CN107146224A - The online image detecting system of train wheel thread defect and method - Google Patents
The online image detecting system of train wheel thread defect and method Download PDFInfo
- Publication number
- CN107146224A CN107146224A CN201710305046.8A CN201710305046A CN107146224A CN 107146224 A CN107146224 A CN 107146224A CN 201710305046 A CN201710305046 A CN 201710305046A CN 107146224 A CN107146224 A CN 107146224A
- Authority
- CN
- China
- Prior art keywords
- image
- wheel
- acquisition device
- image acquisition
- tread
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 230000002950 deficient Effects 0.000 claims abstract description 9
- 230000015556 catabolic process Effects 0.000 claims abstract description 4
- 238000013459 approach Methods 0.000 claims description 26
- 238000005096 rolling process Methods 0.000 claims description 8
- 230000003137 locomotive effect Effects 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 4
- 239000003550 marker Substances 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000004323 axial length Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims 1
- 238000003672 processing method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- 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
- G06T2207/30236—Traffic on road, railway or crossing
-
- 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
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of online image detecting system of train wheel thread defect and method, it is related to image processing method technical field.Methods described comprises the following steps：Wheel is to image zooming-out；Image is split；Image rectification；Image mosaic；Image calibration；Tread whether there is breakdown judge；Tread failure is extracted：If judging existing defects failure in tread image by handling above, then the method that is combined is grown using region growing with seed point and isolate thread defect region from tread image, and calculate the dimension information of thread defect part using the geometrical correspondence of image calibration.Each complete wheel tread information is drawn after image is spliced and handled by methods described, and judgement is carried out to the tread and draws whether defective, thread defect accuracy of detection height, can effectively avoid detecting mistake.
Description
Technical field
The present invention relates to image processing method and systems technology field, more particularly to a kind of train wheel thread defect are online
Image detecting system and method.
Background technology
Wheel is to being the part being in contact on rolling stock with rail, and by left and right two, wheel is fitted in same car securely
Constituted on axle.Take turns to effect be to ensure operation and steering of the rolling stock on rail, bear from the complete of rolling stock
Portion is quiet, dynamic loading, passes it on rail, and will give rolling stock each parts because of the load transmission that guideway irregularity is produced.
Wheel tread defect be wheel to one of major failure type, develop with the high speed and heavy loading of railway, thread defect failure
Appearance it is increasingly frequent.On current railway also there are many problems in the online test method of thread defect, and major defect is to examine
Survey precision poor, it is impossible to correctly identify thread defect.
The content of the invention
The technical problems to be solved by the invention are how to provide a kind of high train wheel of thread defect accuracy of detection to step on
The online image detecting system of planar defect.
In order to solve the above technical problems, the technical solution used in the present invention is：A kind of train wheel thread defect is online
Image detecting system, it is characterised in that：Including computer, four image acquisition devices and four approach switch sensors, first
Image acquisition device and the 3rd image acquisition device are located at the outside of the first rail, the second image acquisition device and the 4th image acquisition device position
In the outside of the second rail, the first image acquisition device and the 3rd image acquisition device and the second image acquisition device and the 4th IMAQ
Using the rail center line between two rails as symmetry axis between device, between the first image acquisition device and the 3rd image acquisition device and
Using image acquisition device center line as symmetry axis between second image acquisition device and the 4th image acquisition device；Each image acquisition device correspondence
One train wheel, the image for shooting correspondence wheel, the axis of each described image collector and the circle of the wheel
The heart is in same level, and the horizontal field of view angle of described image collector is all θ, and the first image acquisition device and the second image are adopted
Storage is located at the right side of locomotive, and the 3rd image acquisition device and the 4th image acquisition device are located at the left side of locomotive, the first IMAQ
The horizontal field of view of device and the 3rd image acquisition device, which has, to partly overlap, the level of the second image acquisition device and the 4th image acquisition device
Visual field, which has, to partly overlap, and four approach switch sensors are equally spaced to be arranged at the second image acquisition device and the 4th image
The inner side of equitant second rail of collector horizontal field of view, and the distance between approach switch sensor is 0.785φ, φFor
The rolling circular diameter of the wheel；When the second wheel triggers the first approach switch sensor, the first wheel is located at the first image
In the horizontal field of view of collector, the 3rd wheel is located in the horizontal field of view of the 3rd image acquisition device, and the second wheel is located at the second figure
In the horizontal field of view of picture collector, the 4th wheel is located in the horizontal field of view of the 4th image acquisition device, four image acquisition devices point
IMAQ is not carried out to corresponding wheel not for the first time；When the second wheel triggers the second approach switch sensor, the first wheel
In the horizontal field of view of the first image acquisition device, the 3rd wheel is located in the horizontal field of view of the 3rd image acquisition device, the second car
Wheel is in the horizontal field of view of the second image acquisition device, and the 4th wheel is located in the horizontal field of view of the 4th image acquisition device, four
Image acquisition device carries out IMAQ second to corresponding wheel respectively；When the second wheel triggers the 3rd approach switch sensor
When, the first wheel is located in the horizontal field of view of the first image acquisition device, and the level that the 3rd wheel is located at the 3rd image acquisition device is regarded
In, the second wheel is located in the horizontal field of view of the second image acquisition device, and the 4th wheel is located at the level of the 4th image acquisition device
In visual field, third time carries out IMAQ to four image acquisition devices to corresponding wheel respectively；When the second wheel triggering the 4th connects
During nearly switch sensor, the first wheel is located in the horizontal field of view of the first image acquisition device, and the 3rd wheel is adopted positioned at the 3rd image
In the horizontal field of view of storage, the second wheel is located in the horizontal field of view of the second image acquisition device, and the 4th wheel is located at the 4th image
In the horizontal field of view of collector, four image acquisition devices distinguish the 4th time and carry out IMAQ to corresponding wheel；Computer connects
Four images of each image acquisition device transmission are received, each complete wheel tread is drawn after image is spliced and handled
Information, and tread progress judgement is drawn whether defective.
