CN106846479A - Three-dimensional visialization of tunnel system and method based on depth camera - Google Patents
Three-dimensional visialization of tunnel system and method based on depth camera Download PDFInfo
- Publication number
- CN106846479A CN106846479A CN201710081447.XA CN201710081447A CN106846479A CN 106846479 A CN106846479 A CN 106846479A CN 201710081447 A CN201710081447 A CN 201710081447A CN 106846479 A CN106846479 A CN 106846479A
- Authority
- CN
- China
- Prior art keywords
- depth
- tunnel
- camera
- depth camera
- whirligig
- 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
Classifications
-
- 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
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The invention discloses a kind of three-dimensional visialization of tunnel system and method based on depth camera, including depth camera device, whirligig, the depth camera device includes microphone assembly, infrared camera, colour imagery shot and infrared camera, the depth camera device is mounted on the whirligig, the whirligig drive depth camera device carries out the rotation of 180 ° on vertical direction, gathers the image of tunnel upper half；Angular transducer is provided with whirligig, the anglec of rotation of whirligig is detected, while elevation-angle controller is provided with whirligig, the acquisition angles of controlling depth cam device.The present invention is by the analysis to tunnel correlated color information, it is also possible to it was observed that geological state overall in tunnel, such as trend in joint, crack, so as to carry out more targeted scientific construction.
Description
Technical field
The present invention relates to a kind of three-dimensional visialization of tunnel system and method based on depth camera.
Background technology
As the country that a scientific and technological, economic each side is developed rapidly, will necessarily be built more during city is built
Many tunnel, subway meet the demand in traffic.Certainly, in order to avoid the generation of accident, in order to tunnel is better anticipated
Situation, allow tunnelling process be in progress more smoothly, we carry out three-dimensional modeling using depth camera to tunnel so that
Allow that the situation in whole tunnel is showed on three dimensions, let us has to tunnel information and more intuitively recognizes,
So as to avoid the generation of some contingencies.
For at present, the range of application of depth camera is than wide.Its main exploitation reason is for instantly very
Popular somatic sensation television game, can make user have preferably experience.However as the continuous progress of technology, depth camera is virtual
Real aspect can also have very novel application, and some boutiques apply on fitting room this virtual technology, Ke Huwu
Need to try on and real clothes effect can be observed；In engineering, range of application mainly includes the weight of small-scale scene (object)
Build, the 3D scanning and printings of object facility；And the depth camera of low cost is added in robot field, and utilize machine
Device people carries out the measurement and prospecting operation that some need not be under the adverse circumstances such as very high-precision dangerous area or ground end high-altitude；
In terms of medical science, the application idea of depth camera is also that quite extensively, the research project of Bern universities of Switzerland is deep using exploitation
Degree camera system, is dissected corpse using sound control and body-sensing software instead of doctor, and University of Washington then grinds in laboratory
Studying carefully can control surgical mechanical arm by the transformation to depth camera, and utilize its sensitive negative-feedback work(
The arm can be controlled to perform operation, or the rehabilitation shape by catching the body kinematics situation of postoperative patient to obtain current patient
Condition etc..
In terms of tunnel detection, advance geologic prediction is mainly and uses engineering geophysical method, i.e., tunnel physical parameter is entered
The method of row analysis.All there is the range of application and detection accuracy of oneself due to various geophysical prospecting methods, therefore our usually bases
The different physical features that detected object has are detected using two or more effective geophysical prospecting method, and to result
Carry out comprehensive analysis.From the point of view of engineering practice effort for many years and experience, in the work physical prospecting of tunnel geological forecast work
The methods such as method main flexible wave reflection method, echolation, infrared detecting method, DC electrical method, this several method is all
Front and side front each side geological information are tunneled to complete-section tunnel boring machine carries out detection analysis, for tunneling boring tunnel digging
That enters that the situation at machine rear substantially takes into account is fewer.Three-dimensional visialization of tunnel technology can be realized being characterized for complicated tunnel, break
Face and the treatment of local section, while some system designs can realize the triangle gridding to tunnel profile, surface area meter
Calculate and tunnel contour line deviates calculating, infrared temperature data can be shown, any cross section sectional drawing and some parts are thin
The displaying of section.Further, by way of software and hardware combining, system can be detected to tunnel deformation, and former to it
Because being analyzed.The degree of accuracy of inspection is (+/- 2mm within 25m) also higher.Tunnel state deterioration multidate information can be grasped,
And system operatio is fairly simple, not examinate person's technical merit limitation mostly.
