CN115205369A - Atmospheric turbulence resistant lamp target image displacement extraction algorithm - Google Patents
Atmospheric turbulence resistant lamp target image displacement extraction algorithm Download PDFInfo
- Publication number
- CN115205369A CN115205369A CN202210931549.7A CN202210931549A CN115205369A CN 115205369 A CN115205369 A CN 115205369A CN 202210931549 A CN202210931549 A CN 202210931549A CN 115205369 A CN115205369 A CN 115205369A
- Authority
- CN
- China
- Prior art keywords
- displacement
- window
- centroid
- lamp target
- extraction algorithm
- 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
- 238000006073 displacement reaction Methods 0.000 title claims abstract description 49
- 238000000605 extraction Methods 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 238000012843 least square support vector machine Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 29
- 238000005457 optimization Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 abstract description 5
- 238000009825 accumulation Methods 0.000 abstract 1
- 238000003384 imaging method Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical group C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Analysis (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of optical image measurement, in particular to an atmospheric turbulence resistant lamp target image displacement extraction algorithm, which comprises the following steps: s1, determining a rough calculation window of a lamp target object in an initial reference image, and calculating the energy of the region; s2, extracting an energy concentration area in a roughing window; s3, detecting a centroid and a gray level square centroid in the effective window; s4, determining a weighted center positioning result of the lamp target in the reference image; s5, repeating S1-S4 in the subsequent deformation graph; s6, calculating the central displacement; the invention provides self-adaptive computing window selection based on energy accumulation, and final weighted center positioning is carried out based on a least square support vector machine, and pixel displacement is obtained through target center positioning results before and after deformation. The displacement extraction algorithm can improve the robustness of the photogrammetry technology to atmospheric turbulence disturbance and the measurement precision of structural displacement.
Description
Technical Field
The invention relates to the technical field of optical image measurement, in particular to an atmospheric turbulence resistant lamp target image displacement extraction algorithm.
Background
Atmospheric disturbances have proven to compromise the accuracy of precision optical measurements such as topography, displacement, and velocity. In the field of precise optical measurement, image restoration and signal filtering methods are commonly adopted at present, which basically do not relate to the optical principle, and the interference elimination effect is limited for the quantitative measurement of the deflection to be carried out in the research. Whereas the correction method by camera system design is not suitable for single-camera measurement applications. The turbulent image processing method widely used in the military field is limited to target detection and cannot be directly applied to displacement measurement. Mahrt et al indicate that atmospheric disturbances can cause blurring and distortion in the target image, thereby increasing target centering errors.
At present, the common center positioning algorithm mainly comprises a centroid method, a fitting method, a least square method and the like. The research of the center positioning algorithm considering the atmospheric disturbance is mainly suitable for artificially designed targets or targets with uniform gray distribution inherent to the surface of the structure, is not suitable for improving the atmospheric disturbance resistance of a light source target positioning algorithm, calculating window self-adaption determination methods proposed by Yang and the like from the angle of image processing, and a real imaging region identification method based on the normal distribution '3 sigma' principle in the field of infrared target radiation intensity measurement, and effectively inhibits the interference of fuzzy degradation on the determination of a calculating region. However, the above studies are only applicable to light source targets with regular shapes such as circles or rectangles, and neglect the influence of imaging distortion that may occur. In addition, the single positioning algorithm is difficult to guarantee the center detection accuracy under the distortion condition. For the latter, a weighted positioning method arises. Because the method has high requirement on the determination of the weight, and the internal link mechanism between the distorted target center and the characteristics of the distorted target center after being influenced by atmospheric disturbance is complex, wang et al propose a target center weighting positioning method based on BPNN to perform weighting processing on center detection results obtained based on various algorithms. However, this study still suffers from two drawbacks: on one hand, the BPNN is based on an empirical risk minimization criterion, and has the defects of 'overfitting', poor popularization capability of a model, difficult determination of a network topological structure, easy falling into local optimization and the like. The LS-SVM adopts the least square linear system error sum of squares as a loss function, and replaces inequality constraint with equality constraint, so that the solving process is changed into the solution of a group of equality equations, the problem of quadratic programming which takes time for solving is avoided, the training speed is greatly accelerated, the LS-SVM does not need to give fitting precision in advance any more, and the LS-SVM has higher prediction precision; on the other hand, the existing BPNN-based weighted positioning method still determines an imaging area by using a fixed threshold, and ignores the influence of the imaging area change caused by atmospheric disturbance on the positioning result.
Disclosure of Invention
The invention aims to provide an atmospheric turbulence resistant lamp target image displacement extraction algorithm, which starts from the influence effect of atmospheric turbulence on lamp target imaging, respectively starts from effective calculation window selection and weighted positioning, and reduces the influence of imaging blur and distortion.
The technical scheme adopted by the invention is as follows:
an atmospheric turbulence resistant lamp target image displacement extraction algorithm comprises the following steps:
s1: a rough calculation window mxn of the lamp target object is determined in the initial reference map and the energy E of the region is calculated as formula (1): g (x, y) represents the gray scale at the pixel coordinates (x, y).
S2: and extracting an energy concentration area in the roughing window. The region needs to satisfy the conditions of both formula (2) and formula (3), i.e., when the gray level g (x, y) is greater than the threshold value g T Calculating energy, and if the energy is not satisfied, readjusting g T Until both conditions are satisfied. Where η represents the CCD camera diffuse speckle energy concentration (η = 80%). g T Indicating a new window decision threshold after the energy concentration is met.
S3: and detecting the centroid and the gray level square centroid in the effective window. The centroid calculation uses formula (4), where the gray scale is the binary gray scale.
For the gray-scale square centroid calculation, the gray-scale value of the pixel itself needs to be adopted. In order to reduce the influence of noise, gray level optimization needs to be performed on the extracted pixels in the effective window, and a specific calculation process is shown in formula (5). The gray scale square centroid calculation adopts formula (6).
S4: a weighted centering result of the lamp target object in the reference map is determined. The centroid (x) obtained 1 ,y 1 ) Sum gray square centroid (x) 2 ,y 2 ) With the true center (x) 0 ,y 0 ) The weighted relationship between them is expressed as:
in the formula eta i Representing the weights of the two positioning results. In actual measurement, the internal link mechanism between the target center detection result and the real center position after being influenced by atmospheric disturbance is complex, and the invention provides that the weight is solved by means of the fitting function of the least square support vector machine LS-SVM algorithm.
S5: S1-S4 are repeated in subsequent deformation maps. However, when determining the energy concentration area in the subsequent deformation map, the threshold g needs to be adjusted on the basis of the assumption that the concentration energy of the target imaging is kept unchanged T The aim is to reduce turbulence causing fluctuations in the effective window. Subsequent weighted centering is then performed within the validity window.
S6: the center displacement is calculated. Assume that the weighted center location result in the reference picture frame _0 is: (x) w0 ,y w0 ) The weighted center location result in the warped map frame _ i is: (x) wi ,y wi ) Then the displacement component is:
in the step S4, a least squares support vector machine method (LS-SVM) is used for solving the weight value. Before the actual structure displacement measurement, images of some on-site stable lamp target objects need to be collected in advance for learning of the LS-SVM. Because in the actual structure, almost no completely immobile target exists, the invention selects the target near the support or the foundation, and takes the minimum variance of the displacement time course of the target as the target optimization function:
and obtaining the optimal weight value through pre-learning. Approximately, the turbulence parameter change in the region in a short time is considered to be small, so the weight value can be directly used for displacement extraction of a subsequent target.
Has the advantages that: compared with the prior art, the method has the following advantages: the method can greatly reduce the monitoring error of the lamp target image displacement caused by atmospheric turbulence, so that the photogrammetry technology has higher precision and robustness against complex environments when being applied to the displacement measurement of the structure.
Drawings
FIG. 1 is a diagram of the basic process of the lamp target image displacement extraction of the present invention.
FIG. 2 is a schematic view of the center positioning of an image of an LED lamp target during displacement measurement of a cable-stayed bridge according to the method of the present invention.
Fig. 3 is a basic flowchart of the LS-SVM of the present invention.
FIG. 4 is a graph of the displacement calculation results of the embodiment of the present invention.
FIG. 5 is a field of a plausibility test for improving the accuracy of algorithm center positioning: test equipment arrangement
(a) A camera arrangement; (b) a displacement table and a target; (c) a camera field of view.
FIG. 6 shows the results of the verification test of the present invention: (a) stationary target positioning results for different algorithms; (b) Of different algorithms
And (5) positioning a moving target.
Detailed Description
For the purpose of enhancing the understanding of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and examples, which are provided for the purpose of illustration only and are not intended to limit the scope of the present invention.
As shown in fig. 1, an atmospheric turbulence resistant lamp target image displacement extraction algorithm includes the following steps:
s1, determining a rough calculation window of a lamp target object in an initial reference image, and calculating the energy of the region;
s2, extracting an energy concentration area in a roughing window;
s3, detecting the centroid and the gray level square centroid in the effective window;
s4, determining a weighted center positioning result of the lamp target in the reference image;
s5, repeating S1-S4 in the subsequent deformation graph;
and S6, calculating the central displacement.
Taking the extraction of the target image displacement of the LED lamp of a cable-stayed bridge as an example, the method comprises the following steps:
s1: in the initial reference map, a rough calculation window M × N (fig. 2 (a)) of the pedestal position light target object is determined, and the energy E of the region is calculated.
S2: the energy concentration region is extracted in the roughing window (fig. 2 (c)).
S3: and detecting the centroid and the gray level square centroid in the effective window.
S4: using the weighted positioning coordinates with the obtained centroid (x) 1 ,y 1 ) Sum gray square centroid (x) 2 ,y 2 ) With the true center (x) 0 ,y 0 ) The expression of (A) is:
in the formula eta i Representing the weights of the two positioning results.
S5: at subsequent times, to ensure that the concentrated energy does not become a criterion, the image threshold is adjusted, an adaptive energy concentrated region (i.e., an effective computation window) is obtained, and S3-S4 are repeated.
S6: and solving the optimal weight. Based on the steps, the pixel displacement of the stable target point at each moment is obtained, the displacement variance is minimum to serve as an optimization objective function, the optimal weight value is fitted by means of the LS-SVM algorithm of the least square support vector machine, and a flow chart is shown in FIG. 3.
S7: for the lamp target at the deformed cross-sectional position, S1 to S5 are repeated and the weight value obtained based on S6 is substituted. Image displacement of the lamp target was obtained (fig. 4).
To further illustrate the superiority of the proposed method, experimental verification was performed, as shown in fig. 5, with the experiment being performed on a campus
The ground is a cement pavement, and the temperature is high in summer of 7 months, which causes the ground to be close to the ground
The severity of atmospheric disturbances. The 850nm infrared lamp with 60W target is adopted in the test, and a band-pass filter is additionally arranged in front of the lens
Can effectively filter the influence of natural stray light below 850 nm. The range of the electric displacement table is 500mm, and the precision is 0.1mm.
S1, continuously collecting the target 50 meters away from the camera and keeping the target still for 5 minutes at the collection frequency of 2 frames per second
Extracting the pixel coordinates of the target center by a gray square centroid method and a centroid method respectively, and then adopting an LS-SVM method to perform
1 1 The displacement fluctuation variance obtained by the weighted coordinates is zero as a target, and the weight value result of the fitting coordinates is as follows: λ =0.4, λ =
0.6, the positioning results of the above three center extraction algorithms are shown in fig. 6 (a).
S2, the target is moved in a stepped manner by 1mm under the control of the displacement table. Using grey square respectively
The centroid method, centroid method and weighting method calculate the vertical displacement of the target, and the result is shown in fig. 6 (b). Data of the displacement table are
And the real reference value obviously has better accuracy and stability of the displacement measurement value obtained by adopting the weighted positioning algorithm.
The lamp target image deformation measuring method can effectively reduce the lamp target displacement measuring error caused by atmospheric turbulence. Also is favorable for the popularization and the application of the night measurement of the displacement of the structures such as a bridge and the like
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. An atmospheric turbulence resistant lamp target image displacement extraction algorithm is characterized by comprising the following steps:
s1, determining a rough calculation window of a lamp target object in an initial reference image, and calculating the energy of the region;
s2, extracting an energy concentration area in a roughing window;
s3, detecting a centroid and a gray level square centroid in the effective window;
s4, determining a weighted center positioning result of the lamp target in the reference image;
s5, repeating S1-S4 in subsequent deformation graphs;
and S6, calculating the center displacement.
2. The atmospheric turbulence resistant lamp target image displacement extraction algorithm of claim 1, wherein in the step S1, a rough calculation window mxn of the lamp target object is determined in the initial reference image, and the energy E of the region is calculated using formula (1), wherein g (x, y) represents the gray scale at pixel coordinates (x, y):
3. the atmospheric turbulence resistant lamp target image displacement extraction algorithm as claimed in claim 2, wherein in the step S2, an energy concentration region, i.e. an effective calculation window, is extracted in a roughing window, and the region needs to satisfy the conditions of formula (2) and formula (3) simultaneously, i.e. when the gray level g (x, y) is greater than the threshold g T Calculating energy, and if the energy is not satisfied, readjusting g T Until both conditions are met, where η represents CCD camera diffuse spot energy concentration, η =80%, g T Indicating a new window decision threshold after the energy concentration is satisfied;
4. the atmospheric turbulence resistant lamp target image displacement extraction algorithm as claimed in claim 3, wherein in the step S3, centroid and gray scale square centroid detection is performed in the effective window, the centroid calculation adopts formula (4), and the gray scale is binary gray scale;
for the calculation of the gray square centroid, the gray value of the pixel itself needs to be adopted, in order to reduce the influence of noise, the gray optimization needs to be performed on the pixel in the extracted effective window, the specific calculation process is as shown in formula (5), and the calculation of the gray square centroid adopts formula (6):
5. the atmospheric turbulence resistant lamp target image displacement extraction algorithm as claimed in claim 4, wherein in the step S4, a least square support vector machine method LS-SVM is adopted for solving the weighted value, before the actual structure displacement measurement, images of some stable lamp target targets in the field are collected in advance for learning of the LS-SVM, targets near a support or a foundation are selected, and the variance of the target displacement time course is the minimum as a target optimization function:
and obtaining the optimal weight value through pre-learning.
6. The atmospheric turbulence resistant lamp target image displacement extraction algorithm as recited in claim 5, wherein in the step S4, weighted center positioning results of the lamp target in the reference map are determined, and the centroid (x) is obtained 1 ,y 1 ) And the gray square centroid (x) 2 ,y 2 ) With the true center (x) 0 ,y 0 ) The weighted relationship between them is expressed as:
in the formula eta i Representing the weights of the two positioning results.
7. The atmospheric turbulence resistant lamp target image displacement extraction algorithm as claimed in claim 6, wherein in the step S6, the central displacement is calculated, assuming that the weighted center positioning result in the reference image frame _0 is: (x) w0 ,y w0 ) The weighted center location result in the warped map frame _ i is: (x) wi ,y wi ) Then the displacement component is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210931549.7A CN115205369B (en) | 2022-08-03 | 2022-08-03 | Anti-atmospheric turbulence lamp target image displacement extraction algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210931549.7A CN115205369B (en) | 2022-08-03 | 2022-08-03 | Anti-atmospheric turbulence lamp target image displacement extraction algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115205369A true CN115205369A (en) | 2022-10-18 |
| CN115205369B CN115205369B (en) | 2024-04-02 |
Family
ID=83586450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210931549.7A Active CN115205369B (en) | 2022-08-03 | 2022-08-03 | Anti-atmospheric turbulence lamp target image displacement extraction algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115205369B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4499597A (en) * | 1982-03-29 | 1985-02-12 | Hughes Aircraft Company | Small-object location utilizing centroid accumulation |
| US4727562A (en) * | 1985-09-16 | 1988-02-23 | General Electric Company | Measurement of scatter in x-ray imaging |
| US5022089A (en) * | 1990-01-19 | 1991-06-04 | Wilson Monti R | Method and apparatus for fast registration using crosshair register marks |
| US20040208385A1 (en) * | 2003-04-18 | 2004-10-21 | Medispectra, Inc. | Methods and apparatus for visually enhancing images |
| US7860344B1 (en) * | 2005-05-06 | 2010-12-28 | Stochastech Corporation | Tracking apparatus and methods using image processing noise reduction |
| CN107610102A (en) * | 2017-08-24 | 2018-01-19 | 东南大学 | A kind of Displacement measuring method based on Tikhonov regularizations |
| CN109035326A (en) * | 2018-06-19 | 2018-12-18 | 北京理工大学 | High-precision location technique based on sub-pix image recognition |
| CN110864587A (en) * | 2019-11-08 | 2020-03-06 | 中国科学院长春光学精密机械与物理研究所 | Seeker aiming positioning method and aiming positioning system |
| CN111050652A (en) * | 2017-09-12 | 2020-04-21 | 皇家飞利浦有限公司 | Spectral (multi-energy) image data for image-guided applications |
| CA3038176A1 (en) * | 2019-03-27 | 2020-09-27 | 4DM Inc. | Object motion mapping from single-pass electro-optical satellite imaging sensors |
| CN112712542A (en) * | 2020-12-25 | 2021-04-27 | 武汉大学 | Foundation cloud picture motion prediction method combining block matching and optical flow method |
| CN112735163A (en) * | 2020-12-25 | 2021-04-30 | 北京百度网讯科技有限公司 | Method for determining static state of target object, road side equipment and cloud control platform |
| CN113192121A (en) * | 2021-04-16 | 2021-07-30 | 西安理工大学 | Light spot center sliding weighting centroid positioning method under atmospheric turbulence |
| US20210383563A1 (en) * | 2021-06-21 | 2021-12-09 | University Of Electronic Science And Technology Of China | Method for quantitatively identifying the defects of large-size composite material based on infrared image sequence |
| CN114108717A (en) * | 2021-12-09 | 2022-03-01 | 上海勘察设计研究院(集团)有限公司 | Foundation pit enclosure top deformation monitoring system and method based on vision measurement |
| CN114166178A (en) * | 2021-12-09 | 2022-03-11 | 上海勘察设计研究院(集团)有限公司 | Real-time deformation monitoring method and system for frame section of tunnel shield machine under construction |
-
2022
- 2022-08-03 CN CN202210931549.7A patent/CN115205369B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4499597A (en) * | 1982-03-29 | 1985-02-12 | Hughes Aircraft Company | Small-object location utilizing centroid accumulation |
| US4727562A (en) * | 1985-09-16 | 1988-02-23 | General Electric Company | Measurement of scatter in x-ray imaging |
| US5022089A (en) * | 1990-01-19 | 1991-06-04 | Wilson Monti R | Method and apparatus for fast registration using crosshair register marks |
| US20040208385A1 (en) * | 2003-04-18 | 2004-10-21 | Medispectra, Inc. | Methods and apparatus for visually enhancing images |
| US7860344B1 (en) * | 2005-05-06 | 2010-12-28 | Stochastech Corporation | Tracking apparatus and methods using image processing noise reduction |
| CN107610102A (en) * | 2017-08-24 | 2018-01-19 | 东南大学 | A kind of Displacement measuring method based on Tikhonov regularizations |
| CN111050652A (en) * | 2017-09-12 | 2020-04-21 | 皇家飞利浦有限公司 | Spectral (multi-energy) image data for image-guided applications |
| CN109035326A (en) * | 2018-06-19 | 2018-12-18 | 北京理工大学 | High-precision location technique based on sub-pix image recognition |
| CA3038176A1 (en) * | 2019-03-27 | 2020-09-27 | 4DM Inc. | Object motion mapping from single-pass electro-optical satellite imaging sensors |
| CN110864587A (en) * | 2019-11-08 | 2020-03-06 | 中国科学院长春光学精密机械与物理研究所 | Seeker aiming positioning method and aiming positioning system |
| CN112712542A (en) * | 2020-12-25 | 2021-04-27 | 武汉大学 | Foundation cloud picture motion prediction method combining block matching and optical flow method |
| CN112735163A (en) * | 2020-12-25 | 2021-04-30 | 北京百度网讯科技有限公司 | Method for determining static state of target object, road side equipment and cloud control platform |
| CN113192121A (en) * | 2021-04-16 | 2021-07-30 | 西安理工大学 | Light spot center sliding weighting centroid positioning method under atmospheric turbulence |
| US20210383563A1 (en) * | 2021-06-21 | 2021-12-09 | University Of Electronic Science And Technology Of China | Method for quantitatively identifying the defects of large-size composite material based on infrared image sequence |
| CN114108717A (en) * | 2021-12-09 | 2022-03-01 | 上海勘察设计研究院(集团)有限公司 | Foundation pit enclosure top deformation monitoring system and method based on vision measurement |
| CN114166178A (en) * | 2021-12-09 | 2022-03-11 | 上海勘察设计研究院(集团)有限公司 | Real-time deformation monitoring method and system for frame section of tunnel shield machine under construction |
Non-Patent Citations (2)
| Title |
|---|
| RIBEIRO D, ET AL: "Non-contact measurement of the dynamic displacement of railway bridges using an advanced video-based system", ENGINEERING STRUCTURES, 31 December 2014 (2014-12-31), pages 164 - 180 * |
| 于姗姗: "基于相机扰动校正的桥梁结构变形测量方法与应用", 东南大学, 15 May 2022 (2022-05-15), pages 1 - 139 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115205369B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615653B (en) | Leakage water area detection and identification method based on deep learning and visual field projection model | |
| CN109472822A (en) | Dimension of object measurement method based on depth image processing | |
| CN105279772B (en) | A kind of trackability method of discrimination of infrared sequence image | |
| CN101887586A (en) | Self-adaptive angular-point detection method based on image contour sharpness | |
| CN114359841B (en) | Video water level identification method based on space-time average | |
| CN110889829A (en) | Monocular distance measurement method based on fisheye lens | |
| CN111914695B (en) | Tidal bore monitoring method based on machine vision | |
| CN110261069B (en) | Detection method for optical lens | |
| CN109359604B (en) | Method for identifying instrument under shadow interference facing inspection robot | |
| CN114719873B (en) | Low-cost fine map automatic generation method and device and readable medium | |
| CN117808796B (en) | Gear surface damage detection method based on computer vision | |
| CN113899349B (en) | Sea wave parameter detection method, equipment and storage medium | |
| CN109671084B (en) | Method for measuring shape of workpiece | |
| CN114565565A (en) | Method for positioning sub-pixels in center of vision measurement target | |
| CN115546072B (en) | Image distortion correction method | |
| CN115205369B (en) | Anti-atmospheric turbulence lamp target image displacement extraction algorithm | |
| CN117315547A (en) | Visual SLAM method for solving large duty ratio of dynamic object | |
| CN112508995A (en) | Coal flow real-time dynamic metering method based on TOF camera | |
| CN116958092A (en) | Power transmission line sag rapid measurement method based on improved stereo matching algorithm | |
| CN114926524B (en) | Method for improving measuring accuracy of effective shielding area of infrared smoke screen | |
| CN114565564B (en) | Fitting centroid sub-pixel positioning method based on correlation method threshold iteration | |
| CN114693659B (en) | Copper pipe surface cleaning effect evaluation method and system based on image processing | |
| CN207319290U (en) | One kind interference far field beam test system | |
| CN115797411A (en) | Method for online identifying deformation of cable bridge of hydropower station by using machine vision | |
| CN110796660B (en) | Image definition evaluation method for airport runway |
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 |