CN107464258A - A kind of method that three-dimensional planar is extracted from image - Google Patents
A kind of method that three-dimensional planar is extracted from image Download PDFInfo
- Publication number
- CN107464258A CN107464258A CN201710628143.0A CN201710628143A CN107464258A CN 107464258 A CN107464258 A CN 107464258A CN 201710628143 A CN201710628143 A CN 201710628143A CN 107464258 A CN107464258 A CN 107464258A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- msub
- dimensional planar
- coordinate
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of method that three-dimensional planar is extracted from image.The depth image of scene is obtained, depth image is traveled through using window；The two-dimensional coordinate of all pixels point in window is converted into three-dimensional world coordinate, obtains the three-dimensional point set of current window；In the three-dimensional point set of current window, 3 pixels are arbitrarily taken, solve three-dimensional planar equation；Calculate each distance for putting the three-dimensional planar with being solved in the three-dimensional point set of current window, point in judgement；Repeatedly establish point in plane and judgement, the optimal three-dimensional planar using the most three-dimensional planar of interior quantity as current window；Optimal three-dimensional planar is screened, the three-dimensional planar of repetition is removed or interior quantity is less than the three-dimensional planar of the interior points threshold value set.Instant invention overcomes the prior art is defective, the real-time of three-dimensional planar extraction is improved.
Description
Technical field
It is more particularly to a kind of to extract three-dimensional planar from image the invention belongs to computer image processing technology field
Method.
Background technology
At present, for the extracting method of three-dimensional planar, the calculating due to generating threedimensional model is complicated and precision is relatively low, looks into
The speed in levelling face is slower, so can not accomplish real-time operation always.For the never stable effective solution of this problem
Scheme.
Chinese patent application (publication number：CN 101639355) disclose " a kind of three dimensional plane extraction method ", the program
Using known threedimensional model and line segment feature therein, straight line Calculation Plane equation is utilized so that the plane found out accurately has
Effect, but the program the problem of overcoming complex model hardly possible to obtain, while the scheme based on straight line, operand is relatively
Greatly, real-time operation can not be accomplished.
Chinese patent application (publication number：CN 102945551B) disclose that " a kind of three dimensional point cloud based on graph theory is put down
Face extracting method ", for the program on the basis of known three-dimensional point cloud, the method extraction that triangle is connected by arest neighbors is coplanar
Triangle so that the plane degree of accuracy of lookup is high, but the amount of calculation of this scheme is extremely huge, it is virtually impossible to accomplish to locate in real time
Reason, and the good approach of acquisition modes neither one of three-dimensional point cloud.
Chinese patent application (publication number：CN 105260737A) disclose a kind of " laser scanning for merging Analysis On Multi-scale Features
Data Physical plane automates extracting method ", the program extracts plane information by the data of laser scanning, due to laser scanning
With very high precision and very high detection frequency so that the plane degree of accuracy of extraction is very high, but this scheme make use of costliness
Laser Scanning Equipment, consumer level market can not be applied to.
In summary, how to overcome the shortcomings of that prior art turns into the acquisition of simple three-dimensional information and operational performance to work as
Emphasis problem urgently to be resolved hurrily in modern three-dimensional planar extractive technique.
The content of the invention
In order to solve the technical problem that above-mentioned background technology proposes, the present invention is intended to provide one kind extracts three-dimensional from image
The method of plane, overcome the real-time that the prior art is defective, and raising three-dimensional planar extracts.
In order to realize above-mentioned technical purpose, the technical scheme is that：
A kind of method that three-dimensional planar is extracted from image, comprises the following steps：
(1) obtain the depth image of scene, depth image be used to characterize in scene object and depth image collecting device it
Between distance；
(2) size is used to be traveled through for the window of a*b pixels to depth image；Wherein, a=2n, b=2m, and n and m are equal
For the integer more than or equal to 6；
(3) in current window, using aperture camera model, the two-dimensional coordinate of all pixels point in window is converted to three
World coordinates is tieed up, obtains the three-dimensional point set of current window；
(4) in the three-dimensional point set of current window, 3 pixels are arbitrarily taken, solve three-dimensional planar equation；
(5) distance of each three-dimensional planar put and solved in the three-dimensional point set of current window is calculated, if distance is less than
The distance threshold of setting, then the point is judged on three-dimensional planar, i.e., the point is the interior point of three-dimensional planar；
(6) repeat step (4)-(5), using the most three-dimensional planar of interior quantity as the optimal three-dimensional flat of current window
Face；
(7) the optimal three-dimensional planar of each window is obtained, these optimal three-dimensional planars are screened, remove the three of repetition
Dimensional plane or interior quantity are less than the three-dimensional planar of the interior points threshold value of setting.
Further, in step (1), obtaining the method for depth image includes the acquisition methods based on photo structure, is based on
The acquisition methods of light flight time and the acquisition methods based on multi-vision visual.
Further, in step (2), size is used to be traveled through for the window of 64*64 pixels to depth image.
Further, in step (3), the two-dimensional coordinate of pixel is converted to by three-dimensional world coordinate using following formula：
In above formula, X, Y, Z are coordinate of the current point in three-dimensional world coordinate system；X, y is current point on imaging plane
Two-dimensional coordinate；Z is the depth value of current point；Cx, cy are two-dimensional coordinate of the camera photocentre on imaging plane；Fx, fy are phase
Machine focus in the horizontal direction, the length of vertical direction.
Further, in step (4), the process for solving three-dimensional planar is as follows：
If three-dimensional planar equation is：
AX+BY+CZ+D=0
In above formula, (X, Y, Z) represents three-dimensional coordinate, and A, B, C, D are equation parameter；
Parameter D is fixed as 1, and the coordinate of 3 points is substituted into above formula respectively, obtains ternary linear function group：
In above formula, (X0,Y0,Z0)、(X1,Y1,Z1)、(X2,Y2,Z2) be respectively 3 points coordinate；
Above-mentioned ternary linear function group is solved, obtains parameter A, B, C value, obtains three-dimensional planar equation.
The beneficial effect brought using above-mentioned technical proposal：
The information that the present invention can be provided efficiently using depth map, the three-dimensional rapidly and accurately found out in image are put down
Face, while there is stronger antinoise antijamming capability, meet the requirement of real-time and precision, for three-dimensional mapping and augmented reality
Good basic-level support is provided Deng sector application.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention；
Fig. 2 is the instance graph of the depth map obtained；
Fig. 3 is the schematic diagram that two-dimensional coordinate is converted to three-dimensional world coordinate.
Embodiment
Below with reference to accompanying drawing, technical scheme is described in detail.
A kind of method that three-dimensional planar is extracted from image, as shown in figure 1, comprising the following steps that.
Step 1, the depth image of scene is obtained.Obtaining the mode of depth map includes the flight based on structure light, based on light
Time and based on multi-vision visual.The depth map of acquisition is a two-dimensional matrix form, and the point of each position in matrix is figure
The pixel of picture, the numerical representation method of pixel be object distance camera in scene physical distance.
The depth map obtained is as shown in Fig. 2 in figure, and 101 be background metope in scene, and 102 be the ground in scene,
103rd, 104 be desktop and display plane；In depth map, the present invention will realize the Different Planes such as 101,102,103,104
Extraction.
Step 2, depth map is traveled through for the window of 64*64 pixel using size.Specific reality is as follows：
Since first pixel of the first row of depth image, 64 pixels are taken, then jump to first of the second row
Pixel, start to take 64 pixels, by that analogy, until the 64th behavior stops；After the completion of, since the 65th pixel of the first row,
64 pixels are taken, according to above-mentioned rule, until the 64th behavior stops；Hereafter utilize above-mentioned rule, traveled through entire image, now
Image divide into several windows of size for 64*64 pixel.
Step 3, in each window, two dimensional image coordinate is turned into three-dimensional world coordinate.According to aperture camera model, such as Fig. 3
Shown, x is the two-dimensional coordinate on imaging plane, i.e. coordinate in image；X is three-dimensional world coordinate corresponding to x；C is camera
Photocentre；F is the focus of camera.The formula that two dimensional image Coordinate Conversion is three-dimensional world coordinate can be derived：
Wherein X, Y, Z are coordinate of the current point in three-dimensional world coordinate system；X, y is current point in two dimensional image coordinate system
In coordinate；Z is the depth value (being obtained from depth image) of current point；Cx, cy are photocentre C in two dimensional image coordinate system
Coordinate；Fx, fy are camera focus F in length both horizontally and vertically；
Using above-mentioned formula, the two-dimensional points in all windows are all converted to the three-dimensional point in three-dimensional world coordinate system.
Step 4,3 points are each arbitrarily taken out from each window, solve plane equation.Typical three-dimensional planar equation
For：
AX+BY+CZ+D=0
3 point (X of taking-up0,Y0,Z0)、(X1,Y1,Z1)、(X2,Y2,Z2) coordinate substitute into above-mentioned equation respectively, ginseng
Number D is fixed as 1, then can generate a ternary linear function group：
After solution, this 3 points of unique three-dimensional planar equation can be obtained.
