CN107016667B - A kind of device obtaining large parts three-dimensional point cloud using binocular vision - Google Patents
A kind of device obtaining large parts three-dimensional point cloud using binocular vision Download PDFInfo
- Publication number
- CN107016667B CN107016667B CN201710168404.5A CN201710168404A CN107016667B CN 107016667 B CN107016667 B CN 107016667B CN 201710168404 A CN201710168404 A CN 201710168404A CN 107016667 B CN107016667 B CN 107016667B
- Authority
- CN
- China
- Prior art keywords
- guide rail
- driving motor
- slide block
- bolted
- lead screw
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
Present invention relates particularly to a kind of devices that large parts three-dimensional point cloud is obtained using binocular vision, including horizontal guide rail screw mechanism, mobile base, turntable, several parts such as mechanical arm and camera system, wherein horizontal guide rail screw mechanism one end is equipped with driving motor, the movement of lead screw rotation realization mobile base horizontal direction is driven by driving motor, driving motor benefit is fixed by bolts on level ground, lead screw one end is fixed in the rotary shaft of driving motor by shaft coupling, the other end of lead screw is fixed in cement platform by a bearing, guide rail is bolted on level ground, mobile base is connect by guide rail slide block with guide rail, mobile base is bolted with turntable, turntable is connect with mechanical arm bearing, mechanical arm is utilized by flange with camera system and is bolted, there are four freedom degrees for present invention tool , it is uniformly controlled by a console, cost is relatively low, and the point cloud suitable for large parts obtains work.
Description
Technical field
The present invention relates to the acquisitions of the three-dimensional point cloud of heavy parts, and in particular to a kind of to obtain large size zero using binocular vision
The device of part three-dimensional point cloud.
Background technique
In real world, all objects be all it is three-dimensional, an objective object has its corresponding shape, line
The information such as reason, color and size, but what traditional equipment recorded is two-dimensional signal mostly, does not include phase and depth is believed
Therefore breath, the object being recorded just lose three-dimensional sense, it has not been convenient to the observation analysis of multi-angle and research, so just urgent need
It wants to be that one kind can be used to rebuild three-dimensional spatial information to the technology that three-dimensional appearance measures, three dimensional point cloud
Technology is numerous scientific researches such as Aeronautics and Astronautics, automobile, ship, pattern-recognition, Reverse Engineering CAD/CAM modeling, computer vision
The important subject in field, point cloud data are a series of set for the space coordinate points for scanning surface in kind and obtaining, it
Not only include the three-dimensional coordinate information of object table millet cake, also includes the information such as color, texture, material object can more meticulously be presented
Three-dimensional detail can draw complex-curved and three-dimensional scenic, convenient storage, while also overcoming in two dimensional image and existing
Some defects.
The further development of Point Cloud Processing technology, in three-dimension tidal current, human body reconstruction, machine vision, work
Acquisition, navigation and the automatic Pilot of industry CAD model, the operation of medicine correction, between the motion sensing control of game role, virtual fitting, it is empty
The numerous areas such as quasi- driving and e-commerce, provide theoretical basis for researcher, not only promote three-dimensional point cloud processing technique
Further application in current academia and industry modeling, and promote three-dimensional reconstruction in more wide field
Preferably applied, so, the research to point cloud data technology has highly important academic significance and application value.
Summary of the invention
Currently, there are mainly two types of the acquisition modes of three-dimensional point cloud: contact and contactless, contact method is commonly set
Standby is three dimensional coordinate measuring machine, point cloud data is obtained by the detecting head of three dimensional coordinate measuring machine, the advantage of such method is
There is no special requirement to testee reflection characteristic and surface color, precision is very high, the disadvantage is that expensive, measuring speed
Slowly, easily scratch measured surface, there are contact pressure and radius compensation, be not suitable for measuring easily-deformable, frangible, soft and super-thin
Object keeps its application limited, and non-contact method is mainly include the following types: laser method, Structure light method, encoded light method and More are dry
The Schlieren method, stereoscopic parallax method etc. are related to, the advantage of non-contact method is that acquisition speed is fast, can measure frangible and easily-deformable object
Body, will not cause surface damage to determinand, and disadvantage is that the edge contour of object is not easy precise measurement, and vulnerable to intensity of illumination and
Object under test Color influences, are affected by working environment, and in non-contact method, and be with laser method using most
It is more, but often price is higher for the three-dimensional space data reduction equipment based on laser, therefore irradiates to based on normal daylight
In the case of three-dimensional point cloud extract research have relatively high practical value.