It is preferred that：Horizontal range between described first image collector and the 3rd image acquisition device and the first rail is
2m, the horizontal range between second image acquisition device and the 4th image acquisition device and the second rail is 2m.
It is preferred that：Horizontal field of view angle θ is 65 °.
It is preferred that：Described image collector is fixed on by the rail by support.
It is preferred that：Described image collector is high-speed cmos video camera.
The invention also discloses a kind of online image detecting method of train wheel thread defect, it is characterised in that including as follows
Step：
Wheel is to image zooming-out：Wheel is extracted in the whole image gathered from image acquisition device to region；
Image is split：Image is split to taking turns using improved Based On Method of Labeling Watershed Algorithm, tread image is extracted；
Image rectification：The transverse and longitudinal coordinate for dividing the image into the tread image extracted carries out geometric correction, and serious to distorting
Inoperative side is cut, and obtains tread expanded view；
Image mosaic：According to last collection moment tread image size, first three moment tread image is entered using cube convolution method
Row interpolation obtains the unified tread image of size, is carried out using the block matching method collection moment adjacent to aforementioned four tread image
Sequentially splicing fusion two-by-two, obtains the complete tread image of each wheel；
Image calibration：User's case marker determines paper and is placed in tread respectively to gather in moment camera photographable position, completes to spliced
Tread image is demarcated, the corresponding relation after being spliced between the pixel distance and dimension information of image；
Tread whether there is breakdown judge：The comentropy for splicing rear tread pattern image by calculating is compared to judge to step on empirical value
Face whether there is major defect failure；
Tread failure is extracted：Using improved splitting and merging to judging that the tread of existing defects is handled, seed is utilized
Point growth is filled to the thread defect image after growth, obtains thread defect image, and the Shi Jishiyong gridding method of defect is entered
Area is calculated using pixel in region in row estimation, image, and the Gao Yukuan of pixel value is utilized in image respectively in image
The max min of row and column in thread defect region ask difference to be obtained to calculate.
Further technical scheme is that methods described also includes before image segmentation：Using MSRCR algorithms to wheel pair
The pre-treatment step that the color information of image is optimized.
Further technical scheme is that the wheel is as follows to the method for image zooming-out：
Input pending image；
Pending image is filtered, using canny operators rim detection is carried out after grayscale equalization, edge pixel point is
Characteristic point；
W ∈ [500,1000] in scanning figure, H ∈ [1000,1600] region, statistical nature point sets up accumulation structure, and accumulator is adopted
With two-dimensional array, two-dimensional array subscript is characterized dot center's coordinate, and accumulator initial value is set to 0；
Each characteristic point in the range of traversal, it is to scan other characteristic points to carry out string midpoint Hough transform, tries to achieve their midpoints,
Corresponding accumulator adds 1, and only string midpoint Hough transform is carried out to untreated characteristic point when calculating next characteristic point；
When accumulator count value is more than threshold value 5, then it is assumed that this position has an ellipse, its corresponding parameter（x0 i, y0 i）It is exactly
Oval corresponding centre coordinate, subscript i represents oval number；
Use each point（x0 i, y0 i）Elliptic equation is moved into origin, 3 couple on origin symmetry is found under new coordinate system
Characteristic point tries to achieve each elliptic equation, compares transverse size, and selection axial length most long ellipse is the length of side, and elliptical center is the centre of form
Square region as wheel to region；
Interception wheel carries out subsequent treatment as final wheel to the positive 120 ° region of image to image.
Further technical scheme is that the block matching method is as follows：
Two adjacent time charts are sequentially loaded into as matrix；
Determine image block scanning window and threshold values；
Start block scan, calculate absolute value difference value between image-region；
Judge whether the difference value exceedes threshold value, if it exceeds threshold value is then continued to scan on, stored if threshold value is not above
Position；
Curve Matching is carried out, splicing result is exported after fusion is weighted to the curve after matching.
Further technical scheme is that the improved splitting and merging comprises the following steps：
Setting judges sentence P and minimum unit size min, builds discriminant function；
Judge whether each region of image meets discriminant function；
It is considered as if discriminant function is met and meets splitting condition, then will meets the sub-district area image quartering of splitting condition, and
Image is judged again；If being unsatisfactory for discriminant function, merging is set to judge sentence Q, and judge sentence Q by merging
Judge whether there is subregion to meet merging condition in image, if it is merge the subregion for meeting merging condition, such as
Fruit is not to terminate.
It is using the beneficial effect produced by above-mentioned technical proposal：The system Computer receives each IMAQ
Four images of device transmission, then each complete wheel tread is drawn after image is spliced and handled by methods described
Information, and whether defective, thread defect accuracy of detection height is drawn to tread progress judgement, it can effectively avoid detection wrong
By mistake.
