CN109035343A - A kind of floor relative displacement measurement method based on monitoring camera - Google Patents
A kind of floor relative displacement measurement method based on monitoring camera Download PDFInfo
- Publication number
- CN109035343A CN109035343A CN201810766873.1A CN201810766873A CN109035343A CN 109035343 A CN109035343 A CN 109035343A CN 201810766873 A CN201810766873 A CN 201810766873A CN 109035343 A CN109035343 A CN 109035343A
- Authority
- CN
- China
- Prior art keywords
- monitoring camera
- relative displacement
- characteristic point
- displacement measurement
- image
- 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
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
Abstract
The floor relative displacement measurement method based on monitoring camera that the present invention relates to a kind of adjusts the angle of monitoring camera by remote operation monitoring camera head, acquires the image under different angle as calibration image;Characteristic point needed for extracting calibration from calibration image, and the calibration according to Zhang Zhengyou scaling method to monitoring camera progress inside and outside parameter;Acquisition measurement video carries out relative displacement measurement;The distortion of image is corrected frame by frame;The characteristic point of each image is extracted, and the characteristic point of adjacent image frame is matched, to realize the tracking of characteristic point;The pixel coordinate that same characteristic point is obtained in consecutive frame is poor, pixel coordinate difference is converted to world coordinates, and carry out relative displacement calculating, according to RANSAC rejecting abnormalities data, completes floor relative displacement measurement.Floor relative displacement measurement method based on monitoring camera proposed by the invention, can complete all operations in remote computer monitoring client, can efficiently and in real time measure to monitored picture, have preferable practical engineering application value.
Description
Technical field
It is especially a kind of based on monitoring the present invention relates to fields such as image processing techniques, machine vision, displacement structure measurements
The floor relative displacement measurement method of camera.
Background technique
The measurement of the relative displacement of architecture storey all has great importance to construction, hazard prediction and scientific experiment.It surveys
Amount the data obtained is the premise of further work, and the accuracy of result and the timeliness for obtaining data will directly affect later period work
The progress of work.Such as the floor relative displacement surveyed, the safety management that can be used for building, guiding plan design, detection vibration for
Destructive assessment after the destruction situation of floor structure and earthquake.Traditional displacement measurement method mainly utilizes profession measurement
Instrument measures, such as: precision theodolite, level and total station, by periodically carrying out geodetic coordinates to ground network point
Measurement, every time measurement after all coordinate value is compared with last time measurement result, thus obtain the direction of ground displacement, size and
Speed.This method is complicated for operation, at high cost, workload is huge, time-consuming, arduously, inefficiency, and and accuracy in measurement is passed through by survey crew
Influence is tested, the application of construction account is limited.
In recent years, with the continuous development of computer technology with the continuous maturation of digital image processing techniques, view-based access control model
Measurement as a kind of non-contact measurement method using more and more extensive.Compared with traditional contact method measurement, view-based access control model
Measurement have the advantages that low cost, efficiently, it is quick, facilitate.Currently, monitoring camera is used widely in safety-security area, popularity rate
Height, but the monitoring camera of such security protection is at low cost, image deformation is serious, can not directly apply in digital photogrammetry.
Therefore, floor relative displacement measurement method of the research based on monitoring camera will be with important theory and realistic meaning.
Summary of the invention
The floor relative displacement measurement method based on monitoring camera that the purpose of the present invention is to provide a kind of, it is existing to overcome
Defect present in technology.
To achieve the above object, the technical scheme is that a kind of floor relative displacement measurement based on monitoring camera
Method is realized in accordance with the following steps:
Step 1: by remote operation monitoring camera head, adjusting the angle of monitoring camera, acquisition is different
Image under angle is as calibration image;
Step 2: characteristic point needed for extracting calibration from calibration image, and according to the calibration side Zhang Zhengyou
Method carries out the calibration of inside and outside parameter to monitoring camera;
Step 3: acquisition measurement video carries out relative displacement measurement;
Step 4: the distortion of image is corrected frame by frame;
Step 5: extracting the characteristic point of each image, and the characteristic point of adjacent image frame is matched, to realize feature
The tracking of point;
Step 6: the pixel coordinate for obtaining same characteristic point in consecutive frame is poor, and pixel coordinate difference is converted to world coordinates,
And relative displacement calculating is carried out, according to RANSAC rejecting abnormalities data, complete floor relative displacement measurement.