The purpose of the invention is to overcome more existing cloud to obtain equipment shortcoming, propose that a kind of utilize images
Machine obtains equipment as scanning means three-dimensional point cloud, it has broader scanning compared with more existing cloud obtains equipment
Range can effectively improve the working efficiency to determinand scanning, and video camera is the difference that can differentiate determinand surface
Color, can be well by determinand from distinguishing in other chaff interferents in environment, the available determinand being more clear
Two identical video cameras are separately fixed on the gripper of mechanical arm front end by the three-D profile of body, the present invention, are imaged using two
Machine simulates human eye, gets the image information of two width different perspectivess of determinand same position, and by computer software to figure
It is extracted as information carries out a cloud analysis, splicing fusion then is carried out to point cloud data, obtains position to be measured on three-dimensional space
Point cloud data, with the movement of mechanical arm, video camera can be scanned with measuring targets different location, in order to get not
With the three dimensional point cloud of position, these three dimensional point clouds are finally subjected to overall splicing and are merged, are formed on computers
The accurate three-D profile of object under test.
The beneficial effects of the present invention are the present invention uses the motion mode of lead screw guide rails mechanism, and such design can be protected
The robust motion for demonstrate,proving equipment eliminates due to adverse effect when ground out-of-flatness acquires point cloud data, reduces one
Divide error to apply the turntable that can be rotated by 360 ° with horizontal direction in the present invention, improves equipment in acquisition number
According to when flexibility, in addition also apply the fluid pressure type forearm that can be stretched, and this fluid pressure type forearm and lower part is big
One hydraulic pressure support bar is equally installed between arm, utilizes the vertical height of the adjustable forearm front-end camera of hydraulic pressure support bar
Degree, using the impulse stroke in the adjustable camera horizon direction of telescopic hydraulic forearm, meanwhile, mechanical arm large arm can also be into
Swing within the scope of row certain angle can greatly improve the efficient working range of video camera using the design of such convolution,
In addition, being also equipped with a gripper driving motor at mechanical arm gripper and fluid pressure type forearm connecting shaft, electricity is driven by gripper
Machine controls gripper and rotates around connecting shaft, so that video camera is more flexible when obtaining data, and binocular camera again can be real
The function of now simulating human eye binocular, reaches the final purpose for obtaining determinand three-D profile.
A kind of device obtaining large parts three-dimensional point cloud using binocular vision, including guide rail one (8), guide rail two (9)
And the lead screw guide rails mechanism that lead screw (11) is constituted, the bolt that guide rail one (8), guide rail two (9) are utilized respectively insertion guide rail interior are solid
It is scheduled on level ground, lead screw (11) one end is connect using shaft coupling with driving motor two (10), and lead screw (11) other end utilizes
Bearing is fixed on cement boss, the guide rail slide block machine that guide rail one (8) and guide rail slide block one (12), guide rail slide block two (13) form
The guide rail slide block mechanism that structure, guide rail two (9) and guide rail slide block three (14), guide rail slide block four (15) form, mobile foundation bottom plate (1)
It is bolted between each sliding block, driving motor one (7) is bolted with pedestal bottom plate (1), each susceptor posts and pedestal
Bottom plate (1), pedestal top plate (2) are bolted, and turntable (16) is bolted with pedestal top plate (2), Y shaped bracket (17) and driving
The connection of motor one (7) shaft coupling, driving motor three (18), driving motor four (19) and Y shaped bracket (17) are bolted, end cap one
(20), end cap two (21) is bolted with Y shaped bracket (17), and mechanical arm large arm (22) is connect with Y shaped bracket (17) bearing, can be stretched
Contracting mechanical arm forearm (24) and large arm (22) by a rotatable axis connection, hydraulic pressure support bar (23) respectively with large arm
(22), forearm (24) axis connection, end gripper (25) and forearm (24) axis connection, gripper control motor (27) and forearm (24) spiral shell
It tethers and connects, gripper control motor (27) is connect with end gripper (25) by shaft coupling, camera system (26) and end gripper
(25) flanged joint.
A kind of device obtaining large parts three-dimensional point cloud using binocular vision, it is characterised in that: pedestal bottom plate
(1) connection is engaged with lead screw (11) screw thread, the bolt that guide rail one (8), guide rail two (9) are utilized respectively insertion guide rail interior is fixed on
On level ground, lead screw (11) one end is connect using shaft coupling with driving motor two (10), and lead screw (11) other end utilizes bearing
It is fixed on cement boss, the guide rail slide block mechanism that guide rail one (8) and guide rail slide block one (12), guide rail slide block two (13) form,
The guide rail slide block mechanism that guide rail two (9) and guide rail slide block three (14), guide rail slide block four (15) form, passes through driving motor two (10)
Lead screw (11) rotation is driven, mobile foundation acquisition is made to move horizontally ability, a cloud can be significantly increased using this design and obtain
When effective travel, reduce when point cloud obtains the drawbacks of moving repeatedly determinand, can effectively reduce by mobile determinand institute
Bring human error.
A kind of device obtaining large parts three-dimensional point cloud using binocular vision, it is characterised in that: driving motor
One (7) are connect with Y shaped bracket (17) by shaft coupling, so that mechanical arm system integrally obtains the freedom degree of a horizontal rotation,
Driving motor three (18), driving motor four (19) and Y shaped bracket (17) are bolted, driving motor three (18), driving motor four
(19) pass through the swing of gear synchronous control mechanical arm large arm (22), end cap one (20), end cap two (21) and Y shaped bracket
(17) it is bolted, mechanical arm large arm (22) is connect with Y shaped bracket (17) bearing, scalable mechanical arm forearm (24) and large arm
(22) by a rotatable axis connection, hydraulic pressure support bar (23) respectively with large arm (22), forearm (24) axis connection, end hand
Pawl (25) and forearm (24) axis connection, gripper control motor (27) are bolted with forearm (24), and package unit shares 4 freedom
Degree, compared with common laser scanner in the market, it is advantageous that structure is simple, and it is easy to control, it is cheap.
Detailed description of the invention:
Fig. 1 is a kind of device pedestal and guide rail installation that large parts three-dimensional point cloud is obtained using binocular vision of the present invention
Schematic diagram；
Fig. 2 is a kind of device sliding block installation signal that large parts three-dimensional point cloud is obtained using binocular vision of the present invention
Figure；
Fig. 3 is that a kind of device integral installation for obtaining large parts three-dimensional point cloud using binocular vision of the present invention is illustrated
Figure.
Fig. 4 is a kind of device Figure of abstract that large parts three-dimensional point cloud is obtained using binocular vision of the present invention.
Claims (3)
1. a kind of device that large parts three-dimensional point cloud is obtained using binocular vision, including lead screw guide rails mechanism, mobile base,
Mechanical arm and camera system composition, it is characterised in that: guide rail one (8), guide rail two (9) and lead screw (11) constitute lead screw guide rails machine
Structure, the bolt that guide rail one (8), guide rail two (9) are utilized respectively insertion guide rail interior are fixed on level ground, lead screw (11) one end
It is connect using shaft coupling with driving motor two (10), lead screw (11) other end is fixed on cement boss using bearing, guide rail one
(8) guide rail slide block mechanism is formed with guide rail slide block one (12), guide rail slide block two (13), guide rail two (9) and guide rail slide block three (14),
Guide rail slide block four (15) forms guide rail slide block mechanism, is bolted between mobile foundation bottom plate (1) and each sliding block, driving motor
One (7) are bolted with pedestal bottom plate (1), and each susceptor posts are bolted with pedestal bottom plate (1), pedestal top plate (2), rotation
Platform (16) is bolted with pedestal top plate (2), and Y shaped bracket (17) is connect with driving motor one (7) shaft coupling, driving motor three
(18), driving motor four (19) is bolted with Y shaped bracket (17), end cap one (20), end cap two (21) and Y shaped bracket (17) spiral shell
It tethers and connects, mechanical arm large arm (22) is connect with Y shaped bracket (17) bearing, and scalable mechanical arm forearm (24) passes through with large arm (22)
A piece rotatable axis connection, hydraulic pressure support bar (23) respectively with large arm (22), forearm (24) axis connection, end gripper (25) with
Forearm (24) axis connection, gripper control motor (27) are bolted with forearm (24), and gripper controls motor (27) and end gripper
(25) it is connected by shaft coupling, camera system (26) and end gripper (25) flanged joint.
2. a kind of device for being obtained large parts three-dimensional point cloud using binocular vision, feature are existed according to claim 1
In: pedestal bottom plate (1) engages connection with lead screw (11) screw thread, and guide rail one (8), guide rail two (9) are utilized respectively insertion guide rail interior
Bolt be fixed on level ground, lead screw (11) one end is connect using shaft coupling with driving motor two (10), and lead screw (11) is separately
One end is fixed on cement boss using bearing, and guide rail one (8) and guide rail slide block one (12), guide rail slide block two (13) form guide rail
Slide block mechanism, guide rail two (9) and guide rail slide block three (14), guide rail slide block four (15) form guide rail slide block mechanism, pass through driving electricity
Machine two (10) drives lead screw (11) rotation, and mobile foundation acquisition is made to move horizontally ability.
3. a kind of device for being obtained large parts three-dimensional point cloud using binocular vision, feature are existed according to claim 1
In: driving motor one (7) is connect with Y shaped bracket (17) by shaft coupling, so that mechanical arm system integrally obtains a horizontal rotation
The freedom degree turned, driving motor three (18), driving motor four (19) and Y shaped bracket (17) are bolted, driving motor three (18),
Swing of the driving motor four (19) by gear synchronous control mechanical arm large arm (22), end cap one (20), end cap two (21)
It is bolted with Y shaped bracket (17), mechanical arm large arm (22) is connect with Y shaped bracket (17) bearing, scalable mechanical arm forearm
(24) with large arm (22) by a rotatable axis connection, hydraulic pressure support bar (23) respectively with large arm (22), forearm (24) axis
Connection, end gripper (25) and forearm (24) axis connection, gripper control motor (27) are bolted with forearm (24), package unit
Share 4 freedom degrees.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710168404.5A CN107016667B (en) | 2017-03-21 | 2017-03-21 | A kind of device obtaining large parts three-dimensional point cloud using binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710168404.5A CN107016667B (en) | 2017-03-21 | 2017-03-21 | A kind of device obtaining large parts three-dimensional point cloud using binocular vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107016667A CN107016667A (en) | 2017-08-04 |
| CN107016667B true CN107016667B (en) | 2019-07-05 |
Family
ID=59440660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710168404.5A Expired - Fee Related CN107016667B (en) | 2017-03-21 | 2017-03-21 | A kind of device obtaining large parts three-dimensional point cloud using binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107016667B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107639638B (en) * | 2017-09-27 | 2024-01-23 | 广东工业大学 | Key mechanical arm based on machine vision |
| CN109839065A (en) * | 2017-11-29 | 2019-06-04 | 刘松林 | A kind of vision measurement test platform |
| CN108444383B (en) * | 2018-03-08 | 2019-06-28 | 大连理工大学 | The box-like process integral measurement method of view-based access control model laser group |
| CN109079751A (en) * | 2018-07-13 | 2018-12-25 | 安徽派日特智能装备有限公司 | A kind of rotary type robot base |
| CN108748210A (en) * | 2018-07-18 | 2018-11-06 | 昆明理工大学 | A kind of light-duty package picks and places robot |
| CN108908272A (en) * | 2018-08-20 | 2018-11-30 | 东南大学 | A kind of two degrees of freedom towards library takes book platform |
| CN109243223B (en) * | 2018-09-28 | 2020-12-15 | 邯郸学院 | Multimedia interaction device |
| CN111174063B (en) * | 2018-11-05 | 2021-06-04 | 安徽省春谷3D打印智能装备产业技术研究院有限公司 | Three-dimensional scanner fixing support for three-dimensional image acquisition of large product |
| CN109866201B (en) * | 2019-04-08 | 2021-03-30 | 清华大学 | Binocular vision system, mobile grabbing robot and automatic goods taking method |
| CN110397254B (en) * | 2019-08-19 | 2022-05-06 | 广东博智林机器人有限公司 | Four-degree-of-freedom motion mechanism and paving robot |
| CN110561399B (en) * | 2019-09-16 | 2022-02-18 | 腾讯科技（深圳）有限公司 | Auxiliary shooting device for dyskinesia condition analysis, control method and device |
| CN110497246B (en) * | 2019-09-18 | 2021-04-30 | 上海理工大学 | Numerical control machining workpiece in-position detection machine based on binocular vision |
| CN111623744A (en) * | 2020-05-14 | 2020-09-04 | 湖北恒义智能科技有限公司 | Curved surface appearance acquisition and measurement system |
