CN110021027A - A kind of trimming point calculating method based on binocular vision - Google Patents
A kind of trimming point calculating method based on binocular vision Download PDFInfo
- Publication number
- CN110021027A CN110021027A CN201910311925.0A CN201910311925A CN110021027A CN 110021027 A CN110021027 A CN 110021027A CN 201910311925 A CN201910311925 A CN 201910311925A CN 110021027 A CN110021027 A CN 110021027A
- Authority
- CN
- China
- Prior art keywords
- point
- trimming
- coordinate
- tripleplane
- binocular vision
- 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
- 238000009966 trimming Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000012797 qualification Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 238000003754 machining Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of trimming point calculating method based on binocular vision includes the following steps: that Binocular vision photogrammetry obtains trimming three-dimensional coordinate；Plane fitting obtains plane I, and trimming three-dimensional coordinate is projected to fit Plane I, obtains Nj；The theoretical coordinate of trimming point and theoretical normal direction are projected into plane I, straight line L is established: calculating NjTo the distance of straight line L, N is obtainedj′；Multiplication cross obtains vector n ", establish straight line L '；Along the theoretical projection direction normal direction n ', N is calculatedjTo the distance D of L ', according to D value according to preset step-length by tripleplane's point NjIt is divided into N group；It selects D value maximum and counts one group that is greater than m in group as group where trimming point；The coordinate of all tripleplane's points is averaged in organizing where the trimming point, obtains trimming point measurement coordinate；This method measurement coordinate precision can reach micro scale, and time of measuring can satisfy the manufacturing testing requirements of the Precision Machinings such as automobile industry in Millisecond.
Description
Technical field
The present invention relates to feature detection fields, and in particular to a kind of trimming point calculating method based on binocular vision.
Background technique
With the development of automatic technology, the raising of social productive forces, manufacturing is more next for the control of product quality
Stringenter, the basic principle for improving manufacturing quality can be attributed to two classes: 1. avoid method-this method of error using high-precision
Process equipment, the transducer detecting mechanism of advanced control structure and high reliability fundamentally improve the part processed
Quality, but this method is complicated for operation, and expensive, there has been no complete real-time proposals at present；2. the method-of error compensation
This method is mutually to be tied using modern test technology, new statistical tolerance method with existing Engineering Control and statistical control method
It closes, studies product size distribution character, analyze the machining state of die clamp, and then control it and adjust, this side
More and more attention has been paid to and the key technology for implementing this method is exactly to measure to method, and measurement can obtain the significant figure of measured object
According to provide basis for subsequent control mode.
In numerous tested features, trimming point is an important classification to be measured, by taking automobile body-in-white as an example, trimming point
Position it is whether accurate, be directly related to the straightness at workpiece edge, be the later period installation, configuration design whether meet the requirements according to
According to；Traditional inspection sample rack is widely used detection instrument the 1970s, and this method is at low cost, but detection speed is slow,
Precision is low (about 0.1mm), and the detection accuracy that precision instrument manufacture requires is not achieved；Another detection method is to be surveyed using three coordinates
Amount machine (CMM) carries out the detection of trimming point, although this method precision is high, measuring speed is very slow, only for space boundary point
It is capable of measuring limited point, the geometries characteristic of space boundary can not be described comprehensively, and measurement process needs manual intervention, needs
Probe damage and probe radius compensation are carried out to measurement result.
Summary of the invention
To solve the above-mentioned problems, the present invention proposes a kind of trimming point calculating method based on binocular vision, effectively improves
The edge point measurement accuracy of measurement accuracy and efficiency, this method can reach some tens of pm magnitude.
A kind of trimming point calculating method based on binocular vision, includes the following steps:
1) the left and right image of two CCD camera measure system acquisition trimming feature is utilized；
2) image preprocessing is carried out to the left and right image, the two-dimensional points for extracting the trimming contour edge of left and right image are sat
Mark Nt, t=1,2 ... s；S is the number of the trimming contour edge two-dimensional points；
3) the trimming profile point in left and right image is transformed into space three-dimensional using polar curve matching process, obtains trimming wheel
Wide three-dimensional point coordinate data；
4) three-dimensional point cloud of plane, carries out a cloud plane fitting, obtains where obtaining tested trimming using spatial digitizer
Fit Plane I, then the three-dimensional point coordinate data projection of trimming profile obtained in step 3) is obtained to the fit Plane I
Tripleplane's point of trimming profile, is denoted as Nj, j=1,2 ..., m, m is the number of tripleplane's point of trimming profile；
5) the coordinate P of the mathematical point of trimming point to be measured and theory normal direction n are projected into the fit Plane I, obtains theory
Subpoint P ' and theoretical projection normal direction n '；
6) according to theoretical subpoint P ' (b1,b2,b3) and theoretical projection normal direction n ' (k1,k2,k3), establish straight line L:
Wherein, (X, Y, Z) is any point on straight line L；
7) tripleplane's point N is calculatedjTo the distance of straight line L, when distance is less than T, T=0.2~0.7mm records this
When tripleplane's point, obtain point set Nj', j=1,2 ..., m ', m ' they are the number for the tripleplane's point being recorded；
8) by the normal direction of fit Plane I and theoretical projection normal direction n ' multiplication cross, direction vector n " (k is obtained4,k5,k6), according to
Theoretical subpoint P ' and direction vector n " establish straight line L ':
Wherein, (X ', Y ', Z ') is that straight line L ' goes up any point；
9) direction normal direction n ' is projected along theory, successively calculates tripleplane's point NjTo the distance D of straight line L ', according to D value
According to preset step-length by tripleplane's point NjIt is divided into N group；Select D value maximum and in group points greater than one group of m as
Group where trimming point；The coordinate of all tripleplane's points is averaged in organizing where the trimming point, trimming point as to be measured
Measure coordinate.
Further, the left and right image is grayscale image.
Further, described image pretreatment includes gaussian filtering, binary image, edge detection.
Further, the coordinate P of the mathematical point and theory normal direction n is the digital-to-analogue of pre-stored trimming point to be measured in system
Normal data value.
Further, the trimming point to be measured is one or more.
Further, further include step 10), measurement coordinate obtained in step 9) and the coordinate of mathematical point are made into difference, when
When difference is less than tolerance threshold value, judges that the trimming point is qualified, otherwise, judge that the trimming point is unqualified.
Further, the fit Plane I is fitted by least square method.
Further, 0.2~0.5mm of the preset step-length value.
Further, m >=2.
The shortcomings that trimming point cloud poor quality that method provided by the present application can effectively avoid binocular vision from obtaining, with three
The three-dimensional point cloud for tieing up plane where scanner obtains tested trimming, carries out a cloud plane fitting, and by trimming point set to be measured and reason
Projected in fit Plane by coordinate points, normal vector, using the theoretical value of tested point as guidance screening calculate it is optimal to
It surveys trimming point and measures coordinate, and then trimming quality is detected；This method measurement coordinate precision can reach micro scale,
Time of measuring can satisfy the manufacturing testing requirements of the Precision Machinings such as automobile industry in Millisecond.
Detailed description of the invention
Fig. 1 is the method for the present invention flow diagram.
Specific embodiment
Technical solution of the present invention is described in detail below in conjunction with drawings and examples.
A kind of trimming point calculating method based on binocular vision, includes the following steps:
1) the left and right gray level image of two CCD camera measure system acquisition trimming feature is utilized；
2) image preprocessings such as gaussian filtering, binary image, edge detection are carried out to left and right image, extracts left and right figure
The two-dimensional points coordinate N of the trimming contour edge of picturet, t=1,2 ... s；S is the number of trimming contour edge two-dimensional points；
3) the trimming profile point in left and right image is transformed into space three-dimensional using polar curve matching process, obtains trimming wheel
Wide three-dimensional point coordinate data；
4) three-dimensional point cloud of plane, carries out a cloud by least square method where obtaining tested trimming using spatial digitizer
Plane fitting obtains fit Plane I, then the three-dimensional point coordinate data projection of trimming profile obtained in step 3) is flat to fitting
Face I obtains tripleplane's point of trimming profile, is denoted as Nj, j=1,2 ..., m, m is of tripleplane's point of trimming profile
Number；
5) the coordinate P of the mathematical point of trimming point to be measured and theory normal direction n are projected into fit Plane I, obtains theoretical projection
Point P ' and theoretical projection normal direction n '；
In the present embodiment, the coordinate P and theory normal direction n of mathematical point are the digital-to-analogue of pre-stored trimming point to be measured in system
Normal data value.
Trimming point to be measured is one；
6) according to theoretical subpoint P ' (b1,b2,b3) and theoretical projection normal direction n ' (k1,k2,k3), establish straight line L:
7) tripleplane's point N is calculatedjTo the distance of straight line L, when distance is less than T, T=0.2~0.7mm records this
When tripleplane's point, obtain point set Nj', j=1,2 ..., m ', m ' they are the number for the tripleplane's point being recorded；
8) the normal direction multiplication cross theory of fit Plane I projects normal direction n ', obtains direction vector n " (k4,k5,k6), according to theory
Subpoint P ' and direction vector n " establish straight line L ':
9) direction normal direction n ' is projected along theory, successively calculates tripleplane's point NjTo the distance D of straight line L ', according to D value
According to preset step-length by tripleplane point NjIt is divided into N group；It selects D value maximum and counts one group that is greater than m as trimming in group
Group where point；The coordinate of all tripleplane's points is averaged in organizing where trimming point, the measurement coordinate as trimming point to be measured.
In this implementation, step-length 0.3, m value 3, detailed process are as follows: project the direction normal direction n ' along theory, successively calculate
Tripleplane point NjTo the distance D of straight line L ', and by tripleplane point NjAccording to the following formula, by closely to remote, being successively divided into N group；
0.3n < D < 0.3 (n+1), n=0,1,2,3 ... N；
I.e. 0~0.3 is the 1st group, and 0.3~0.6 is the 2nd group, and 0.6~0.9 is the 3rd group ... and so on, exhaustive all
Tripleplane point Nj, N group is divided altogether；
Filter out one group of tripleplane that points in and group farthest along the theoretical projection direction normal direction n ' distance are greater than 3
Point；The coordinate of this group of tripleplane's point is averaged, the measurement coordinate as final trimming point to be measured.
Further including step 10) makees difference for measurement coordinate obtained in step 9) and the coordinate of mathematical point, when difference is less than
When tolerance threshold value, judges that the trimming point is qualified, otherwise, judge that the trimming point is unqualified.
The description that specific exemplary embodiment of the present invention is presented in front is for the purpose of illustration and description.Front
Description be not intended to become without missing, be not intended to limit the invention to disclosed precise forms, it is clear that root
It is possible for much changing and change all according to above-mentioned introduction.It selects exemplary implementation scheme and is described to be to explain this hair
Bright certain principles and practical application, so that others skilled in the art can be realized and utilize of the invention each
Kind exemplary implementation scheme and its different selection forms and modification.The scope of the present invention be intended to by the appended claims and
Its equivalent form is limited.
Claims (9)
1. a kind of trimming point calculating method based on binocular vision, characterized by the following steps:
1) the left and right image of two CCD camera measure system acquisition trimming feature is utilized；
2) image preprocessing is carried out to the left and right image, extracts the two-dimensional points coordinate N of the trimming contour edge of left and right imaget,
T=1,2 ... s；S is the number of the trimming contour edge two-dimensional points；
3) the trimming profile point in left and right image is transformed into space three-dimensional using polar curve matching process, obtains trimming profile
Three-dimensional point coordinate data；
4) three-dimensional point cloud of plane, carries out a cloud plane fitting, is fitted where obtaining tested trimming using spatial digitizer
Plane I, then the three-dimensional point coordinate data projection of trimming profile obtained in step 3) is obtained into trimming to the fit Plane I
Tripleplane's point of profile, is denoted as Nj, j=1,2 ..., m, m is the number of tripleplane's point of trimming profile；
5) the coordinate P of the mathematical point of trimming point to be measured and theory normal direction n are projected into the fit Plane I, obtains theoretical projection
Point P ' and theoretical projection normal direction n '；
6) according to theoretical subpoint P ' (b1, b2, b3) and theoretical projection normal direction n ' (k1, k2, k3), establish straight line L:
7) tripleplane's point N is calculatedjTo the distance of straight line L, when distance is less than T, T=0.2~0.7mm records three at this time
Subpoint is tieed up, point set N is obtainedj', j=1,2 ..., m ', m ' they are the number for the tripleplane's point being recorded；
8) by the normal direction of fit Plane I and theoretical projection normal direction n ' multiplication cross, direction vector n " (k is obtained4, k5, k6), according to theory
Subpoint P ' and direction vector n " establish straight line L ':
9) direction normal direction n ' is projected along theory, successively calculates tripleplane's point NjTo the distance D of straight line L ', according to D value according to pre-
If step-length is by tripleplane's point NjIt is divided into N group；It selects D value maximum and counts one group that is greater than m as trimming point in group
Place group；The coordinate of all tripleplane's points is averaged in organizing where the trimming point, and the measurement of trimming point as to be measured is sat
Mark.
2. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: the left and right image is
Grayscale image.
3. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: described image pretreatment packet
Include gaussian filtering, binary image, edge detection.
4. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: the coordinate of the mathematical point
P and theory normal direction n is the digital-to-analogue normal data value of pre-stored trimming point to be measured in system.
5. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: the trimming point to be measured is
It is one or more.
6. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: it further include step 10), it will
Measurement coordinate and the coordinate of mathematical point obtained in step 9) make difference, when difference is less than tolerance threshold value, judge the trimming point
Otherwise qualification judges that the trimming point is unqualified.
7. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: the fit Plane I is logical
Cross least square method fitting.
8. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: the preset step-length value
0.2~0.5mm.
9. the trimming point calculating method based on binocular vision as described in claim 1, it is characterised in that: m >=2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910311925.0A CN110021027B (en) | 2019-04-18 | 2019-04-18 | Edge cutting point calculation method based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910311925.0A CN110021027B (en) | 2019-04-18 | 2019-04-18 | Edge cutting point calculation method based on binocular vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110021027A true CN110021027A (en) | 2019-07-16 |
| CN110021027B CN110021027B (en) | 2021-03-16 |
Family
ID=67191768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910311925.0A Active CN110021027B (en) | 2019-04-18 | 2019-04-18 | Edge cutting point calculation method based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110021027B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112710313A (en) * | 2020-12-31 | 2021-04-27 | 广州极飞科技股份有限公司 | Overlay path generation method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09259283A (en) * | 1996-03-22 | 1997-10-03 | Matsushita Electric Ind Co Ltd | Method and device for calculating projection area of three-dimensional model |
| US20110032203A1 (en) * | 2000-02-22 | 2011-02-10 | Pryor Timothy R | Human interfaces for vehicles, homes, and other applications |
| CN108615699A (en) * | 2018-05-29 | 2018-10-02 | 深圳信息职业技术学院 | A kind of wafer alignment system and method and the optical imaging device for wafer alignment |
| CN109248963A (en) * | 2018-11-27 | 2019-01-22 | 东莞市骏毅机电科技有限公司 | A kind of transmitting drawing die trimming structure of power battery shell |
-
2019
- 2019-04-18 CN CN201910311925.0A patent/CN110021027B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09259283A (en) * | 1996-03-22 | 1997-10-03 | Matsushita Electric Ind Co Ltd | Method and device for calculating projection area of three-dimensional model |
| US20110032203A1 (en) * | 2000-02-22 | 2011-02-10 | Pryor Timothy R | Human interfaces for vehicles, homes, and other applications |
| CN108615699A (en) * | 2018-05-29 | 2018-10-02 | 深圳信息职业技术学院 | A kind of wafer alignment system and method and the optical imaging device for wafer alignment |
| CN109248963A (en) * | 2018-11-27 | 2019-01-22 | 东莞市骏毅机电科技有限公司 | A kind of transmitting drawing die trimming structure of power battery shell |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112710313A (en) * | 2020-12-31 | 2021-04-27 | 广州极飞科技股份有限公司 | Overlay path generation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110021027B (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106863014B (en) | A kind of five-axle number control machine tool linear axis geometric error detection method | |
| CN107186548B (en) | A kind of five-axle number control machine tool rotating shaft geometric error detection method | |
| CN102519400B (en) | Large slenderness ratio shaft part straightness error detection method based on machine vision | |
| CN102800096B (en) | Robustness estimation algorithm of camera parameter | |
| CN103292701A (en) | Machine-vision-based online dimensional measurement method of precise instrument | |
| CN107044821A (en) | A kind of measuring method and system of contactless tubing object | |
| CN109978938A (en) | A kind of pillow spring detection method based on machine vision | |
| CN112614098A (en) | Blank positioning and machining allowance analysis method based on augmented reality | |
| CN111047588A (en) | Imaging measurement method for size of shaft type small part | |
| CN103759672A (en) | Vision measurement method for ice cream stick plane contour dimensions | |
| CN109990711B (en) | Appearance quality detection method for punched nickel-plated steel strip | |
| CN115060452B (en) | Panoramic error detection method applied to large wind tunnel spray pipe molded surface | |
| CN112734858A (en) | Binocular calibration precision online detection method and device | |
| CN108627103A (en) | A kind of 2D laser measurement methods of parts height dimension | |
| CN110940271A (en) | Method for detecting, monitoring and intelligently carrying and installing large-scale industrial manufacturing of ships and the like based on space three-dimensional measurement and control network | |
| CN108844469B (en) | Method and system for testing workpiece step height based on laser | |
| CN110021027A (en) | A kind of trimming point calculating method based on binocular vision | |
| CN109115127A (en) | A kind of sub-pix peak point extraction algorithm based on Bezier | |
| CN106645168A (en) | Detection method for surface concave-convex defect of boom cylinder of crane | |
| CN114111576B (en) | Aircraft skin gap surface difference detection method | |
| CN113743483B (en) | Road point cloud error scene analysis method based on spatial plane offset analysis model | |
| CN113155648B (en) | Material micro-deformation measurement method and system based on impact test | |
| CN115685164A (en) | Three-dimensional laser imager working parameter testing system and method | |
| CN112414316B (en) | Strain gauge sensitive grid size parameter measuring method | |
| CN109902694A (en) | A kind of extracting method of square hole feature |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee after: Yi Si Si (Hangzhou) Technology Co.,Ltd. Address before: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee before: ISVISION (HANGZHOU) TECHNOLOGY Co.,Ltd. |