In an embodiment of the present invention, in the step S1, monitoring camera cloud platform rotation is controlled by remote computer,
To obtain the calibration picture of the required Different Plane of two-dimensional camera calibration.
In an embodiment of the present invention, in the step S2, the characteristic point is that existing floor floor tile stitching portion is pre-
If characteristic point.
In an embodiment of the present invention, in the step S2, also monitoring camera radial distortion is corrected.
In an embodiment of the present invention, it in the step S2, selects and is made based on the resulting outer ginseng value of the last one plane
For ginseng value outside monitoring camera used in subsequent measurement.
In an embodiment of the present invention, in the step S4, by the measurement video of monitoring camera acquisition by setting in advance
Single frames picture is extracted at fixed interval, carries out distortion correction frame by frame to it according to resulting camera radial distortion parameter, abnormal to eliminate
Become.
In an embodiment of the present invention, it in the step S5, is carried out using SIFT algorithm and Robust Algorithm of Image Corner Extraction special
Sign point extracts.
In an embodiment of the present invention, different to calculating resulting characteristic point by RANSAC and removing in the step S5
Normal match point.
In an embodiment of the present invention, in the step S6, by the conversion of coordinate system, as follows by one
Characteristic point is transformed into pixel coordinate system from world coordinate system:
Wherein, ZCTo put the Z coordinate in camera coordinates system, [u v 1]TIt is characterized the coordinate a little in image coordinate system,
fx、fyFor focal length, u0、v0For principal point coordinate, R is the spin matrix of 3*3, and T is the translation vector of 3*1, [XW YW ZW 1]TFor point
Coordinate in world coordinate system;
It is as follows that conversion of the characteristic point from pixel coordinate to world coordinates is as follows according to back projection:
By obtaining the pixel coordinate of matching characteristic point, the world coordinates of two characteristic points is calculated, utilizes range formula
Obtain displacement result.
Compared to the prior art, the invention has the following advantages: the building proposed by the invention based on monitoring camera
Layer relative displacement measurement method, can complete all operations in remote computer monitoring client, can be efficiently and in real time to monitoring picture
Face measures, and has preferable practical engineering application value.
Detailed description of the invention
Fig. 1 is displacement measurement method entire block diagram in the present invention.
Fig. 2, which is that camera calibration is used in the present invention, demarcates picture.
Fig. 3 (a) is that camera calibration characteristic point takes 1 schematic diagram of a shooting angle in the present invention.
Fig. 3 (b) is that camera calibration characteristic point takes 2 schematic diagram of a shooting angle in the present invention.
Fig. 3 (c) is that camera calibration characteristic point takes 3 schematic diagram of a shooting angle in the present invention.
Fig. 4 is to join the result figure in camera coordinates system in the present invention outside camera calibration.
Fig. 5 (a) is that the 1st frame schematic diagram of single frames picture is extracted in the embodiment of the present invention 1.
Fig. 5 (b) is that the 26th frame schematic diagram of single frames picture is extracted in the embodiment of the present invention 1.
Fig. 5 (c) is that the 51st frame schematic diagram of single frames picture is extracted in the embodiment of the present invention 1.
Fig. 6 (a) is that the 1st frame schematic diagram is corrected in pattern distortion in the embodiment of the present invention 2.
Fig. 6 (b) is that the 26th frame schematic diagram is corrected in pattern distortion in the embodiment of the present invention 2.
Fig. 6 (c) is that the 51st frame schematic diagram is corrected in pattern distortion in the embodiment of the present invention 2.
Fig. 7 (a) is that SIFT feature extracts the 1st frame schematic diagram in the embodiment of the present invention 1.
Fig. 7 (b) is that SIFT feature extracts the 126th frame schematic diagram in the embodiment of the present invention 1.