| CN113551612A (en) * | 2021-06-18 | 2021-10-26 | 中广核检测技术有限公司 | CRDM thermal casing wear loss measuring device |
| CN113442121A (en) * | 2021-07-30 | 2021-09-28 | 上海宜硕网络科技有限公司 | Mechanical arm, adjusting method and device thereof, and electronic equipment |
| CN114485466B (en) * | 2022-01-26 | 2023-11-21 | 哈尔滨理工大学 | Planet gear tooth form machining error measuring device and self-adaptive on-machine measuring method |
| CN114955074A (en) * | 2022-06-06 | 2022-08-30 | 苏州松生机电设备有限公司 | Automatic pile up top income formula case packer |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122172B (en) * | 2010-12-31 | 2013-03-13 | 中国科学院计算技术研究所 | Image pickup system and control method thereof for machine motion control |
| CN102590245B (en) * | 2012-02-23 | 2013-10-16 | 丹东华日理学电气股份有限公司 | Intelligent X-ray digital flat imaging detection system device and detection method |
| CN204154274U (en) * | 2014-11-05 | 2015-02-11 | 哈尔滨理工大学 | A kind of Binocular vision photogrammetry device |
| CN205664790U (en) * | 2016-06-08 | 2016-10-26 | 杭州非白三维科技有限公司 | Three -dimensional scanning system that combines machine people |
-
2017
- 2017-03-21 CN CN201710168404.5A patent/CN107016667B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122172B (en) * | 2010-12-31 | 2013-03-13 | 中国科学院计算技术研究所 | Image pickup system and control method thereof for machine motion control |
| CN102590245B (en) * | 2012-02-23 | 2013-10-16 | 丹东华日理学电气股份有限公司 | Intelligent X-ray digital flat imaging detection system device and detection method |
| CN204154274U (en) * | 2014-11-05 | 2015-02-11 | 哈尔滨理工大学 | A kind of Binocular vision photogrammetry device |
| CN205664790U (en) * | 2016-06-08 | 2016-10-26 | 杭州非白三维科技有限公司 | Three -dimensional scanning system that combines machine people |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107016667A (en) | 2017-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107016667B (en) | A kind of device obtaining large parts three-dimensional point cloud using binocular vision | |
| CN105953747B (en) | Structured light projection full view 3-D imaging system and method | |
| CN102012217B (en) | Method for measuring three-dimensional geometrical outline of large-size appearance object based on binocular vision | |
| CN201522266U (en) | Computer-based binocular vision false-tooth scanning device | |
| CN106017325B (en) | Improved non-contact optical measurement method for complex surface and irregular object volume | |
| CN101403606B (en) | Large visual field dual-shaft measuring apparatus based on line-structured light | |
| CN103047944B (en) | Three-dimensional object measuring method and device | |
| CN102062588A (en) | Computer binocular vision denture scanning device and three-dimensional reconstruction method thereof | |
| CN104215198A (en) | Scanner for scanning three-dimensional profile of internal surface of tubular object | |
| CN102506711B (en) | Line laser vision three-dimensional rotate scanning method | |
| CN107560547B (en) | Scanning system and scanning method | |
| CN207036047U (en) | A kind of New Image detector | |
| CN110196431A (en) | Inexpensive interior 3D laser scanning and ranging system and method based on ARM | |
| WO2022111105A1 (en) | Intelligent visual 3d information acquisition apparatus with free posture | |
| CN104266585A (en) | Scanning system with shooting angle self-regulating function | |
| CN105136820A (en) | Pipeline defect detection robot based on annular laser three-dimensional scanning | |
| CN112257537B (en) | Intelligent multi-point three-dimensional information acquisition equipment | |
| CN111442817A (en) | Non-contact structured light binocular vision sewage level measuring device and method | |
| CN105865421A (en) | Water tank three-dimensional topographic measurement device based on camera image processing technology | |
| CN205352322U (en) | Large -scale complicated curved surface measurement system | |
| CN206556605U (en) | The image scanning of carrying Kinect a kind of and three-dimensional modeling equipment platform | |
| CN106204533A (en) | A kind of three-dimensional scanner | |
| Li et al. | Using laser measuring and SFM algorithm for fast 3D reconstruction of objects | |
| CN204329892U (en) | A kind of device based on line laser triangulation irregularly shaped object volume | |
| Palka et al. | 3D object digitization devices in manufacturing engineering applications and services |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190705 Termination date: 20200321 |