In sum, need to overcome some known difficult during tunnel scene imaging, on the one hand will be to extensive
Scene to carry out reconstruction be to need to take sizable internal memory, and process of reconstruction needs to expend considerable time, the opposing party
Face color information in tunnel adverse circumstances is not that easily can just extract very much, due to the deficiency of hardware condition facility,
Need to spend more energy during the treatment of later stage color information.And environment is poor in tunnel, some are quicker
Sense is equipped in tunnel commonly using can inevitably reduce the life-span, it is therefore desirable to increase good safeguard measure.
The content of the invention
The present invention is in order to solve the above problems, it is proposed that a kind of three-dimensional visialization of tunnel system and side based on depth camera
Be carried to depth camera on complete-section tunnel boring machine and be subject to mechanical rotary device and protection device by method, the present invention,
In the tunneling process of complete-section tunnel boring machine, the tunnel cross-section experienced during being advanced is filmed one by one.Pass through
Treatment to tunnel vision information, analysis obtain the overall condition in current tunnel.
To achieve these goals, the present invention is adopted the following technical scheme that：
A kind of three-dimensional visialization of tunnel system based on depth camera, including depth camera device, whirligig, it is described
Depth camera device includes microphone assembly, infrared camera, colour imagery shot and infrared camera, the depth camera
Device is mounted on the whirligig, and the whirligig drive depth camera device carries out 180 ° on vertical direction
Rotation, gathers the image of tunnel upper half；
Angular transducer is provided with the whirligig, the anglec of rotation of whirligig is detected, while on whirligig
It is provided with elevation-angle controller, the acquisition angles of controlling depth cam device.
The depth camera device is arranged on support, and the support is fixed on whirligig.
The depth camera device is provided with waterproof case.
Modeling method based on said system, comprises the following steps：
(1) depth information and image information of depth camera device collection are obtained；
(2) image for collecting is sampled, floating-point, smoothing techniques, from image obtain depth camera dress
The motion track put；
(3) large-scale virtual space is set up, in the information fusion that will be collected according to the sampling interval to Virtual Space, is formed
Threedimensional model.
In the step (1), the depth camera being mounted on complete-section tunnel boring machine is obtained with the advance two of machine
The depth and colour information in tunnel are taken, wherein the part for repeating to photograph as can constantly add as the optimization of photographic intelligence
Plus tunnel information, the lower limit of redundancy can't be set.
In the step (2), set according to threshold value and depth image data is converted, the data outside threshold range
It is invalid to set distance.
In the step (2), depth data is carried out into sampling processing, increase the speed for the treatment of, while to the weight in scene
Build object to be processed, its reconstruction model can be optimized by smoothing techniques to mobile small-sized object, while by smooth
Algorithm has carried out denoising, has also processed the dynamic change in some scenes, any cut-off being not exhibited by raw video
Or sky can also be filled, with camera closer to object, by using the data of new higher precision, body surface can quilt
Continuous optimization.