Fig. 8 (a) is that SIFT feature slightly matches schematic diagram in the embodiment of the present invention 1.
Fig. 8 (b) is that SIFT feature carefully matches schematic diagram in the embodiment of the present invention 1.
Fig. 9 (a) is that RANSAC removes the 26th frame schematic diagram of error hiding characteristic point in the embodiment of the present invention 1.
Fig. 9 (b) is that RANSAC removes the 51st frame schematic diagram of error hiding characteristic point in the embodiment of the present invention 1.
Figure 10 (a) is that the 26th frame enlarged diagram of error hiding characteristic point is removed in the embodiment of the present invention 1.
Figure 10 (b) is that the 51st frame enlarged diagram of error hiding characteristic point is removed in the embodiment of the present invention 1.
Figure 11 is relative displacement calculated result figure in the embodiment of the present invention 1.
Figure 12 (a) is that the 1st frame schematic diagram of single frames picture is extracted in the embodiment of the present invention 2.
Figure 12 (b) is that the 26th frame schematic diagram of single frames picture is extracted in the embodiment of the present invention 2.
Figure 12 (c) is that the 51st frame schematic diagram of single frames picture is extracted in the embodiment of the present invention 2.
Figure 13 (a) is the direction relative displacement Orthogonal Decomposition x result figure in the embodiment of the present invention 2.
Figure 13 (b) is the direction relative displacement Orthogonal Decomposition y result figure in the embodiment of the present invention 2.
Specific embodiment
With reference to the accompanying drawing, technical solution of the present invention is specifically described.
The present invention provides a kind of floor relative displacement measurement method based on monitoring camera, firstly, passing through computer remote
The rotation of monitoring camera holder is controlled, the plane picture of different angle needed for acquiring two-dimensional calibrations simultaneously extracts picture feature point, into
The calibration of row camera internal reference, outer ginseng and radial distortion.Select the Camera extrinsic of last picture as outer used in subsequent measurement
Ginseng, and no longer rotate camera head.Secondly, extracting single frames figure by preset interval from the video that monitoring camera is shot
Piece carries out distortion correction to it according to resulting camera radial distortion parameter, to eliminate distortion.Again, SIFT feature is extracted
And Feature Points Matching is carried out, while matching characteristic point is subjected to the conversion from pixel coordinate to world coordinates.Finally, being displaced
It calculates and error hiding characteristic point is rejected.Concrete principle block diagram is referring to Fig. 1.
Further, in the present embodiment, monitoring camera used is that connection regards prestige brand and model as the network monitoring of ID-550
Camera acquires 20 calibration pictures using the camera.Using the intersection point of floor tile as characteristic point, as shown in Fig. 2, every picture mentions
The characteristic point taken is 20, and calibrating parameters are as shown in table 1 below.Fig. 3 (a)~(c) is to demarcate feature under different cameral shooting angle
Point takes schematic diagram a little.
1 camera calibration parameter of table
Embodiment 1
Mobile monitor camera is displaced by a small margin to simulate floor, is shot with monitoring camera to live video, the video of acquisition
Length is 5 seconds, shares 149 frames.Since the 1st frame, using 25 frames as interval to video carry out the extraction of single frames picture, the respectively the 1st
Frame, the 26th frame, the 51st frame, the 76th frame, the 101st frame, the 126th frame, shown in the single frames picture example such as Fig. 5 (a) to (c) of part.It obtains
After getting single frames picture, distortion correction, picture example such as Fig. 6 (a) to (c) after correction are carried out to picture using camera calibration parameter
It is shown.
Further, SIFT feature extraction is carried out to the picture after distortion correction, then carries out spy with the 1st frame picture respectively
Sign point matching needs to carry out smart matching to reject error hiding characteristic point as far as possible, and essence matching is calculated using by RANSAC
Method finds Matching Model, and rejects Mismatching point to carry out.Wherein, Fig. 8 (a) is the 1st frame picture and the 126th frame picture feature point
Thick matching, Fig. 8 (b) are that the 1st frame picture is matched with the 126th frame picture feature point essence.It is special according to two width pictures after matching characteristic point
Levy the location information of point, available misalignment.Fig. 9 (a) to (b) is essence matching schematic diagram, and straight line as shown in the figure is
The Matching Model that RANSAC is found out meets the point of this model within a certain error range for smart match point, other point points is accidentally
With point, Figure 10 (a) to (b) is schematic diagram after the amplification of Fig. 9 (a) to (b) ordinate.
