CN106767337B - Machine vision-based inclination angle reading method for rail inspection trolley verification platform - Google Patents
Machine vision-based inclination angle reading method for rail inspection trolley verification platform Download PDFInfo
- Publication number
- CN106767337B CN106767337B CN201710043215.5A CN201710043215A CN106767337B CN 106767337 B CN106767337 B CN 106767337B CN 201710043215 A CN201710043215 A CN 201710043215A CN 106767337 B CN106767337 B CN 106767337B
- Authority
- CN
- China
- Prior art keywords
- rail inspection
- inspection trolley
- machine vision
- verification platform
- computer
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/24—Measuring arrangements characterised by the use of mechanical techniques for measuring angles or tapers; for testing the alignment of axes
- G01B5/243—Measuring arrangements characterised by the use of mechanical techniques for measuring angles or tapers; for testing the alignment of axes for measuring chamfer
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Machines For Laying And Maintaining Railways (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention provides a machine vision-based inclination angle reading method for a rail inspection trolley verification platform, which comprises a computer, a camera, an auxiliary light source, a rail inspection trolley verification platform and a movable gauge block combination, wherein the computer is provided with halcon machine vision image processing software: the camera is connected with the computer through a network cable, the movable gauge block combination is placed between the upper supporting block and the lower cushion block of the rail inspection trolley verification platform, and the camera is matched with the auxiliary light source and faces the movable gauge block combination. The machine vision-based data verification method disclosed by the invention replaces the traditional manual data reading based on the machine vision, so that the objectivity and the accuracy in the verification process are effectively ensured, and the verification result is more scientific.
Description
Technical Field
The invention relates to an inclination angle reading device of a rail inspection trolley verification platform, in particular to a machine vision-based inclination angle reading method of the rail inspection trolley verification platform.
Background
At present, when the general rail inspection trolley inspection platform is used for inspecting the ultrahigh height, manual operation is mainly adopted to read data. In general, a person may have discriminant errors when reading data, and particularly, in some verification items for repeated measurement, the verification work is completed once by the same method, and eyes are fatigued, so that each verification has slight difference, and the verification result error is large. Human eye detection has a serious defect, namely subjectivity caused by emotion, and a verification result can change along with the mood of a verifier, so that the objectivity of the verification result is poor. After the block quantity value is manually measured, the data is converted into data which really requires by a formula, and the process is relatively complicated. The identification result data is mainly recorded by people and lacks of scientific rigor. In the past, data of the current verification situation is not kept after verification, and the data processing is carried out by the personal calculation, so that the persuasion of the verification certificate is not high.
Disclosure of Invention
Aiming at the problems, the invention provides the inclination angle reading method of the rail inspection trolley verification platform based on machine vision, which replaces the traditional manual reading of data, effectively ensures the objectivity and the accuracy in the verification process and enables the verification result to be more scientific.
The invention relates to a machine vision-based inclination angle reading device for a rail inspection trolley verification platform, which comprises: the system comprises a computer, a camera, an auxiliary light source, a rail inspection trolley verification platform and a movable gauge block combination, wherein the computer is provided with halcon machine vision image processing software: the camera is connected with the computer through a network cable, the movable gauge block combination is placed between the upper supporting block and the lower cushion block of the rail detection trolley verification platform, and the camera is matched with the auxiliary light source and faces the movable gauge block combination.
Furthermore, the camera is a gigabit network industrial camera.
Further, the computer is provided with a gigabit network card.
Further, the method of the device comprises the following steps:
(1) And selecting an auxiliary light source according to the environment, and transmitting the shot activity gauge block combined image to the computer in real time through a network cable by the camera.
(2) The halcon machine vision image processing software of the computer carries out the following processing steps on the image:
A. screening the images, extracting the images at a certain moment, and selecting an R channel image with high contrast;
B. selecting an ROI for the screenshot of the R channel image;
C. performing OSTU automatic threshold processing on the ROI, segmenting a rail inspection trolley verification platform and an activity gauge block combination from an image, and selecting a maximum communication area for filtering;
D. performing rectangular element corrosion operation on the movable gauge block combination, performing minimum external rectangle operation on the upper and lower areas obtained by corrosion, wherein the vertical distance between the two minimum external rectangles is H 1 。
(3) The computer processes the obtained data and stores the calculation result, and the data processing method comprises the following steps:
the height H of the combination of the movable gauge blocks is as follows:
H＝H 1 -H 2 -H 3
wherein H 2 Height H of upper supporting block of platform for rail inspection trolley verification 3 And the height of a lower base plate of the platform is detected for the rail detection trolley. The computer simulates all the combined heights of the activity gauge blocks, and compares the difference with the measured height H of the activity gauge block combination to obtain the height H of the activity gauge block combination with the minimum difference 4 As a correction value.
The inclination angle theta of the rail inspection trolley verification platform is as follows:
and L is the length of the bevel edge of the known rail inspection trolley verification platform.
The invention has the following beneficial effects: based on machine vision measurement, artificial discrimination errors are avoided, the accuracy of repeated examination timing is improved, subjectivity is removed, manual reading data and conversion data are removed, automatic data processing and storage are carried out, the result is more scientific, and persuasion of the examination result is improved.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of the present invention;
FIG. 2 is a diagram illustrating an operation effect of a minimum circumscribed rectangle according to an embodiment of the present invention;
fig. 3 is a schematic measurement diagram of the rail inspection trolley verification platform according to the embodiment of the invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The invention relates to a machine vision-based inclination angle reading device for a rail inspection trolley verification platform, which comprises: the detection system comprises a computer, a camera, an auxiliary light source, a rail inspection trolley detection platform and a movable gauge block combination, wherein the computer is provided with halcon machine vision image processing software: the camera is connected with the computer through a network cable, the movable gauge block combination is placed between the upper supporting block and the lower cushion block of the rail detection trolley verification platform, and the camera is matched with the auxiliary light source and faces the movable gauge block combination.
The test selects a camera as a gigabit industrial camera, selects a computer processor as Inter corei3-2310M,2.10GHz,4G RAM, and has the test picture size of 960 × 720pixels and ROI pixels of 37829pixels, and the average time of the test is as follows: (194.8 +170.0+ 162.0)/3 =175.3ms, which meets the speed requirement of measurement.
Known as H 2 ＝50mm，H 3 ＝20mm，L＝1505mm。
The method of the device comprises the following steps:
(1) And selecting an auxiliary light source according to the environment, and transmitting the shot activity gauge block combined image to the computer in real time through a network cable by the camera.
(2) And the halcon machine vision image processing software of the computer carries out the following processing steps on the image:
A. screening the images, extracting the images at a certain moment, and selecting an R channel image with high contrast;
B. selecting an ROI (region of interest) for the screenshot of the R channel image;
C. performing OSTU automatic threshold processing on the ROI, segmenting a rail inspection trolley verification platform and an activity gauge block combination from an image, and selecting a maximum communication area for filtering;
D. performing rectangular element corrosion operation on the movable gauge block combination, performing minimum circumscribed rectangle operation on the upper and lower regions obtained by corrosion, and obtaining a vertical distance H between two minimum circumscribed rectangles as shown in FIG. 2 1 ＝120.24mm。
(3) The computer processes the obtained data and stores the calculation result, and the data processing method comprises the following steps:
the height H of the combination of the movable gauge blocks is as follows:
H＝H 1 -H 2 -H 3 ＝120.24-50-20＝50.24mm
the computer simulates all the combined heights of the activity gauge blocks, and compares the difference values with the measured height H of the activity gauge block combination to obtain the height correction value H of the activity gauge block combination with the minimum difference value 4 ＝50.01mm。
The inclination angle theta of the rail inspection trolley verification platform is as follows:
the foregoing embodiments are merely illustrative of the principles of the invention and its efficacy, and are not to be construed as limiting the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all modifications and variations be included herein by the present inventors without departing from the spirit and scope of the invention, which is defined by the following claims.
Claims (3)
1. The method for reading the inclination angle of the rail inspection trolley verification platform based on machine vision uses a rail inspection trolley verification platform inclination angle reading device based on machine vision, and the reading device comprises a computer provided with halcon machine vision image processing software, a camera, an auxiliary light source, the rail inspection trolley verification platform and a movable gauge block combination: the camera passes through the net twine and is connected with the computer, and the combination of activity gage block is placed between the last supporting block and the lower bolster of rail inspection dolly verification platform, and camera cooperation auxiliary light source is just facing activity gage block combination, its characterized in that: the reading method comprises the following steps:
(1) Selecting an auxiliary light source according to the environment, and transmitting the shot activity gauge block combined image to a computer in real time by a camera through a network cable;
(2) The image is processed by the halcon machine vision image processing software of the computer according to the following steps:
A. screening the images, extracting the images at a certain moment, and selecting an R channel image with high contrast;
B. selecting an ROI for the screenshot of the R channel image;
C. performing OSTU automatic threshold processing on the ROI, segmenting a rail inspection trolley verification platform and an activity gauge block combination from an image, and selecting a maximum connected region for filtering;
D. performing rectangular element corrosion operation on the movable gauge block combination, performing minimum external rectangle operation on the upper and lower areas obtained by corrosion, wherein the vertical distance between the two minimum external rectangles is H 1 ；
(3) The computer processes the obtained data and stores the calculation result, and the data processing method comprises the following steps:
the height H of the combination of the movable gauge blocks is as follows:
H＝H 1 -H 2 -H 3
wherein H 2 Height H of upper supporting block of platform for rail inspection trolley verification 3 The height of a lower base plate of the platform is verified for the rail inspection trolley, the computer simulates all the combined heights of the movable gauge blocks, and the difference value of the combined heights of the movable gauge blocks is compared with the measured height H of the combination of the movable gauge blocks to obtain the height H of the combination of the movable gauge blocks with the minimum difference value 4 As the correction value, there is used,
the inclination angle theta of the rail inspection trolley verification platform is as follows:
and L is the length of the bevel edge of the known rail inspection trolley verification platform.
2. The machine vision-based rail inspection trolley verification platform inclination angle reading method as claimed in claim 1, characterized in that: the camera is a gigabit network industrial camera.
3. The machine vision-based rail inspection trolley verification platform inclination angle reading method as claimed in claim 1, characterized in that: the computer is provided with a gigabit network card.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710043215.5A CN106767337B (en) | 2017-01-19 | 2017-01-19 | Machine vision-based inclination angle reading method for rail inspection trolley verification platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710043215.5A CN106767337B (en) | 2017-01-19 | 2017-01-19 | Machine vision-based inclination angle reading method for rail inspection trolley verification platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106767337A CN106767337A (en) | 2017-05-31 |
| CN106767337B true CN106767337B (en) | 2023-03-28 |
Family
ID=58945234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710043215.5A Active CN106767337B (en) | 2017-01-19 | 2017-01-19 | Machine vision-based inclination angle reading method for rail inspection trolley verification platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106767337B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107671858A (en) * | 2017-10-11 | 2018-02-09 | 上海交通大学 | A kind of Halcon vision processing systems and method for being integrated in the control of Labview robots |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104792542A (en) * | 2015-04-08 | 2015-07-22 | 吉林大学 | Automobile brake performance detecting system calibrating apparatus and automobile brake performance detecting system calibrating method based on stereoscopic vision |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020183995A1 (en) * | 2001-06-05 | 2002-12-05 | Alastair Veitch | System and method for simulating railroad rail testing |
| DE10345861A1 (en) * | 2003-10-01 | 2005-05-12 | Db Netz Ag | Method for non-contact measurement of angles and distances |
| CN101021417B (en) * | 2007-03-21 | 2010-05-19 | 于起峰 | Long straight rail geometric parameter photogrammetry |
| CN101264766B (en) * | 2008-05-15 | 2010-04-07 | 中国人民解放军国防科学技术大学 | Orbit geometry parameter image measuring device and method for substituting chord wire method |
| CN101592473B (en) * | 2009-06-19 | 2010-10-13 | 济南蓝动激光技术有限公司 | Laser measuring instrument for track lifting and lining for railway works |
| CN103264711B (en) * | 2013-05-31 | 2016-06-08 | 株洲时代电子技术有限公司 | A kind of orbital-elements measurement system |
| CN203615919U (en) * | 2013-11-27 | 2014-05-28 | 广州计量检测技术研究院 | Railway gauging rule detector and automatic measuring device thereof |
| CN103790108B (en) * | 2013-12-16 | 2015-09-09 | 重庆岩安科技有限公司 | Bridge comprehensive detection device |
| CN204388805U (en) * | 2014-12-31 | 2015-06-10 | 北京二七轨道交通装备有限责任公司 | A kind of rail detects dolly |
| CN104652202B (en) * | 2015-02-13 | 2016-08-24 | 中铁第一勘察设计院集团有限公司 | For examining and determine the measurement apparatus of high speed railway track measuring instrument |
-
2017
- 2017-01-19 CN CN201710043215.5A patent/CN106767337B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104792542A (en) * | 2015-04-08 | 2015-07-22 | 吉林大学 | Automobile brake performance detecting system calibrating apparatus and automobile brake performance detecting system calibrating method based on stereoscopic vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106767337A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109507192B (en) | Magnetic core surface defect detection method based on machine vision | |
| CN109870461B (en) | Electronic components quality detection system | |
| CN108445011B (en) | Defect detection system and method based on deep learning | |
| WO2018000731A1 (en) | Method for automatically detecting curved surface defect and device thereof | |
| CN106226157B (en) | Concrete structure member crevices automatic detection device and method | |
| CN107798279B (en) | Face living body detection method and device | |
| CN110210448B (en) | Intelligent face skin aging degree identification and evaluation method | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN106934800A (en) | A kind of metal plate and belt detection method of surface flaw and device based on YOLO9000 networks | |
| CN106442556A (en) | Device and method for detecting surface defects of perforated plate workpiece | |
| CN111415339B (en) | Image defect detection method for complex texture industrial product | |
| US11315229B2 (en) | Method for training defect detector | |
| CN106371148A (en) | Millimeter wave image-based human body foreign substance detection method and system | |
| US11657644B2 (en) | Automatic ruler detection | |
| CN107644417B (en) | Method for detecting appearance defect of strain gauge | |
| US20220076021A1 (en) | System and method for automatic visual inspection with deep learning | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| JP7226493B2 (en) | Contact wire wear inspection method | |
| TW202219494A (en) | A defect detection method and a defect detection device | |
| CN106767337B (en) | Machine vision-based inclination angle reading method for rail inspection trolley verification platform | |
| CN107832696B (en) | A kind of electric operating object in situ security feature identifying system | |
| US20170140206A1 (en) | Symbol Detection for Desired Image Reconstruction | |
| CN117571721A (en) | Method and device for detecting surface defects of circuit board bonding pad and storage medium | |
| CN113012104A (en) | Device fin quantity detection method, controller, device and storage medium | |
| JP2006254330A (en) | Quantitative evaluation method of gray scale image on paper or sheet-like base material |
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 |