In the step (2), its posture is constantly obtained when camera is moved by using the registration Algorithm of interactive, this
The relative pose of camera when sample system knows current camera relative to start frame all the time.Followed the trail of for posture and typically use two
Plant registration Algorithm.The first is to use the point cloud that the point cloud and acquisition from depth image data for coming will be calculated from reconstructed object
Registration is carried out, or the single data using such as to the different angles of visual field of Same Scene carry out registration；Second algorithm can
With being obtained in that the tracking result of higher precision when cube is processed to re-establishing, but the object for being moved in scene
The algorithm may be not healthy and strong enough, if the tracking in scene is interrupted, then needs to take the photograph the position of camera with last
Can just proceed to follow the trail of as head aligned in position.
In the step (2), the translational speed according to depth camera device sets the size of smoothing parameter.
In the step (3), the depth image data fusion produced from known poses camera is regarded to represent camera
The cube of the scenery in wild scope.This fusion to depth data is frame by frame, to be carried out continuously, and finally, is regarded from sensor
Point position carries out light projection to re-establishing cube, the point cloud being calculated using ray casting algorithm, then calculates its normal vector,
With the point cloud with normal vector and the input picture registration of next frame, the pose of next frame input picture is calculated.So it is a circulation
Process.The dot matrix cloud of reconstruction can produce the three-dimensional reconstruction cube for having rendered.
In the step (3), by the precision for setting the size of sampling step length to set model.Note setting for sampling step length
Put scope and have to be larger than 0 and less than minimum volume axle voxel resolution, weight will be caused beyond the sampling step length value of this scope
Threedimensional model after building lacks the details on curved surface or curved surface.
In the step (3), the focusing on of this system realizes large-scale scene modeling, special due to tunnel model
Property, therefore attempt being set up than in a big way in the side of tunnelling advance, because the limitation of GPU internal memories, system is using profit
Modeled with CPU internal memories.In modeling process by the way of processed offline.Winding detection and winding optimization are with the addition of in algorithm,
According to the result that winding optimizes, the coordinate of point is updated so that what the place of winding rebuild twice can align.When camera rotation or
When the distance of person's movement exceedes certain threshold value, present frame is added and is done key frame and is carried out winding detection, winding is detected
First by finding the key frame of matching, if there is the image of matching, the SURF of the matching image that will be stored in internal memory is special
Levy and a little index out again and with depth image.The SURF points of given two field pictures describe sub- Ui and Um, with FLANN lookup algorithms come
Set up the matching relationship of SURF, if it is possible to which the SURF points quantity for matching is no more than given threshold, then it is assumed that this is not one
Effective matching, the matching relationship of SURF is set up by matching, by the matching between the SURF that previous step is set up, is calculated with RANSAC
Method estimates the pose between two frames, and camera pose is optimized with LM algorithm optimizations re-projection error again after obtaining pose.It is excellent again with ICP
Change the pose that above-mentioned algorithm is calculated, if the error between match point is less than given threshold, then it is assumed that this is one effective
Winding.
Beneficial effects of the present invention are：
(1) tunnel threedimensional model can integrally be showed, allow user for whole tunnel have more intuitively it is cognitive with
Impression；
(2) by the analysis for tunnel correlated color information, it is also possible to it was observed that geological state overall in tunnel, such as
Trend in crack etc., so as to carry out more targeted scientific construction.Block mold is to system of analysis rock office checking relevant parameter
Had certain effect for the influence that complete-section tunnel boring machine is produced.
Brief description of the drawings
Fig. 1 is schematic diagram profile of the invention.
Fig. 2 is depth camera installation drawing of the invention.
Fig. 3 is design flow diagram of the present invention.
Wherein, 1 depth camera is represented, 2 represent mechanical rotary device, and 3 represent tunnel surface, and 4 represent shell protection dress
Put, 9 represent microphone array, and 10 represent infrared camera, and 11 represent colour imagery shot, and 12 represent infrared camera, and 13 represent
The elevation angle controls motor, and 14 represent support.