Brief description of the drawings
Fig. 1 is the schematic layout diagram of system described in the embodiment of the present invention；
Fig. 2 is the side structure schematic view of an image acquisition device and corresponding wheel in system described in the embodiment of the present invention；
Fig. 3 is approach switch sensor setting principle schematic diagram in system described in the embodiment of the present invention；
Fig. 4 is the flow chart of methods described of the embodiment of the present invention；
Fig. 5 is that the flow chart to image zooming-out is taken turns in methods described of the embodiment of the present invention；
Fig. 6-9 is four sub-pictures of the second image acquisition device collection in methods described of the embodiment of the present invention；
Figure 10-13 is the figure after Fig. 6-9 is cut in methods described of the embodiment of the present invention；
Figure 14 is the result figure of ellipses detection in methods described of the embodiment of the present invention；
Figure 15 is taken turns in methods described of the embodiment of the present invention to interception partial schematic diagram；
Figure 16-17 is to taking turns the comparison diagram strengthened image before and after the processing with MSRCR algorithms；
Figure 18-19 is to taking turns the design sketch after splitting to image using improved Based On Method of Labeling Watershed Algorithm；
Figure 20 is the tread expanded view in methods described of the embodiment of the present invention；
Figure 21-24 is that tread image enters row interpolation and obtains the unified tread image of size in methods described of the embodiment of the present invention；
Figure 25 is to splice flow chart in the embodiment of the present invention；
Figure 26 is splicing result figure in the embodiment of the present invention:
Figure 27-28 is segmentation tread image and plane rectification figure in the embodiment of the present invention；
Figure 29 is defective tread image processing flow figure in the embodiment of the present invention；
Figure 30 is the result figure handled using improved splitting and merging in the embodiment of the present invention；
Figure 31 is thread defect image in the embodiment of the present invention；
Wherein：1st, the first image acquisition device 2, the second image acquisition device 3, the 3rd image acquisition device 4, the 4th image acquisition device 5,
One rail 6, the second rail 7, rail center line 8, image acquisition device center line 9, the first wheel 10, the first approach switch sensor 11,
Second wheel 12, the 3rd wheel 13, the 4th wheel 14, the second approach switch sensor 15, three approach switch sensors the 16, the 4th
The effective coverage of tread portions in approach switch sensor 17, support 18, wheel 19, rail 20, every image.
Embodiment
With reference to the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground is described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Many details are elaborated in the following description to facilitate a thorough understanding of the present invention, still the present invention can be with
It is different from other manner described here using other to implement, those skilled in the art can be without prejudice to intension of the present invention
In the case of do similar popularization, therefore the present invention is not limited by following public specific embodiment.
Embodiment one
As shown in figure 1, present embodiment discloses a kind of online image detecting system of train wheel thread defect, including computer,
Four image acquisition devices and four approach switch sensors.First image acquisition device 1 and the 3rd image acquisition device 3 are located at first
The outside of rail 5, the second image acquisition device 2 and the 4th image acquisition device 4 are located at the outside of the second rail 6.First IMAQ
With the iron between two articles of rails between the image acquisition device 3 of device 1 and the 3rd and the second image acquisition device 2 and the 4th image acquisition device 4
Rail center line 7（Horizontal dotted line shown in Fig. 1）For symmetry axis；Between first image acquisition device 1 and the 3rd image acquisition device 3 and the second figure
With image acquisition device center line 8 between the picture image acquisition device 4 of collector 2 and the 4th（Described image collector center line refers to the first figure
As between the first midpoint between collector and the 3rd image acquisition device and the second image acquisition device and the 4th image acquisition device
The second midpoint between line, shown in Fig. 1 indulge dotted line）For symmetry axis；One train wheel of each image acquisition device correspondence,
Image for shooting correspondence wheel, the axis of each described image collector is with the circle centre position of the wheel in same level
On face, the horizontal field of view angle of described image collector is all θ.
First image acquisition device 1 and the second image acquisition device are located at the right side of locomotive, the 3rd image acquisition device 3 and the 4th figure
As collector 4 is located at the left side of locomotive.The horizontal field of view of first image acquisition device 1 and the 3rd image acquisition device 3 has part weight
Folded, the horizontal field of view of the second image acquisition device 2 and the 4th image acquisition device 4, which has, to partly overlap.Four proximity switches are passed
Sensor is equally spaced to be arranged at the second image acquisition device 2 and equitant second rail 6 of the horizontal field of view of the 4th image acquisition device 4
Inner side, and the distance between approach switch sensor is 0.785φ, φFor the rolling circular diameter of the wheel.
When the second wheel 11 triggers the first approach switch sensor 10, the first wheel 9 is located at the first image acquisition device 1
In horizontal field of view, the 3rd wheel 12 is located in the horizontal field of view of the 3rd image acquisition device 3, and the second wheel 11 is adopted positioned at the second image
In the horizontal field of view of storage 2, the 4th wheel 13 is located in the horizontal field of view of the 4th image acquisition device 4, four image acquisition devices point
IMAQ is not carried out to corresponding wheel not for the first time；When the second wheel 11 triggers the second approach switch sensor 14, first
Wheel 9 is located in the horizontal field of view of the first image acquisition device 1, and the 3rd wheel 12 is located at the horizontal field of view of the 3rd image acquisition device 3
Interior, the second wheel 11 is located in the horizontal field of view of the second image acquisition device 2, and the 4th wheel 13 is located at the 4th image acquisition device 4
In horizontal field of view, four image acquisition devices carry out IMAQ second to corresponding wheel respectively；When the second wheel 11 is triggered
During three approach switch sensors 15, the first wheel 9 is located in the horizontal field of view of the first image acquisition device 1, the 3rd wheel 12
In in the horizontal field of view of the 3rd image acquisition device 3, the second wheel 11 is located in the horizontal field of view of the second image acquisition device 2, and the 4th
Wheel 13 is located in the horizontal field of view of the 4th image acquisition device 4, and four image acquisition devices respectively to corresponding wheel enter by third time
Row IMAQ；When the second wheel 11 triggers four approach switch sensors 16, the first wheel 9 is located at the first image acquisition device
In 1 horizontal field of view, the 3rd wheel 12 is located in the horizontal field of view of the 3rd image acquisition device 3, and the second wheel 11 is located at the second figure
In the horizontal field of view of picture collector 2, the 4th wheel 13 is located in the horizontal field of view of the 4th image acquisition device 4, four IMAQs
Device distinguishes the 4th time and carries out IMAQ to corresponding wheel；Computer receives four images of each image acquisition device transmission,
Draw each complete wheel tread information after image is spliced and handled, and judgement carried out to the tread drawn be
It is no defective.
It is preferred that, as shown in figure 1, between the image acquisition device 3 of described first image collector 1 and the 3rd and the first rail 5
Horizontal range be 2m, the horizontal range between the image acquisition device 4 of the second image acquisition device 2 and the 4th and the second rail 6
For 2m.It should be noted that above-mentioned horizontal range can carry out appropriate adjustment, the invention is not limited in above-mentioned specific
Numerical value.
It is preferred that, as shown in figure 1, horizontal field of view angle θ is 65 °.Further, as shown in Fig. 2 described image collector is logical
Support 17 is crossed to be fixed on by the rail.It is preferred that, described image collector is high-speed cmos video camera.It should be noted that
The occurrence of the horizontal field of view angle θ can also be other values, and the concrete form of described image collector can also be other shapes
Formula, such as high speed camera.
When a wheel is by one of approach switch sensor, the front and back wheel of bogie can trigger two in succession
Individual switching signal, it is assumed that current of traffic to the right when, then previous switching signal is used for controlling the first image acquisition device 1 and the
Two image acquisition devices 2 are shot, and latter switching signal is used for controlling the 3rd image acquisition device 3 and the 4th image acquisition device 4 to clap
Take the photograph.Or, it is assumed that current of traffic to the right when, the first wheel pass through first sensor when trigger a switching signal, this is opened
OFF signal is used to control first to fourth figure collector to be shot simultaneously.
Tread region top and bottom part distort than more serious it is difficult to carry in the image photographed due to image acquisition device
Effective information is taken out, so if wanting to obtain at least needs 3 images on the picture theory of whole tread.But examined in actual design
Consider necessary redundancy section in every image, whole tread image is obtained present invention uses the image of 4 diverse locations.
For make the tread region in every image account for whole tread ratio it is identical and be evenly distributed on whole tread, in the present invention
4 approach switch sensors are set in order to which at equal intervals, interval width is the girth that 1/4 wheel rolling is justified, that is, is spaced.Settings and shooting schematic diagram of the Fig. 3 for sensor（Horizontal arrow refers to the traveling side of locomotive in Fig. 3
To）.
It is middle in order to only be used in reducing influence of the distortion critical regions to treatment effect as far as possible per pictures in invention
120 ° of tread region.Therefore using 4 approach switch sensors do every pictures that trigger source photographs all with front and rear figure
There is 15 ° of redundancy section between piece, in being finally spliced into by these redundancy sections from 4 images entirely for processing
The image of tread.
Embodiment two
As shown in figure 4, the embodiment of the invention discloses a kind of online image detecting method of train wheel thread defect, including it is as follows
Step：
S101：Wheel is to image zooming-out：Wheel is extracted in the whole image gathered from image acquisition device to region；
Because the image of image acquisition device initial acquisition is larger, it is necessary to cut to initial pictures, wheel is extracted to image, wheel
Extracting method to image is as follows：
With second camera（Second image acquisition device）Gather exemplified by trailing bogie front right tread, second camera is close in the system
Lower shoot of switch sensor triggering control obtains part tread image when wheel passes through 4 proximity transducer correspondence positions to obtain
Tread image completely is obtained, as Figure 6-9.
Used to gather in 4 wheel proximity transducer correspondence position wheel tread images, second camera shooting process
Larger field angle, this causes collection image to include excessive background information, influences the image processing efficiency of tread portions target image.
Thus need to cut tread image before tread image procossing is carried out, extract wheel tread region.Camera collection figure
Picture size is 6000*4000, and the present invention uses I2=imcrop (1, [ABCD]) cuts function and cuts second camera collection image,
Wherein, 1 processing object diagram 6 is represented,（A, B）Represent position of the top left corner pixel in original image after cutting；C represents to scheme after cutting
The width of picture, D represents the height of image after cutting.Because camera image collection is by proximity transducer control, IMAQ moment camera
It is substantially stationary to relative position with taking turns, thus present position is relatively fixed wheel tread image in the picture.To prevent vibration etc.
Influence of noise, it is [2,300 1,400 1000 that in the case where keeping certain corner redundancy condition, second camera correspondence, which cuts each parameter of function,
1100], [2,400 1,300 1,200 1300], [2,900 1,200 1,200 1400], [3,500 1,000 1,200 1600] Fig. 6-9
In each figure cutting effect as shown in figures 10-13.
