CN106323241A - Method for measuring three-dimensional information of person or object through monitoring video or vehicle-mounted camera - Google Patents

Method for measuring three-dimensional information of person or object through monitoring video or vehicle-mounted camera Download PDF

Info

Publication number
CN106323241A
CN106323241A CN201610413959.7A CN201610413959A CN106323241A CN 106323241 A CN106323241 A CN 106323241A CN 201610413959 A CN201610413959 A CN 201610413959A CN 106323241 A CN106323241 A CN 106323241A
Authority
CN
China
Prior art keywords
point
dimensional
formula
video
coordinates
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
Application number
CN201610413959.7A
Other languages
Chinese (zh)
Inventor
廖广军
武垚欣
陈玮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Police College
Original Assignee
Guangdong Police College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Police College filed Critical Guangdong Police College
Priority to CN201610413959.7A priority Critical patent/CN106323241A/en
Publication of CN106323241A publication Critical patent/CN106323241A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C11/00Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C11/00Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
    • G01C11/36Videogrammetry, i.e. electronic processing of video signals from a single source or from different sources to give parallax or range information
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S11/00Systems for determining distance or velocity not using reflection or reradiation
    • G01S11/12Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

The invention discloses a method for measuring three-dimensional information of a person or an object through a monitoring video or a vehicle-mounted camera, and relates to the technical field of video monitoring. The method comprises the following steps: 1, acquiring two or more images in different visual angles according to a video monitoring picture; 2, calibrating the camera, and establishing a mapping relation between 3D to 2D (three-dimensional to two-dimensional); 3, extracting a feature point, performing stereo matching, and calculating the three-dimensional information of the feature point of the object to be measured in the video picture according to the perspective transformation principle and a collinearity equation; and 4, establishing a perspective transformation relation between coordinates of a space object point of the feature point and coordinates of a picture image point through close shot photographic measurement. The method can be used for measuring the three-dimensional information of the person or the object through the monitoring video or the vehicle-mounted camera.

Description

A kind of by monitor video or vehicle-mounted camera measurement people or the method for object dimensional
Technical field:
The present invention relates to a kind of by monitor video or vehicle-mounted camera measurement people or the method for object dimensional, belong to video Monitoring technical field.
Background technology:
Carry out the method for personage's space measurement currently with monitor video and have three kinds of methods: 1, proportion measurement, i.e. need to look for Reference substance in a fixed video, as desk, doorframe etc. are easier to obtain the object of length, the people that will measure (or object) with Object of reference contrast obtains height (or length).The method necessarily requires, with reference to thing, not allow, also have one in some situation Determine error;2, carry out investigations experiment, i.e. returns to video presence and looks for similar people or thing to be simulated, by allowing the effect in video Similar to former video, estimate the height of people or the length of object.The method subjective factors is relatively strong, and error is the biggest;3, profit The three-dimensional measurement of video pictures labelling point is obtained, by known in reality scene 6 or the three-dimensional of above point with perspective transform Data, utilize perspective change to seek the three-dimensional data of the labelling point in picture.It is generally used for people or thing occurs in rule environment. For irregular environment, scene three-dimensional information need to be obtained with three-dimensional laser scanner.The former requirement of rule environment typically cannot Meeting, and the three-dimensional laser scanner of the latter is expensive, cost is high.
Summary of the invention:
For the problems referred to above, the present invention provides a kind of and measures people or object dimensional by monitor video or vehicle-mounted camera Method.
The described method of the present invention comprises the steps:
Step one, obtained the image of different visual angles of object under test two or more than two by video monitoring picture;
Step 2, calibrating camera, set up the mapping relations of 3D to 2D;
Step 3, extraction characteristic point, carry out Stereo matching and combine perspective transform principle and collinearity equation, calculates video and draws The three-dimensional information of the characteristic point of object under test in face:
By image slices point coordinatesWith dimensional target point coordinateConnected by collinearity equation, it may be assumed that
In formula: aijFor the element of spin matrix R, they are foreign side parallactic angle element ω, the function of k, φ, are write as (2) formula:
In formula: x0、y0, f be referred to as elements of interior orientation, XS、YS、ZSAnd ω, k, Φ are referred to as elements of exterior orientation, interior exterior orientation Element typically has 9, and wherein 3 elements of interior orientation can be by obtaining the qualification of camera, it is generally understood that be unknown number,
Needing in real work (1), (2) formula are carried out linear transformation (DLT), its transformation results is:
In formula: Li(i=1,2 ..., 11) it is unknown number;X, y are image slices point coordinates;X, Y, Z are that the space of scene is sat Mark, △ x, △ y be distorted error of object lens and plate distortion poor, when required precision is the highest, can consider when video camera is gunlock,
Formula (3) is organized into about LiLinear equation as follows:
XL1+YL2+ZL3+L4+X(x+Δx)L9+Y(x+Δx)L10+Z(x+Δx)L11=-(x+ Δ x)
XL5+YL6+ZL7+L8+X(x+Δx)L9+Y(x+Δx)L10+Z(x+Δx)L11=-(y+ Δ y)
Space coordinates (the X of known n pointi,Yi,Zi) and the picture point coordinate (x of correspondencei,yi), i=1,2 ..., n.Then About 2n LiLinear equation, can be expressed as follows with matrix form:
Formula (4) can be reduced to
ML=U
Wherein, M is 2n × 11 matrix of left end in formula (4), and L is 11 unknown dimensional vectors, and U is the 2n dimension of formula (4) right-hand member Vector, and M, U is known vector,.
As 2n > 11 time, the solution obtaining above-mentioned linear equation (4) with method of least square is:
L=(MTM)-1MTU
To sum up, when not considering △ x, △ y, at least need 6 pairs of corresponding point just can solve Li(i=1,2 ..., 11) these 11 Unknown number, thus set up contacting between image slices point coordinates system and dimensional target point coordinate system;
Step 4, set up characteristic point dimensional target point coordinate and the perspective transform of picture photo point coordinates by close-range photogrammetry Relation, thus obtain the three-dimensional information of at least 6 characteristic points in scene, characteristic point is mapped in video pictures, sets up to be measured Video pictures and the perspective transform relation of dimensional target point, realize perspective by the means such as collinearity equation and least square fitting and become Change asking for of each coefficient of matrix, then can ask for any spy of object under test in video pictures to be measured by perspective transformation matrices Levy three-dimensional information a little.
The invention have the benefit that the present invention use intersect than and generally acknowledge under perspective geometry specified conditions not Degeneration, after a regular length of known vehicle, directly determines car speed from video recording, has used twice perspective breakthroughly Converter technique, uses up short to have an X-rayed in video pictures by the three-dimensional information of real world for the first time, sets up video to be measured and draw Face and the perspective transform relation of dimensional target point, realize perspective transformation matrix by the means such as collinearity equation and least square fitting Asking for of each coefficient, then can ask for the three-dimensional information of arbitrary characteristics point in video pictures to be measured by perspective transformation matrices (perspective transform for the second time).Making this method break through proportion measurement necessarily needs subjective judgment in object of reference and investigative experiment to be main Restriction, avoid tradition to utilize perspective transform in rule environment, or to need to utilize high in irregular environment simultaneously Expensive three-dimensional laser scanner obtains the constraint of scene three-dimensional information.
Accompanying drawing illustrates:
For ease of explanation, the present invention is embodied as and accompanying drawing is described in detail by following.
Fig. 1 is the coordinate system of real world, camera and image, and Fig. 2 is the video needing in detailed description of the invention one to judge Image, Fig. 3 is true chest image in detailed description of the invention one.
Detailed description of the invention:
For making the object, technical solutions and advantages of the present invention of greater clarity, concrete below by shown in accompanying drawing Embodiment describes the present invention.However, it should be understood that these describe the most exemplary, and it is not intended to limit the model of the present invention Enclose.Additionally, in the following description, the description to known features and technology is eliminated, to avoid unnecessarily obscuring the present invention's Concept.
Detailed description of the invention one:
Cut to pieces in case certain doubtful killing a person, need to study and judge the height (as shown in Figure 2) of chest in video monitoring picture, to obtain Take the clue that whether be enough to load an adult female in judging this case.Being analyzed Fig. 2, in image, suspect is in walking appearance State, in scene, other reference substances are also difficult to the reference as proportion measurement.Video pictures to be measured is not in the space of rule, It is difficult to obtain the three-dimensional information of more than 6 labelling points.
The method using the present invention, we utilize the three-dimensional reconstruction principle of stereoscopic vision,
By obtaining the image of the different visual angles of two or more than two, object;
Calibrating camera, sets up the mapping relations of 3D to 2D;
Extract characteristic point, carry out Stereo matching and combine perspective transform principle and collinearity equation, calculate in video pictures and treat The three-dimensional information of the characteristic point of survey object:
By image slices point coordinatesWith dimensional target point coordinateConnected by collinearity equation, it may be assumed that
In formula: aijFor the element of spin matrix R, they are foreign side parallactic angle element ω, the function of k, φ, are write as (2) formula:
In formula: x0、y0, f be referred to as elements of interior orientation, XS、YS、ZSAnd ω, k, Φ are referred to as elements of exterior orientation, interior exterior orientation Element typically has 9, and wherein 3 elements of interior orientation can be by obtaining the qualification of camera, it is generally understood that be unknown number,
Needing in real work (1), (2) formula are carried out linear transformation (DLT), its transformation results is:
In formula: Li(i=1,2 ..., 11) it is unknown number;X, y are image slices point coordinates;X, Y, Z are that the space of scene is sat Mark, △ x, △ y be distorted error of object lens and plate distortion poor, when required precision is the highest, can consider when video camera is gunlock,
Formula (3) is organized into about LiLinear equation as follows:
XL1+YL2+ZL3+L4+X(x+Δx)L9+Y(x+Δx)L10+Z(x+Δx)L11=-(x+ Δ x)
XL5+YL6+ZL7+L8+X(x+Δx)L9+Y(x+Δx)L10+Z(x+Δx)L11=-(y+ Δ y)
Space coordinates (the X of known n pointi,Yi,Zi) and the picture point coordinate (x of correspondencei,yi), i=1,2 ..., n. Then about 2n LiLinear equation, can be expressed as follows with matrix form:
Formula (4) can be reduced to
ML=U
Wherein, M is 2n × 11 matrix of left end in formula (4), and L is 11 unknown dimensional vectors, and U is the 2n dimension of formula (4) right-hand member Vector, and M, U is known vector,.
As 2n > 11 time, the solution obtaining above-mentioned linear equation (4) with method of least square is:
L=(MTM)-1MTU
To sum up, when not considering △ x, △ y, at least need 6 pairs of corresponding point just can solve Li(i=1,2 ..., 11) these 11 Unknown number, thus set up contacting between image slices point coordinates system and dimensional target point coordinate system;
The three-dimensional data of acquisition is mapped in video pictures Fig. 2 to be measured, just can realize chest in Fig. 2 by space measurement The measurement of height, the height measuring gained chest is 15.5cm.
According to this measurement height, provide suspect in picture to be lifted chest by investigation department and can not accommodate adult female's body The clue of body.After cracking of cases, pointed out by suspect, it is thus achieved that chest in video is as it is shown on figure 3, chest true altitude is 16.2cm。
Wherein step 2 sets up the mapping relations of 3D to 2D by the following method: uses Zhang Zhengyou camera calibration algorithm, presses Following steps are carried out:
1) under homogeneous coordinates, the relation between three-dimensional point M and its subpoint m can be expressed asWherein, k is any non-zero scale factor, and [R, t] represents external parameters of cameras, Wherein R is the spin matrix of 3 × 3, and t represents the translation vector being tied to camera coordinates system from world coordinates, and K represents video camera internal reference Matrix, wherein (uo,vo) it is principal point coordinate, fu, fvRepresenting the scale factor in x-axis y-axis direction respectively, s represents about two coordinates The distortion of system;
2) H=K [r is made1,r2, t], H is homography matrix, and as made Z=0, then R only has r1,r2, then three-dimensional point M With the relation between its subpoint m can be reduced toEvery pictures can calculate a homography matrix H,
6) homography matrix H is write as 3 column vector form of 3X3, then H can be write as [h1,h2,h3]=λ K [r1,r2, t],
Haveλ is a scaling scalar factor, namely the inverse of k,
By r1,r2Orthogonal formula: h1K-TK-1h2=0, make hi=[hi1,hi2,hi3]T, then front formula can be rewritten into:
OrderB=[B11 B12 B22 B13 B23 B33],
Then obtained by internal reference restrictive condition
I.e. Vb=0,
V is 2 × 6 matrixes, say, that every photo can set up two equation group, 6 unknown numbers, then need 6 sides Journey just can solve, so at least needing 3 photos just can solve unknown number, solving of b matrix, camera internal reference matrix K determines that , thus every pictures (R t) can also determine.