Specific embodiment：
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
Because scene is larger, and the mode of real-time processing is quite to expend GPU internal memories, therefore we are using offline
The method of processing data, i.e., first collect all information in tunnel, data is processed on this basis then, so as to keep away
Exempt from the situation of Out of Memory.Wherein, processed offline is also classified into both of which, and a kind of is first to set up the model of small range,
Then all of small-scale model of place is stitched together one by one, is then in addition first to get all of data, data are unified
Analyze and process, calculate last threedimensional model.The method that we use the latter, because for split-join model,
Some errors are wherein there will certainly be, it is many that this is poorer than the precision of the latter.Depth camera from multiple angles by obtaining
The depth image data got is merged to rebuild the single frames smooth surface model of object.When sensor is moved, shine
The position of camera and pose information are recorded, and these information include position and orientation.Due to it is understood that each frame
Associating between the posture and frame and frame of image, the data that multiframe is gathered from different perspectives can be fused into what single frames was rebuild
Fixed point cube.We are envisioned that down a huge virtual cube in space, and the inside is our real worlds
Scene, when our movable sensors, depth data information is continuously added.
First, depth camera is carried on complete-section tunnel boring machine machine, and utilizes hardware rotation device, complete
Scanning carries out 180 ° of scanning-tunnelling upper half area panoramas during section tunnel boring machine advances, because complete-section tunnel boring machine
Pace to be much smaller than the sweep speed of depth camera, and the multiple scanning of depth camera is more beneficial for scene
The reconstruction of real information, and the true motion track of depth camera camera also has algorithm and calculated later, therefore I
Can leave out of consideration depth camera video camera true and motion track it is whether regular.
Further, the relevant depth information of scene is got using the infrared camera of depth camera, depth herein
Degree information can embody the position of the current taken specific camera of object, obtain in addition under its colour information and storage
Come.
Further, photographic intelligence is processed, is set according to threshold value and depth image data is converted, in threshold value
It is invalid that data outside scope set distance, can so be excluded outside three-dimensional reconstruction some special objects.
Further, registration is carried out to depth data after treatment, includes the latest position for calculating camera, track position
Acquisition can be calculated according to trajectory calculation algorithm, the calculating of this parameter can cause that system understands camera relative to start frame
When camera position, and data are carried out with the process of smoothing techniques, the size for smoothing parameter can be moved according to camera
Dynamic speed determines, so as to can ensure that detail of information retains number.
Further, virtual cubic space is set up, requirement of the Virtual Space for Y-axis herein, namely before tunnel
Enter direction ratio larger.The difficulty of large scale scene modeling is main in terms of this, the requirement ratio due to Real-time modeling set for internal memory
It is larger, therefore employ the mode of processed offline.Depth real-coded GA and camera position letter after by smoothing denoising
Breath processed, certainly also treatment scene in some other small dynamic changes, or wisp movement or disappearance, after from
Sensor viewpoint position the light for re-establishing cube is projected, lighting required for cloud sequence can be rendered after reconstruction
Three-dimension Reconstruction Model.
Further, by the precision for setting the size of sampling step length to set model, the size of sampling step length will consider
Application and the run time and the aspect such as exquisite degree of last model of program to internal memory.
The present invention is equipped on complete-section tunnel boring machine.
As shown in Figure 1 and Figure 2, the depth camera 3-D imaging system that complete-section tunnel boring machine is carried, including can be by
The mechanical device of camera is rotated, the overall space in tunnel three-dimensional modeling can be carried out.It is depth camera that whole system includes
Head can rotate the mechanical rotary device that can photograph tunnel upper half, protect the canning of camera, and can be right
Tunnel scene is capable of the depth camera of three-dimensional modeling.By the three-D imaging method for designing build the three-dimensional of tunnel scene
Mould.
Rotate the mechanical device of camera, it is possible to achieve itself is determined according to the speed that complete-section tunnel boring machine advances
The speed of rotation, it is ensured that some positions for shooting tunnel space will not be missed.
Due to subterranean tunnel space Duo Shui, moist situation, general device is mounted on complete-section tunnel boring machine facility
It is easy to be influenceed by severe external condition, causes shortening for service life, therefore we use protection device by system
Protected than more sensitive cam device, and this canning can't influence the shooting effect of camera.