Further, for the smart matching characteristic point extracted, it is transformed into world coordinates, conversion meter from pixel coordinate
It is as follows to calculate formula:
Wherein, ZCTo put the Z coordinate in camera coordinates system, [u v 1]TTo put the coordinate in image coordinate system, fx、
fyFor focal length, u0、v0For principal point coordinate, R is the spin matrix of 3*3, and T is the translation vector of 3*1, [XW YW ZW 1]TExist for point
Coordinate in world coordinate system.ZCJoin outside camera calibration and obtain, Fig. 4 is embodiment of the Camera extrinsic in camera coordinates system.[u v
1]TFor the pixel coordinate of smart matching characteristic point, fx、fy、u0、v0Join outside camera calibration internal reference and obtain, R, T join outside camera calibration
It obtains.
Further, the mean value of the variation of the world coordinates according to match point smart on different frame can obtain relative motion
Displacement, as shown in figure 11.As a result positive and negative respectively represent in is displaced to the left, to the right.Fitting a straight line situation and displacement result are as follows
Shown in table
2 fitting a straight line of table and displacement result (compared to the 1st frame)
Embodiment 2
Ceiling fan by being fixed on ceiling moves to generate moving target known to motion amplitude, fixed on a flabellum
The handmarking of one black, and its movement is tracked with method of the invention.The video length of acquisition is 79 seconds, totally 1982
Frame.Since the 1st frame, the extraction of single frames picture is carried out to video using 1 frame as interval.After getting single frames picture, camera mark is utilized
Determine parameter and distortion correction is carried out to picture, Figure 12 (a) to (c) is the single frames picture exemplary diagram that part has carried out distortion correction.
Further, feature point extraction is carried out to the picture after distortion correction, then carries out characteristic point with the 1st frame picture respectively
Matching.Unlike the first embodiment, due to artificially black adhesive plaster being specified to be characterized a little herein, so without carrying out characteristic point
Essence matching.After matching characteristic point, according to the location information of 2 width picture feature points, available misalignment.
Further, for the matching characteristic point extracted, it is transformed into world coordinates from pixel coordinate, conversion calculates
Formula is identical as the calculation formula in embodiment 1.
Further, in order to obtain straight-line displacement the case where, Orthogonal Decomposition is carried out to the displacement of black adhesive plaster.
Further, shift length calculating is carried out by range formula, obtains the calculated result of matching characteristic point.To all
Single frames picture calculated, final displacement result is obtained, as shown in Figure 13 (a) to (b).Following two table of partial dislocation result
It is shown
The 3 part direction x displacement result of table (compared to the 1st frame)
The 4 part direction y displacement result of table (compared to the 1st frame)
Further, in order to which the precision calculated camera calibration and displacement is verified, 20 calibration picture distortion are rectified
After just, the two o'clock of actual range known to 60 groups is taken from this 20 picture, actual range is 600mm herein, then carries out pixel seat
The conversion for marking world coordinates is gone forward side by side row distance calculating, and some numerical results are as shown in the table
5 part verification result of table
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
When with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (9)
1. a kind of floor relative displacement measurement method based on monitoring camera, which is characterized in that realize in accordance with the following steps:
Step 1: by remote operation monitoring camera head, adjusting the angle of monitoring camera, the image acquired under different angle is made
For calibration image;
Step 2: from calibration image extract calibration needed for characteristic point, and according to Zhang Zhengyou scaling method to monitoring camera into
The calibration of row inside and outside parameter;
Step 3: acquisition measurement video carries out relative displacement measurement;
Step 4: the distortion of image is corrected frame by frame;
Step 5: extracting the characteristic point of each image, and the characteristic point of adjacent image frame is matched, to realize characteristic point
Tracking;
Step 6: the pixel coordinate for obtaining same characteristic point in consecutive frame is poor, and pixel coordinate difference is converted to world coordinates, is gone forward side by side
Row relative displacement calculates, and according to RANSAC rejecting abnormalities data, completes floor relative displacement measurement.
2. a kind of floor relative displacement measurement method based on monitoring camera according to claim 1, which is characterized in that
In the step S1, monitoring camera cloud platform rotation is controlled by remote computer, to obtain the required difference of two-dimensional camera calibration
The calibration picture of plane.
3. a kind of floor relative displacement measurement method based on monitoring camera according to claim 1, which is characterized in that
In the step S2, the characteristic point is the preset characteristic point in existing floor floor tile stitching portion.
4. a kind of floor relative displacement measurement method based on monitoring camera according to claim 1, which is characterized in that
In the step S2, also monitoring camera radial distortion is demarcated.
5. a kind of floor relative displacement measurement method based on monitoring camera according to claim 1, which is characterized in that
In the step S2, select based on the resulting outer ginseng value of the last one plane of monitoring camera as monitoring phase used in subsequent measurement
Ginseng value outside machine.
6. a kind of floor relative displacement measurement method based on monitoring camera according to claim 4, which is characterized in that
In the step S4, single frames picture will be extracted by preset interval in the measurement video of monitoring camera acquisition, according to gained
Camera radial distortion parameter distortion correction frame by frame is carried out to it, with eliminate distortion.
7. a kind of floor relative displacement measurement method based on monitoring camera according to claim 1, which is characterized in that
In the step S5, feature point extraction is carried out using SIFT algorithm and Robust Algorithm of Image Corner Extraction.
8. a kind of floor relative displacement measurement method based on monitoring camera according to claim 1, which is characterized in that
In the step S5, Exceptional point is removed by RANSAC to resulting characteristic point is calculated.
9. a kind of floor relative displacement measurement method based on monitoring camera according to claim 1, which is characterized in that
In the step S6, by the conversion of coordinate system, a characteristic point is transformed into pixel from world coordinate system as follows
Coordinate system:
Wherein, ZCTo put the Z coordinate in camera coordinates system, [u v 1]TIt is characterized the coordinate a little in image coordinate system, fx、fy
For focal length, u0、v0For principal point coordinate, R is the spin matrix of 3*3, and T is the translation vector of 3*1, [XW YW ZW 1]TIt is alive to put
Coordinate in boundary's coordinate system;
It is as follows that conversion of the characteristic point from pixel coordinate to world coordinates is as follows according to back projection:
By obtaining the pixel coordinate of matching characteristic point, the world coordinates of two characteristic points is calculated, is obtained using range formula
Displacement result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810766873.1A CN109035343A (en) | 2018-07-12 | 2018-07-12 | A kind of floor relative displacement measurement method based on monitoring camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810766873.1A CN109035343A (en) | 2018-07-12 | 2018-07-12 | A kind of floor relative displacement measurement method based on monitoring camera |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109035343A true CN109035343A (en) | 2018-12-18 |
Family
ID=64642056
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810766873.1A Pending CN109035343A (en) | 2018-07-12 | 2018-07-12 | A kind of floor relative displacement measurement method based on monitoring camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109035343A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112215896A (en) * | 2020-09-01 | 2021-01-12 | 深圳市瑞立视多媒体科技有限公司 | Camera frame data processing method and device for multi-camera calibration and computer equipment |
CN113203361A (en) * | 2021-04-14 | 2021-08-03 | 甘肃建投科技研发有限公司 | Thickness rapid measurement device for prefabricated wallboard production |
US20220044420A1 (en) * | 2020-08-10 | 2022-02-10 | National Taiwan University Of Science And Technology | Earthquake monitoring system and earthquake monitoring method |
WO2024067435A1 (en) * | 2022-09-30 | 2024-04-04 | 浙江大学 | Video-based multi-object displacement tracking monitoring method and apparatus |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419055A (en) * | 2008-10-30 | 2009-04-29 | 北京航空航天大学 | Space target position and pose measuring device and method based on vision |
CN104677340A (en) * | 2013-11-30 | 2015-06-03 | 中国科学院沈阳自动化研究所 | Point character based monocular vision pose measurement method |
-
2018
- 2018-07-12 CN CN201810766873.1A patent/CN109035343A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419055A (en) * | 2008-10-30 | 2009-04-29 | 北京航空航天大学 | Space target position and pose measuring device and method based on vision |
CN104677340A (en) * | 2013-11-30 | 2015-06-03 | 中国科学院沈阳自动化研究所 | Point character based monocular vision pose measurement method |
Non-Patent Citations (3)
Title |
---|
杨洁: "双目立体视觉测距技术研究", 《中国优秀硕士学位论文全文数据库(电子期刊)信息科技辑》 * |
王政等: "基于张正友标定算法的内参数线性与非线性解算", 《郑州师范教育》 * |
肖颖: "基于双目视觉的DIC测量技术研究", 《中国优秀硕士学位论文全文数据库(电子期刊)信息科技辑》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220044420A1 (en) * | 2020-08-10 | 2022-02-10 | National Taiwan University Of Science And Technology | Earthquake monitoring system and earthquake monitoring method |
US11625837B2 (en) * | 2020-08-10 | 2023-04-11 | National Taiwan University Of Science And Technology | Earthquake monitoring system and earthquake monitoring method |
CN112215896A (en) * | 2020-09-01 | 2021-01-12 | 深圳市瑞立视多媒体科技有限公司 | Camera frame data processing method and device for multi-camera calibration and computer equipment |
CN112215896B (en) * | 2020-09-01 | 2024-01-30 | 深圳市瑞立视多媒体科技有限公司 | Multi-camera calibrated camera frame data processing method and device and computer equipment |
CN113203361A (en) * | 2021-04-14 | 2021-08-03 | 甘肃建投科技研发有限公司 | Thickness rapid measurement device for prefabricated wallboard production |
WO2024067435A1 (en) * | 2022-09-30 | 2024-04-04 | 浙江大学 | Video-based multi-object displacement tracking monitoring method and apparatus |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Brilakis et al. | Progressive 3D reconstruction of infrastructure with videogrammetry | |
CN104200086B (en) | Wide-baseline visible light camera pose estimation method | |
CN109035343A (en) | A kind of floor relative displacement measurement method based on monitoring camera | |
CN106323176B (en) | A kind of three-dimensional displacement monitoring method of open-pit slope | |
US20090154793A1 (en) | Digital photogrammetric method and apparatus using intergrated modeling of different types of sensors | |
CN111473739A (en) | Video monitoring-based surrounding rock deformation real-time monitoring method for tunnel collapse area | |
CN103093459B (en) | Utilize the method that airborne LiDAR point cloud data assisted image mates | |
CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
CN107357286A (en) | Vision positioning guider and its method | |
CN106408601B (en) | A kind of binocular fusion localization method and device based on GPS | |
Rumpler et al. | Automated end-to-end workflow for precise and geo-accurate reconstructions using fiducial markers | |
CN104704384A (en) | Image processing method, particularly used in a vision-based localization of a device | |
CN104173054A (en) | Measuring method and measuring device for height of human body based on binocular vision technique | |
CN109685886A (en) | A kind of distribution three-dimensional scenic modeling method based on mixed reality technology | |
CN106033614B (en) | A kind of mobile camera motion object detection method under strong parallax | |
CN110146030A (en) | Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation | |
CN109373908A (en) | A kind of earth surface of side slope system for monitoring displacement and method | |
CN103411587A (en) | Positioning and attitude-determining method and system | |
CN106504287A (en) | Monocular vision object space alignment system based on template | |
Fritsch et al. | Multi-sensors and multiray reconstruction for digital preservation | |
Crispel et al. | All-sky photogrammetry techniques to georeference a cloud field | |
CN104318566B (en) | Can return to the new multi-view images plumb line path matching method of multiple height values | |
CN101685532B (en) | Method for correcting simple linear wide-angle lens | |
Jiang et al. | Determination of construction site elevations using drone technology | |
US20130093880A1 (en) | Height Measurement Apparatus And 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |