CN117115189A - Track 3D geometric form monitoring method and system based on machine vision - Google Patents
Track 3D geometric form monitoring method and system based on machine vision Download PDFInfo
- Publication number
- CN117115189A CN117115189A CN202310835808.0A CN202310835808A CN117115189A CN 117115189 A CN117115189 A CN 117115189A CN 202310835808 A CN202310835808 A CN 202310835808A CN 117115189 A CN117115189 A CN 117115189A
- Authority
- CN
- China
- Prior art keywords
- image
- track
- relative displacement
- monitoring
- machine vision
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000006073 displacement reaction Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000005622 photoelectricity Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
-
- 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
- G06T2207/10016—Video; Image sequence
- G06T2207/10021—Stereoscopic video; Stereoscopic image sequence
-
- 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
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a track 3D geometrical form monitoring method and system based on machine vision, wherein the method comprises the steps of continuously shooting a monitored track through a depth camera, marking an image at a first moment, intercepting a frame of image every other time period, respectively converting a reference image and the monitored image into numerical matrixes, performing image digital processing on the numerical matrixes, extracting and drawing track boundaries to obtain a reference 3D geometrical form image and a monitored 3D geometrical form image, and comparing the monitored 3D geometrical form image with the reference 3D geometrical form image to obtain horizontal relative displacement and vertical relative displacement of the track at different moments. The system comprises a depth camera, a processing module, a display module and an alarm module. The application can realize real-time, high-precision and non-contact monitoring of the 3D geometric form of the track and improve the safety and stability of the track.
Description
Technical Field
The application relates to the technical field of track monitoring, in particular to a track 3D geometric form monitoring method and system based on machine vision.
Background
Track monitoring refers to the use of various sensors or devices to locate, measure, evaluate, control, etc. the track to ensure the safety and stability of the track. The track monitoring has important significance in the fields of railways, subways, high-speed railways and the like, for example, the track monitoring is utilized to detect and early warn the abnormality such as track settlement, deformation, cracks, abrasion and the like.
The rail in the subway tunnel is used as an important facility for bearing the running of the train, settlement and displacement of different degrees can occur in long-term operation, and the rail is deformed to different degrees, so that the running posture position of the train is changed, and safety accidents such as vehicle body inclination, limit invasion, derailment and the like can occur when the rail is severely overrun. Therefore, the 3D geometry monitoring and dynamic management of the track in the subway tunnel are required, the relative displacement of the track is measured regularly, and the deformation condition of the track is mastered.
The prior art for monitoring structural deformation in a subway tunnel adopts contact type layout monitoring equipment on a track to complete monitoring, such as a monitoring method based on a displacement sensor, a monitoring method based on an eddy current type displacement sensor, a monitoring method based on a light splitting interference type laser displacement meter, a monitoring method based on a contact type sensor and the like, converts displacement into electric signals by utilizing the principles of electromagnetism, capacitance, resistance, photoelectricity and the like, and outputs the electric signals, and can be used for measuring parameters such as horizontal displacement, vertical displacement, inclination angle and the like of the track.
The method has the defects that the contact state and stability between the train and the track can be influenced during the running process of the train, so that the monitoring equipment is damaged or disabled, or the safe running of the train is influenced; in addition, the nonlinear monitoring result obtained by the method needs to be subjected to nonlinear correction or conversion when the track deformation is calculated, so as to eliminate nonlinear errors or convert nonlinear data into linear data. Therefore, an additional error may be introduced in calculating the amount of track deformation.
Disclosure of Invention
The application provides a machine vision-based track 3D geometric form monitoring method and system, which solve the problems of non-linearity, low accuracy, poor instantaneity, great influence by environment and the like of a track monitoring result in the prior art.
In order to achieve the above purpose, the technical scheme adopted by the application is as follows:
in one aspect, the application provides a machine vision-based track 3D geometry monitoring method, comprising:
continuously shooting the monitoring track through a depth-of-field camera;
marking the image at the first moment to be used as a reference image for subsequent comparison;
intercepting a frame of image at every other time period as a monitoring image at the moment;
respectively converting all monitoring images of the reference image into numerical matrixes;
performing image digitization on the numerical matrix, extracting and drawing a track boundary to obtain a reference 3D geometrical morphology image and a monitoring 3D geometrical morphology image;
and comparing the monitored 3D geometrical form image with the reference 3D geometrical form image to obtain the horizontal relative displacement and the vertical relative displacement of the track at different moments.
Further, the method further comprises the following steps:
setting a threshold range of horizontal relative displacement and vertical relative displacement of the track;
when the horizontal relative displacement or the vertical relative displacement of the track at a certain moment is detected to exceed a threshold range, an alarm is triggered.
Further, image digitization processing is performed on the logarithmic matrix, and track boundaries are extracted and drawn, specifically including:
filtering the numerical matrix to remove irrelevant or interference data;
performing dimension reduction on the numerical matrix, and converting the color image into a gray image;
threshold segmentation is carried out on the numerical matrix, a track image is extracted, and background interference is removed;
carrying out fuzzy processing on the track image to eliminate noise points;
performing edge detection on the track image to obtain track edge information;
reconstructing the track edge information, and drawing a track boundary image under the real image.
Further, edge detection is performed on the track image to obtain track edge information, which specifically includes: and determining low threshold and high threshold parameter values for each track image, and scanning the track images pixel by using a Canny function to complete edge detection.
Further, reconstructing the track edge information, and drawing a track boundary image under a real image, which specifically comprises: and processing the track edge information by using HoughLinesP and line functions to obtain a track boundary image under the real image.
In another aspect, the present application provides a machine vision based rail 3D geometry monitoring system comprising:
the depth-of-field camera is used for continuously shooting the monitoring track;
a processing module coupled to the depth camera and configured to perform the method of claim 1;
and the display module is connected with the processing module and is used for displaying the reference 3D geometric form image and monitoring the 3D geometric form image as well as the horizontal relative displacement and the vertical relative displacement.
Further, the method further comprises the following steps:
and the alarm module is connected with the processing module, and when the processing module judges that the track has abnormal deformation according to the horizontal relative displacement and the vertical relative displacement, the alarm module sends an alarm signal.
Furthermore, the depth camera selects a flight time camera.
Compared with the prior art, the application has the following beneficial effects:
according to the application, a machine vision technology is adopted, and depth information of each pixel point on the surface of the track is obtained through the depth camera, so that the non-contact type monitoring of the 3D geometric form of the track is realized, and the defect of using a contact type sensor or equipment to monitor the track is avoided.
The method adopts an image digital processing technology to carry out the steps of filtering, dimension reduction, threshold segmentation, blurring, edge detection, reconstruction and the like on the digital matrix, thereby extracting and drawing the track boundary, obtaining a reference 3D geometrical form image and a monitoring 3D geometrical form image, further realizing high-precision linear monitoring of the 3D geometrical form of the track, and avoiding the extra error caused by processing the monitoring result by using a nonlinear conversion or correction technology in the prior art.
The method adopts an image comparison technology to register and calculate the monitored 3D geometric form image and the reference 3D geometric form image, so as to obtain the horizontal relative displacement and the vertical relative displacement of the track at different moments, and realize the real-time monitoring of the 3D geometric form of the track.
Of course, it is not necessary for all of the above advantages to be achieved simultaneously in practicing the various aspects of the application.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the method of embodiment 1 of the present application.
Fig. 2 is a schematic view of tunnel field layout according to embodiment 1 of the present application.
Fig. 3 is a schematic representation of the deformation of the 3D geometry of the track.
Detailed Description
The application will be described in further detail below with reference to the drawings by means of specific embodiments. Wherein like elements in different embodiments are numbered alike in association. In the following embodiments, numerous specific details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted, or replaced by other elements, materials, or methods in different situations. In some instances, related operations of the present application have not been shown or described in the specification in order to avoid obscuring the core portions of the present application, and may be unnecessary to persons skilled in the art from a detailed description of the related operations, which may be presented in the description and general knowledge of one skilled in the art.
Furthermore, the described features, operations, or characteristics of the description may be combined in any suitable manner in various embodiments. Also, various steps or acts in the method descriptions may be interchanged or modified in a manner apparent to those of ordinary skill in the art. Thus, the various orders in the description and drawings are for clarity of description of only certain embodiments, and are not meant to be required orders unless otherwise indicated.
The numbering of the components itself, e.g., "S1", "S2", etc., is used herein only to distinguish between the described objects and does not have any sequential or technical meaning. The term "coupled" as used herein includes both direct and indirect coupling (coupling), unless otherwise indicated.
Example 1:
referring to fig. 1, a machine vision-based track 3D geometry monitoring method, in this embodiment, is used for track detection in a subway tunnel, and specifically includes the following steps:
s1, continuously shooting a monitoring track in a subway tunnel through a depth camera;
s2, intercepting a frame of image at intervals of a time period to serve as a monitoring image of the moment, and marking the image of the first moment to serve as a reference image for subsequent comparison;
s3, respectively converting the reference image and the monitoring image into numerical matrixes, and distributing a depth value of each pixel point for each numerical matrix so as to process the track image;
s4, filtering the logarithmic matrix, and eliminating irrelevant or interference data;
s5, performing dimension reduction on the digital matrix, reducing the RGB 3 dimension to 2 dimension, and converting the color image into a gray image;
the function formula of the dimension reduction process is as follows:
gray_image＝cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
s6, carrying out threshold segmentation on the numerical matrix, extracting a track image and removing background interference;
s7, denoising the orbit image by using a convolutional neural network function or a Gaussian blur function, and eliminating noise points in the image;
a fuzzy function formula:
output2＝cv2.GaussianBlur(gray_image,(9,9),5)；
plt.imshow(output2)
plt.show()
s8, determining low threshold values and high threshold value parameter values for each track image, and scanning the track images pixel by using a Canny function to finish edge detection;
s9, processing the track edge information by using HoughLinesP and line functions to obtain a track boundary image under the real image of the tunnel;
s10, performing edge covering processing on an area to be shielded in the track boundary image by using a mask_of_image function;
s11, comparing the reference 3D geometrical form image with the monitored 3D geometrical form image to obtain horizontal relative displacement and vertical relative displacement of the track at different moments.
S12, setting a threshold range of horizontal relative displacement and vertical relative displacement of the track;
and S13, when the horizontal relative displacement or the vertical relative displacement of the track at a certain moment is detected to exceed a threshold range, triggering an alarm.
Example 2:
the present embodiment provides an example Python program for implementing machine vision measurement of rail geometry using OpenCV library:
import cv2
import numpy as np
p1, reading the image and converting it into a grayscale image:
img＝cv2.imread('railway.jpg')
gray＝cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
p2, gaussian filtering and Canny edge detection are carried out on the gray level image:
blur＝cv2.GaussianBlur(gray,(5,5),0)
edges＝cv2.Canny(blur,50,150,apertureSize＝3)
p3, carrying out Hough line transformation to detect a straight line:
lines＝cv2.HoughLines(edges,1,np.pi/180,200)
p4, traversing each detected straight line:
for line in lines:
rho,theta＝line[0]
a＝np.cos(theta)
b＝np.sin(theta)
x0＝a*rho
y0＝b*rho
x1＝int(x0+1000*(-b))
y1＝int(y0+1000*(a))
x2＝int(x0-1000*(-b))
y2＝int(y0-1000*(a))
and P5, drawing the detected straight line on the original image:
cv2.line(img,(x1,y1),(x2,y2),(0,0,255),2)
p6, displaying a result image:
cv2.imshow('result',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
in this example, an image of a train track is first read and converted to a grayscale image. Then, gaussian filtering and Canny edge detection are performed on the gray image so as to detect the edges of the tracks. Next, all straight lines are detected using hough line transformation, and each straight line is drawn. Finally, the rendered resulting image is displayed to facilitate viewing the geometry of the rail, making any necessary measurements to help understand the geometry of the rail and any deformation.
Example 3:
referring to fig. 2, the present embodiment provides a machine vision-based track 3D geometry monitoring device, which includes:
a depth camera 1 for continuously shooting the monitoring track 5;
a processing module 2, connected to the depth camera 1, and configured to implement the method of 1;
a display module 3 connected to the processing module 2 for displaying the reference 3D geometry image and monitoring the 3D geometry image and the horizontal and vertical relative displacements;
and the alarm module is connected with the processing module 2, and when the processing module 2 judges that the track has abnormal deformation according to the horizontal relative displacement and the vertical relative displacement, an alarm signal is sent to the alarm module.
In this embodiment, a time-of-flight (ToF) camera is selected as the upper wall of the tunnel 4 to which the depth camera 1 is fixed. Time-of-flight (ToF) cameras typically include an infrared emitter that emits light and an infrared receiver that receives light reflected from objects. With these rays, the depth camera can calculate the distance of each pixel from the camera, thereby generating a depth image.
Referring to fig. 3, fig. 3 is a schematic diagram of monitoring the deformation of the 3D geometry of the track. In the figure, Δx represents a displacement variable of the monitor rail in the horizontal direction, and Δy represents a displacement variable of the monitor rail in the vertical direction. Setting the threshold range of horizontal relative displacement as delta Xmin to delta Xmax, setting the threshold range of vertical relative displacement as delta Ymin to delta Ymax, and determining specific numerical values according to the design specification and safety standard of the track;
comparing the horizontal relative displacement DeltaX and the vertical relative displacement DeltaY of the monitoring track with a threshold range, and judging whether abnormal deformation exists or not;
if the delta Xmin is less than or equal to delta X and less than or equal to delta Xmax, and the delta Ymin is less than or equal to delta Y and less than or equal to delta Ymax, the monitoring track is not abnormal deformed, and the monitoring at the next moment is continued.
If DeltaX < DeltaXminor DeltaX > DeltaXmaxor DeltaY < DeltaYminor DeltaY > DeltaYmax, the monitoring track is deformed beyond the normal range, and an alarm module is triggered and needs to be processed in time.
In this embodiment, the alarm module is configured to start an audible and visual alarm, a vibration alarm or a short message alarm to remind relevant personnel to process in time.
When the processing module 2 judges that the horizontal relative displacement or the vertical relative displacement of the track exceeds a preset threshold value, an alarm signal is sent to the alarm module, and the alarm module selects a proper alarm mode to alarm according to the content of the alarm signal. For example, if the content of the alarm signal is that the horizontal relative displacement of the track exceeds a threshold value, the alarm module starts an audible and visual alarm and a vibration alarm in the monitoring room to remind on-site monitoring personnel to verify dangerous situations; meanwhile, the alarm module starts a short message alarm and sends related information to the mobile phone number of the appointed person.
The foregoing description of the application has been presented for purposes of illustration and description, and is not intended to be limiting. Several simple deductions, modifications or substitutions may also be made by a person skilled in the art to which the application pertains, based on the idea of the application.
Claims (8)
1. The track 3D geometry monitoring method based on machine vision is characterized by comprising the following steps of:
continuously shooting the monitoring track through a depth-of-field camera;
marking the image at the first moment to be used as a reference image for subsequent comparison;
intercepting a frame of image at every other time period as a monitoring image at the moment;
respectively converting all monitoring images of the reference image into numerical matrixes;
performing image digitization on the numerical matrix, extracting and drawing a track boundary to obtain a reference 3D geometrical morphology image and a monitoring 3D geometrical morphology image;
and comparing the monitored 3D geometrical form image with the reference 3D geometrical form image to obtain the horizontal relative displacement and the vertical relative displacement of the track at different moments.
2. The machine vision based orbit 3D geometry monitoring method of claim 1, further comprising:
setting a threshold range of horizontal relative displacement and vertical relative displacement of the track;
when the horizontal relative displacement or the vertical relative displacement of the track at a certain moment is detected to exceed a threshold range, an alarm is triggered.
3. The machine vision based orbit 3D geometry monitoring method according to claim 1 or 2, wherein the image digitizing process is performed on the logarithmic matrix, and the orbit boundaries are extracted and drawn, specifically comprising:
filtering the numerical matrix to remove irrelevant or interference data;
performing dimension reduction on the numerical matrix, and converting the color image into a gray image;
threshold segmentation is carried out on the numerical matrix, a track image is extracted, and background interference is removed;
carrying out fuzzy processing on the track image to eliminate noise points;
performing edge detection on the track image to obtain track edge information;
reconstructing the track edge information, and drawing a track boundary image under the real image.
4. The machine vision based rail 3D geometry monitoring method of claim 3, wherein edge detection is performed on the rail image to obtain rail edge information, and the method specifically comprises: and determining low threshold and high threshold parameter values for each track image, and scanning the track images pixel by using a Canny function to complete edge detection.
5. The machine vision based track 3D geometry monitoring method of claim 3, wherein reconstructing track edge information and drawing a track boundary image under a real image specifically comprises: and processing the track edge information by using HoughLinesP and line functions to obtain a track boundary image under the real image.
6. Machine vision based rail 3D geometry monitoring system, characterized by comprising:
the depth-of-field camera is used for continuously shooting the monitoring track;
a processing module coupled to the depth camera and configured to perform the method of claim 1;
and the display module is connected with the processing module and is used for displaying the reference 3D geometric form image and monitoring the 3D geometric form image as well as the horizontal relative displacement and the vertical relative displacement.
7. The machine vision based rail 3D geometry monitoring system of claim 6, further comprising:
and the alarm module is connected with the processing module, and when the processing module judges that the track has abnormal deformation according to the horizontal relative displacement and the vertical relative displacement, the alarm module sends an alarm signal.
8. The machine vision based orbit 3D geometry monitoring system of claim 6, wherein the depth of field camera is a time of flight camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310835808.0A CN117115189A (en) | 2023-07-10 | 2023-07-10 | Track 3D geometric form monitoring method and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310835808.0A CN117115189A (en) | 2023-07-10 | 2023-07-10 | Track 3D geometric form monitoring method and system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117115189A true CN117115189A (en) | 2023-11-24 |
Family
ID=88800959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310835808.0A Pending CN117115189A (en) | 2023-07-10 | 2023-07-10 | Track 3D geometric form monitoring method and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115189A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303549A (en) * | 2015-06-29 | 2016-02-03 | 北京格灵深瞳信息技术有限公司 | Method of determining position relation between detected objects in video image and device |
| CN109089047A (en) * | 2018-09-29 | 2018-12-25 | Oppo广东移动通信有限公司 | Control method and apparatus, the storage medium, electronic equipment of focusing |
| CN112697064A (en) * | 2021-03-24 | 2021-04-23 | 北京大成国测科技有限公司 | Intelligent track deformation identification system based on vision and laser radar |
| CN112866675A (en) * | 2019-11-12 | 2021-05-28 | Oppo广东移动通信有限公司 | Depth map generation method and device, electronic equipment and computer-readable storage medium |
| WO2021141338A1 (en) * | 2020-01-09 | 2021-07-15 | 씨드로닉스 주식회사 | Device and method for monitoring ship and harbor |
| CN113610786A (en) * | 2021-07-27 | 2021-11-05 | 中国科学院光电技术研究所 | Track deformation monitoring method based on visual measurement |
| CN114076568A (en) * | 2022-01-19 | 2022-02-22 | 中铁第一勘察设计院集团有限公司 | Air-ground-depth integrated visual slope automatic monitoring system and method |
| US20220073113A1 (en) * | 2020-09-04 | 2022-03-10 | Avante International Technology, Inc. | Real-time rail wear and defect monitoring system employing distance measuring devices |
| CN114913131A (en) * | 2022-04-20 | 2022-08-16 | 北京交通大学 | Vertical absolute and relative vertical deformation detection method for ballastless track structure |
| CN115082398A (en) * | 2022-06-17 | 2022-09-20 | 上海铁路北斗测量工程技术有限公司 | Railway track deformation detection method and system and readable storage medium |
| KR20220133453A (en) * | 2021-03-25 | 2022-10-05 | (주)한울전력기술 | Mobile unmanned reobot operating system linked with location-based system using acoustic sensor and control method thereof |
| KR102500879B1 (en) * | 2022-10-21 | 2023-02-17 | 손인규 | Real Time Track Distortion Measuring System and Its Method |
| CN115982809A (en) * | 2022-12-06 | 2023-04-18 | 中铁四局集团第五工程有限公司 | Shield tunnel central axis self-fitting method, shield tunnel central axis self-fitting system, computer and storage medium |
-
2023
- 2023-07-10 CN CN202310835808.0A patent/CN117115189A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303549A (en) * | 2015-06-29 | 2016-02-03 | 北京格灵深瞳信息技术有限公司 | Method of determining position relation between detected objects in video image and device |
| CN109089047A (en) * | 2018-09-29 | 2018-12-25 | Oppo广东移动通信有限公司 | Control method and apparatus, the storage medium, electronic equipment of focusing |
| CN112866675A (en) * | 2019-11-12 | 2021-05-28 | Oppo广东移动通信有限公司 | Depth map generation method and device, electronic equipment and computer-readable storage medium |
| WO2021141338A1 (en) * | 2020-01-09 | 2021-07-15 | 씨드로닉스 주식회사 | Device and method for monitoring ship and harbor |
| US20220073113A1 (en) * | 2020-09-04 | 2022-03-10 | Avante International Technology, Inc. | Real-time rail wear and defect monitoring system employing distance measuring devices |
| WO2022051270A1 (en) * | 2020-09-04 | 2022-03-10 | Avante International Technology, Inc. | Real-time rail wear and defect monitoring system employing distance measuring devices |
| CN112697064A (en) * | 2021-03-24 | 2021-04-23 | 北京大成国测科技有限公司 | Intelligent track deformation identification system based on vision and laser radar |
| KR20220133453A (en) * | 2021-03-25 | 2022-10-05 | (주)한울전력기술 | Mobile unmanned reobot operating system linked with location-based system using acoustic sensor and control method thereof |
| CN113610786A (en) * | 2021-07-27 | 2021-11-05 | 中国科学院光电技术研究所 | Track deformation monitoring method based on visual measurement |
| CN114076568A (en) * | 2022-01-19 | 2022-02-22 | 中铁第一勘察设计院集团有限公司 | Air-ground-depth integrated visual slope automatic monitoring system and method |
| CN114913131A (en) * | 2022-04-20 | 2022-08-16 | 北京交通大学 | Vertical absolute and relative vertical deformation detection method for ballastless track structure |
| CN115082398A (en) * | 2022-06-17 | 2022-09-20 | 上海铁路北斗测量工程技术有限公司 | Railway track deformation detection method and system and readable storage medium |
| KR102500879B1 (en) * | 2022-10-21 | 2023-02-17 | 손인규 | Real Time Track Distortion Measuring System and Its Method |
| CN115982809A (en) * | 2022-12-06 | 2023-04-18 | 中铁四局集团第五工程有限公司 | Shield tunnel central axis self-fitting method, shield tunnel central axis self-fitting system, computer and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| ZHOUJIE WU 等: "Three-dimensional shape and deformation measurement on complex structure parts", 《SCIENTIFIC REPORTS》, 31 December 2022 (2022-12-31) * |
| 范先铮: "基于机器视觉的铁路轨道监测方法", 《北京测绘》, vol. 36, no. 12, 31 December 2022 (2022-12-31) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107678036B (en) | Vehicle-mounted non-contact type contact net geometric parameter dynamic detection system and method | |
| US6909514B2 (en) | Wheel profile inspection apparatus and method | |
| CN104655043B (en) | One kind is based on contour registration method in the measurement of machine vision train guide rail profile | |
| CN107703513B (en) | Non-contact net relative position detection method based on image processing | |
| CN111289261B (en) | Detection method for in-warehouse bottom piece | |
| CN103984961A (en) | Image detection method for detecting foreign matter at bottom of vehicle | |
| CN109238756B (en) | Dynamic image detection equipment and detection method for freight car operation fault | |
| CN110174059B (en) | Monocular image-based pantograph height and pull-out value measuring method | |
| CN210719028U (en) | Contact net geometric parameters detection device based on three-dimensional point cloud | |
| CN113554667B (en) | Three-dimensional displacement detection method and device based on image recognition | |
| CN110322428B (en) | Method and device for detecting tunnel diseases and electronic equipment | |
| Lu et al. | Vision-based structural displacement measurement under ambient-light changes via deep learning and digital image processing | |
| CN115931874A (en) | Carrying type magnetic suspension intelligent dynamic inspection system and gap width detection method | |
| CN107621229B (en) | Real-time railway track width measurement system and method based on area array black-and-white camera | |
| CN110567397B (en) | Fastener spring tongue separation detection method | |
| CN113610786A (en) | Track deformation monitoring method based on visual measurement | |
| CN117115189A (en) | Track 3D geometric form monitoring method and system based on machine vision | |
| CN102069821B (en) | Measuring method for non-contact steel rail sagging surface | |
| CN113819841A (en) | Machine vision-based plate shape detection device and detection method thereof | |
| JP3228603B2 (en) | Image monitoring device and its use | |
| Rikhotso et al. | 3D rail modelling and measurement for rail profile condition assessment | |
| CN109238149B (en) | Vehicle body attitude detection device and contact line dynamic offset detection system | |
| CN107150701A (en) | Train wheel physical dimension measuring method and its detection means | |
| CN205607332U (en) | Measuring device is striden to bridge crane crane span structure based on machine vision | |
| CN110634122A (en) | Fastener elastic strip displacement detection 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 |