Distance of the tunnel relative to camera is gone out so as to build complete tunnel by depth photo imaging detection
Threedimensional model.
Although above-mentioned be described with reference to accompanying drawing to specific embodiment of the invention, not to present invention protection model
The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not
Need the various modifications made by paying creative work or deformation still within protection scope of the present invention.
Claims (10)
1. a kind of three-dimensional visialization of tunnel system based on depth camera, it is characterized in that：Including depth camera device, rotating dress
Put, the depth camera device includes microphone assembly, infrared camera, colour imagery shot and infrared camera, the depth
Degree cam device is mounted on the whirligig, and the whirligig drive depth camera device is carried out on vertical direction
180 ° of rotation, gather the image of tunnel upper half；
Angular transducer is provided with the whirligig, the anglec of rotation of whirligig is detected, while being set on whirligig
There are elevation-angle controller, the acquisition angles of controlling depth cam device.
2. a kind of three-dimensional visialization of tunnel system based on depth camera as claimed in claim 1, it is characterized in that：The depth
Cam device is arranged on support, and the support is fixed on whirligig.
3. a kind of three-dimensional visialization of tunnel system based on depth camera as claimed in claim 1, it is characterized in that：The depth
Cam device is provided with waterproof case.
4. the modeling method of the system being based on as any one of claim 1-3, it is characterized in that：Comprise the following steps：
(1) depth information and image information of depth camera device collection are obtained；
(2) image for collecting is sampled, floating-point, smoothing techniques, depth camera device is obtained from image
Motion track；
(3) large-scale virtual space is set up, in the information fusion that will be collected according to the sampling interval to Virtual Space, forms three-dimensional
Model.
5. modeling method as claimed in claim 4, it is characterized in that：In the step (1), complete-section tunnel boring machine is mounted in
On depth camera with before machine so that obtain tunnel depth and colour information, wherein the part for repeating to photograph can
As the optimization of photographic intelligence, tunnel information is as constantly added, the lower limit of redundancy can't be set.
6. modeling method as claimed in claim 4, it is characterized in that：In the step (2), set to depth image according to threshold value
Data are converted, and it is invalid that the data outside threshold range set distance.
7. modeling method as claimed in claim 4, it is characterized in that：In the step (2), calculated by using the registration of interactive
Method constantly obtains its posture when camera is moved, and is followed the trail of for posture and uses the point Yun Yucong that will be calculated from reconstructed object
The point cloud obtained in depth image data carries out registration, or individually uses the number of the different angles of visual field such as to Same Scene
According to carrying out registration.
8. modeling method as claimed in claim 4, it is characterized in that：In the step (2), according to the movement of depth camera device
Speed sets the size of smoothing parameter, is to represent camera by the depth image data fusion produced from known poses camera
The cube of scenery within the vision, this fusion to depth data is frame by frame, to be carried out continuously, finally, from sensor
Viewpoint position carries out light projection to re-establishing cube, the point cloud being calculated using ray casting algorithm, then calculates its normal direction
Amount, with the point cloud with normal vector and the input picture registration of next frame, calculates the pose of next frame input picture.
9. modeling method as claimed in claim 4, it is characterized in that：In the step (3), using offline place in modeling process
The mode of reason, is optimized using winding detection and winding, according to the result that winding optimizes, updates the coordinate of point so that the ground of winding
The result alignment that side rebuilds twice.