Understand that tread image still includes excessive background information by Figure 10-13, the present invention is used before tread region is extracted
From the graph further segmentation object wheel is to image for the method for ellipses detection, because wheel is by wheel proximity transducer and makes it
Trigger in camera collection wheel tread image process, camera is fixed with wheel relative position, thus tread region is being schemed in image
Relative position is fixed as in, by taking Figure 13 as an example, directly according to lower right-most portion tread oval feature visibility point feature in image
Delimit the rectangular area for including part elliptical circular arc（W ∈ [500,1000], H ∈ [1000,1600]）Ellipses detection is carried out, favorably
The accuracy that amount of calculation improves detection is reduced simultaneously in evading complex background interference.Shown in concrete operations flow chart 5：
Input pending image；
Pending image is filtered, using canny operators rim detection is carried out after grayscale equalization, edge pixel point is
Characteristic point；
W ∈ [500,1000] in scanning figure, H ∈ [1000,1600] region, statistical nature point sets up accumulation structure, and accumulator is adopted
With two-dimensional array, two-dimensional array subscript is characterized dot center's coordinate, and accumulator initial value is set to 0；
Each characteristic point in the range of traversal, it is to scan other characteristic points to carry out string midpoint Hough transform, tries to achieve their midpoints,
Corresponding accumulator adds 1, and only string midpoint Hough transform is carried out to untreated characteristic point when calculating next characteristic point；
When accumulator count value is more than threshold value 5, then it is assumed that this position has an ellipse, its corresponding parameter（x0 i, y0 i）It is exactly
Oval corresponding centre coordinate, subscript i represents oval number；
Use each point（x0 i, y0 i）Elliptic equation is moved into origin, 3 couple on origin symmetry is found under new coordinate system
Characteristic point tries to achieve each elliptic equation, compares transverse size, and selection axial length most long ellipse is the length of side, and elliptical center is the centre of form
Square region as wheel to region；
Interception wheel carries out subsequent treatment as final wheel to the positive 120 ° region of image to image.Figure 14 is ellipses detection
Result figure.
Specifically, in order to remove influence of the distortion critical regions to segmentation tread region, to the wheel that extracts to region also
Need further to reduce the wheel extracted above to region.Positive 120 ° of tread region is only needed in the present invention as final
Wheel carries out subsequent treatment to image, so the square area length of side finally intercepted is 0.866 Ф.Figure 15 is the embodiment of the present invention
Taken turns in methods described to interception partial schematic diagram.
Further, split for the ease of later image, the step of methods described also includes image preprocessing：Use
MSRCR algorithms strengthen image taking turns, and comparison diagram is as shown in figs. 16-17 before and after the processing.
S102：Image is split：Image is split to taking turns using improved Based On Method of Labeling Watershed Algorithm, tread figure is extracted
Picture, as depicted in figs. 18-19；
S103：Image rectification：The transverse and longitudinal coordinate for dividing the image into the tread image extracted carries out geometric correction, and tight to distorting
The inoperative side of weight is cut, and obtains tread expanded view, as shown in figure 20；
S104：Image mosaic：According to last collection moment tread image size, using cube convolution method to first three moment tread figure
The unified tread image of size is obtained as entering row interpolation, using block matching method to the aforementioned four tread image adjacent collection moment
Sequentially splicing fusion two-by-two is carried out, the complete tread image of each wheel is obtained；
In the state of camera remains stationary, wheel sequentially passes through the different proximity transducer triggering camera collection images in 4 positions, because
And 4 moment correspondence wheel tread image pixel numbers are different.The present invention is used according to last collection moment tread image size
Cube convolution method enters row interpolation to first three moment tread image and obtains the unified tread image of size, as further illustrated in figures 21-24.
The present invention, which using the block matching method collection moment adjacent to aforementioned four tread image sequentially two-by-two splice, melts
Close.Splice flow as shown in figure 25.Specific method is as follows：
Two adjacent time charts are sequentially loaded into as matrix；
Determine image block scanning window and threshold values；
Start block scan, calculate absolute value difference value between image-region；
Judge whether the difference value exceedes threshold value, if it exceeds threshold value is then continued to scan on, stored if threshold value is not above
Position；
Curve Matching is carried out, splicing result is exported after fusion is weighted to the curve after matching.
Splicing result is as shown in figure 26.
S105：Image calibration：User's case marker determines paper and is placed in tread respectively to gather in moment camera photographable position, completes pair
Spliced tread image is demarcated, the corresponding relation after being spliced between the pixel distance and dimension information of image；
User's case marker determines paper and is placed in tread respectively to gather in moment camera photographable position, by taking the 4th camera collection position as an example,
Split tread image and plane rectification image as shown in Figure 27-28：Demarcating each grid of paper isPros
Shape, image detection scaling board grid pixel be about in 34*34, that is, image 1 pixel distance represent 1 mm distances, complete figure
As demarcation.
S106：Tread whether there is breakdown judge：By the comentropy and empirical value ratio that calculate splicing rear tread pattern image
Relatively come judge tread whether there is major defect failure；
The comentropy of 4 wheels in comparison diagram 21-24, as shown in table 1, defective car is can be seen that from the contrast of information entropy
Wheel information content is substantially greater than normal wheels.
Table 1 whether there is the tread image information entropy contrast of thread defect
| Tread type | Wheel 1 | Wheel 2 | Wheel 3 | Wheel 4 |
| Comentropy | 2.9213 | 3.3264 | 3.4781 | 2.8125 |
S107：Tread failure is extracted：Using improved splitting and merging to judging that the tread of existing defects is handled, utilize
Seed point growth is filled to the thread defect image after growth, obtains thread defect image, to the Shi Jishiyong grid of defect
Method is estimated that area is calculated using pixel in region in image, and the Gao Yukuan of pixel value is to utilize figure respectively in image
The max min of the row and column in the thread defect region as in asks difference to be obtained to calculate.
Handled using improved splitting and merging, the defective tread image flow chart after processing as shown in figure 29, is located
Manage design sketch as shown in figure 30.Processing is filled to the thread defect image after growth using seed point growth, so as to obtain
Thread defect image, as shown in figure 31.Illustrated to understand that each pixel distance of image herein can be with by image rectification above
It is 1mm to be approximately considered, then defect real area can be estimated using gridding method, and area utilizes pixel in region in image
Point is calculated.In image the Gao Yukuan of pixel value respectively be utilize image in thread defect region row and column maximum most
Small value asks difference to be obtained to calculate.Defects detection result is as shown in table 2.
The thread defect parameter of table 2 compares
| Defect area (mm2) | The width (mm) of defect part | The height (mm) of defect part | |
| Actual defects | 1336（Estimation） | 37 | 96 |
| Split rear tread pattern | 1298 | 42 | 94 |
It is using the beneficial effect produced by above-mentioned technical proposal：The system Computer receives each image acquisition device and passed
Four times defeated images, then each complete wheel tread letter is drawn after image is spliced and handled by methods described
Breath, and whether defective, thread defect accuracy of detection height is drawn to tread progress judgement, it can effectively avoid detection wrong
By mistake.
Claims (10)
1. a kind of online image detecting system of train wheel thread defect, it is characterised in that：Including computer, four IMAQs
Device and four approach switch sensors, the first image acquisition device（1）With the 3rd image acquisition device（3）Positioned at the first rail（5）
Outside, the second image acquisition device（2）With the 4th image acquisition device（4）Positioned at the second rail（6）Outside, the first IMAQ
Device（1）With the 3rd image acquisition device（3）With the second image acquisition device（2）With the 4th image acquisition device（4）Between with two rails
Between rail center line（7）For symmetry axis, the first image acquisition device（1）With the 3rd image acquisition device（3）Between and the second figure
As collector（2）With the 4th image acquisition device（4）Between with image acquisition device center line（8）For symmetry axis；Each image acquisition device
One train wheel of correspondence, the image for shooting correspondence wheel, axis and the wheel of each described image collector
Circle centre position in same level, the horizontal field of view angle of described image collector is all θ, the first image acquisition device（1）With
Two image acquisition devices（2）Positioned at the right side of locomotive, the 3rd image acquisition device（3）With the 4th image acquisition device（4）Positioned at locomotive
Left side, the first image acquisition device（1）With the 3rd image acquisition device（3）Horizontal field of view have partly overlap, the second IMAQ
Device（2）With the 4th image acquisition device（4）Horizontal field of view have partly overlap, four approach switch sensors are equally spaced
It is arranged at the second image acquisition device（2）With the 4th image acquisition device（4）Equitant second rail of horizontal field of view（6）Inner side,
And the distance between approach switch sensor is 0.785φ, φFor the rolling circular diameter of the wheel；When the second wheel（11）Touch
Send out the first approach switch sensor（10）When, the first wheel（9）Positioned at the first image acquisition device（1）Horizontal field of view in, the 3rd
Wheel（12）Positioned at the 3rd image acquisition device（3）Horizontal field of view in, the second wheel（11）Positioned at the second image acquisition device（2）'s
In horizontal field of view, the 4th wheel（13）Positioned at the 4th image acquisition device（4）Horizontal field of view in, four image acquisition devices difference the
IMAQ once is carried out to corresponding wheel；When the second wheel（11）Trigger the second approach switch sensor（14）When, first
Wheel（9）Positioned at the first image acquisition device（1）Horizontal field of view in, the 3rd wheel（12）Positioned at the 3rd image acquisition device（3）'s
In horizontal field of view, the second wheel（11）Positioned at the second image acquisition device（2）Horizontal field of view in, the 4th wheel（13）Positioned at the 4th
Image acquisition device（4）Horizontal field of view in, four image acquisition devices carry out IMAQ second to corresponding wheel respectively；When
Second wheel（11）Trigger the 3rd approach switch sensor（15）When, the first wheel（9）Positioned at the first image acquisition device（1）Water
Look squarely in field, the 3rd wheel（12）Positioned at the 3rd image acquisition device（3）Horizontal field of view in, the second wheel（11）Positioned at the second figure
As collector（2）Horizontal field of view in, the 4th wheel（13）Positioned at the 4th image acquisition device（4）Horizontal field of view in, four figure
As collector, third time carries out IMAQ to corresponding wheel respectively；When the second wheel（11）Trigger the 4th proximity switch sensing
Device（16）When, the first wheel（9）Positioned at the first image acquisition device（1）Horizontal field of view in, the 3rd wheel（12）Positioned at the 3rd figure
As collector（3）Horizontal field of view in, the second wheel（11）Positioned at the second image acquisition device（2）Horizontal field of view in, the 4th car
Wheel（13）Positioned at the 4th image acquisition device（4）Horizontal field of view in, four image acquisition devices distinguish the 4th time to corresponding wheel
Carry out IMAQ；Computer receives four images of each image acquisition device transmission, after image is spliced and handled
Go out each complete wheel tread information, and tread progress judgement is drawn whether defective.
2. the online image detecting system of train wheel thread defect as claimed in claim 1, it is characterised in that：First figure
As collector（1）With the 3rd image acquisition device（3）With the first rail（5）Between horizontal range be 2m, second image adopts
Storage（2）With the 4th image acquisition device（4）With the second rail（6）Between horizontal range be 2m.
3. the online image detecting system of train wheel thread defect as claimed in claim 1, it is characterised in that：Horizontal field of view angle
θ is 65 °.
4. the online image detecting system of train wheel thread defect as claimed in claim 1, it is characterised in that：Described image is adopted
Storage passes through support（17）It is fixed on by the rail.
5. the online image detecting system of train wheel thread defect as claimed in claim 1, it is characterised in that：Described image is adopted
Storage is high-speed cmos video camera.
6. a kind of usage right requires that the detecting system in 1-5 described in any one carries out train wheel thread defect in line image
Detection method, it is characterised in that comprise the following steps：
Wheel is to image zooming-out：Wheel is extracted in the whole image gathered from image acquisition device to region；
Image is split：Image is split to taking turns using improved Based On Method of Labeling Watershed Algorithm, tread image is extracted；
Image rectification：The transverse and longitudinal coordinate for dividing the image into the tread image extracted carries out geometric correction, and serious to distorting
Inoperative side is cut, and obtains tread expanded view；
Image mosaic：According to last collection moment tread image size, first three moment tread image is entered using cube convolution method
Row interpolation obtains the unified tread image of size, is carried out using the block matching method collection moment adjacent to aforementioned four tread image
Sequentially splicing fusion two-by-two, obtains the complete tread image of each wheel；
Image calibration：User's case marker determines paper and is placed in tread respectively to gather in moment camera photographable position, completes to spliced
Tread image is demarcated, the corresponding relation after being spliced between the pixel distance and dimension information of image；
Tread whether there is breakdown judge：The comentropy for splicing rear tread pattern image by calculating is compared to judge to step on empirical value
Face whether there is major defect failure；
Tread failure is extracted：Using improved splitting and merging to judging that the tread of existing defects is handled, seed is utilized
Point growth is filled to the thread defect image after growth, obtains thread defect image, and the Shi Jishiyong gridding method of defect is entered
Area is calculated using pixel in region in row estimation, image, and the Gao Yukuan of pixel value is utilized in image respectively in image
The max min of row and column in thread defect region ask difference to be obtained to calculate.
7. the online image detecting method of train wheel thread defect as claimed in claim 6, it is characterised in that methods described exists
Also include before image segmentation：The pre-treatment step optimized using MSRCR algorithms to the color information taken turns to image.
8. the online image detecting method of train wheel thread defect as claimed in claim 6, it is characterised in that the wheel is to figure
As the method extracted is as follows：
Input pending image；
Pending image is filtered, using canny operators rim detection is carried out after grayscale equalization, edge pixel point is
Characteristic point；
W ∈ [500,1000] in scanning figure, H ∈ [1000,1600] region, statistical nature point sets up accumulation structure, and accumulator is adopted
With two-dimensional array, two-dimensional array subscript is characterized dot center's coordinate, and accumulator initial value is set to 0；
Each characteristic point in the range of traversal, it is to scan other characteristic points to carry out string midpoint Hough transform, tries to achieve their midpoints,
Corresponding accumulator adds 1, and only string midpoint Hough transform is carried out to untreated characteristic point when calculating next characteristic point；
When accumulator count value is more than threshold value 5, then it is assumed that this position has an ellipse, its corresponding parameter（x0 i, y0 i）It is exactly
Oval corresponding centre coordinate, subscript i represents oval number；
Use each point（x0 i, y0 i）Elliptic equation is moved into origin, 3 couples of spies on origin symmetry are found under new coordinate system
Levy and a little try to achieve each elliptic equation, compare transverse size, selection axial length most long ellipse is the length of side, and elliptical center is the centre of form
Square region is as wheel to region；
Interception wheel carries out subsequent treatment as final wheel to the positive 120 ° region of image to image.
9. the online image detecting method of train wheel thread defect as claimed in claim 6, it is characterised in that：Described piece
Method of completing the square is as follows：
Two adjacent time charts are sequentially loaded into as matrix；
Determine image block scanning window and threshold values；
Start block scan, calculate absolute value difference value between image-region；
Judge whether the difference value exceedes threshold value, if it exceeds threshold value is then continued to scan on, stored if threshold value is not above
Position；
Curve Matching is carried out, splicing result is exported after fusion is weighted to the curve after matching.
