CN107958452A - A kind of monitoring method of car wheel-set operation posture, apparatus and system - Google Patents
A kind of monitoring method of car wheel-set operation posture, apparatus and system Download PDFInfo
- Publication number
- CN107958452A CN107958452A CN201711157455.4A CN201711157455A CN107958452A CN 107958452 A CN107958452 A CN 107958452A CN 201711157455 A CN201711157455 A CN 201711157455A CN 107958452 A CN107958452 A CN 107958452A
- Authority
- CN
- China
- Prior art keywords
- wheel
- subgraph
- wheel rim
- pair
- detection
- 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
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
Monitoring method, apparatus and system the embodiment of the invention discloses a kind of car wheel-set operation posture.Wherein, method treats the contact picture picture of measuring wheel pair and corresponding rack wheel pair including what acquisition camera gathered in real time, and chooses detection zone on contact picture picture, to generate wheel rim friction detection subgraph and take turns to glitch detection subgraph；Detection subgraph and wheel are rubbed to wheel rim respectively to glitch detection subgraph progress image processing operations, second elemental area of the first elemental area of wheel rim friction detection subgraph printing opacity object block with wheel to glitch detection subgraph printing opacity object block is calculated；According to the numerical value comparison of the first elemental area, wheel rim friction detection zone area and preset first threshold value, according to the second elemental area, wheel to the numerical value comparison of glitch detection region area and default second threshold, obtain treating measuring wheel pair rotates against operation posture.The technical solution that the application provides improves the monitoring accuracy and efficiency of car wheel-set operation posture.
Description
Technical field
The present embodiments relate to rail traffic vehicles wheel to monitoring technical field, transported more particularly to a kind of car wheel-set
The monitoring method of row posture, apparatus and system.
Background technology
With rolling stock technology towards at a high speed, heavy－duty direction develop, to car wheel-set operation detection requirement also get over
Come higher.The part to being in contact for rolling stock with rail is taken turns, same root axle is fitted in by the wheel of left and right two securely
It is upper to be formed, it is the important component of rail traffic vehicles walking system.The effect of wheel pair is to ensure rolling stock on rail
Operation and turn to, subject that the whole from rolling stock is quiet, dynamic loading, and pass it on rail, additionally will be because of circuit
Irregularity, and each parts of the load transmission produced to rolling stock, the quality of its quality directly determine vehicle operation
Safety and quality, to influence the key factor of safe train operation.
Travelled by vehicle system is before entrucking and vehicle is both needed to carry out a series of experiments verification in manufacturing enterprise, generally by traveling
System or vehicle fall to put carries out experimental verification on examination power rack is accompanied.Car wheel-set is with rack wheel to relative rotary motion, mould
Intend endless track to run for car wheel-set.
Accompany examination power rack each wheel to it is front and rear be each equipped with monitoring camera be used for shoot take turns to contact surface relative motion
State, testing crew are maked an inspection tour observation wheel to rotating against operating status by artificial monitor video or manual site, are such as found
Car wheel-set wipes the abnormal operating such as wheel, bounce, and manually circular accompanies examination power rack operating personnel and stops immediately immediately.Manually inspection
That surveys car wheel-set rotates against operation posture, and not only work efficiency is low, but also the uncertainty of artificial detection error, causes to supervise
The accuracy of survey is relatively low.
In consideration of it, how to substitute existing personal monitoring's car wheel-set and rack wheel pair rotates against operation posture, with
The monitoring accuracy and efficiency of car wheel-set operation posture are improved, is those skilled in the art's urgent problem to be solved.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of monitoring method of car wheel-set operation posture, apparatus and system, generation
That has replaced existing personal monitoring's car wheel-set and rack wheel pair rotates against operation posture, improves car wheel-set operation posture
Monitoring accuracy and efficiency.
In order to solve the above technical problems, the embodiment of the present invention provides following technical scheme：
On the one hand the embodiment of the present invention provides a kind of monitoring method of car wheel-set operation posture, including：
Obtain the vehicle that camera gathers in real time and treat contact picture picture of the measuring wheel pair with corresponding rack wheel pair, connect described
Wheel rim friction detection zone and wheel are chosen on contacting surface image to glitch detection region, and generates wheel rim friction detection subgraph and wheel
To glitch detection subgraph；
Rub respectively to the wheel rim and detect subgraph and the wheel to glitch detection subgraph progress image procossing, to carry
Respective printing opacity object block is taken, the first elemental area and the institute of the wheel rim friction detection subgraph printing opacity object block is calculated
State second elemental area of the wheel to glitch detection subgraph printing opacity object block；
According to first elemental area, wheel rim friction detection zone area and the default first numerical value for judging threshold value
Comparison, obtains the wheel rim Frotteurism for treating measuring wheel pair；According to second elemental area, the wheel to glitch detection
Region area and the default second numerical value comparison for judging threshold value, obtain described treating the wheel of measuring wheel pair to bounce state；
According to the wheel rim Frotteurism and the wheel to state of beating, obtain it is described treat measuring wheel pair rotate against operation
Posture；
Wherein, the wheel rim friction detection zone and the wheel are misaligned to glitch detection region；The camera and light
Source transmitter corresponds, and is oppositely arranged on the radially opposite sides for treating each wheel of measuring wheel centering respectively, and the light source is sent out
Camera described in emitter face, the contact point of lower whorl pair in the camera face, the focus of the camera, light source hair
The focus of emitter is located in same parallel lines with the contact point.
Optionally, it is described to be commented according to first elemental area, wheel rim friction detection zone area with default first
Sentence the numerical value comparison of threshold value, obtain the wheel rim Frotteurism enclosed mass for treating measuring wheel pair：
Calculate the first ratio of first elemental area and wheel rim friction detection zone area；
Judge whether first ratio is 0；
If so, then the wheel rim Frotteurism for treating measuring wheel pair is abnormal；If it is not, then judge first ratio whether etc.
Threshold value is judged in described first；
If so, then the wheel rim Frotteurism for treating measuring wheel pair is normal；If it is not, the then wheel rim friction for treating measuring wheel pair
State is subnormal.
Optionally, it is described according to second elemental area, the wheel second comments glitch detection region area with presetting
Sentence the numerical value comparison of threshold value, obtain described treating that the wheel of measuring wheel pair includes bounce state：
Calculate second ratio of second elemental area with the wheel to glitch detection region area；
Judge whether second ratio is 0；
If so, then the wheel for treating measuring wheel pair is normal to bounce state；If it is not, then judge whether second ratio is big
In equal to the described second judge threshold value；
If so, then the wheel for treating measuring wheel pair is abnormal to bounce state；If it is not, then the wheel for treating measuring wheel pair is to bounce
State is subnormal.
Optionally, further include：
When the wheel rim Frotteurism for treating measuring wheel pair or it is described wheel be not normal to bounce state, treat measuring wheel pair to described
Run posture and carry out failure sorted early warning.
Optionally, it is described that figure is carried out to glitch detection subgraph to wheel rim friction detection subgraph and the wheel respectively
As processing includes：
Image denoising is carried out successively to glitch detection subgraph to wheel rim friction detection subgraph and the wheel respectively
Processing, image segmentation, morphological images processing and connected component analysis.
Optionally, it is described respectively to the wheel rim rub detection subgraph and it is described wheel to glitch detection subgraph successively into
The processing of row image denoising, image segmentation, morphological images processing and connected component analysis include：
Rub to the wheel rim and detect subgraph and the wheel to glitch detection subgraph progress Gaussian smoothing, to go
Subgraph and the wheel are detected to the noise spot in glitch detection subgraph picture point imaging process except the wheel rim rubs；
According to default first segmentation threshold, the second segmentation threshold, to the wheel rim friction detection subgraph after smoothing processing
Binarization operation is carried out to glitch detection subgraph with wheel, wheel rim friction detection subgraph and the wheel examine bounce
Survey the respective transmission region of subgraph and light tight region is split；
Etching operation and swollen is carried out to glitch detection subgraph to the wheel rim of binary conversion treatment friction detection subgraph and wheel
Swollen operation, to obtain the wheel rim friction detection subgraph and the wheel to the respective transmission region of glitch detection subgraph and not
Transmission region；
Wheel rim friction detection subgraph by etching operation and expansive working and wheel carry out glitch detection subgraph
Connected component is analyzed, to obtain the wheel rim friction detection subgraph printing opacity object block and the wheel to glitch detection subgraph printing opacity
Position, shape and the size of object block.
Optionally, first elemental area that the wheel rim friction detection subgraph printing opacity object block is calculated and institute
Stating wheel includes the second elemental area of glitch detection subgraph printing opacity object block：
The wheel rim friction detection subgraph printing opacity object block and the wheel are calculated to glitch detection subgraph printing opacity target
Position, shape and the size of block；
Rubbed according to the wheel rim and detect subgraph printing opacity object block and the wheel to glitch detection subgraph printing opacity target
Position, shape and the size of block, calculate the first elemental area of the wheel rim friction detection subgraph printing opacity object block；
Position, shape and size according to the wheel to glitch detection subgraph printing opacity object block, calculate the wheel to jumping
Second elemental area of dynamic detection subgraph printing opacity object block.
On the other hand the embodiment of the present invention provides a kind of monitoring device of car wheel-set operation posture, including：
Subgraph generation module, measuring wheel pair and corresponding rack wheel pair are treated for obtaining the vehicle that camera gathers in real time
Contact picture picture, chooses wheel rim friction detection zone and wheel to glitch detection region on the contact picture picture, and generates wheel
Edge friction detection subgraph and wheel are to glitch detection subgraph；
Image processing module, subgraph and the wheel are detected to glitch detection subgraph for rubbing respectively to the wheel rim
Image procossing is carried out, to extract respective printing opacity object block, the wheel rim friction detection subgraph printing opacity object block is calculated
The first elemental area and the wheel to the second elemental area of glitch detection subgraph printing opacity object block；
State analyzing module, for rubbing detection zone area with presetting according to first elemental area, the wheel rim
The numerical value comparison of first threshold, obtains the wheel rim Frotteurism for treating measuring wheel pair；According to second elemental area, institute
Numerical value comparison of the wheel to glitch detection region area and default second threshold is stated, obtains the wheel for treating measuring wheel pair to bounce
State；
Wheel, for being taken turns according to the wheel rim Frotteurism with described to state of beating, is judged running posture judgment module
It is described treat measuring wheel pair rotate against operation posture.
The embodiment of the present invention finally additionally provides a kind of monitoring system of car wheel-set operation posture, including：
Multiple light sources transmitter, multiple cameras and processor, the processor is based on performing and being stored in memory
The step of car wheel-set runs posture method as described in preceding any one is realized during calculation machine program；
The number of camera is treat measuring wheel to number twice, and the number of light source emitter is to treat measuring wheel to the two of number
Times, camera is corresponded with light source emitter；
Camera is oppositely arranged on the radially opposite sides for treating each wheel of measuring wheel centering respectively with light source emitter, and light source is sent out
Emitter face camera, the contact point of lower whorl pair in camera face, the focus of camera, the focus of light source emitter with up and down
Wheel butt contact is located in same parallel lines；
Each camera is connected with the processor, and the processor, which is arranged on, accompanies on examination power rack.
Optionally, the light source emitter is infrared light supply transmitter, with the corresponding camera of the light source emitter
For infrared camera.
An embodiment of the present invention provides a kind of monitoring method of car wheel-set operation posture, obtains what camera gathered in real time
Treat the contact picture picture of measuring wheel pair and corresponding rack wheel pair, and detection zone is chosen on contact picture picture, rubbed with generating wheel rim
Detection subgraph and wheel are wiped to glitch detection subgraph；Detection subgraph and wheel are rubbed to wheel rim respectively to glitch detection subgraph
Image processing operations are carried out, to extract respective printing opacity object block, wheel rim friction detection subgraph printing opacity object block is calculated
The first elemental area and wheel to the second elemental area of glitch detection subgraph printing opacity object block；According to the first elemental area,
The numerical value comparison of wheel rim friction detection zone area and preset first threshold value, obtains treating the wheel rim Frotteurism of measuring wheel pair；
According to the second elemental area, wheel to the numerical value comparison of glitch detection region area and default second threshold, obtain treating measuring wheel
To wheel to beat state；According to wheel rim Frotteurism with wheel to state of beating, obtain treating measuring wheel pair rotates against operation appearance
State.
The advantages of technical solution that the application provides, is, based on camera imaging vision detection technology, using being arranged on
Treat that measuring wheel treats upper camera real-time capture on contact picture picture of the measuring wheel pair with corresponding rack wheel pair, by analyzing contact surface
The size comparison of the printing opacity object block area of image detection region, corresponding detection zone area and predetermined threshold value, is treated
The relative rotary motion posture of measuring wheel pair and corresponding rack wheel pair, so that judge to treat whether measuring wheel is abnormal operation posture,
Fully-automatic vehicle wheel is realized to running attitude monitoring, it is low to solve artificial detection car wheel-set row posture work efficiency, and people
The uncertainty of work detection error, the problem of causing accuracy relatively low, improve car wheel-set operation posture monitoring accuracy and
Efficiency, advantageously ensures that the security and stability of vehicle operation.
In addition, the embodiment of the present invention provides corresponding realization device also directed to the monitoring method of car wheel-set operation posture
And system, further such that the method has more practicality, described device and system have the advantages that corresponding.
Brief description of the drawings
, below will be to embodiment or existing for the clearer explanation embodiment of the present invention or the technical solution of the prior art
Attached drawing is briefly described needed in technology description, it should be apparent that, drawings in the following description are only this hair
Some bright embodiments, for those of ordinary skill in the art, without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow diagram for the monitoring method that a kind of car wheel-set provided in an embodiment of the present invention runs posture；
Fig. 2 is the structure diagram of an illustrative example provided in an embodiment of the present invention；
Fig. 3 treats signal of the measuring wheel pair with the contact picture picture of corresponding rack wheel pair for vehicle provided in an embodiment of the present invention
Figure；
Fig. 4 rubs detection zone and wheel to glitch detection region selection schematic diagram for wheel rim provided in an embodiment of the present invention；
Fig. 5 is the flow diagram for the monitoring method that another car wheel-set provided in an embodiment of the present invention runs posture；
Fig. 6 is a kind of embodiment knot for the monitoring device that car wheel-set provided in an embodiment of the present invention runs posture
Composition；
Fig. 7 is another embodiment for the monitoring device that car wheel-set provided in an embodiment of the present invention runs posture
Structure chart；
Fig. 8 is a kind of embodiment knot for the monitoring device that car wheel-set provided in an embodiment of the present invention runs posture
Composition.
Embodiment
In order to make those skilled in the art more fully understand the present invention program, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiment is only part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Lower all other embodiments obtained, belong to the scope of protection of the invention.
Term " first ", " second ", " the 3rd " " in the description and claims of this application and above-mentioned attached drawing
Four " etc. be for distinguishing different objects, rather than for describing specific order.In addition term " comprising " and " having " and
Their any deformations, it is intended that cover non-exclusive include.Such as contain the process of series of steps or unit, method,
The step of system, product or equipment are not limited to list or unit, but the step of may include not list or unit.
After the technical solution of the embodiment of the present invention is described, the various non-limiting realities of detailed description below the application
Apply mode.
Referring first to Fig. 1, Fig. 1 is the stream for the monitoring method that a kind of car wheel-set provided in an embodiment of the present invention runs posture
Journey schematic diagram, the embodiment of the present invention may include herein below：
S101：Obtain the vehicle that camera gathers in real time and treat contact picture picture of the measuring wheel pair with corresponding rack wheel pair,
On contact picture picture choose wheel rim friction detection zone and wheel to glitch detection region, and generate wheel rim friction detection subgraph and
Wheel is to glitch detection subgraph.
Vehicle treat measuring wheel to by be placed on accompany examination power rack on dispatch from the factory before verification experimental verification wheel pair quality, one
A wheel treats that measuring wheel pair, to corresponding, will treat that measuring wheel is put in rack wheel to upper to falling, vehicle wheel with rack wheel to there is two wheels
Pair with rack wheel to contacting with each other, top treats the wheel of measuring wheel pair for vehicle, is below the wheel of corresponding rack wheel pair.
Under a kind of specific embodiment, referring to Fig. 2, illustrating for the monitoring system hardware layout structure of car wheel-set and rack wheel pair
Figure, upper and lower two wheels (wheel of a vehicle, the wheel of rack) share a camera and a light source emitter,
One wheel is to including two wheels, corresponding two cameras and two light source emitters.Camera is a pair of with light source emitter one
Should, the radially opposite sides for treating each wheel of measuring wheel centering, and light source emitter face camera are oppositely arranged on respectively, and camera is just
To the contact point of upper lower whorl pair, the focus of camera, the focus of light source emitter and contact point are located in same parallel lines,
That is, infrared light supply, thermal camera and rail contact face must be in one plane.
The application rotates against operation posture by monitor car wheel-set and rack wheel pair, to judge the fortune of car wheel-set
Turn whether to occur wiping the abnormal working order such as wheel, bounce.Contact surface of the measuring wheel pair with corresponding rack wheel pair can be treated by monitoring
Image is analyzed, and due to taking turns to unanimously running at high speed, the abnormal moment may be very short.Statistical result showed, image processing speed must
40 frames/second must be more than, therefore need to obtain the image of contact surface in real time, car wheel-set contacts rail level in schematic diagram with rack wheel to join
Read shown in Fig. 3.
Wheel rim friction detection zone and wheel are misaligned to glitch detection region, are setting wheel rim friction detection zone and wheel pair
During the ratio of width to height in glitch detection region, test of many times proves, it is preferred that the ratio of width to height of wheel rim friction detection zone may be configured as
1：2, light transmission part is located at region centre；Take turns and 2 may be configured as to the ratio of width to height in glitch detection region：1, in two wheel treads
Heart point is regional center.Certainly, other ratios are may be alternatively provided as, this does not influence the realization of the application.
Whether the Novel presentation of general wheel pair examines wheel to lead to occurring to wipe wheel phenomenon to wipe the bounce of wheel or wheel pair
Cross choose contact picture picture wheel rim friction detection zone judged, wheel rim friction detection zone be contact picture picture in up and down
The region in left and right gap is taken turns, and whether detection wheel to beating, can be by choosing the wheel of contacting surface image to glitch detection region
Judged, upper and lower wheel tread central area is arranged to wheel to glitch detection region, see shown in Fig. 2 and Fig. 4.
Under normal operating conditions, treat to have an interval between the wheel rim of the upper wheel of measuring wheel pair and the lower whorl of corresponding rack,
It can see from the angle of imaging in wheel rim friction detection zone and have light through next；If wheel rim friction detection zone does not have
Light, which passes through, to be come, that explanation has exception, and upper and lower wheel rim touches together, wheel rim can be caused to abrade, so as to cause exception.
Under normal circumstances, treat the upper wheel of measuring wheel pair and the lower whorl of corresponding rack vertical direction can be leaning closely against together, from
The angle of imaging can see wheel to not having any light in glitch detection region through next；If wheel has glitch detection region
Light through come, that explanation on wheel there is a situation where to jump up and down, can cause up and down wheel tread abrade, so as to cause exception.
The wheel rim chosen from contact picture picture friction detection zone is extracted for generating wheel rim friction detection
Image；By the wheel chosen from contact picture picture to glitch detection region, extract for taking turns to glitch detection subgraph.
S102：Detection subgraph and wheel are rubbed to wheel rim respectively to glitch detection subgraph progress image procossing, with extraction
Respective printing opacity object block, is calculated the first elemental area of wheel rim friction detection subgraph printing opacity object block and takes turns to bounce
Detect the second elemental area of subgraph printing opacity object block.
The detection subgraph that rubs to wheel rim carries out image denoising processing, image segmentation, morphological images processing and connects successively
Entire body is analyzed, and obtains the first elemental area of wheel rim friction detection subgraph printing opacity object block；To taking turns to glitch detection subgraph
Image denoising processing, image segmentation, morphological images processing and connected component analysis are carried out successively, and wheel is calculated to glitch detection
The detailed process of second elemental area of subgraph printing opacity object block can be as follows, the two processes can be carried out at the same time, example
Such as using multithreading at the same time carry out at a series of images glitch detection subgraph wheel rim friction detection subgraph and wheel
Reason, one by one can also carry out it, sequencing the application does not limit this.
1st, rub to wheel rim and detect subgraph and wheel to glitch detection subgraph progress Gaussian smoothing, to remove wheel rim
Friction detection subgraph and wheel are to the noise spot in glitch detection subgraph picture point imaging process.
It can rub to detect subgraph and take turns to wheel rim and carry out Gaussian smoothing respectively to glitch detection subgraph, filtered points imaging
During noise：
In formula, x, y represent current point to the distance of corresponding points.
The Gaussian kernel of 5*5 can specifically be used.
2nd, according to default first segmentation threshold, the second segmentation threshold, to the wheel rim friction detection subgraph after smoothing processing
Picture and wheel carry out binarization operation to glitch detection subgraph, and wheel rim is rubbed and detects subgraph and wheel to glitch detection subgraph
As respective transmission region and light tight region are split.
First segmentation threshold, the second segmentation threshold are the threshold value obtained according to many experiments statistical analysis, it is preferred that one
In kind preferably experiment, corresponding first segmentation threshold of wheel rim friction detection subgraph may be configured as 150；Wheel is to glitch detection
Corresponding second segmentation threshold of image can be set to 100.Certainly, or other values, the application do not do this any restriction.
3rd, the wheel rim of binary conversion treatment friction detection subgraph and wheel carry out glitch detection subgraph etching operation and
Expansive working, to obtain wheel rim friction detection subgraph and wheel to the respective transmission region of glitch detection subgraph and light tight area
Domain.
Wheel rim friction detection subgraph and wheel pass through binarization operation to glitch detection subgraph, in printing opacity and lighttight
Intermediate region can form the Small object of some scattered segmentations, such as dot, thin edge line etc., it is necessary to these filtered Small objects,
It can draw printing opacity and lighttight target area.
To the image after binaryzation, etching operation can be carried out first, for example with the corrosion core of 7*7, remove scattered small mesh
Mark, then carries out expansive working, can use the expansion core of 7*7, ensures the size of printing opacity and light tight target area.
4th, to the wheel rim friction detection subgraph by etching operation and expansive working and wheel to glitch detection subgraph into
Row connected component is analyzed, to obtain wheel rim friction detection subgraph printing opacity object block and wheel to glitch detection subgraph printing opacity object block
Position, shape and size.
Connected component analysis, is a kind of image labeling algorithm, marks out bright spot by image scanning and composition bright spot connects
Region forms transmission region.The position of bright spot in image can be marked in general image, finally counts the point of bright block
The feature such as number and central point, particle.
Calculating the position of wheel rim friction detection subgraph printing opacity object block and wheel to glitch detection subgraph printing opacity object block
Put, after shape and size, the detection subgraph printing opacity object block that can be rubbed according to wheel rim and wheel are to glitch detection subgraph printing opacity
Position, shape and the size of object block, calculate the first elemental area of wheel rim friction detection subgraph printing opacity object block；Can basis
Position, shape and the size to glitch detection subgraph printing opacity object block are taken turns, calculates wheel to glitch detection subgraph printing opacity target
Second elemental area of block.
S103：According to the first elemental area, wheel rim friction detection zone area and the default first numeric ratio for judging threshold value
Compared with relation, obtain treating the wheel rim Frotteurism of measuring wheel pair；According to the second elemental area, wheel to glitch detection region area with presetting
Second judges the numerical value comparison of threshold value, obtains treating the wheel of measuring wheel pair to bounce state.
Treating the analytic process of the wheel rim Frotteurism of measuring wheel pair can be：
Calculate the first ratio of the first elemental area and wheel rim friction detection zone area；
Judge whether the first ratio is 0；
If so, the wheel rim Frotteurism for then treating measuring wheel pair is abnormal；If it is not, then judging whether the first ratio is commented equal to first
Sentence threshold value；
If so, then treat that the wheel rim Frotteurism of measuring wheel pair is normal；If it is not, then treat that the wheel rim Frotteurism of measuring wheel pair is secondary
Normally.
For example, first judge threshold value (percentage) T is pre-set1, may be, for example, 20%, by the first elemental area with
The percentage (the first ratio) of wheel rim friction detection zone area is set to R1, with T1Compare.If not finding transmission region, i.e.,
R1=0, the projection portion taken turns in expression is contacted with lower whorl, and rail wheel is abnormal；If 0<R1<T1, the lug boss taken turns in expression
It is point smaller with the gap of lower whorl, exception may be caused, it is as subnormal；If R1=T1, represent the gap of upper and lower wheel rim
It is moderate, rail wheel normal operation；If R1＞ T1, represent that the gap of upper and lower wheel rim is larger, the subnormal operation of rail wheel.
Taking turns can be to the analytic process for state of beating：
Calculate second ratio of second elemental area with wheel to glitch detection region area；
Judge whether the second ratio is 0；
If so, the wheel for then treating measuring wheel pair is normal to bounce state；If it is not, then judging whether the second ratio is more than or equal to the
Two judge threshold value；
If so, the wheel for then treating measuring wheel pair is abnormal to bounce state；If it is not, the wheel for then treating measuring wheel pair is secondary to bounce state
Normally.
For example, second judge threshold value (percentage) T is pre-set2, may be, for example, 2%, by the second elemental area with
Take turns and R is set to the percentage (the second ratio) of glitch detection region area2, with T2Compare.If not finding transmission region, i.e.,
R2=0, wheel and lower whorl are in close contact in expression, rail wheel normal operation；If 0<R2<T2, wheel and lower wheel tread are deposited in expression
In small gap, upper wheel slightly takeoffs, and may cause exception, as subnormal；If R2>=T2, wheel and lower whorl in expression
Contact surface has occurred and that the obvious phenomenon of takeofing of wheel, occurs abnormal there is larger gap.
It should be noted that the first judge threshold value and the second judge threshold value are the threshold obtained according to many experiments statistical analysis
Value, present techniques personnel can be chosen according to actual conditions.
S104：According to wheel rim Frotteurism with wheel to state of beating, obtain treating measuring wheel pair rotates against operation posture.
In technical solution provided in an embodiment of the present invention, based on camera imaging vision detection technology, using being arranged on
Treat that measuring wheel treats upper camera real-time capture on contact picture picture of the measuring wheel pair with corresponding rack wheel pair, by analyzing contact surface
The size comparison of the printing opacity object block area of image detection region, corresponding detection zone area and predetermined threshold value, is treated
The relative rotary motion posture of measuring wheel pair and corresponding rack wheel pair, so that judge to treat whether measuring wheel is abnormal operation posture,
Fully-automatic vehicle wheel is realized to running attitude monitoring, it is low to solve artificial detection car wheel-set row posture work efficiency, and people
The uncertainty of work detection error, the problem of causing accuracy relatively low, improve car wheel-set operation posture monitoring accuracy and
Efficiency, advantageously ensures that the security and stability of vehicle operation.
Based on above-described embodiment, referring to Fig. 5, the application can further include：
S105：When the wheel rim Frotteurism for the treatment of measuring wheel pair or wheel be normal to bounce state, measuring wheel is treated to operation appearance
State carries out failure sorted early warning
Wheel rim Frotteurism can be normal, subnormal, abnormal, and it is different that exception can also be divided into generally abrasion exception, heavy wear
Often, it equally can be normal, subnormal, abnormal to take turns to bounce state, abnormal to be also divided into general exception, severely subnormal.
Wheel rim Frotteurism and wheel are to when the bounce state state of at least one is not normal condition, alarming.Examine
Consider it is subnormal in the state of, it is merely meant that treating that measuring wheel to that may be abnormal, actually has not occurred exception, can carry out one
Level alarm, so that staff treats that measuring wheel to carrying out key monitoring, finds the exception of wheel pair in time to this.
When wheel rim Frotteurism and wheel to bounce state for it is abnormal when, different stage can be carried out according to the abnormal order of severity
Early warning, such as general abnormal can be secondary alarm, and moderate abnormality can be that three-level is alarmed, and severely subnormal can be level Four alarm, no
The alarm of same level can be by setting different alarm volumes to be distinguished, or can be distinguished by different sound, this
Field technology personnel can be chosen according to specific actual conditions, and the application does not do this any restriction.
In addition, color that can also be by the indicator light of setting while early warning is carried out or brightness, carry out different degrees of
The alarm of (different stage).
By carrying out grading forewarning system, be conducive to prompt that user is abnormal or what i.e. exception will occur treats measuring wheel in time
It is right, different measures is taken according to the early warning of different stage in time, such as wheel pair is replaced, be conducive to improve car wheel-set operation appearance
The monitoring accuracy and efficiency of state, so as to advantageously ensure that the security and stability of vehicle operation.
The embodiment of the present invention provides corresponding realization device also directed to the monitoring method of car wheel-set operation posture, into one
Step is so that the method has more practicality.Below to the monitoring device of car wheel-set provided in an embodiment of the present invention operation posture
It is introduced, the prison of the monitoring device and above-described car wheel-set operation posture of car wheel-set operation posture described below
Survey method can correspond reference.
Referring to Fig. 6, Fig. 6 is that car wheel-set provided in an embodiment of the present invention runs the monitoring device of posture a kind of specific real
The structure chart under mode is applied, which may include：
Subgraph generation module 601, measuring wheel pair and corresponding rack wheel are treated for obtaining the vehicle that camera gathers in real time
To contact picture picture, wheel rim friction detection zone and wheel are chosen on contact picture picture to glitch detection region, and generates wheel
Edge friction detection subgraph and wheel are to glitch detection subgraph.
Image processing module 602, carries out glitch detection subgraph for rub respectively to wheel rim detection subgraph and wheel
Image procossing, to extract respective printing opacity object block, is calculated the first picture of wheel rim friction detection subgraph printing opacity object block
Vegetarian noodles is long-pending and takes turns the second elemental area to glitch detection subgraph printing opacity object block.
State analyzing module 603, for according to the first elemental area, wheel rim friction detection zone area and default first threshold
The numerical value comparison of value, obtains treating the wheel rim Frotteurism of measuring wheel pair；According to the second elemental area, wheel to glitch detection region
The numerical value comparison of area and default second threshold, obtains treating the wheel of measuring wheel pair to bounce state.
Wheel is to running posture judgment module 604, for treating measuring wheel to state of beating, judgement with wheel according to wheel rim Frotteurism
To rotate against operation posture.
Optionally, in other embodiments of the present embodiment, the state analyzing module 603 can include：
First computing unit, for calculating the first ratio of the first elemental area and wheel rim friction detection zone area；
First judging unit, for judging whether the first ratio is 0；
First Predicated execution unit, for if so, the wheel rim Frotteurism for then treating measuring wheel pair is abnormal；If it is not, then judge
Whether the first ratio, which is equal to first, is judged threshold value；If so, then treat that the wheel rim Frotteurism of measuring wheel pair is normal；It is if it is not, then to be measured
The wheel rim Frotteurism of wheel pair is subnormal.
It may also include：
Second computing unit, for calculating second ratio of second elemental area with wheel to glitch detection region area；
First judging unit, for judging whether the second ratio is 0；
First Predicated execution unit, for if so, the wheel for then treating measuring wheel pair is normal to bounce state；If it is not, then judge
Whether the second ratio, which is more than or equal to second, is judged threshold value；If so, the wheel for then treating measuring wheel pair is abnormal to bounce state；If it is not, then
The wheel for treating measuring wheel pair is subnormal to bounce state.
Optionally, in some embodiments of the present embodiment, referring to Fig. 7, described device can also for example include：
Alarm module 605, for not being normal to bounce state when the wheel rim Frotteurism or wheel for the treatment of measuring wheel pair, to be measured
Wheel carries out failure sorted early warning to operation posture.
In a kind of specific embodiment, alarm module 605 can be buzzer, may also include indicator light.
In some specific embodiments, described image processing module 602 may include：
Denoising unit, carries out at Gaussian smoothing glitch detection subgraph for rub to wheel rim detection subgraph and wheel
Reason, to remove wheel rim friction detection subgraph and wheel to the noise spot in glitch detection subgraph picture point imaging process；
Cutting unit, for according to default first segmentation threshold, the second segmentation threshold, rubbing to the wheel rim after smoothing processing
Wipe detection subgraph and wheel and binarization operation is carried out to glitch detection subgraph, wheel rim is rubbed into detection subgraph and wheel to jumping
Move the respective transmission region of detection subgraph and light tight region is split；
Morphological images processing unit, for the wheel rim friction detection subgraph and wheel to binary conversion treatment to glitch detection
Subgraph carries out etching operation and expansive working, to obtain stating wheel rim friction detection subgraph and take turns each to glitch detection subgraph
From transmission region and light tight region；
Connected component analytic unit, for the wheel rim friction detection subgraph and wheel pair by etching operation and expansive working
Glitch detection subgraph carries out connected component analysis, to obtain wheel rim friction detection subgraph printing opacity object block and wheel to glitch detection
Position, shape and the size of subgraph printing opacity object block.
The function of each function module of the device of car wheel-set operation posture can be according to above-mentioned side described in the embodiment of the present invention
Method specific implementation in method embodiment, its specific implementation process are referred to the associated description of above method embodiment, herein
Repeat no more.
From the foregoing, it will be observed that the embodiment of the present invention is based on camera imaging vision detection technology, treat measuring wheel to upper using being arranged on
Camera real-time capture treat contact picture picture of the measuring wheel pair with corresponding rack wheel pair, by analyzing contact picture as detection zone
The size comparison of the printing opacity object block area in domain, corresponding detection zone area and predetermined threshold value, obtains treating measuring wheel pair and phase
Answer the relative rotary motion posture of rack wheel pair, so as to judge to treat whether measuring wheel is abnormal operation posture, realize it is complete from
Dynamic car wheel-set operation attitude monitoring, it is low to solve artificial detection car wheel-set row posture work efficiency, and artificial detection is slipped up
Uncertainty, the problem of causing accuracy relatively low, improve the monitoring accuracy and efficiency of car wheel-set operation posture, be conducive to
Ensure the security and stability of vehicle operation.
The embodiment of the present invention additionally provides a kind of monitoring device of car wheel-set operation posture, specifically may include：
Memory, for storing computer program；
Processor, for performing computer program, to realize, as above car wheel-set described in any one embodiment runs posture
The step of monitoring method.
The function of each function module of the monitoring device of car wheel-set operation posture can be according to upper described in the embodiment of the present invention
The method specific implementation in embodiment of the method is stated, its specific implementation process is referred to the associated description of above method embodiment,
Details are not described herein again.
From the foregoing, it will be observed that the embodiment of the present invention realizes fully-automatic vehicle wheel to running attitude monitoring, solves artificial detection
Car wheel-set row posture work efficiency is low, and the uncertainty of artificial detection error, the problem of causing accuracy relatively low, improves
Car wheel-set runs the monitoring accuracy and efficiency of posture, advantageously ensures that the security and stability of vehicle operation.
The embodiment of the present invention additionally provides a kind of computer-readable recording medium, is stored with the prison of car wheel-set operation posture
Ranging sequence, as above vehicle wheel described in any one embodiment when the monitoring program of car wheel-set operation posture is executed by processor
To run posture monitoring method the step of.
The function of each function module of computer-readable recording medium described in the embodiment of the present invention can be real according to the above method
The method specific implementation in example is applied, its specific implementation process is referred to the associated description of above method embodiment, herein no longer
Repeat.
From the foregoing, it will be observed that the embodiment of the present invention realizes fully-automatic vehicle wheel to running attitude monitoring, solves artificial detection
Car wheel-set row posture work efficiency is low, and the uncertainty of artificial detection error, the problem of causing accuracy relatively low, improves
Car wheel-set runs the monitoring accuracy and efficiency of posture, advantageously ensures that the security and stability of vehicle operation.
The embodiment of the present invention finally additionally provides a kind of monitoring system of car wheel-set operation posture, refers to Fig. 8, can wrap
Include：
Multiple light sources transmitter 801, multiple cameras 802 and processor 803.
The number of camera 802 is treat measuring wheel to number twice, and the number of light source emitter 801 is to treat measuring wheel to number
Twice, camera 802 is corresponded with light source emitter 801.
Camera 802 is oppositely arranged on the radially opposite sides for treating each wheel of measuring wheel centering respectively with light source emitter 801, and
801 face camera 802 of light source emitter, the contact point of lower whorl pair, the focus of camera 802, light source in 802 face of camera
The focus of transmitter 801 is located in same parallel lines with upper lower whorl butt contact.
In order to make camera real-time capture contact picture picture, camera frame per second can be arranged to 50 frames/second, it is ensured that can be complete
Wheel is captured to abnormal operation state.
Each camera 802 is connected with processor 803, and the contact picture picture collected is sent into processor 803, place
Reason device 803, which is arranged on, accompanies on examination power rack.
To avoid situation of the general visible easily by external interference, infrared light can be used to be imaged, scene can be avoided all
The available light interference of surrounding environment, ensures the stability and reliability of detection.When light source emitter is infrared light supply transmitter, with
The corresponding camera of light source emitter is infrared camera.
Processor 803 is realized when being used to perform the computer program stored in memory such as any one of preceding car wheel-set operation
Posture embodiment of the method, the function of each function module of the processor 803 can run posture method according to above-mentioned car wheel-set
Method specific implementation in embodiment, its specific implementation process are referred to the associated description of above method embodiment, herein not
Repeat again.
It should be noted that during due to catching wheel to the image of contact surface, the external environment for the contact plane taken turns pair is dark,
In order to improve the clarity of imaging, increase light source emitter, light source emitter can be any type light source, and the application does not make this
Any restriction.
From the foregoing, it will be observed that the embodiment of the present invention realizes fully-automatic vehicle wheel to running attitude monitoring, solves artificial detection
Car wheel-set row posture work efficiency is low, and the uncertainty of artificial detection error, the problem of causing accuracy relatively low, improves
Car wheel-set runs the monitoring accuracy and efficiency of posture, advantageously ensures that the security and stability of vehicle operation.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be with it is other
The difference of embodiment, between each embodiment same or similar part mutually referring to.For dress disclosed in embodiment
For putting, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related part is referring to method part
Explanation.
Professional further appreciates that, with reference to each exemplary unit of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, generally describes each exemplary composition and step according to function in the above description.These
Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical solution.Specialty
Technical staff can realize described function to each specific application using distinct methods, but this realization should not
Think beyond the scope of this invention.
Can directly it be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
A kind of monitoring method of car wheel-set operation posture provided by the present invention, apparatus and system have been carried out in detail above
It is thin to introduce.Specific case used herein is set forth the principle of the present invention and embodiment, and above example is said
It is bright to be only intended to help the method and its core concept for understanding the present invention.It should be pointed out that the ordinary skill for the art
For personnel, without departing from the principle of the present invention, some improvement and modification, these improvement can also be carried out to the present invention
Also fallen into modification in the protection domain of the claims in the present invention.
Claims (10)
- A kind of 1. monitoring method of car wheel-set operation posture, it is characterised in that including：Obtain the vehicle that camera gathers in real time and treat contact picture picture of the measuring wheel pair with corresponding rack wheel pair, in the contact surface Wheel rim friction detection zone and wheel are chosen on image to glitch detection region, and generates wheel rim friction detection subgraph and wheel to jumping Dynamic detection subgraph；Rub respectively to the wheel rim and detect subgraph and the wheel to glitch detection subgraph progress image procossing, it is each to extract From printing opacity object block, the first elemental area of wheel rim friction detection subgraph printing opacity object block and the wheel is calculated To the second elemental area of glitch detection subgraph printing opacity object block；According to first elemental area, wheel rim friction detection zone area compared with the default first numerical value for judging threshold value Relation, obtains the wheel rim Frotteurism for treating measuring wheel pair；According to second elemental area, the wheel to glitch detection region Area and the default second numerical value comparison for judging threshold value, obtain described treating the wheel of measuring wheel pair to bounce state；According to the wheel rim Frotteurism and the wheel to state of beating, obtain it is described treat measuring wheel pair rotate against operation appearance State；Wherein, the wheel rim friction detection zone and the wheel are misaligned to glitch detection region；The camera is sent out with light source Emitter corresponds, and is oppositely arranged on the radially opposite sides for treating each wheel of measuring wheel centering, and the light source emitter respectively Camera described in face, the contact point of lower whorl pair, the focus of the camera, the light source emitter in the camera face Focus and the contact point be located in same parallel lines.
- 2. the monitoring method of car wheel-set according to claim 1 operation posture, it is characterised in that described according to described the One elemental area, wheel rim friction detection zone area and the default first numerical value comparison for judging threshold value, obtain described Treat the wheel rim Frotteurism enclosed mass of measuring wheel pair：Calculate the first ratio of first elemental area and wheel rim friction detection zone area；Judge whether first ratio is 0；If so, then the wheel rim Frotteurism for treating measuring wheel pair is abnormal；If it is not, then judging whether first ratio is equal to institute State the first judge threshold value；If so, then the wheel rim Frotteurism for treating measuring wheel pair is normal；If it is not, the then wheel rim Frotteurism for treating measuring wheel pair To be subnormal.
- 3. the monitoring method of car wheel-set according to claim 1 operation posture, it is characterised in that described according to described the Two elemental areas, the wheel obtain described glitch detection region area and the default second numerical value comparison for judging threshold value Treating the wheel of measuring wheel pair includes bounce state：Calculate second ratio of second elemental area with the wheel to glitch detection region area；Judge whether second ratio is 0；If so, then the wheel for treating measuring wheel pair is normal to bounce state；If it is not, then judge whether second ratio is more than Threshold value is judged in described second；If so, then the wheel for treating measuring wheel pair is abnormal to bounce state；If it is not, then the wheel for treating measuring wheel pair is to bounce state To be subnormal.
- 4. the monitoring method of the car wheel-set operation posture according to claims 1 to 3 any one, it is characterised in that also Including：When the wheel rim Frotteurism for treating measuring wheel pair or it is described wheel be to bounce state it is normal, to it is described treat measuring wheel to run Posture carries out failure sorted early warning.
- 5. the monitoring method of the car wheel-set operation posture according to claims 1 to 3 any one, it is characterised in that institute Stating respectively includes glitch detection subgraph progress image procossing wheel rim friction detection subgraph and the wheel：Respectively to the wheel rim rub detection subgraph and it is described wheel glitch detection subgraph is carried out successively image denoising processing, Image segmentation, morphological images processing and connected component analysis.
- 6. the monitoring method of car wheel-set operation posture according to claim 5, it is characterised in that described respectively to described Wheel rim friction detection subgraph and the wheel carry out glitch detection subgraph image denoising processing, image segmentation, form successively Learning image procossing and connected component analysis includes：Rub to the wheel rim and detect subgraph and the wheel to glitch detection subgraph progress Gaussian smoothing, to remove Wheel rim friction detection subgraph and the wheel are stated to the noise spot in glitch detection subgraph picture point imaging process；According to default first segmentation threshold, the second segmentation threshold, to the wheel rim friction detection subgraph and wheel after smoothing processing Binarization operation is carried out to glitch detection subgraph, the wheel rim is rubbed and detects subgraph and the wheel to glitch detection The respective transmission region of image and light tight region are split；Wheel rim friction detection subgraph and wheel to binary conversion treatment carry out etching operation to glitch detection subgraph and expansion is grasped Make, to obtain wheel rim friction detection subgraph and the wheel to the respective transmission region of glitch detection subgraph and light tight Region；To being connected by etching operation with the wheel rim friction detection subgraph of expansive working with wheel to glitch detection subgraph Body is analyzed, to obtain the wheel rim friction detection subgraph printing opacity object block and the wheel to glitch detection subgraph printing opacity target Position, shape and the size of block.
- 7. the monitoring method of car wheel-set operation posture according to claim 6, it is characterised in that described that institute is calculated State wheel rim friction detection subgraph printing opacity object block the first elemental area and it is described wheel to glitch detection subgraph printing opacity target Second elemental area of block includes：The wheel rim friction detection subgraph printing opacity object block and the wheel are calculated to glitch detection subgraph printing opacity object block Position, shape and size；Rubbed according to the wheel rim and detect subgraph printing opacity object block and the wheel to glitch detection subgraph printing opacity object block Position, shape and size, calculate the first elemental area of the wheel rim friction detection subgraph printing opacity object block；Position, shape and size according to the wheel to glitch detection subgraph printing opacity object block, calculate the wheel and bounce are examined Survey the second elemental area of subgraph printing opacity object block.
- A kind of 8. monitoring device of car wheel-set operation posture, it is characterised in that including：Subgraph generation module, treats measuring wheel to being contacted with corresponding rack wheel pair for obtaining the vehicle that camera gathers in real time Face image, chooses wheel rim friction detection zone and wheel to glitch detection region on the contact picture picture, and generates wheel rim and rub Detection subgraph and wheel are wiped to glitch detection subgraph；Image processing module, subgraph and the wheel are detected to the progress of glitch detection subgraph for rubbing respectively to the wheel rim Image procossing, to extract respective printing opacity object block, it is calculated the of wheel rim friction detection subgraph printing opacity object block One elemental area and second elemental area taken turns to glitch detection subgraph printing opacity object block；State analyzing module, for according to first elemental area, wheel rim friction detection zone area and default first The numerical value comparison of threshold value, obtains the wheel rim Frotteurism for treating measuring wheel pair；According to second elemental area, the wheel To the numerical value comparison of glitch detection region area and default second threshold, the wheel for treating measuring wheel pair is obtained to shape of beating State；Wheel to running posture judgment module, for according to the wheel rim Frotteurism and the wheel to state of beating, described in judgement That treats measuring wheel pair rotates against operation posture.
- A kind of 9. monitoring system of car wheel-set operation posture, it is characterised in that including：Multiple light sources transmitter, multiple cameras and processor, the processor are used to perform the computer stored in memory The step of car wheel-set runs posture method as described in any one of claim 1 to 7 is realized during program；The number of camera is treat measuring wheel to number twice, and the number of light source emitter is treat measuring wheel to number twice, is taken the photograph As head and light source emitter correspond；Camera is oppositely arranged on the radially opposite sides for treating each wheel of measuring wheel centering, and light source emitter respectively with light source emitter Face camera, the contact point of lower whorl pair in camera face, the focus of camera, the focus of light source emitter and upper lower whorl pair Contact point is located in same parallel lines；Each camera is connected with the processor, and the processor, which is arranged on, accompanies on examination power rack.
- 10. the monitoring system of car wheel-set operation posture according to claim 9, it is characterised in that the light source transmitting Device is infrared light supply transmitter, is infrared camera with the corresponding camera of the light source emitter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711157455.4A CN107958452B (en) | 2017-11-20 | 2017-11-20 | Method, device and system for monitoring running attitude of vehicle wheel set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711157455.4A CN107958452B (en) | 2017-11-20 | 2017-11-20 | Method, device and system for monitoring running attitude of vehicle wheel set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107958452A true CN107958452A (en) | 2018-04-24 |
| CN107958452B CN107958452B (en) | 2021-08-13 |
Family
ID=61963929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711157455.4A Active CN107958452B (en) | 2017-11-20 | 2017-11-20 | Method, device and system for monitoring running attitude of vehicle wheel set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107958452B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112393603A (en) * | 2020-03-26 | 2021-02-23 | 中冶长天国际工程有限责任公司 | Trolley wheel fault detection method, device, equipment and medium |
| CN112598705A (en) * | 2020-12-17 | 2021-04-02 | 太原理工大学 | Vehicle body posture detection method based on binocular vision |
| CN112991311A (en) * | 2021-03-29 | 2021-06-18 | 深圳大学 | Vehicle overweight detection method, device and system and terminal equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2677922Y (en) * | 2004-01-19 | 2005-02-09 | 广东工业大学 | Structural optical visual sensing step-by-step drive wheel set measuring device |
| CN201673122U (en) * | 2009-07-20 | 2010-12-15 | 北京福斯达轨道交通技术有限公司 | Dynamic detector for railway wheel tread scratch image |
| CN104608799A (en) * | 2014-12-12 | 2015-05-13 | 郑州轻工业学院 | Information fusion technology based train wheel set tread damage online detection and recognition method |
| US20170161586A1 (en) * | 2015-12-08 | 2017-06-08 | Nuctech Company Limited | Train type identification method and system, and security inspection method and system |
-
2017
- 2017-11-20 CN CN201711157455.4A patent/CN107958452B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2677922Y (en) * | 2004-01-19 | 2005-02-09 | 广东工业大学 | Structural optical visual sensing step-by-step drive wheel set measuring device |
| CN201673122U (en) * | 2009-07-20 | 2010-12-15 | 北京福斯达轨道交通技术有限公司 | Dynamic detector for railway wheel tread scratch image |
| CN104608799A (en) * | 2014-12-12 | 2015-05-13 | 郑州轻工业学院 | Information fusion technology based train wheel set tread damage online detection and recognition method |
| US20170161586A1 (en) * | 2015-12-08 | 2017-06-08 | Nuctech Company Limited | Train type identification method and system, and security inspection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 卢湖川: "基于CCD的火车轮对智能测量系统", 《吉林大学学报（信息科学版）》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112393603A (en) * | 2020-03-26 | 2021-02-23 | 中冶长天国际工程有限责任公司 | Trolley wheel fault detection method, device, equipment and medium |
| CN112598705A (en) * | 2020-12-17 | 2021-04-02 | 太原理工大学 | Vehicle body posture detection method based on binocular vision |
| CN112598705B (en) * | 2020-12-17 | 2024-05-03 | 太原理工大学 | Binocular vision-based vehicle body posture detection method |
| CN112991311A (en) * | 2021-03-29 | 2021-06-18 | 深圳大学 | Vehicle overweight detection method, device and system and terminal equipment |
| CN112991311B (en) * | 2021-03-29 | 2021-12-10 | 深圳大学 | Vehicle overweight detection method, device and system and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107958452B (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107958452A (en) | A kind of monitoring method of car wheel-set operation posture, apparatus and system | |
| Molodova et al. | Automatic detection of squats in railway infrastructure | |
| Taştimur et al. | Rail defect detection with real time image processing technique | |
| Dubey et al. | Maximally stable extremal region marking-based railway track surface defect sensing | |
| CN103034850B (en) | Trouble of moving freight car detection system (TFDS) block key loss fault automatic identification method | |
| CN102854191A (en) | Real-time visual detection and identification method for high speed rail surface defect | |
| JP6533363B2 (en) | Artifact detection method and video artifact detector | |
| CN111080668A (en) | Brake pad wear fault detection method and system | |
| CN113298059A (en) | Pantograph foreign matter intrusion detection method, device, computer equipment, system and storage medium | |
| JP4262878B2 (en) | Rotating machine abnormal sound diagnosis processing method | |
| CN111080601A (en) | Method for identifying fault image of pull ring grinding shaft of derailment brake device of railway wagon | |
| CN104732510B (en) | A kind of camera lens blackspot detection method and device | |
| CN105480258B (en) | A kind of tire tread defects detection method and device | |
| JP7420692B2 (en) | Welding system, welding method, welding support device, program, learning device, and learned model generation method | |
| CN113706566A (en) | Perfuming spray performance detection method based on edge detection | |
| CN115631146A (en) | Image-based pantograph carbon slide strip defect detection method | |
| CN111445485B (en) | Online abrasive particle image data processing method | |
| Wang et al. | An improved YOLOv8 algorithm for rail surface defect detection | |
| Hashmi et al. | Computer-vision based visual inspection and crack detection of railroad tracks | |
| JP7356010B2 (en) | Surface texture inspection device and surface texture inspection method | |
| Tastimur et al. | A real time interface for vision inspection of rail components and surface in railways | |
| CN114897921A (en) | Pantograph abrasion value and pantograph abnormity real-time detection method based on machine vision | |
| Aydin et al. | A vision based inspection system using gaussian mixture model based interactive segmentation | |
| CN111627000A (en) | Bow net arc discharge detection method and system | |
| Choi et al. | Assessing workers perceived risk during construction task using a wristband-type biosensor |
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 |