10. modeling method as claimed in claim 9, it is characterized in that：In the step (3), when camera rotates or mobile
When distance exceedes threshold value, present frame is added and is done key frame and is carried out winding detection, winding detection is first by finding
The key frame of matching, if there is the image of matching, the SURF characteristic points and depth map of the matching image that will be stored in internal memory
Come as indexing out again.The SURF of given two field pictures describes sub- Ui and Um, the matching relationship of SURF is set up with FLANN, such as
The SURF points quantity that fruit can match is no more than given threshold, then it is assumed that this is not an effective matching, is built by matching
The matching relationship of vertical SURF, by the matching between the SURF that previous step is set up, the pose between two frames is estimated with RANSAC algorithms,
Obtain after pose optimizing camera pose with LM algorithm optimizations re-projection error again, the pose being calculated with ICP re-optimizations, if
Error between match point is less than given threshold, then it is assumed that this is an effective winding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710081447.XA CN106846479B (en) | 2017-02-15 | 2017-02-15 | Three-dimensional visialization of tunnel system and method based on depth camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710081447.XA CN106846479B (en) | 2017-02-15 | 2017-02-15 | Three-dimensional visialization of tunnel system and method based on depth camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106846479A true CN106846479A (en) | 2017-06-13 |
| CN106846479B CN106846479B (en) | 2018-11-30 |
Family
ID=59127287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710081447.XA Active CN106846479B (en) | 2017-02-15 | 2017-02-15 | Three-dimensional visialization of tunnel system and method based on depth camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106846479B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886129A (en) * | 2017-11-13 | 2018-04-06 | 湖南大学 | A kind of mobile robot map closed loop detection method of view-based access control model bag of words |
| CN109375263A (en) * | 2018-12-04 | 2019-02-22 | 山东大学 | A kind of earthquake advanced prediction device, system and method suitable for drill+blast tunnel |
| CN110186651A (en) * | 2018-02-23 | 2019-08-30 | 宁波舜宇车载光学技术有限公司 | MTF test equipment for camera lens |
| CN110415329A (en) * | 2018-04-26 | 2019-11-05 | 财团法人工业技术研究院 | Three-dimensional modeling apparatus and calibration method applied to it |
| CN111258410A (en) * | 2020-05-06 | 2020-06-09 | 北京深光科技有限公司 | Man-machine interaction equipment |
| WO2021042668A1 (en) * | 2019-09-06 | 2021-03-11 | 山东大学 | Tunnel surrounding rock structure virtual reproduction system carried on tbm, and method thereof |
| CN113284242A (en) * | 2021-06-18 | 2021-08-20 | 中铁隧道局集团有限公司 | Tunnel design system based on big data and AI |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413352A (en) * | 2013-07-29 | 2013-11-27 | 西北工业大学 | Scene three-dimensional reconstruction method based on RGBD multi-sensor fusion |
| CN104599314A (en) * | 2014-06-12 | 2015-05-06 | 深圳奥比中光科技有限公司 | Three-dimensional model reconstruction method and system |
| KR20160019613A (en) * | 2014-08-11 | 2016-02-22 | 한국전력공사 | Apparatus for modeling 3d of underground structure and method thereof |
-
2017
- 2017-02-15 CN CN201710081447.XA patent/CN106846479B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413352A (en) * | 2013-07-29 | 2013-11-27 | 西北工业大学 | Scene three-dimensional reconstruction method based on RGBD multi-sensor fusion |
| CN104599314A (en) * | 2014-06-12 | 2015-05-06 | 深圳奥比中光科技有限公司 | Three-dimensional model reconstruction method and system |
| KR20160019613A (en) * | 2014-08-11 | 2016-02-22 | 한국전력공사 | Apparatus for modeling 3d of underground structure and method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 陈晓明等: "基于Kinect深度信息的实时三维重建和滤波算法研究", 《计算机应用研究》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886129B (en) * | 2017-11-13 | 2021-06-08 | 湖南大学 | Mobile robot map closed-loop detection method based on visual word bag |
| CN107886129A (en) * | 2017-11-13 | 2018-04-06 | 湖南大学 | A kind of mobile robot map closed loop detection method of view-based access control model bag of words |
| CN110186651A (en) * | 2018-02-23 | 2019-08-30 | 宁波舜宇车载光学技术有限公司 | MTF test equipment for camera lens |
| CN110186651B (en) * | 2018-02-23 | 2021-08-03 | 宁波舜宇车载光学技术有限公司 | MTF test equipment for lens |
| CN110415329A (en) * | 2018-04-26 | 2019-11-05 | 财团法人工业技术研究院 | Three-dimensional modeling apparatus and calibration method applied to it |
| CN110415329B (en) * | 2018-04-26 | 2023-10-13 | 财团法人工业技术研究院 | Three-dimensional modeling device and calibration method applied to same |
| CN109375263A (en) * | 2018-12-04 | 2019-02-22 | 山东大学 | A kind of earthquake advanced prediction device, system and method suitable for drill+blast tunnel |
| WO2021042668A1 (en) * | 2019-09-06 | 2021-03-11 | 山东大学 | Tunnel surrounding rock structure virtual reproduction system carried on tbm, and method thereof |
| US11263809B2 (en) | 2019-09-06 | 2022-03-01 | Shandong University | TBM-mounted virtual reconstruction system and method for surrounding rock structure of tunnel |
| CN111258410B (en) * | 2020-05-06 | 2020-08-04 | 北京深光科技有限公司 | Man-machine interaction equipment |
| CN111258410A (en) * | 2020-05-06 | 2020-06-09 | 北京深光科技有限公司 | Man-machine interaction equipment |
| CN113284242A (en) * | 2021-06-18 | 2021-08-20 | 中铁隧道局集团有限公司 | Tunnel design system based on big data and AI |
| CN113284242B (en) * | 2021-06-18 | 2022-05-31 | 中铁隧道局集团有限公司 | Tunnel design system based on big data and AI |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106846479B (en) | 2018-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846479B (en) | Three-dimensional visialization of tunnel system and method based on depth camera | |
| US10855936B2 (en) | Skeleton-based effects and background replacement | |
| US10605602B2 (en) | Surveying system | |
| CN108961395B (en) | A method of three dimensional spatial scene is rebuild based on taking pictures | |
| US10592747B2 (en) | Method and apparatus for 3-D auto tagging | |
| CN107836012B (en) | Projection image generation method and device, and mapping method between image pixel and depth value | |
| JP6974873B2 (en) | Devices and methods for retrieving depth information from the scene | |
| CN101329771B (en) | Method for rapidly modeling of urban street base on image sequence | |
| CN110084832A (en) | Correcting method, device, system, equipment and the storage medium of camera pose | |
| CN108154550A (en) | Face real-time three-dimensional method for reconstructing based on RGBD cameras | |
| CN109631887A (en) | Inertial navigation high-precision locating method based on binocular, acceleration and gyroscope | |
| JP7427188B2 (en) | 3D pose acquisition method and device | |
| CN105825518A (en) | Sequence image rapid three-dimensional reconstruction method based on mobile platform shooting | |
| US10659686B2 (en) | Conversion of an interactive multi-view image data set into a video | |
| RU2572637C2 (en) | Parallel or serial reconstructions in online and offline modes for 3d measurements of rooms | |
| El-Hakim et al. | Effective 3d modeling of heritage sites | |
| WO2018019272A1 (en) | Method and apparatus for realizing augmented reality on the basis of plane detection | |
| US11928778B2 (en) | Method for human body model reconstruction and reconstruction system | |
| CN108253962A (en) | New energy pilotless automobile localization method under a kind of low light environment | |
| CN109242951A (en) | A kind of face's real-time three-dimensional method for reconstructing | |
| CN109613974A (en) | A kind of AR household experiential method under large scene | |
| Gomez-Lahoz et al. | Recovering traditions in the digital era: the use of blimps for modelling the archaeological cultural heritage | |
| Fua et al. | Markerless full body shape and motion capture from video sequences | |
| CN110520904A (en) | Display control unit, display control method and program | |
| CN206115390U (en) | Virtual roaming device in digit coastal city based on virtual reality helmet |
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 |