CN115082555A - High-precision displacement real-time measurement system and method of RGBD monocular camera - Google Patents

High-precision displacement real-time measurement system and method of RGBD monocular camera Download PDF

Info

Publication number
CN115082555A
CN115082555A CN202210563873.8A CN202210563873A CN115082555A CN 115082555 A CN115082555 A CN 115082555A CN 202210563873 A CN202210563873 A CN 202210563873A CN 115082555 A CN115082555 A CN 115082555A
Authority
CN
China
Prior art keywords
camera
time
identification object
real
displacement
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
CN202210563873.8A
Other languages
Chinese (zh)
Inventor
高林
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.)
Xian Aerospace Propulsion Testing Technique Institute
Original Assignee
Xian Aerospace Propulsion Testing Technique Institute
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 Xian Aerospace Propulsion Testing Technique Institute filed Critical Xian Aerospace Propulsion Testing Technique Institute
Priority to CN202210563873.8A priority Critical patent/CN115082555A/en
Publication of CN115082555A publication Critical patent/CN115082555A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention provides a high-precision real-time displacement measurement system and method of an RGBD monocular camera, and solves the problem that self-calibration in the displacement measurement process cannot be directly realized through monocular vision in the prior art. The measuring system disclosed by the invention comprises a target identification module, an RGBD camera measuring module and a displacement real-time calculating module; the specific method comprises the following steps: obtaining pixel coordinates of the central points of the left and right side identification objects by a target identification module by adopting an angular point detection algorithm; measuring by adopting an RGBD camera measuring module to obtain a world coordinate value of the central point of the left recognition object; and calculating a camera matrix according to the pixel coordinate and the world coordinate value of the central point of the left identification object by adopting a displacement real-time calculation module, further completing self-calibration of the camera, and calculating the world coordinate value of the central point of the right identification object by combining the pixel coordinate of the central point of the right identification object and the calculated camera matrix, thereby realizing high-precision real-time measurement of displacement.

Description

High-precision displacement real-time measurement system and method of RGBD monocular camera
Technical Field
The invention belongs to the field of non-contact measurement of displacement of an object in a three-dimensional space, and particularly relates to a high-precision displacement real-time measurement system and method of an RGBD monocular camera.
Background
With the continuous improvement of the deep learning theory and the rapid development of the computer vision technology, many new methods for measuring object displacement in a non-contact manner appear, such as a monocular vision-based measurement method, a binocular stereo vision-based measurement method, an RGBD camera-based vision measurement method and the like. In recent years, especially non-contact measurement of displacement and other physical quantities based on RGBD cameras has progressed most rapidly, which benefits from the rapid development of deep learning algorithms and vision chips.
The non-contact measurement and analysis of the three-dimensional displacement field in the aviation and aerospace fields are always concerned, and how to realize the high-precision measurement of the three-dimensional displacement field by using the existing hardware and vision chips is a challenging research subject. At present, algorithms for measuring object displacement by combining with an RGBD monocular camera are fewer, and the precision difference of measurement results obtained by different measurement algorithms is larger.
Disclosure of Invention
The invention aims to provide a high-precision real-time displacement measurement system and a high-precision real-time displacement measurement method for an RGBD monocular camera, and mainly solves the problem that the prior art cannot measure a three-dimensional displacement field in a high-precision and rapid self-calibration mode.
To achieve the above object, the present invention provides the following solutions:
a high-precision displacement real-time measurement system of an RGBD monocular camera is characterized in that: the system comprises a target identification module, an RGBD camera measurement module and a displacement real-time calculation module;
the target identification module is used for identifying and obtaining the pixel coordinates of the central point of the identification object; the RGBD camera measuring module is used for measuring the pixel coordinate of the center point of the identification object to obtain a world coordinate value of the center point of the identification object; the displacement real-time calculation module is used for obtaining a real-time camera matrix M through the pixel coordinate of the central point of the identification object, the world coordinate value and the known internal reference matrix of the camera, and further realizing high-precision displacement real-time measurement of the identification object.
In addition, the invention also provides a high-precision displacement real-time measurement method of the RGBD monocular camera, which specifically comprises the following steps:
s1, marking the left side identification object and the right side identification object;
s2, recognizing the pixel coordinate (u) of the center point of the left recognized object by the target recognition module 1 ,v 1 )；
Defining a world coordinate system O w -X w Y w Z w In which O is w Z w Is the main lightAn axial direction;
defining an image coordinate system o' -uv, wherein u represents an X direction and v represents a Y direction;
s3, using the RGBD camera measurement module to determine the pixel coordinate (u) identified in S2 1 ,v 1 ) Measuring to obtain the world coordinate value P of the central point of the left identification object w1 Said P is w1 ＝(X w1 ，Y w1 ，Z w1 )；
S4, based on the pixel coordinate (u) identified in S2 1 ,v 1 ) And the world coordinate value P measured at S3 w1 Calculating a camera matrix M of the RGBD camera through a displacement real-time calculation module, and further completing self-calibration of the camera;
s5, adopting the method of S2 to identify the pixel coordinate (u) of the center point of the right identification object 2 ,v 2 ) And the world coordinate value P of the center point of the right recognition object is obtained by using the value of the camera matrix M obtained in S4 w2 Said P is w2 ＝(X w2 ，Y w2 ，Z w2 )；
S6, defining the world coordinate values of the left side identification object and the right side identification object at the time 0 as P w1 And P w2 ；
Defining the world coordinate values of the left side identification object and the right side identification object at the time t as P respectively w1 ' and P w2 ', wherein P w1 '＝(X w1 '，Y w1 '，Z w1 ')，P w2 '＝(X w2 '，Y w2 '，Z w2 ')；
Then the real-time displacement of the left side recognized object and the right side recognized object on the X axis from time 0 to time t is: WYx ═ X w1 ' - X w1 |+|X w2 ' - X w2 And the real-time displacement of the left side identification object and the right side identification object on the Y axis from the time 0 to the time t is as follows: WYy ═ Y w1 ' - Y w1 |+|Y w2 ' - Y w2 And completing the high-precision displacement real-time measurement of the left side identification object and the right side identification object.
Further, in S4, the camera matrix M is calculated in real time according to the movement of the camera position, and the calculation formula is:
Figure BDA0003657035670000021
k is an internal reference matrix of the camera, lambda is a coefficient constant, R is an external reference rotation matrix of the camera, and t is an external reference translation matrix of the camera.
Further, in S2, the target identification module identifies by using a corner detection algorithm.
Compared with the prior art, the invention has the beneficial effects that:
1. the high-precision real-time displacement measurement system of the RGBD monocular camera comprises the target identification module, the RGBD camera measurement module and the real-time displacement calculation module, can realize the rapid self-calibration measurement of the RGBD camera on the premise of no calibration module, solves the problem of complicated calibration process in the displacement measurement, and saves the measurement time and the labor cost.
2. According to the high-precision real-time measurement method for the displacement of the RGBD monocular camera, provided by the invention, the high-precision measurement of a three-dimensional displacement field is realized by adopting the high-precision distance measurement function of the RGBD monocular camera, and powerful data support is provided for actual displacement measurement.
3. According to the high-precision real-time displacement measurement method for the RGBD monocular camera, provided by the invention, the real-time measurement of the displacement of the central point of any marker in a three-dimensional space can be realized by identifying the central pixel coordinate of the point to be measured, and the method has better performance than that of a monocular camera which can only realize in-plane two-dimensional displacement measurement.
Drawings
Fig. 1 is a schematic diagram of a high-precision real-time displacement measurement system of an RGBD monocular camera according to the present invention.
FIG. 2 is a flow chart of a high-precision displacement real-time measurement method of an RGBD monocular camera according to the present invention.
FIG. 3 is a camera imaging model diagram of an RGBD measuring module of the high-precision displacement real-time measuring method of the RGBD monocular camera according to the present invention;
FIG. 4 is a labeled original view of a left side identifying object and a right side identifying object in an embodiment of the present invention;
FIG. 5 is a grayscale view of FIG. 4;
FIG. 6 is an extracted view of a left side identifier and a right side identifier in an embodiment of the present invention;
fig. 7 is a measurement result detection diagram of the left side identification object and the right side identification object in the embodiment of the invention;
fig. 8 is a real-time displacement variation diagram of a high-precision displacement real-time measurement method of an RGBD monocular camera according to an embodiment of the present invention;
fig. 9 is a graph showing the displacement variation measured by the pull rod type displacement sensor collected by the PXI data acquisition system.
In the drawings:
the system comprises a 1-RGBD monocular camera high-precision displacement real-time measuring system, a 2-target recognition module, a 3-RGBD camera measuring module and a 4-displacement real-time calculating module.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
As shown in fig. 1, a high-precision displacement real-time measurement system 1 of an RGBD monocular camera includes a target identification module 2, an RGBD camera measurement module 3 and a displacement real-time calculation module 4; the target identification module 2 is used for identifying and obtaining the pixel coordinates of the central point of the identification object; the RGBD camera measuring module 3 is used for obtaining a world coordinate value of the central point of the identification object through pixel coordinate measurement of the central point of the identification object; the displacement real-time calculation module 4 is used for calculating a camera matrix M according to the pixel coordinate of the center point of the left identification object, the world coordinate value of the center point of the left identification object and the known reference matrix K of the camera, and then calculating the world coordinate value of the center point of the right identification object by measuring the pixel coordinate of the center point of the right identification object and the calculated camera matrix M, so that the variation value of the real-time displacement measurement of the left identification object and the right identification object is obtained, and the high-precision displacement real-time measurement of the RGBD monocular camera is realized.
In addition, as shown in fig. 2, the invention further provides a high-precision displacement real-time measurement method of the RGBD monocular camera, which includes the following steps:
and S1, marking the left side identification object and the right side identification object, wherein the left side identification object and the right side identification object refer to any two positions in the surface.
S2, recognizing the pixel coordinate (u) of the center point of the left recognized object by the object recognition module 2 1 ,v 1 ) In this embodiment, the target identification module 2 adopts a corner detection algorithm for identification, and the corner detection algorithm can quickly and accurately identify the required information and provide accurate basic data for subsequent measurement and calculation.
Defining the coordinate system of the camera in the target recognition module as O c -X c Y c Z c In which O is c Is a light center, O c Z c Is the main optical axis direction;
defining a world coordinate system O w -X w Y w Z w In which O is w Z w Is the main optical axis direction;
an image coordinate system o' -uv is defined, where u denotes the X direction and v denotes the Y direction.
S3, measuring the pixel coordinate (u) of S2 by using RGBD camera 1 ,v 1 ) Measuring to obtain the world coordinate value P of the central point of the left identification object w1 In which P is w1 ＝(X w1 ，Y w1 ，Z w1 ) In this step, the RGBD camera measurement module 3 uses an RGBD camera to perform measurement.
As shown in fig. 3, it is a diagram of a camera imaging model of an RGBD camera measurement module.
S4, based on the pixel coordinate (u) of S2 1 ,v 1 ) And the world coordinate value P obtained at S3 w1 And calculating to obtain a camera matrix M of the RGBD camera through the displacement real-time calculation module 4, and further completing the self-calibration of the camera.
In this step, the camera matrix M is calculated in real time according to the movement of the camera position, and the specific calculation formula is:
Figure BDA0003657035670000051
namely:
Figure BDA0003657035670000052
since the target identification module 2 selects a fixed-focus camera, K is a known value, λ is a coefficient constant, R is a camera extrinsic parameter rotation matrix, and t is a camera extrinsic parameter translation matrix.
S5, adopting the method of S2 to identify the pixel coordinate (u) of the center point of the right identification object 2 ,v 2 ) And obtaining the accurate world coordinate value P of the center point of the right side identification object by using the value of the camera matrix M obtained in the step S4 and the calculation formula of the step S4 w2 In which P is w2 ＝(X w2 ，Y w2 ，Z w2 )。
S6, defining the world coordinate value of the left side identification object at the time 0 as P w1 Then P is w1 ＝(X w1 ，Y w1 ，Z w1 )；
Defining the world coordinate value of the right side identification object at the time 0 as P w2 Then P is w2 ＝(X w2 ，Y w2 ，Z w2 )；
Defining the world coordinate value of the left side identification object at the time t as P w1 ', then P w1 '＝(X w1 '，Y w1 '，Z w1 ')；
Defining the world coordinate value of the right side identification object at the time t as P w2 ', then P w2 '＝(X w2 '，Y w2 '，Z w2 ')。
Then the real-time displacement of the left side recognized object and the right side recognized object on the X axis from time 0 to time t is: WYx ═ X w1 ' - X w1 |+|X w2 ' - X w2 And the real-time displacement of the left side identification object and the right side identification object on the Y axis from the time 0 to the time t is as follows: WYy ═ Y w1 ' - Y w1 |+|Y w2 '-Y w2 And then high-precision displacement implementation measurement of the left side identification object and the right side identification object is completed.
The embodiment adopts the mode that black square identification objects are adhered to two sides of the sliding sealing section of the test bed to measure the displacement of the heater in real time. The method adopts an off-line verification mode, the configuration environment of a computer for the algorithm verification is an i5-6200U processor and an 8G memory, an RGBD camera is adopted to shoot a video with a resolution of 1080P and a 30 frame/s, and software is used in a background to intercept heater displacement video data with a size of 1430 multiplied by 878 and a time of about 60 s.
The specific method comprises the following steps: fixing the RGBD camera on a tripod, and adjusting a horizontal adjuster to enable the RGBD camera to be close to a horizontal state; aligning a tripod to the center position of the square marker, and adjusting the distance between the RGBD camera and the recognized objects to enable the two recognized objects to be located at the center position of a viewing frame of the RGBD camera; the image of the mark point of the heater heat test is processed by an algorithm to obtain an original graph shown in fig. 4, a gray scale graph shown in fig. 5, an identification object extraction graph shown in fig. 6, and an identification object detection result graph shown in fig. 7.
As can be seen from fig. 4 to 7, it is possible to measure the heater displacement by attaching black square identifiers to both sides of the sliding seal section of the test bed.
As shown in fig. 7, in the whole time period of the heater thermal test, the identification object in the video moves stably along with the displacement of the sliding seal section, the identification object is clearly extracted from the background image, and the validity of the identification algorithm in the target identification module 2 can be verified. The horizontal axis displacement data is processed and output to a text file, about 0.17s is needed after 60s video data is processed, the algorithm can be verified to meet the real-time requirement of heater displacement measurement, and the displacement data is acquired and processed based on machine vision in fig. 8. The discontinuity in the data is not recognized by the camera, and the figure shows that the displacement is not obvious from 0 frame to 400 frames of images, the displacement (WY) fluctuates around 0mm, the displacement (WY) obtained from 400 frames to 1400 frames of images increases in a parabolic manner, and the overall growth is fast.
As shown in fig. 8, the maximum displacement measured by the RGBD monocular camera-based real-time displacement measurement method of the present invention is 15.7324mm, and the displacement is measured accurately to 0.0001mm, whereas the displacement measurement method based on monocular vision of the conventional method can measure 15.711mm, and the measurement accuracy is measured accurately to 0.001 mm. In addition, the monocular camera can only realize in-plane two-dimensional displacement measurement, and the invention adopts the high-precision distance measurement function of the RGBD monocular camera, can realize the high-precision measurement of a three-dimensional displacement field by identifying the central pixel coordinate of a point to be measured, and provides powerful data support for the actual displacement measurement.
As shown in fig. 9, compared with displacement data measured by a pull rod type displacement sensor acquired by a PXI data acquisition system, the same time interval is selected for comparison, specifically, WY data of 6833 th row to 12833 th row is taken, and 60s time data is obtained by conversion from 100 points/s of sampling rate.
Comparing fig. 8 and fig. 9, the measurement results of the measurement method of the present invention and the measurement method of the pull rod type displacement sensor are compared: the maximum displacement measured by the measuring method is 15.7324mm, the maximum displacement measured by the pull rod type displacement sensor is 15.7330mm, the difference between the two is only 0.0006mm, but the displacement measurement precision reaches 0.001mm, so that the accuracy of the measurement result of the measuring method is verified to be close to the measurement precision of the pull rod type displacement sensor in a wireless mode, but the pull rod type displacement sensor can only realize contact type high-precision displacement measurement, the displacement measuring system based on the RGBD monocular camera completely meets the requirement of non-contact type high-precision displacement measurement, and the final measurement result also provides powerful data support for the non-contact measurement of a three-dimensional displacement field in the fields of aviation and aerospace.
The calibration of the camera is the most basic and important link in systems such as size measurement, pose tracking, defect detection and the like, and the high-precision displacement real-time measurement system and method of the RGBD monocular camera are also suitable for the research of the calibration process of the camera and are within the protection scope of the invention.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents. The present invention is directed to a super-resolution real-time displacement measurement system and method, so as to solve the problems mentioned in the background above.

Claims (4)

1. The utility model provides a high accuracy displacement real-time measurement system of RGBD monocular camera which characterized in that: the system comprises a target identification module (2), an RGBD camera measuring module (3) and a displacement real-time calculating module (4);
the target identification module (2) is used for identifying pixel coordinates of the central point of the identification object;
the RGBD camera measuring module (3) is used for measuring the pixel coordinate of the center point of the identification object to obtain the world coordinate value of the center point of the identification object;
the displacement real-time calculation module (4) is used for obtaining a real-time camera matrix M through the pixel coordinate of the central point of the identification object, the world coordinate value and the known internal reference matrix of the camera, and further realizing high-precision displacement real-time measurement of the identification object.
2. A high-precision displacement real-time measurement method of an RGBD monocular camera is characterized by comprising the following steps:
s1, marking the left side identification object and the right side identification object;
s2, recognizing the pixel coordinate (u) of the center point of the left recognition object by the object recognition module (2) 1 ,v 1 )；
Defining a world coordinate system O w -X w Y w Z w In which O is w Z w Is the main optical axis direction;
defining an image coordinate system o' -uv, wherein u represents an X direction and v represents a Y direction;
s3, adopting RGBD camera measurement module (3) to measure the pixel coordinate (u) identified in S2 1 ,v 1 ) Measuring to obtain the world coordinate value P of the central point of the left identification object w1 Said P is w1 ＝(X w1 ，Y w1 ，Z w1 )；
S4, based on the pixel coordinate (u) identified in S2 1 ,v 1 ) And the world coordinate value P measured at S3 w1 A camera matrix M of the RGBD camera is calculated through the displacement real-time calculation module (4), and then self-calibration of the camera is completed;
s5, adopting the method of S2 to identify the pixel coordinate (u) of the center point of the right identification object 2 ,v 2 ) And using the value of the camera matrix M obtained in S4 to obtain the world coordinate value P of the center point of the right side recognized object w2 Said P is w2 ＝(X w2 ，Y w2 ，Z w2 )；
S6, defining the world coordinate values of the left side identification object and the right side identification object at the time 0 as P w1 And P w2 ；
Defining the world coordinate values of the left side identification object and the right side identification object at the time t as P respectively w1 ' and P w2 ', wherein P w1 '＝(X w1 '，Y w1 '，Z w1 ')，P w2 '＝(X w2 '，Y w2 '，Z w2 ')；
Then the real-time displacement of the left side recognized object and the right side recognized object on the X axis from time 0 to time t is: WYx ═ X w1 '-X w1 |+|X w2 '-X w2 And the real-time displacement of the left side identification object and the right side identification object on the Y axis from the time 0 to the time t is as follows: WYy ═ Y w1 '-Y w1 |+|Y w2 '-Y w2 And completing the high-precision displacement real-time measurement of the left side identification object and the right side identification object.
3. The RGBD monocular camera high-precision displacement real-time measurement method according to claim 2, wherein:
in S4, the camera matrix M is calculated in real time according to the movement of the camera position, and the calculation formula is:
Figure FDA0003657035660000021
k is an internal reference matrix of the camera, lambda is a coefficient constant, R is an external reference rotation matrix of the camera, and t is an external reference translation matrix of the camera.
4. The RGBD monocular camera high-precision displacement real-time measurement method according to claim 3, wherein: in S2, the target identification module (2) identifies by using a corner detection algorithm.
CN202210563873.8A 2022-05-23 2022-05-23 High-precision displacement real-time measurement system and method of RGBD monocular camera Pending CN115082555A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210563873.8A CN115082555A (en) 2022-05-23 2022-05-23 High-precision displacement real-time measurement system and method of RGBD monocular camera

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210563873.8A CN115082555A (en) 2022-05-23 2022-05-23 High-precision displacement real-time measurement system and method of RGBD monocular camera

Publications (1)

Publication Number Publication Date
CN115082555A true CN115082555A (en) 2022-09-20

Family

ID=83249632

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210563873.8A Pending CN115082555A (en) 2022-05-23 2022-05-23 High-precision displacement real-time measurement system and method of RGBD monocular camera

Country Status (1)

Country Link
CN (1) CN115082555A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116681778A (en) * 2023-06-06 2023-09-01 固安信通信号技术股份有限公司 Distance measurement method based on monocular camera

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116681778A (en) * 2023-06-06 2023-09-01 固安信通信号技术股份有限公司 Distance measurement method based on monocular camera
CN116681778B (en) * 2023-06-06 2024-01-09 固安信通信号技术股份有限公司 Distance measurement method based on monocular camera

Similar Documents

Publication Publication Date Title
CN109308693B (en) Single-binocular vision system for target detection and pose measurement constructed by one PTZ camera
CN109658457B (en) Method for calibrating arbitrary relative pose relationship between laser and camera
US8600192B2 (en) System and method for finding correspondence between cameras in a three-dimensional vision system
CN111784778B (en) Binocular camera external parameter calibration method and system based on linear solving and nonlinear optimization
CN108986070B (en) Rock crack propagation experiment monitoring method based on high-speed video measurement
CN107025670A (en) A kind of telecentricity camera calibration method
CN110889829A (en) Monocular distance measurement method based on fisheye lens
CN111210478B (en) Common-view-free multi-camera system external parameter calibration method, medium and system
US20120147149A1 (en) System and method for training a model in a plurality of non-perspective cameras and determining 3d pose of an object at runtime with the same
CN109341668B (en) Multi-camera measuring method based on refraction projection model and light beam tracking method
Mi et al. A vision-based displacement measurement system for foundation pit
CN109269525B (en) Optical measurement system and method for take-off or landing process of space probe
CN102445323A (en) Image processing-based heliostat fault diagnosis method and system
CN113358231B (en) Infrared temperature measurement method, device and equipment
Zhong et al. Stereo-rectification and homography-transform-based stereo matching methods for stereo digital image correlation
CN113763479B (en) Calibration method of refraction and reflection panoramic camera and IMU sensor
CN111709985A (en) Underwater target ranging method based on binocular vision
CN115082555A (en) High-precision displacement real-time measurement system and method of RGBD monocular camera
CN102798380B (en) Method for measuring motion parameters of target in linear array image
CN117197241A (en) Robot tail end absolute pose high-precision tracking method based on multi-eye vision
Su et al. Obtaining obstacle information by an omnidirectional stereo vision system
CN113781581B (en) Depth of field distortion model calibration method based on target loose attitude constraint
CN115307865A (en) Model deformation measurement method for high-temperature hypersonic flow field
CN110766740B (en) Real-time high-precision binocular range finding system and method based on pedestrian tracking
CN115100126A (en) Intelligent sensing method for plane displacement field of bridge structure

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