Claims (2)

1. measure people or the method for object dimensional by monitor video or vehicle-mounted camera for one kind, it is characterised in that: described method Comprise the steps:
Step one, obtained the image of different visual angles of object under test two or more than two by video monitoring picture;
Step 2, calibrating camera, set up the mapping relations of 3D to 2D;
Step 3, extraction characteristic point, carry out Stereo matching and combine perspective transform principle and collinearity equation, calculating in video pictures The three-dimensional information of the characteristic point of object under test:
By image slices point coordinatesWith dimensional target point coordinateConnected by collinearity equation, it may be assumed that
In formula: aijFor the element of spin matrix R, they are foreign side parallactic angle element ω, the function of k, φ, are write as (2) formula:
In formula: x0、y0, f be referred to as elements of interior orientation, XS、YS、ZSAnd ω, k, Φ are referred to as elements of exterior orientation, internal and external orientation Typically having 9, wherein 3 elements of interior orientation can be by obtaining the qualification of camera, it is generally understood that be unknown number,
Needing in real work (1), (2) formula are carried out linear transformation (DLT), its transformation results is:
In formula: Li(i=1,2 ..., 11) it is unknown number;X, y are image slices point coordinates;X, Y, Z are the space coordinates of scene, △ x, △ y be distorted error of object lens and plate distortion poor, when required precision is the highest, can consider when video camera is gunlock,
Formula (3) is organized into about LiLinear equation as follows:
XL1+YL2+ZL3+L4+X(x+△x)L9+Y(x+△x)L10+Z(x+△x)L11=-(x+ △ x)
XL5+YL6+ZL7+L8+X(x+△x)L9+Y(x+△x)L10+Z(x+△x)L11=-(y+ △ y)
Space coordinates (the X of known n pointi,Yi,Zi) and the picture point coordinate (x of correspondencei,yi), i=1,2 ..., n.Then about 2n LiLinear equation, can be expressed as follows with matrix form:
Formula (4) can be reduced to
ML=U
Wherein, M is 2n × 11 matrix of left end in formula (4), and L is 11 unknown dimensional vectors, and U is the 2n dimensional vector of formula (4) right-hand member, And M, U are known vector,.
As 2n > 11 time, the solution obtaining above-mentioned linear equation (4) with method of least square is:
L=(MTM)-1MTU
To sum up, when not considering △ x, △ y, at least need 6 pairs of corresponding point just can solve Li(i=1,2 ..., 11) these 11 the unknowns Number, thus set up contacting between image slices point coordinates system and dimensional target point coordinate system;
Step 4, set up by close-range photogrammetry characteristic point dimensional target point coordinate and picture photo point coordinates perspective transform close System, thus obtain the three-dimensional information of at least 6 characteristic points in scene, characteristic point is mapped in video pictures, sets up to be measured regarding Frequently picture and the perspective transform relation of dimensional target point, realize perspective transform by the means such as collinearity equation and least square fitting Asking for of each coefficient of matrix, then can ask for the arbitrary characteristics of object under test in video pictures to be measured by perspective transformation matrices The three-dimensional information of point.
It is the most according to claim 1 a kind of by monitor video or vehicle-mounted camera measurement people or the method for object dimensional, It is characterized in that: step 2 sets up the mapping relations of 3D to 2D by the following method: use Zhang Zhengyou camera calibration algorithm, by such as Lower step is carried out:
1) under homogeneous coordinates, the relation between three-dimensional point M and its subpoint m can be expressed asWherein, k is any non-zero scale factor, and [R, t] represents external parameters of cameras, Wherein R is the spin matrix of 3 × 3, and t represents the translation vector being tied to camera coordinates system from world coordinates, and K represents video camera internal reference Matrix, wherein (uo,vo) it is principal point coordinate, fu, fvRepresenting the scale factor in x-axis y-axis direction respectively, s represents about two coordinates The distortion of system;
2) H=K [r is made1,r2, t], H is homography matrix, and as made Z=0, then R only has r1,r2, then three-dimensional point M and it Relation between subpoint m can be reduced toEvery pictures can calculate a homography matrix H,
3) homography matrix H is write as 3 column vector form of 3X3, then H can be write as [h1,h2,h3]=λ K [r1,r2, t],
Haveλ is a scaling scalar factor, namely the inverse of k,
By r1,r2Orthogonal formula: h1K-TK-1h2=0, make hi=[hi1,hi2,hi3]T, then front formula can be rewritten into: hi TBhj= vij Tb,
vij=[hi1hj1,hi1hj2+hi2hj1,hi2hj2,hi3hj1+hi1hj3,hi3hj2+hi2hj3,hi3hj3]T
OrderB=[B11 B12 B22 B13 B23 B33],
Then obtained by internal reference restrictive condition
I.e. Vb=0,
V is 2 × 6 matrixes, say, that every photo can set up two equation group, 6 unknown numbers, then just need 6 equations Can solve, so at least needing 3 photos just can solve unknown number, solving of b matrix, camera internal reference matrix K determines that, from And every pictures (R t) can also determine.
CN201610413959.7A 2016-06-12 2016-06-12 Method for measuring three-dimensional information of person or object through monitoring video or vehicle-mounted camera Pending CN106323241A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610413959.7A CN106323241A (en) 2016-06-12 2016-06-12 Method for measuring three-dimensional information of person or object through monitoring video or vehicle-mounted camera

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610413959.7A CN106323241A (en) 2016-06-12 2016-06-12 Method for measuring three-dimensional information of person or object through monitoring video or vehicle-mounted camera

Publications (1)

Publication Number Publication Date
CN106323241A true CN106323241A (en) 2017-01-11

Family

ID=57725141

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610413959.7A Pending CN106323241A (en) 2016-06-12 2016-06-12 Method for measuring three-dimensional information of person or object through monitoring video or vehicle-mounted camera

Country Status (1)

Country Link
CN (1) CN106323241A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107818685A (en) * 2017-10-25 2018-03-20 司法部司法鉴定科学技术研究所 A kind of method that state of motion of vehicle is obtained based on Vehicular video
CN108042172A (en) * 2017-12-06 2018-05-18 上海波城医疗科技有限公司 Bone surgery one channel alignment system
CN108042173A (en) * 2017-12-06 2018-05-18 上海波城医疗科技有限公司 Drilled tunnel alignment system
CN109520477A (en) * 2018-10-30 2019-03-26 成都飞机工业(集团)有限责任公司 A method of the high-acruracy survey scale factor based on two dimension photography
CN109658465A (en) * 2018-12-07 2019-04-19 广州华端科技有限公司 Data processing, image rebuilding method and device in image reconstruction process
CN110197104A (en) * 2018-02-27 2019-09-03 杭州海康威视数字技术股份有限公司 Distance measuring method and device based on vehicle
CN110377015A (en) * 2018-04-13 2019-10-25 北京三快在线科技有限公司 Robot localization method and robotic positioning device
CN110798618A (en) * 2019-10-30 2020-02-14 广州海格星航信息科技有限公司 Camera resource scheduling method and device in dynamic tracking
CN114234908A (en) * 2021-10-29 2022-03-25 广东省国土资源测绘院 Method, equipment, medium and product for monitoring seawall settlement

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1648600A (en) * 2004-12-09 2005-08-03 武汉大学 Method for three-dimensional measurement of sheet metal part using single non-measuring digital camera
US20060017720A1 (en) * 2004-07-15 2006-01-26 Li You F System and method for 3D measurement and surface reconstruction
CN102914295A (en) * 2012-09-21 2013-02-06 上海大学 Computer vision cube calibration based three-dimensional measurement method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060017720A1 (en) * 2004-07-15 2006-01-26 Li You F System and method for 3D measurement and surface reconstruction
CN1648600A (en) * 2004-12-09 2005-08-03 武汉大学 Method for three-dimensional measurement of sheet metal part using single non-measuring digital camera
CN102914295A (en) * 2012-09-21 2013-02-06 上海大学 Computer vision cube calibration based three-dimensional measurement method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张长命: "双目立体视觉技术在三维测量中的应用研究", 《信息科技辑》 *
王新宇: "基于计算机立体视觉的三维重建", 《信息科技辑》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107818685A (en) * 2017-10-25 2018-03-20 司法部司法鉴定科学技术研究所 A kind of method that state of motion of vehicle is obtained based on Vehicular video
CN108042172A (en) * 2017-12-06 2018-05-18 上海波城医疗科技有限公司 Bone surgery one channel alignment system
CN108042173A (en) * 2017-12-06 2018-05-18 上海波城医疗科技有限公司 Drilled tunnel alignment system
CN108042173B (en) * 2017-12-06 2019-11-12 上海波城医疗科技有限公司 Drilled tunnel positioning system
CN108042172B (en) * 2017-12-06 2019-11-15 上海波城医疗科技有限公司 Bone surgery one channel positioning system
CN110197104B (en) * 2018-02-27 2022-03-29 杭州海康威视数字技术股份有限公司 Distance measurement method and device based on vehicle
CN110197104A (en) * 2018-02-27 2019-09-03 杭州海康威视数字技术股份有限公司 Distance measuring method and device based on vehicle
CN110377015B (en) * 2018-04-13 2021-04-27 北京三快在线科技有限公司 Robot positioning method and robot positioning device
CN110377015A (en) * 2018-04-13 2019-10-25 北京三快在线科技有限公司 Robot localization method and robotic positioning device
CN109520477A (en) * 2018-10-30 2019-03-26 成都飞机工业(集团)有限责任公司 A method of the high-acruracy survey scale factor based on two dimension photography
CN109520477B (en) * 2018-10-30 2021-01-26 成都飞机工业(集团)有限责任公司 High-precision scale factor measuring method based on two-dimensional photography
CN109658465A (en) * 2018-12-07 2019-04-19 广州华端科技有限公司 Data processing, image rebuilding method and device in image reconstruction process
CN110798618A (en) * 2019-10-30 2020-02-14 广州海格星航信息科技有限公司 Camera resource scheduling method and device in dynamic tracking
CN114234908A (en) * 2021-10-29 2022-03-25 广东省国土资源测绘院 Method, equipment, medium and product for monitoring seawall settlement

Similar Documents

Publication Publication Date Title
CN106323241A (en) Method for measuring three-dimensional information of person or object through monitoring video or vehicle-mounted camera
Carbonneau et al. Cost‐effective non‐metric photogrammetry from consumer‐grade sUAS: implications for direct georeferencing of structure from motion photogrammetry
CN104596502B (en) Object posture measuring method based on CAD model and monocular vision
US11010925B2 (en) Methods and computer program products for calibrating stereo imaging systems by using a planar mirror
KR101758058B1 (en) Apparatus and method for estimating camera motion using depth information, augmented reality system
CN106920276B (en) A kind of three-dimensional rebuilding method and system
CN108474658B (en) Ground form detection method and system, unmanned aerial vehicle landing method and unmanned aerial vehicle
CN104537707B (en) Image space type stereoscopic vision moves real-time measurement system online
US20130249901A1 (en) Systems and methods for geometrically mapping two-dimensional images to three-dimensional surfaces
CN103983186B (en) Binocular vision system bearing calibration and calibration equipment
CN102737406A (en) Three-dimensional modeling apparatus and method
CN110675436A (en) Laser radar and stereoscopic vision registration method based on 3D feature points
CN109410234A (en) A kind of control method and control system based on binocular vision avoidance
KR20160095560A (en) Apparatus and methdo for calibrating a camera
CN107590444A (en) Detection method, device and the storage medium of static-obstacle thing
CN108362205A (en) Space ranging method based on fringe projection
Seo et al. A branch-and-bound algorithm for globally optimal calibration of a camera-and-rotation-sensor system
Jurjević et al. 3D data acquisition based on OpenCV for close-range photogrammetry applications
CN113048985B (en) Camera relative motion estimation method under known relative rotation angle condition
KR20150119770A (en) Method for measuring 3-dimensional cordinates with a camera and apparatus thereof
Aliakbarpour et al. Geometric exploration of virtual planes in a fusion-based 3D data registration framework
Aliakbarpour et al. Inertial-visual fusion for camera network calibration
KR102422292B1 (en) Method and apparatus for obtaining 3D-coordinates from 2D-image
Khosravani et al. Coregistration of kinect point clouds based on image and object space observations
Li et al. Binocular stereo vision calibration experiment based on essential matrix

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20170111