reality imagery is should
Class risk.
If there are feature of risk in the reality imagery at step d1. user location, BIM mould is actually positioned on by user
Locating absolute position in type is shot on image in conjunction with the target tracking algorithm of the api interface of AR technology with 3D engine renders
Feature of risk, and increased virtual information posture is converted according to the attitude matrix of the practical object estimated.
If there are feature of risk in the reality imagery at step d2. user location, BIM visualization model, superposition are utilized
Display prompts what can be taken to build when all default corresponding Risk-warning information of feature of risk under prelocalization and posture
View measure.
Step e. system self-clocking after recognizing feature of risk, if because personnel do not do reaction or not in time far from risk
Feature, which leads to recognize feature of risk there are the duration, to reach setting time, then mobile terminal will be in the form of audio alarm to user
It carries out continuing warning, and automatically generates risk alert, background server end is uploaded to by wireless module, notifies on-site supervision room
Administrative staff.
The step c includes the following steps:
Preset feature of risk item collection is indicated with D1=D1 (p1, p2 ..., pn) in risk classifications library.
With D2=D2, (p ' 1, p ' 2 ..., p ' n) is indicated the feature set of reality imagery.
By the content degree of correlation Sim feature set between D1 and D2 between vector represented under geometric space coordinate angle
Cosine value indicate, with for judging that similarity degree, W1k, W2k respectively indicate the weight of D1 and D2 k-th characteristic item.
The present invention also designs a kind of equipment for the visualization Risk Identification based on bim and ar technology,
The equipment includes:
For acquiring the reality imagery at user location and user location to be uploaded to background client terminal, and receive client
The mobile terminal of the feedback information issued.
For carrying out BIM modeling to scene and receiving the real shadow at mobile terminal user location collected and user location
Picture carries out feature identification to reality imagery to carry out characteristic similarity matching with preset risk classifications library, works as characteristic similarity
Reach preset threshold value, then identifies such risk in BIM model, and issuing to mobile terminal includes the anti-of BIM model image
The background client terminal of feedforward information.
The present invention compared with the existing technology, the advantage is that:
(1) visualization Risk Identification scheme is provided using BIM and AR technology, intuitively quickly feature of risk is distinguished
Know.
(2) risk information and the default counter-measure suggested are fed back into user, informs user at the first time, provided strong
Decision support.
(3) engineering site level of security is promoted to risk visualized management and early warning with BIM and AR technology.
Detailed description of the invention
Fig. 1 is that the present invention is based on the scheme frameworks of bim and the visualization Risk Identification of ar technology in an embodiment
Schematic diagram.
Fig. 2 is the step flow chart of the visualization Risk Identification based on bim and ar technology in an embodiment.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings, and the structure and principle of this device and method are to this profession
It is very clearly for people.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
Referring to Fig. 1 and Fig. 2, in the present embodiment, the visualization Risk Identification based on bim and ar technology is substantially
Steps are as follows:
Step 1: creating project using BIM modeling software, true absolute coordinate is selected to model.
Step 2:BIM engineering site model foundation, what the engineering entity geometry appearance information and needs for assigning basis were shown
Engineering entity and article additional information in place.
Step 3: acquiring reality imagery using the camera of mobile device, include locating module and gyro in mobile device
For instrument to acquire user location, the gyroscope can also acquire the posture of user.
Step 4: it is docked by the api interface of AR technology with the image recognition engine of cloud server using internet, it is real
When transmission acquisition reality imagery.
Step 5: the reality imagery of acquisition being carried out to cut frame, carries out Yunnan snub-nosed monkey, completes denoising and image optimization.
Step 6: Object identifying and edge extracting are carried out, captures the object and profile in picture using iconic model, and
Carry out the extraction and mark of characteristics of objects point.
Step 7: machine learning module: using thousands of risk source pictures as training data source, to geometrical characteristic, face
Color, behavior state and physical attribute are set as the type of risk source, utilize CNN neural network pair as feature, corresponding output variable
Data carry out classification and regression analysis in entirety training library, obtain the correlation models of default feature and output variable.
Step 8:, be correlation models given threshold, setting similarity decision condition " if similarity >=80%, return
Value is risk, is otherwise devoid of risk."
Step 9: the characteristic point of extraction is passed to machine learning module, the machine learning set up with preparatory risk source images
Correlation models (prediction model) in training library, if carrying out the feature of characteristic similarity metrics match and certain class risk in library
Reach preset threshold with degree and the identification object in reality imagery is then determined as such risk, otherwise returns the result as devoid of risk.
Step 10: absolute position locating in BIM model is actually positioned on using user, in conjunction with AR technology api interface
Target tracking algorithm, with the related information to be shown on 3D engine renders subject, and increased virtual information appearance
State is converted according to the attitude matrix of the practical object estimated, is realized virtually with the linkage of real-world object, is realized that enhancing is existing
Real experience.
Step 11: if there are risks in current visual angle, using BIM visualization model, Overlapping display works as prelocalization and posture
Under corresponding Risk-warning information, prompt the suggestion and measure that can take, otherwise continue return step 3.
Step 12: personnel read BIM+AR feedback information, react or act.
Step 13: system self-clocking after recognizing risk source, if because personnel do not do reaction or not in time far from risk
Source, which leads to recognize risk source there are the duration, to be reached 10 seconds, will carry out continuing warning to user in the form of audio alarm, and
Risk alert is automatically generated, by wireless module upload server end, notifies on-site supervision room administrative staff.
Step 14: further being acted according to personnel, the identification and early warning process of step 3-13 is repeated.
Embodiment
Firstly, true absolute coordinate system is selected to carry out engineering site bim model creation, the engineering entity for assigning basis is several
Engineering entity and article additional information in what appearance information and the place for needing to show.
Assuming that road is through foundation pit side in the actual construction process by staff, there are unclosed enclosing structures before the visual field.This
When personnel may by the factors such as site machinery running, personnel transfer, environment be mixed and disorderly, attention not in enclosing structure, so as to
Energy can be from unclosed enclosing structure from high falling, because generating safety accident caused by this risk source.
However, fast automatic auxiliary risk source identification and early warning skill can be provided with BIM, AR and machine vision technique
Art.Field Force acquires reality imagery, locating module and gyroscope assisted acquisition user location using the camera of mobile device
With posture.At the scene when operation, mobile device carries out continued operation, real-time capture location information and field image.Mobile device
It is docked using internet by the image recognition engine with cloud server, transmits the image acquired in real time.Herein, cloud service
Device can carry out acquisition image to cut frame, and carry out Yunnan snub-nosed monkey, complete denoising and image optimization.
Machine learning module is preset in server: being directed to " unclosed enclosing structure " this risk source, is advanced with hundreds of
Unclosed structure picture as training data source, to the basic geometrical characteristic of unclosed enclosing structure, color, behavior state and
The physical attribute of unclosed state is cashed out as feature, these characteristic features are corresponded into output variable and are set as [unclosed to enclose
Keep off structure], classification and regression analysis are carried out to data in entirety training library using CNN neural network, obtain default feature and defeated
The correlation models of variable out.For correlation models given threshold, set similarity decision condition " if similarity >=80%,
Return value is risk, is otherwise devoid of risk."
The feature available feature item collection of default training library risk source picture " enclosing is unclosed " with D1=D1 (p1,
P2 ..., pn) it indicates.
Using the characterization image of aforementioned pretreatment optimization, Object identifying and edge extracting are carried out, is caught using iconic model
The object and profile in picture are caught, and carries out the extraction and mark of characteristics of objects point.Object identifying, i.e. Image outline identification with
And there are many Object Snap mode, in the prior art, identification technology and method to the object in image are comparative maturity, this reality
The Object identifying and edge extracting method in mode are applied, using the method in following documents: He Suli is based on chamfered shape and again
Image recognition new method [D] the Guangdong University of Technology of miscellaneous network, 2016.Feature set D2=D2 (p ' 1, p ' in actual video
2 ..., p ' n) indicate.
In correlation models, by the content degree of correlation Sim feature set between D1 and D2 under geometric space coordinate institute
Indicate that the cosine value of angle between vector indicates, for judging similarity degree.W1k, W2k respectively indicate D1 and D2 k-th feature
The weight of item.
Identification based on live enclosing image is determined as if it judges that similitude reaches 80% with " enclosing is unclosed "
There are such risk sources.The target tracking algorithm for the AR technology api interface herein being related to is the method for the prior art, Yi Xiexin
The interface that breath science-and-technology enterprise provides may be directly applied to exploitation and realize the algorithm, such as the content of following documents: Wang Yuxi, Zhang Feng
Army, Liu Yue augmented reality present Research and development trend [J] science and technology Leader, 2018,36 (10): 75-83.Utilize user
It is actually positioned on absolute position locating in BIM model, in conjunction with the target tracking algorithm of AR technology api interface, with 3D engine wash with watercolours
The title and parameter information of enclosing mathematical model are contaminated, Overlapping display is worked as corresponding Risk-warning information under prelocalization and posture and " deposited
In [unclosed enclosing structure] risk source ", prompt the suggestion and measure " please be far from [unclosed enclosing structure] " that can be taken, and root
The posture of the practical object gone out according to estimates carries out rigid space coordinate transform to the virtual information posture of the object, and by this
The model image showed after transformation is sent to mobile device so that user is able to observe feature of risk, with realize virtually with
The experience of augmented reality is realized in the linkage of real-world object.
The principle of posture changing is as follows: increased virtual information posture is carried out according to the posture of the practical object estimated
Rigid space coordinate transform is realized virtually with the linkage of real-world object, realizes the experience of augmented reality.Specific spatial attitude transformation
Matrix is as follows:
Above formula is rigid body translation transformation matrix, and wherein vx, vy, vz indicate flat on three-dimensional space x, tri- directions y, z
Shifting amount.
Above formula is rigid body around x, y, z axis rotational transformation matrix, and wherein θ is indicated in three-dimensional space on x, tri- directions y, z
Rotation angle.It is obtained by above-mentioned rigid body translation transformation matrix and x, y, z axis rotational transformation matrix
System self-clocking after recognizing unclosed enclosing structure, Field Force read BIM+AR feedback information, can
It is reacted or is acted according to prompt, if because personnel do not do reaction or cause to recognize risk source presence not in time far from risk source
Duration reaches 10 seconds, will carry out continuing warning to user in the form of audio alarm, and automatically generate risk alert, and pass through nothing
Wire module upload server end notifies on-site supervision room administrative staff, and associated alarm data save in the server, is later period people
Member's safety education, responsibility investigation etc. provide data and support.
Mobile terminal keeps continued operation, and circulation identification various risks source simultaneously provides personnel safety early warning.
Claims (8)
1. a kind of visualization Risk Identification based on bim Yu ar technology, it is characterised in that the visualization Risk Identification
Method includes the following steps:
The reality imagery at user location and user location is acquired to be uploaded to background client terminal in real time by mobile terminal, and is received
The feedback information that client is issued；
BIM modeling and real-time reception mobile terminal user location collected and user location are carried out to scene by background client terminal
The reality imagery at place carries out feature identification to reality imagery to carry out characteristic similarity matching with preset risk classifications library, if
Characteristic similarity reaches preset threshold value, then background client terminal identifies such risk in BIM model, and issues to mobile terminal
Feedback information including BIM model image.
2. a kind of visualization Risk Identification based on bim Yu ar technology as described in claim 1, it is characterised in that described
Visualization Risk Identification specifically comprise the following steps:
Step a. uses true absolute coordinate, and the BIM model at scene is established by background client terminal；
Step b. learns preset feature of risk using machine learning module, using risk source picture as training data
Source, using the geometrical characteristic of risk source picture, color, behavior state and physical attribute as feature of risk, and corresponding will export becomes
Amount is set as the type of risk source, carries out classification and regression analysis to data in entirety training library using CNN neural network, obtains pre-
If feature of risk and output variable correlation models, and the correlation models of preset feature of risk and output variable are deposited
It is stored in the risk classifications library of background client terminal.
3. a kind of visualization Risk Identification based on bim Yu ar technology as claimed in claim 1 or 2, it is characterised in that
The visualization Risk Identification specifically comprises the following steps:
Step c. acquires the reality imagery at user location, posture and user location by mobile terminal and is uploaded to backstage client
End carries out Object identifying and edge extracting to reality imagery by client, and will extract in obtained feature and risk classifications library
Preset risk classifications are matched, if match degree is greater than the preset threshold, determine that the identification object in reality imagery is such
Risk.
4. a kind of visualization Risk Identification based on bim Yu ar technology as claimed in claim 1 or 3, it is characterised in that
The visualization Risk Identification specifically comprises the following steps:
If there are feature of risk in the reality imagery at step d1. user location, it is actually positioned in BIM model by user
Locating absolute position is shot the risk on image with 3D engine renders in conjunction with the target tracking algorithm of the api interface of AR technology
Feature, and virtual information posture is converted according to the attitude matrix of the practical object estimated.
5. a kind of visualization Risk Identification based on bim Yu ar technology as described in claim 1 or 4, it is characterised in that
The visualization Risk Identification specifically comprises the following steps:
If there are feature of risk in the reality imagery at step d2. user location, BIM visualization model, Overlapping display are utilized
When the default corresponding Risk-warning information of feature of risk all under prelocalization and posture, and the suggestion that can be taken is prompted to arrange
It applies.
6. a kind of visualization Risk Identification based on bim Yu ar technology as described in claim 1 or 6, it is characterised in that
The visualization Risk Identification specifically comprises the following steps:
Step e. system self-clocking after recognizing feature of risk, if because personnel do not do reaction or not in time far from feature of risk
Lead to recognize feature of risk there are the duration and to reach setting time, then mobile terminal will carry out user in the form of audio alarm
Lasting warning, and risk alert is automatically generated, background server end, the management of notice on-site supervision room are uploaded to by wireless module
Personnel.
7. a kind of visualization Risk Identification based on bim Yu ar technology as claimed in claim 3, it is characterised in that described
Step c include the following steps:
Preset feature of risk item collection is indicated with D1=D1 (p1, p2 ..., pn) in risk classifications library；
With D2=D2, (p ' 1, p ' 2 ..., p ' n) is indicated the feature set of reality imagery；
By the content degree of correlation Sim feature set between D1 and D2 between vector represented under geometric space coordinate more than angle
String value indicates, to be used to judge that similarity degree, W1k, W2k respectively indicate the weight of D1 and D2 k-th characteristic item,
8. a kind of equipment for the visualization Risk Identification as described in claim 1 based on bim and ar technology, special
Sign is that the equipment includes:
For acquiring the reality imagery at user location and user location to be uploaded to background client terminal, and receives client and sent out
The mobile terminal of feedback information out；
For carrying out BIM modeling to scene and receiving the reality imagery at mobile terminal user location collected and user location,
Feature identification is carried out to carry out characteristic similarity matching with preset risk classifications library, when characteristic similarity reaches to reality imagery
Preset threshold value then identifies such risk in BIM model, and issues the feedback letter including BIM model image to mobile terminal
The background client terminal of breath.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810981440.8A CN109523105A (en) | 2018-08-27 | 2018-08-27 | A kind of visualization Risk Identification and equipment based on bim Yu ar technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810981440.8A CN109523105A (en) | 2018-08-27 | 2018-08-27 | A kind of visualization Risk Identification and equipment based on bim Yu ar technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109523105A true CN109523105A (en) | 2019-03-26 |
Family
ID=65770803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810981440.8A Pending CN109523105A (en) | 2018-08-27 | 2018-08-27 | A kind of visualization Risk Identification and equipment based on bim Yu ar technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109523105A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111460138A (en) * | 2020-03-02 | 2020-07-28 | 广州高新工程顾问有限公司 | BIM-based digital engineering supervision method and system |
| CN111563680A (en) * | 2020-05-06 | 2020-08-21 | 北方工业大学 | BIM-based assembly type building construction safety protection method and device and electronic equipment |
| CN114327049A (en) * | 2021-12-07 | 2022-04-12 | 北京五八信息技术有限公司 | Prompting method and device based on AR application, electronic equipment and readable medium |
| CN115909387A (en) * | 2023-01-06 | 2023-04-04 | 江苏狄诺尼信息技术有限责任公司 | Engineering lofting method based on enhanced image processing technology |
| CN116109080A (en) * | 2022-12-29 | 2023-05-12 | 无锡泰禾宏科技有限公司 | Building integrated management platform based on BIM and AR |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679291A (en) * | 2017-09-14 | 2018-02-09 | 中建三局第建设工程有限责任公司 | Construction operation management method, storage device and mobile terminal based on BIM and AR |
| CN107783463A (en) * | 2017-09-20 | 2018-03-09 | 中国十七冶集团有限公司 | A kind of base pit engineering intellectuality construction and monitoring system based on BIM technology |
| CN108074021A (en) * | 2016-11-10 | 2018-05-25 | 中国电力科学研究院 | A kind of power distribution network Risk Identification system and method |
-
2018
- 2018-08-27 CN CN201810981440.8A patent/CN109523105A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108074021A (en) * | 2016-11-10 | 2018-05-25 | 中国电力科学研究院 | A kind of power distribution network Risk Identification system and method |
| CN107679291A (en) * | 2017-09-14 | 2018-02-09 | 中建三局第建设工程有限责任公司 | Construction operation management method, storage device and mobile terminal based on BIM and AR |
| CN107783463A (en) * | 2017-09-20 | 2018-03-09 | 中国十七冶集团有限公司 | A kind of base pit engineering intellectuality construction and monitoring system based on BIM technology |
Non-Patent Citations (3)
| Title |
|---|
| LIEYUN DING: "A deep hybrid learning model to detect unsafe behavior: Integrating convolution neural networks and long short-term memory", 《AUTOMATION IN CONSTRUCTION》 * |
| 杜长亮: "BIM和AR技术结合在施工现场的应用研究", 《中国优秀硕士学位论文全文数据库》 * |
| 秦松华: "基于BIM和AR技术的石化项目全生命周期风险管理", 《项目管理技术》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111460138A (en) * | 2020-03-02 | 2020-07-28 | 广州高新工程顾问有限公司 | BIM-based digital engineering supervision method and system |
| CN111563680A (en) * | 2020-05-06 | 2020-08-21 | 北方工业大学 | BIM-based assembly type building construction safety protection method and device and electronic equipment |
| CN114327049A (en) * | 2021-12-07 | 2022-04-12 | 北京五八信息技术有限公司 | Prompting method and device based on AR application, electronic equipment and readable medium |
| CN114327049B (en) * | 2021-12-07 | 2023-07-25 | 北京五八信息技术有限公司 | AR application-based prompting method and device, electronic equipment and readable medium |
| CN116109080A (en) * | 2022-12-29 | 2023-05-12 | 无锡泰禾宏科技有限公司 | Building integrated management platform based on BIM and AR |
| CN116109080B (en) * | 2022-12-29 | 2023-09-12 | 无锡泰禾宏科技有限公司 | Building integrated management platform based on BIM and AR |
| CN115909387A (en) * | 2023-01-06 | 2023-04-04 | 江苏狄诺尼信息技术有限责任公司 | Engineering lofting method based on enhanced image processing technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523105A (en) | A kind of visualization Risk Identification and equipment based on bim Yu ar technology | |
| US20200320345A1 (en) | System and method for visual recognition using synthetic training data | |
| US8630460B2 (en) | Incorporating video meta-data in 3D models | |
| CN105426827A (en) | Living body verification method, device and system | |
| Paletta et al. | 3D attention: measurement of visual saliency using eye tracking glasses | |
| CN104599287B (en) | Method for tracing object and device, object identifying method and device | |
| CN103679742B (en) | Method for tracing object and device | |
| Nar et al. | Abnormal activity detection for bank ATM surveillance | |
| JP2011186576A (en) | Operation recognition device | |
| CN108229375B (en) | Method and device for detecting face image | |
| Sigalas et al. | Full-body pose tracking—the top view reprojection approach | |
| Guo et al. | Gesture recognition of traffic police based on static and dynamic descriptor fusion | |
| Kim et al. | 3D human-gesture interface for fighting games using motion recognition sensor | |
| Migniot et al. | 3d human tracking in a top view using depth information recorded by the xtion pro-live camera | |
| Funes Mora et al. | A semi-automated system for accurate gaze coding in natural dyadic interactions | |
| Megalingam | Human action recognition: A review | |
| Xu et al. | A novel method for hand posture recognition based on depth information descriptor | |
| CN111428609A (en) | Human body posture recognition method and system based on deep learning | |
| Benedek et al. | Lidar-based gait analysis in people tracking and 4D visualization | |
| KR20130081126A (en) | Method for hand-gesture recognition and apparatus thereof | |
| Li et al. | A low-cost head and eye tracking system for realistic eye movements in virtual avatars | |
| Paletta et al. | An integrated system for 3D gaze recovery and semantic analysis of human attention | |
| Bednarık et al. | Human gesture recognition using top view depth data obtained from Kinect sensor | |
| De Cecco et al. | Monte Carlo human identification refinement using joints uncertainty | |
| Patil et al. | Virtual interactive hand gestures recognition system in real time environment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190326 |
|
| RJ01 | Rejection of invention patent application after publication |