10. the online image detecting method of train wheel thread defect as claimed in claim 6, it is characterised in that：It is described to improve
Splitting and merging comprise the following steps：
Setting judges sentence P and minimum unit size min, builds discriminant function；
Judge whether each region of image meets discriminant function；
It is considered as if discriminant function is met and meets splitting condition, then will meets the sub-district area image quartering of splitting condition, and
Image is judged again；If being unsatisfactory for discriminant function, merging is set to judge sentence Q, and judge sentence Q by merging
Judge whether there is subregion to meet merging condition in image, if it is merge the subregion for meeting merging condition, such as
Fruit is not to terminate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305046.8A CN107146224B (en) | 2017-05-03 | 2017-05-03 | The online image detecting system of train wheel thread defect and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305046.8A CN107146224B (en) | 2017-05-03 | 2017-05-03 | The online image detecting system of train wheel thread defect and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107146224A true CN107146224A (en) | 2017-09-08 |
| CN107146224B CN107146224B (en) | 2018-07-17 |
Family
ID=59775483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710305046.8A Active CN107146224B (en) | 2017-05-03 | 2017-05-03 | The online image detecting system of train wheel thread defect and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107146224B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921845A (en) * | 2018-07-10 | 2018-11-30 | 深圳大学 | Wheel tread rehabilitation plan generation method and device |
| CN111080632A (en) * | 2019-12-20 | 2020-04-28 | 石家庄铁道大学 | Wheel set tread polygon monitoring method and device and terminal equipment |
| CN113160176A (en) * | 2021-04-23 | 2021-07-23 | 歌尔股份有限公司 | Defect detection method and device |
| CN115439481A (en) * | 2022-11-09 | 2022-12-06 | 青岛平电锅炉辅机有限公司 | Deaerator welding quality detection method based on image processing |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105203552A (en) * | 2015-09-18 | 2015-12-30 | 南京拓控信息科技有限公司 | 360-degree tread image detecting system and method |
| CN106404791A (en) * | 2016-08-24 | 2017-02-15 | 北京主导时代科技有限公司 | Train, on-line wheel tread image detection device and flaw detection system |
-
2017
- 2017-05-03 CN CN201710305046.8A patent/CN107146224B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105203552A (en) * | 2015-09-18 | 2015-12-30 | 南京拓控信息科技有限公司 | 360-degree tread image detecting system and method |
| CN106404791A (en) * | 2016-08-24 | 2017-02-15 | 北京主导时代科技有限公司 | Train, on-line wheel tread image detection device and flaw detection system |
Non-Patent Citations (2)
| Title |
|---|
| CHRIS NORMAN等: "DESIGN OF A SYSTEM TO MEASURE TRACK MODULUS FROM A MOVING RAILCAR", 《PROCEEDINGS OF RAILWAY ENGINEERING CONFERENCE》 * |
| 孙冉: "在线式轮对踏面擦伤成像检测系统", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921845A (en) * | 2018-07-10 | 2018-11-30 | 深圳大学 | Wheel tread rehabilitation plan generation method and device |
| CN111080632A (en) * | 2019-12-20 | 2020-04-28 | 石家庄铁道大学 | Wheel set tread polygon monitoring method and device and terminal equipment |
| CN111080632B (en) * | 2019-12-20 | 2023-05-26 | 石家庄铁道大学 | Wheel set tread polygon monitoring method and device and terminal equipment |
| CN113160176A (en) * | 2021-04-23 | 2021-07-23 | 歌尔股份有限公司 | Defect detection method and device |
| CN113160176B (en) * | 2021-04-23 | 2022-10-18 | 歌尔股份有限公司 | Defect detection method and device |
| CN115439481A (en) * | 2022-11-09 | 2022-12-06 | 青岛平电锅炉辅机有限公司 | Deaerator welding quality detection method based on image processing |
| CN115439481B (en) * | 2022-11-09 | 2023-02-21 | 青岛平电锅炉辅机有限公司 | Deaerator welding quality detection method based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107146224B (en) | 2018-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107146224A (en) | The online image detecting system of train wheel thread defect and method | |
| CN109784333B (en) | Three-dimensional target detection method and system based on point cloud weighted channel characteristics | |
| CN104835164B (en) | A kind of processing method and processing device of binocular camera depth image | |
| EP2713310A2 (en) | System and method for detection and tracking of moving objects | |
| EP3340171B1 (en) | Depth image denoising method and denoising device | |
| CN107067382A (en) | A kind of improved method for detecting image edge | |
| CN104574353B (en) | The surface defect decision method of view-based access control model conspicuousness | |
| CN105678776B (en) | Laser vision sensor based weld image feature point extraction method | |
| CN107180416B (en) | Train wheel tread image deformity correction method and system | |
| CN102663760A (en) | Location and segmentation method for windshield area of vehicle in images | |
| CN104616258B (en) | A kind of rapid defogging method for road image | |
| CN107239748A (en) | Robot target identification and localization method based on gridiron pattern calibration technique | |
| CN102542282B (en) | Mosaic detection method and mosaic detection device for passive images | |
| CN103913149B (en) | A kind of binocular range-measurement system and distance-finding method thereof based on STM32 single-chip microcomputer | |
| CN108830133A (en) | Recognition methods, electronic device and the readable storage medium storing program for executing of contract image picture | |
| CN114820474A (en) | Train wheel defect detection method based on three-dimensional information | |
| CN103577828B (en) | A kind of Approach for road detection based on edge feature | |
| CN106596584B (en) | A kind of method and apparatus of viscose filament yarn spilt filament detection | |
| CN107480678A (en) | A kind of chessboard recognition methods and identifying system | |
| CN106022268A (en) | Identification method and device of speed limiting sign | |
| CN111257329A (en) | Smartphone camera defect detection method and detection system | |
| CN106651837A (en) | White glass plate surface edge breakage defect detecting method | |
| CN107330906A (en) | Improvement thinning algorithm based on curve matching | |
| CN107154053A (en) | Moving target detecting method under static background | |
| CN114241436A (en) | Lane line detection method and system for improving color space and search window |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210412 Address after: 215200 558 FENHU Road, Wujiang District, Suzhou, Jiangsu Patentee after: Suzhou Huayun Shichuang Intelligent Technology Co.,Ltd. Address before: 050043 No. 17, North Second Ring Road, Hebei, Shijiazhuang Patentee before: SHIJIAZHUANG TIEDAO University |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240109 Address after: Room 617, Building 1B, Launching Area of Yangtze River Delta International R&D Community, No. 286, Qinglonggang Road, High speed Railway New Town, Xiangcheng District, Suzhou City, Jiangsu Province, 215000 Patentee after: Suzhou Huichuang Yunlian Intelligent Technology Co.,Ltd. Address before: 215200 558 FENHU Road, Wujiang District, Suzhou, Jiangsu Patentee before: Suzhou Huayun Shichuang Intelligent Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |