CN107595388A - A kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point - Google Patents
A kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point Download PDFInfo
- Publication number
- CN107595388A CN107595388A CN201710646652.6A CN201710646652A CN107595388A CN 107595388 A CN107595388 A CN 107595388A CN 201710646652 A CN201710646652 A CN 201710646652A CN 107595388 A CN107595388 A CN 107595388A
- Authority
- CN
- China
- Prior art keywords
- point
- mark point
- polar curve
- picture
- witch ball
- 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
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point, this method is the three-dimensional geometry size characteristic using witch ball mark point, reject the pseudo- matching double points of near infrared binocular visual indicia point, to obtain quick, robust stereo matching results, so as to which the 3 d space coordinate of mark point be precisely calculated, and then realize real-time, robust the track and localization to mark point.The present invention can efficiently and accurately find corresponding relation of the mark point in left and right cameras picture point, pseudo- matching effectively be eliminated, so as to eliminate interference of the false three dimensions point to optical alignment, to improve the positioning precision of near-infrared optical alignment system and robustness.
Description
Technical field
The present invention relates to computer vision and computer assisted surgery research field, refers in particular to one kind and is based on witch ball mark
Remember the near infrared binocular visual stereoscopic matching process of point.
Background technology
Closely during the last ten years, the image-guided treatment system based on optical alignment is widely used in neurosurgery, oral jaw
Operation in terms of face surgery, orthopaedic surgical procedure, tumour radiotherapy, even soft tissue organs.Target spot precise positioning is shadow
As guiding treatment system is straight applied to core content the most key in the therapies such as radiotherapy, surgical operation, the positioning precision of target spot
The effect of connecing the influence therapy.
For the image-guided treatment system based on optical alignment, the positioning precision of target spot depends primarily on near-infrared optical
The positioning precision of alignment system.Currently, the image-guided treatment system of main flow, such as the StealthStation hands of Medtronic Inc.
Art navigation system and the VectorVision Sky systems of Brain companies, using the Polaris optics of Canadian NDI companies
Alignment system is as position indicator, for tracking the witch ball mark point being pasted on operation tool and patient.Polaris systems
Traceable active light-emitting type and passive illuminated two kinds of mark points.Active light-emitting type mark point passes through a system control unit control
The sequence of light of luminescent marking point processed so that at a time one and only one mark point is traced into by Polaris systems, because
And stereo matching problem is not present.But during using active light-emitting type mark point (being usually near-infrared luminous diode), in 1 second
It at most can be traced to 32 mark points, and during tracking, if mark point is in mobile status, is also easy to produce tracking and misses
Difference.In addition, each active light-emitting type mark point is connected with wire, cause the use of active light-emitting type mark point very inconvenient.
And when using passive illuminated mark point (being usually witch ball mark point), Polaris systems can at most track 50 marks simultaneously
Remember point, because no wire is connected with mark point, passive illuminated mark point is very easy to use.But passive illuminated mark
Note point is also easy to produce stereo matching problem during use, when two or more mark point and two camera sensor copolars are put down
During face, more than 1 false three dimensions point will occur, cause to produce false three dimensions point in three dimensions and influence most
Whole positioning precision.To find out its cause, it is the Stereo Matching Algorithm existing defects of Polaris systems and causes Stereo matching occur
Problem.
Equally, as voluntarily built near infrared binocular vision positioning system using industrial camera, still there is 2 for the system
Caused stereo matching problem during above mark point copolar plane, so as to produce multiple false three dimensions points.
Therefore, a kind of robust, stable near infrared binocular visual stereoscopic matching process are designed for improving optical alignment system
The position stability and positioning precision of system are significant.
The content of the invention
It is an object of the invention in witch ball marked point process is tracked, work as appearance near infrared binocular alignment system
During more than 2 mark point copolar planes, picture point of these mark points in left and right cameras is no longer uniquely matched and generates puppet
Matching double points, so as to more than 1 false three dimensions point this problem occur, there is provided a kind of based on the near of witch ball mark point
Infrared binocular vision solid matching method, this method can quickly and accurately find the correct of left and right cameras mark point picture point
Corresponding relation, so as to effectively eliminate pseudo- matching double points and because of pseudo- matching double points and caused by false three dimensions point, so as to carry
The position stability and positioning precision of high near infrared binocular vision positioning system.
To achieve the above object, technical scheme provided by the present invention is:A kind of near-infrared based on witch ball mark point
Binocular vision solid matching method, this method are the three-dimensional geometry size characteristics using witch ball mark point, reject Near-infrared Double
The pseudo- matching double points of mark point are visually felt, to obtain quick, robust stereo matching results, so as to which mark point be precisely calculated
3 d space coordinate, and then realize to real-time, robust the track and localization of mark point;Wherein, it is described to be marked using witch ball
The three-dimensional geometry size characteristic of point, the procedure for rejecting mark point puppet matching double points are as follows:
1) the geometric center subpixel coordinates of left and right cameras mark point imaging spot are calculated, remember the coordinate for mark point
Picpointed coordinate;
2) the Epipolar geometry principle according to binocular vision, draws corresponding pole of the left video camera picture point on right camera review
Line;
3) find out on right camera review it is all fall picture point on polar curve;
There was only a picture point on the polar curve in right camera review if 4) fall, this is calculated according to principle of triangulation
The three dimensional space coordinate of point;If multiple picture points be present on the polar curve, need to observe following rule:First, according to triangulation
Principle calculates left video camera picture point corresponding to the polar curve and the three dimensional space coordinate point of multiple picture point formation on polar curve, then structure
The spheroid using these three dimensional space coordinate points as the centre of sphere, using the actual measurement gained radius size of witch ball as radius is built out, then
The profile of mark point imaging spot is extracted on left video camera, then calculates the circular cone that the profile is formed centrally with left camera light
Face, finally judge whether circular conical surface is tangent with the spheroid that builds, is correct match point if tangent, if nontangential, for
Pseudo- match point.
In step 1), the imaging of all mark points is obtained by image processing methods such as Threshold segmentation, connected domain extractions
Spot, the geometric center subpixel coordinates of spot are then imaged using calculated with weighted average method mark point, using the coordinate as note
For the picpointed coordinate of mark point.
In step 2), left and right cameras internal and external parameter and left and right are obtained from the calibration result of binocular camera system
Transformation matrix between camera coordinate system, according to the Epipolar geometry principle of binocular vision, draw out left video camera picture point and taken the photograph on the right side
Corresponding polar curve on camera image.
In step 3), a distance threshold is set, calculates all mark point picture points and the polar curve on right camera review
Distance, if the distance of picture point and the polar curve is less than threshold value, then it is assumed that the picture point is located on the polar curve, on the contrary then do not fall in the polar curve
On, so as to find on right camera review it is all fall picture point on the polar curve.
In step 4), judged according to the picture point number on polar curve is fallen on right camera review:If a, it is located at right shooting
Picture point on machine image polar curve only has 1, then the matching double points are correct matching double points, are directly counted according to principle of triangulation
Calculate the three dimensions point coordinates corresponding to the matching double points;If b, the picture point on right camera review polar curve be 2 with
When upper, it need to carry out rejecting pseudo- matching double points according to the three-dimensional geometry size characteristic of witch ball mark point, wherein the pseudo- match point
It is as follows to reject calculating process:
It is p 4-1) to remember left video camera picture point corresponding to the polar curveli, the photocentre of left and right cameras is olAnd orIf right shooting
Picture point number in machine image on the polar curve is N, and corresponding point is designated as prj, j=1,2 ..., N, by pliAnd prjCarry out one
Matched to one, form the combination of N kinds, two light o are calculated according to principle of triangulationlpliAnd orprjIntersection point Pij, as pli
And prjCorresponding three dimensional space coordinate point;
4-2) radius of sphericity for remembering witch ball mark point is R, using 4-1) in the three dimensional space coordinate point that is calculated as ball
The heart, construct the virtual sphere V that radius is Rij;
4-3) to the imaging spot of i-th of the mark point obtained on left camera review by image processing method
Reason, obtains its contour line, then carries out justifying fitting obtaining justifying C to the contour linei, calculate itself and left video camera photocentre olFormed
Circular conical surface Sli;
One threshold value t 4-4) is set, calculates circular conical surface SliWhether with virtual sphere VijIt is tangent, it is left video camera if tangent
Picture point p in planeliWith the picture point p in right camera planerjFor correct matching double points, if nontangential, for pseudo- match point
It is right.
The present invention compared with prior art, has the following advantages that and beneficial effect:
Near infrared binocular visual stereoscopic matching process based on witch ball mark point proposed by the invention, can efficiently,
Corresponding relation of the mark point in left and right cameras picture point is correctly found, effectively eliminates pseudo- matching, so as to eliminate falseness three
Interference of the dimension space point to optical alignment, to improve the positioning precision of near-infrared optical alignment system and robustness.
Brief description of the drawings
Fig. 1 is the extraction result that left and right cameras image tagged point is imaged spot geometric center in the inventive method.
Fig. 2 be in the inventive method on left camera review corresponding to a picture point a on right camera review polar curve effect
Figure.
Fig. 3 is the schematic diagram for the matching double points three dimensional space coordinate for calculating left and right cameras picture point.
Fig. 4 is calculating circular conical surface SlaWith the schematic diagram of virtual globoid tangent relation.
Embodiment
With reference to specific embodiment, the invention will be further described.
The near infrared binocular visual stereoscopic matching process based on witch ball mark point that the present embodiment is provided, can enter one
Step improves the positioning robustness and precision of near-infrared optical alignment system.This method is the three-dimensional geometry using witch ball mark point
Size characteristic realizes the identification to mark point puppet matching double points, calculates left and right cameras mark point first and is imaged in the geometry of spot
Heart subpixel coordinates, remember the picpointed coordinate that the coordinate is mark point, then the Epipolar geometry principle according to binocular vision, draw left
Corresponding polar curve of the video camera picture point on right camera review, then calculate on right camera review it is all fall on polar curve
Mark point picture point, if the picture point fallen in right camera review on a certain polar curve only has one, according to principle of triangulation meter
Calculate the three dimensional space coordinate of the point;If multiple picture points be present on the polar curve, the pole is calculated according to principle of triangulation
Left video camera picture point corresponding to line and the three dimensional space coordinate point that multiple picture points are formed on polar curve, are then constructed three-dimensional with these
Space coordinates point is the centre of sphere, the spheroid using witch ball real radius as radius, and the mark is then extracted on left camera review
The profile of point imaging spot, then the circular conical surface that the profile is formed centrally with left camera light is calculated, finally whether calculate circular conical surface
It is tangent with constructed spheroid, it is correct match point if tangent, if nontangential, for pseudo- match point.Comprise the following steps that:
First, the left images that left and right cameras photographs simultaneously are obtained, calculate left and right cameras mark point imaging spot
Geometric center subpixel coordinates.Left and right cameras is obtained by image processing methods such as Threshold segmentation, connected domain acquisitions respectively
The imaging spot of all mark points on image, obtains the result as shown in (a) in Fig. 1, then using calculated with weighted average method mark
The geometric center subpixel coordinates of note point imaging spot, if there is the gray value of m pixel in the region of mark point imaging spot
More than threshold value t, and the gray value of ith pixel point therein is set as vi, pixel coordinate qi=[qix,qiy]T, then in the region
The subpixel coordinates of the heart are(b) is represented by centre dot in Fig. 1, and the subpixel coordinates are designated as marking
The picpointed coordinate of point.
By obtaining left and right cameras internal and external parameter and left and right cameras coordinate in the calibration result of binocular camera system
Transformation matrix between system, by taking any one mark point picture point a on image as an example, according to the Epipolar geometry principle of binocular vision, draw
Polar curve m corresponding on right camera review the picture point a gone out on left camera reviewra, as shown in Figure 2.
Distance threshold k is set, calculates all mark point picture points and polar curve m on right camera reviewraDistance, if picture point with
Polar curve mraDistance be less than threshold value k, then it is assumed that the picture point is located at polar curve mraOn, it is on the contrary then do not fall in polar curve mraOn, it is calculated
Fall in polar curve mraOn picture point quantity be N, then note fall in polar curve mraOn picture point subpixel coordinates be prj(j=1,2 ...,
N)。
Then, judged according to the picture point quantity fallen on right camera review on polar curve:If 1) N=1, polar curve mra
Corresponding left video camera picture point and the matching double points of the picture point composition on right video camera polar curve are correct matching double points, according to three
Angular measurement principle directly calculates the three dimensions point coordinates corresponding to the matching double points;, need to be according to witch ball mark if 2) N >=2
The three-dimensional geometry size characteristic of note point carries out rejecting pseudo- matching double points.Remember polar curve mraCorresponding left video camera picture point a sub-pix
Coordinate is pla, the photocentre of left and right cameras is olAnd or, by plaAnd prjOne-to-one pairing is carried out, the combination of N kinds is formed, uses triangle
Measuring principle can calculate two light olplaAnd orprjIntersection point paj(j=1,2 ..., N), from o under system coordinate systemlPoint arrives
plaThe vector of pointFor:
Similarly, from o under system coordinate systemrPoint arrives prjThe vector of pointFor:
Wherein tla、trjFor arbitrary value, Bla=[qlax,qlay,1]T, Brj=[qrjx,qrjy,1]T, RlgaAnd TlgaIt is to be taken the photograph from a left side
Camera coordinate system transformation is to the rotation translation matrix of system coordinates, and RrgjAnd TrgjIt is to transform to system from right camera coordinate system
The rotation translation matrix of coordinate, solve equation groupThree dimensions point P can be tried to achieveaj(j=1,
2 ..., N) coordinate under system, as shown in Figure 3.
The radius of sphericity for actually measuring witch ball mark point is designated as R, with the three dimensional space coordinate point being the previously calculated
Paj(j=1,2 ..., N) is the centre of sphere, constructs multiple virtual sphere V that radius is Raj(j=1,2 ..., N);
At the imaging spot for the mark point a that the processing of the methods of to passing through threshold value on left camera review acquires
Reason, goes out its contour line using Candy limb recognition operator identifications, then carries out justifying fitting obtaining justifying C to the contour linela, calculate
Go out itself and left video camera photocentre olThe circular conical surface S of formationla, as shown in Figure 4.
One threshold value t is set, calculates circular conical surface SlaWhether with virtual sphere VajIt is tangent, it is left camera plane if tangent
On picture point plaWith the picture point p in right camera planerjFor correct matching double points, if nontangential, for pseudo- matching double points.
Similarly, corresponding to other mark point picture points on right video camera imaging face on left camera review can be calculated
With point.
In summary, the inventive method can efficiently and accurately find mark point and be closed in the corresponding of left and right cameras picture point
System, pseudo- matching is effectively eliminated, so as to eliminate interference of the false three dimensions point to optical alignment, to improve near-infrared optical
The positioning precision and robustness of alignment system, are worthy to be popularized.
Embodiment described above is only the preferred embodiments of the invention, and the practical range of the present invention is not limited with this, therefore
The change that all shape, principles according to the present invention are made, it all should cover within the scope of the present invention.
Claims (5)
- A kind of 1. near infrared binocular visual stereoscopic matching process based on witch ball mark point, it is characterised in that:This method is profit With the three-dimensional geometry size characteristic of witch ball mark point, the pseudo- matching double points of rejecting near infrared binocular visual indicia point, to obtain Quickly, the stereo matching results of robust, so as to which the 3 d space coordinate of mark point be precisely calculated, and then realize to mark point Real-time, robust track and localization;Wherein, the three-dimensional geometry size characteristic using witch ball mark point, mark point is rejected The procedure of pseudo- matching double points is as follows:1) the geometric center subpixel coordinates of left and right cameras mark point imaging spot are calculated, remember the picture point that the coordinate is mark point Coordinate;2) the Epipolar geometry principle according to binocular vision, draws corresponding polar curve of the left video camera picture point on right camera review;3) find out on right camera review it is all fall picture point on polar curve;There was only a picture point on the polar curve in right camera review if 4) fall, the point is calculated according to principle of triangulation Three dimensional space coordinate;If multiple picture points be present on the polar curve, need to observe following rule:First, according to principle of triangulation Calculate left video camera picture point corresponding to the polar curve and the three dimensional space coordinate point that multiple picture points are formed on polar curve, then construct Spheroid using these three dimensional space coordinate points as the centre of sphere, using the actual measurement gained radius size of witch ball as radius, then on a left side The profile of mark point imaging spot is extracted on video camera, then calculates the circular conical surface that the profile is formed centrally with left camera light, Finally judge whether circular conical surface is tangent with the spheroid that builds, is correct match point if tangent, if nontangential, for pseudo- With point.
- 2. a kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point according to claim 1, its It is characterised by:In step 1), the imaging spot of all mark points is obtained by Threshold segmentation, connected domain extraction, is then used Calculated with weighted average method mark point is imaged the geometric center subpixel coordinates of spot, using the coordinate as the picture point for being designated as mark point Coordinate.
- 3. a kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point according to claim 1, its It is characterised by:In step 2), left and right cameras internal and external parameter and a left side are obtained from the calibration result of binocular camera system Transformation matrix between right camera coordinate system, according to the Epipolar geometry principle of binocular vision, left video camera picture point is drawn out on the right side Corresponding polar curve on camera review.
- 4. a kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point according to claim 1, its It is characterised by:In step 3), a distance threshold is set, calculates all mark point picture points and the polar curve on right camera review Distance, if the distance of picture point and the polar curve is less than threshold value, then it is assumed that the picture point is located on the polar curve, on the contrary then do not fall in the polar curve On, so as to find on right camera review it is all fall picture point on the polar curve.
- 5. a kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point according to claim 1, its It is characterised by:In step 4), judged according to the picture point number on polar curve is fallen on right camera review:If a, it is located at right shooting Picture point on machine image polar curve only has 1, then the matching double points are correct matching double points, are directly counted according to principle of triangulation Calculate the three dimensions point coordinates corresponding to the matching double points;If b, the picture point on right camera review polar curve be 2 with When upper, it need to carry out rejecting pseudo- matching double points according to the three-dimensional geometry size characteristic of witch ball mark point, wherein the pseudo- match point It is as follows to reject calculating process:It is p 4-1) to remember left video camera picture point corresponding to the polar curveli, the photocentre of left and right cameras is olAnd orIf right camera review In picture point number on the polar curve be N, corresponding point is designated as prj, j=1,2 ..., N, by pliAnd prjCarry out one-to-one match somebody with somebody It is right, the combination of N kinds is formed, two light o are calculated according to principle of triangulationlpliAnd orprjIntersection point Pij, as pliAnd prjIt is right The three dimensional space coordinate point answered;4-2) radius of sphericity for remembering witch ball mark point is R, using 4-1) in the three dimensional space coordinate point that is calculated as the centre of sphere, structure Build out the virtual sphere V that radius is Rij;4-3) the imaging spot of i-th of mark point to being obtained on left camera review by image processing method is handled, Its contour line is obtained, then carries out justifying fitting obtaining justifying C to the contour linei, calculate itself and left video camera photocentre olThe circle of formation Conical surface Sli;One threshold value t 4-4) is set, calculates circular conical surface SliWhether with virtual sphere VijIt is tangent, in left camera plane if tangent Picture point pliWith the picture point p in right camera planerjFor correct matching double points, if nontangential, for pseudo- matching double points.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710646652.6A CN107595388B (en) | 2017-08-01 | 2017-08-01 | Near-infrared binocular vision stereo matching method based on reflective ball mark points |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710646652.6A CN107595388B (en) | 2017-08-01 | 2017-08-01 | Near-infrared binocular vision stereo matching method based on reflective ball mark points |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107595388A true CN107595388A (en) | 2018-01-19 |
CN107595388B CN107595388B (en) | 2020-02-18 |
Family
ID=61064031
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710646652.6A Active CN107595388B (en) | 2017-08-01 | 2017-08-01 | Near-infrared binocular vision stereo matching method based on reflective ball mark points |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107595388B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410277A (en) * | 2018-11-15 | 2019-03-01 | 广州科莱瑞迪医疗器材股份有限公司 | A kind of virtual tag point filter method and system |
CN109538208A (en) * | 2018-12-21 | 2019-03-29 | 冀中能源峰峰集团有限公司 | A kind of compound positioning system of cutting head of roadheader and method |
CN110812710A (en) * | 2019-10-22 | 2020-02-21 | 苏州雷泰智能科技有限公司 | Accelerator frame rotation angle measuring system and method and radiotherapy equipment |
CN110969659A (en) * | 2019-10-31 | 2020-04-07 | 浙江未来技术研究院(嘉兴) | Space positioning device and method for passive marking point |
CN111028284A (en) * | 2019-10-31 | 2020-04-17 | 浙江未来技术研究院(嘉兴) | Binocular vision stereo matching method and device based on homonymous mark points |
CN113208731A (en) * | 2021-04-23 | 2021-08-06 | 上海大学 | Binocular vision system-based hand and eye calibration method for surgical puncture robot |
CN113499137A (en) * | 2021-07-07 | 2021-10-15 | 南开大学 | Surgical robot navigation positioning system and measurement visual angle multi-target optimization method |
CN116047412A (en) * | 2023-03-28 | 2023-05-02 | 深圳惟德精准医疗科技有限公司 | Artifact coordinate removal method of marker and related device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103297798A (en) * | 2012-03-02 | 2013-09-11 | 包崇兵 | Three-dimensional reconstruction method of scene spots in binocular stereo visual system |
CN103968829A (en) * | 2014-05-13 | 2014-08-06 | 清华大学 | Three-dimensional space orientation tracking method and three-dimensional space orientation tracking system based on virtual marker |
CN104224320A (en) * | 2013-06-19 | 2014-12-24 | 上海优益基医疗器械有限公司 | Surgical navigation-based wireless surface registering tool and implementation method thereof |
CN106580470A (en) * | 2016-10-18 | 2017-04-26 | 南京医科大学附属口腔医院 | System and method for head positioning on basis of binocular vision |
-
2017
- 2017-08-01 CN CN201710646652.6A patent/CN107595388B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103297798A (en) * | 2012-03-02 | 2013-09-11 | 包崇兵 | Three-dimensional reconstruction method of scene spots in binocular stereo visual system |
CN104224320A (en) * | 2013-06-19 | 2014-12-24 | 上海优益基医疗器械有限公司 | Surgical navigation-based wireless surface registering tool and implementation method thereof |
CN103968829A (en) * | 2014-05-13 | 2014-08-06 | 清华大学 | Three-dimensional space orientation tracking method and three-dimensional space orientation tracking system based on virtual marker |
CN106580470A (en) * | 2016-10-18 | 2017-04-26 | 南京医科大学附属口腔医院 | System and method for head positioning on basis of binocular vision |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410277A (en) * | 2018-11-15 | 2019-03-01 | 广州科莱瑞迪医疗器材股份有限公司 | A kind of virtual tag point filter method and system |
CN109410277B (en) * | 2018-11-15 | 2022-03-08 | 广州科莱瑞迪医疗器材股份有限公司 | Virtual mark point filtering method and system |
CN109538208A (en) * | 2018-12-21 | 2019-03-29 | 冀中能源峰峰集团有限公司 | A kind of compound positioning system of cutting head of roadheader and method |
CN110812710A (en) * | 2019-10-22 | 2020-02-21 | 苏州雷泰智能科技有限公司 | Accelerator frame rotation angle measuring system and method and radiotherapy equipment |
CN110812710B (en) * | 2019-10-22 | 2021-08-13 | 苏州雷泰智能科技有限公司 | Accelerator frame rotation angle measuring system and method and radiotherapy equipment |
CN110969659A (en) * | 2019-10-31 | 2020-04-07 | 浙江未来技术研究院(嘉兴) | Space positioning device and method for passive marking point |
CN111028284A (en) * | 2019-10-31 | 2020-04-17 | 浙江未来技术研究院(嘉兴) | Binocular vision stereo matching method and device based on homonymous mark points |
CN110969659B (en) * | 2019-10-31 | 2024-03-15 | 浙江清华长三角研究院 | Spatial positioning device and method for passive mark point |
CN113208731A (en) * | 2021-04-23 | 2021-08-06 | 上海大学 | Binocular vision system-based hand and eye calibration method for surgical puncture robot |
CN113499137A (en) * | 2021-07-07 | 2021-10-15 | 南开大学 | Surgical robot navigation positioning system and measurement visual angle multi-target optimization method |
CN116047412A (en) * | 2023-03-28 | 2023-05-02 | 深圳惟德精准医疗科技有限公司 | Artifact coordinate removal method of marker and related device |
CN116047412B (en) * | 2023-03-28 | 2023-06-02 | 深圳惟德精准医疗科技有限公司 | Artifact coordinate removal method of marker and related device |
Also Published As
Publication number | Publication date |
---|---|
CN107595388B (en) | 2020-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107595388A (en) | A kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point | |
CN106091984B (en) | A kind of three dimensional point cloud acquisition methods based on line laser | |
CN103913131B (en) | Free curve method vector measurement method based on binocular vision | |
US9066086B2 (en) | Methods for generating stereoscopic views from monoscopic endoscope images and systems using the same | |
CN109360240A (en) | A kind of small drone localization method based on binocular vision | |
CN106295512B (en) | Vision data base construction method and indoor orientation method in more correction lines room based on mark | |
CN106705849B (en) | Calibrating Technique For The Light-strip Sensors | |
CN105232161B (en) | Surgical robot mark point recognition and location method | |
CN104036488A (en) | Binocular vision-based human body posture and action research method | |
CN104123751A (en) | Combined type measurement and three-dimensional reconstruction method combing Kinect and articulated arm | |
CN110633005A (en) | Optical unmarked three-dimensional human body motion capture method | |
CN104766309A (en) | Plane feature point navigation and positioning method and device | |
CN102252661B (en) | Globoid three-dimensional positioning method for machine vision | |
CN108288293A (en) | A kind of scaling method based on line-structured light | |
CN111768449B (en) | Object grabbing method combining binocular vision with deep learning | |
CN112168357B (en) | System and method for constructing spatial positioning model of C-arm machine | |
CN107016697A (en) | A kind of height measurement method and device | |
CN107220999A (en) | The research of workpiece circular arc Edge Feature Points matching process | |
CN108154536A (en) | The camera calibration method of two dimensional surface iteration | |
CN109740659A (en) | A kind of image matching method and device, electronic equipment, storage medium | |
CN107121061A (en) | A kind of drilling point law vector method for solving constrained based on elliptic cone | |
CN104166995B (en) | Harris-SIFT binocular vision positioning method based on horse pace measurement | |
Li et al. | A vision-based navigation system with markerless image registration and position-sensing localization for oral and maxillofacial surgery | |
CN106504257A (en) | A kind of radiotherapy head position attitude measuring and calculation method | |
CN109364385A (en) | Tumor-localizing method based on binocular vision |
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 |