Step 5, the distance of point and plane is calculated, point in judgement.Utilize the range formula of point to face：
Distance of the institute a little with plane in window is calculated, when distance is less than the threshold value of setting, that is, thinks that this point is being put down
On face, it is interior point, is otherwise exterior point.
Step 6, several times, it is the optimal of current window to choose the most plane of interior point quantity for repeat step 4-5 operation
Three-dimensional planar.
Step 7, plane is screened.Because window size is 64*64, the larger plane meeting such as metope and ground in image
It is present in simultaneously among multiple windows, now needs to contrast the optimal three-dimensional planar that each window calculates, remove identical plane
With too small plane (interior points are very few).
The technological thought of embodiment only to illustrate the invention, it is impossible to protection scope of the present invention is limited with this, it is every according to
Technological thought proposed by the present invention, any change done on the basis of technical scheme, each falls within the scope of the present invention.
Claims (5)
- A kind of 1. method that three-dimensional planar is extracted from image, it is characterised in that comprise the following steps：(1) depth image of scene is obtained, depth image is used to characterize in scene between object and depth image collecting device Distance；(2) size is used to be traveled through for the window of a*b pixels to depth image；Wherein, a=2n, b=2m, and n and m are big In the integer equal to 6；(3) in current window, using aperture camera model, the two-dimensional coordinate of all pixels point in window is converted into three-dimensional generation Boundary's coordinate, obtain the three-dimensional point set of current window；(4) in the three-dimensional point set of current window, 3 pixels are arbitrarily taken, solve three-dimensional planar equation；(5) distance of each three-dimensional planar put and solved in the three-dimensional point set of current window is calculated, if distance is less than setting Distance threshold, then judge the point on three-dimensional planar, i.e., the point be three-dimensional planar interior point；(6) repeat step (4)-(5), the optimal three-dimensional planar using the most three-dimensional planar of interior quantity as current window；(7) the optimal three-dimensional planar of each window is obtained, these optimal three-dimensional planars are screened, the three-dimensional for removing repetition is put down Face or interior quantity are less than the three-dimensional planar of the interior points threshold value of setting.
- A kind of 2. method that three-dimensional planar is extracted from image according to claim 1, it is characterised in that：In step (1), Obtaining the method for depth image includes the acquisition methods based on photo structure, the acquisition methods based on the light flight time and based on more The acquisition methods visually felt.
- A kind of 3. method that three-dimensional planar is extracted from image according to claim 1, it is characterised in that：In step (2), Size is used to be traveled through for the window of 64*64 pixels to depth image.
- A kind of 4. method that three-dimensional planar is extracted from image according to claim 1, it is characterised in that：In step (3), The two-dimensional coordinate of pixel is converted to by three-dimensional world coordinate using following formula：<mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mi>X</mi> <mo>=</mo> <mfrac> <mrow> <mo>(</mo> <mi>x</mi> <mo>-</mo> <mi>c</mi> <mi>x</mi> <mo>)</mo> <mo>&CenterDot;</mo> <mi>z</mi> </mrow> <mrow> <mi>f</mi> <mi>x</mi> </mrow> </mfrac> </mtd> </mtr> <mtr> <mtd> <mi>Y</mi> <mo>=</mo> <mfrac> <mrow> <mo>(</mo> <mi>y</mi> <mo>-</mo> <mi>c</mi> <mi>y</mi> <mo>)</mo> <mo>&CenterDot;</mo> <mi>z</mi> </mrow> <msup> <mi>h</mi> <mn>2</mn> </msup> </mfrac> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>Z</mi> <mo>=</mo> <mi>z</mi> </mrow> </mtd> </mtr> </mtable> </mfenced>In above formula, X, Y, Z are coordinate of the current point in three-dimensional world coordinate system；X, y is two of current point on imaging plane Dimension coordinate；Z is the depth value of current point；Cx, cy are two-dimensional coordinate of the camera photocentre on imaging plane；Fx, fy are that camera is burnt Point in the horizontal direction, the length of vertical direction.
- A kind of 5. method that three-dimensional planar is extracted from image according to claim 1, it is characterised in that：In step (4), The process for solving three-dimensional planar is as follows：If three-dimensional planar equation is：AX+BY+CZ+D=0In above formula, (X, Y, Z) represents three-dimensional coordinate, and A, B, C, D are equation parameter；Parameter D is fixed as 1, and the coordinate of 3 points is substituted into above formula respectively, obtains ternary linear function group：<mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mi>A</mi> <msub> <mi>X</mi> <mn>0</mn> </msub> <mo>+</mo> <mi>B</mi> <msub> <mi>Y</mi> <mn>0</mn> </msub> <mo>+</mo> <mi>C</mi> <msub> <mi>Z</mi> <mn>0</mn> </msub> <mo>+</mo> <mn>1</mn> <mo>=</mo> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mi>A</mi> <msub> <mi>X</mi> <mn>1</mn> </msub> <mo>+</mo> <mi>B</mi> <msub> <mi>Y</mi> <mn>1</mn> </msub> <mo>+</mo> <mi>C</mi> <msub> <mi>Z</mi> <mn>1</mn> </msub> <mo>+</mo> <mn>1</mn> <mo>=</mo> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mi>A</mi> <msub> <mi>X</mi> <mn>2</mn> </msub> <mo>+</mo> <mi>B</mi> <msub> <mi>Y</mi> <mn>2</mn> </msub> <mo>+</mo> <mi>C</mi> <msub> <mi>Z</mi> <mn>2</mn> </msub> <mo>+</mo> <mn>1</mn> <mo>=</mo> <mn>0</mn> </mtd> </mtr> </mtable> </mfenced> 1In above formula, (X0,Y0,Z0)、(X1,Y1,Z1)、(X2,Y2,Z2) be respectively 3 points coordinate；Above-mentioned ternary linear function group is solved, obtains parameter A, B, C value, obtains three-dimensional planar equation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710628143.0A CN107464258A (en) | 2017-07-28 | 2017-07-28 | A kind of method that three-dimensional planar is extracted from image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710628143.0A CN107464258A (en) | 2017-07-28 | 2017-07-28 | A kind of method that three-dimensional planar is extracted from image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107464258A true CN107464258A (en) | 2017-12-12 |
Family
ID=60547692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710628143.0A Pending CN107464258A (en) | 2017-07-28 | 2017-07-28 | A kind of method that three-dimensional planar is extracted from image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107464258A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086724A (en) * | 2018-08-09 | 2018-12-25 | 北京华捷艾米科技有限公司 | A kind of method for detecting human face and storage medium of acceleration |
| CN111340598A (en) * | 2020-03-20 | 2020-06-26 | 北京爱笔科技有限公司 | Method and device for adding interactive label |
| CN111862185A (en) * | 2020-07-24 | 2020-10-30 | 唯羲科技有限公司 | Method for extracting plane from image |
| CN112729167A (en) * | 2020-12-21 | 2021-04-30 | 福建汇川物联网技术科技股份有限公司 | Calculation method and device of plane equation |
| CN113008895A (en) * | 2021-01-29 | 2021-06-22 | 广州信邦智能装备股份有限公司 | Block fitting defect detection method based on three-dimensional data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639355A (en) * | 2009-08-26 | 2010-02-03 | 中国人民解放军国防科学技术大学 | Three dimensional plane extraction method |
| CN102945551A (en) * | 2012-10-16 | 2013-02-27 | 同济大学 | Graph theory based three-dimensional point cloud data plane extracting method |
| CN105021124A (en) * | 2015-04-16 | 2015-11-04 | 华南农业大学 | Planar component three-dimensional position and normal vector calculation method based on depth map |
| CN105160650A (en) * | 2015-07-07 | 2015-12-16 | 南京华捷艾米软件科技有限公司 | Method for extracting depth continuity object images from image |
| CN105260737A (en) * | 2015-11-25 | 2016-01-20 | 武汉大学 | Automatic laser scanning data physical plane extraction method with multi-scale characteristics fused |
| CN105652873A (en) * | 2016-03-04 | 2016-06-08 | 中山大学 | Mobile robot obstacle avoidance method based on Kinect |
| US9607207B1 (en) * | 2014-03-31 | 2017-03-28 | Amazon Technologies, Inc. | Plane-fitting edge detection |
-
2017
- 2017-07-28 CN CN201710628143.0A patent/CN107464258A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639355A (en) * | 2009-08-26 | 2010-02-03 | 中国人民解放军国防科学技术大学 | Three dimensional plane extraction method |
| CN102945551A (en) * | 2012-10-16 | 2013-02-27 | 同济大学 | Graph theory based three-dimensional point cloud data plane extracting method |
| US9607207B1 (en) * | 2014-03-31 | 2017-03-28 | Amazon Technologies, Inc. | Plane-fitting edge detection |
| CN105021124A (en) * | 2015-04-16 | 2015-11-04 | 华南农业大学 | Planar component three-dimensional position and normal vector calculation method based on depth map |
| CN105160650A (en) * | 2015-07-07 | 2015-12-16 | 南京华捷艾米软件科技有限公司 | Method for extracting depth continuity object images from image |
| CN105260737A (en) * | 2015-11-25 | 2016-01-20 | 武汉大学 | Automatic laser scanning data physical plane extraction method with multi-scale characteristics fused |
| CN105652873A (en) * | 2016-03-04 | 2016-06-08 | 中山大学 | Mobile robot obstacle avoidance method based on Kinect |
Non-Patent Citations (4)
| Title |
|---|
| EDUARDO VERA 等: "Hough Transform for Real-Time Plane Detection in Depth Images", 《HTTPS://WWW.VISGRAF.IMPA.BR/DATA/REFBIB/PS_PDF/PRL2018/VERA2018.PDF》 * |
| HANI JAVAN HEMMAT 等: "Fast Planar Segmentation of Depth Images", 《IMAGE PROCESSING: ALGORITHMS AND SYSTEMS XIII》 * |
| RIFAT KURBAN 等: "Plane Segmentation of Kinect Point Clouds using RANSAC", 《ICIT 2015 THE 7TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY》 * |
| 陈正兵: "基于深度图像的室内三维平面分割方法研究", 《电子设计工程》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086724A (en) * | 2018-08-09 | 2018-12-25 | 北京华捷艾米科技有限公司 | A kind of method for detecting human face and storage medium of acceleration |
| CN111340598A (en) * | 2020-03-20 | 2020-06-26 | 北京爱笔科技有限公司 | Method and device for adding interactive label |
| CN111340598B (en) * | 2020-03-20 | 2024-01-16 | 北京爱笔科技有限公司 | Method and device for adding interactive labels |
| CN111862185A (en) * | 2020-07-24 | 2020-10-30 | 唯羲科技有限公司 | Method for extracting plane from image |
| CN112729167A (en) * | 2020-12-21 | 2021-04-30 | 福建汇川物联网技术科技股份有限公司 | Calculation method and device of plane equation |
| CN112729167B (en) * | 2020-12-21 | 2022-10-25 | 福建汇川物联网技术科技股份有限公司 | Calculation method and device of plane equation |
| CN113008895A (en) * | 2021-01-29 | 2021-06-22 | 广州信邦智能装备股份有限公司 | Block fitting defect detection method based on three-dimensional data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107464258A (en) | A kind of method that three-dimensional planar is extracted from image | |
| US20190197311A1 (en) | Evaluation Method of Solar Energy Utilization Potential in Urban High-density Areas Based on Low-altitude Photogrammetry | |
| CN104574501B (en) | A kind of high-quality texture mapping method for complex three-dimensional scene | |
| CN103530881B (en) | Be applicable to the Outdoor Augmented Reality no marks point Tracing Registration method of mobile terminal | |
| CN104574393B (en) | A kind of three-dimensional pavement crack pattern picture generates system and method | |
| CN109816012A (en) | A kind of multiscale target detection method of integrating context information | |
| CN106123772B (en) | A kind of nuclear fuel rod pose automatic identification equipment and method | |
| CN106683173A (en) | Method of improving density of three-dimensional reconstructed point cloud based on neighborhood block matching | |
| CN113744337B (en) | Synchronous positioning and mapping method integrating vision, IMU and sonar | |
| CN105989604A (en) | Target object three-dimensional color point cloud generation method based on KINECT | |
| CN107369204B (en) | Method for recovering basic three-dimensional structure of scene from single photo | |
| CN102902355A (en) | Space interaction method of mobile equipment | |
| CN103227888B (en) | A kind of based on empirical mode decomposition with the video stabilization method of multiple interpretational criteria | |
| CN106485753A (en) | Method and apparatus for the camera calibration of pilotless automobile | |
| CN105160703A (en) | Optical flow computation method using time domain visual sensor | |
| CN107301648A (en) | Redundant points cloud minimizing technology based on overlapping region boundary angles | |
| CN103914860A (en) | Crystal bar position look-up table generation method and device | |
| CN110795978B (en) | Road surface point cloud data extraction method and device, storage medium and electronic equipment | |
| CN103438834A (en) | Hierarchy-type rapid three-dimensional measuring device and method based on structured light projection | |
| CN110516639B (en) | Real-time figure three-dimensional position calculation method based on video stream natural scene | |
| CN101794459A (en) | Seamless integration method of stereoscopic vision image and three-dimensional virtual object | |
| CN110096993A (en) | The object detection apparatus and method of binocular stereo vision | |
| CN103913149A (en) | Binocular range finding system based on STM 32 single chip microcomputer and range finding method thereof | |
| Wang et al. | A method for detecting windows from mobile LiDAR data | |
| CN104517280B (en) | Three-dimensional imaging method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171212 |
|
| RJ01 | Rejection of invention patent application after publication |