CN107261257A - Air detection method and device in a kind of woven hose based on machine vision - Google Patents
Air detection method and device in a kind of woven hose based on machine vision Download PDFInfo
- Publication number
- CN107261257A CN107261257A CN201710380377.8A CN201710380377A CN107261257A CN 107261257 A CN107261257 A CN 107261257A CN 201710380377 A CN201710380377 A CN 201710380377A CN 107261257 A CN107261257 A CN 107261257A
- Authority
- CN
- China
- Prior art keywords
- woven hose
- image
- air
- detection method
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 40
- 239000007788 liquid Substances 0.000 claims description 58
- 238000004458 analytical method Methods 0.000 claims description 57
- 238000012545 processing Methods 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000005286 illumination Methods 0.000 claims description 14
- 238000003384 imaging method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 26
- 239000000741 silica gel Substances 0.000 description 26
- 229910002027 silica gel Inorganic materials 0.000 description 26
- 238000001802 infusion Methods 0.000 description 23
- 230000008859 change Effects 0.000 description 7
- 239000012780 transparent material Substances 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000002572 peristaltic effect Effects 0.000 description 6
- 239000003086 colorant Substances 0.000 description 4
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 210000002784 stomach Anatomy 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 239000011521 glass Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 2
- 210000004276 hyalin Anatomy 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000000474 nursing effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 239000002904 solvent Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010000060 Abdominal distension Diseases 0.000 description 1
- 206010001526 Air embolism Diseases 0.000 description 1
- 208000031361 Hiccup Diseases 0.000 description 1
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010253 intravenous injection Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000009738 saturating Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
- A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
- A61M5/16831—Monitoring, detecting, signalling or eliminating infusion flow anomalies
Landscapes
- Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Engineering & Computer Science (AREA)
- Anesthesiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Hematology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses air detection method and device in a kind of woven hose based on machine vision, its woven hose image gathered in real time based on machine vision technique Direct Recognition, the form for corresponding to woven hose region in image is analyzed, the air form in woven hose is detected with this.The air form that air detection scheme can be in effective detection woven hose in the woven hose constituted accordingly, and its accuracy of detection is high, it is reliable and stable.
Description
Technical field
The present invention relates to medical field, and in particular to the air detection technology during automatic infusion in infusion pipeline.
Background technology
In venoclysis, general micro air can be dissolved by internal blood；If it exceeds a certain amount of air enters
Blood vessel may cause air embolism, extremely dangerous for patient.
In enteral feed, because patient can not normally feed, it is necessary to by conduit, nutrient solution is injected into patient's stomach
In.If large quantity of air enters in stomach, patient can not discharge air by having the hiccups.Generation gaseous distention, may be supportted when serious
Broken coat of the stomach, threatens patients ' lives safety.
Therefore, the air in detection woven hose is very important.Due to the air in woven hose, there are two kinds of forms：1. folder
The miscellaneous bubble in liquid；2. in pipe without or a small amount of liquid for being attached to tube wall, presentation empty pipe condition.
And it is existing for transfusion inner air tube detection method have it is several under it is several：
Detected 1. being realized using ultrasonic wave by the speed difference of different medium.I.e. in infusion pipeline both sides, one end transmitting
Ultrasonic wave, the other end receives ultrasonic wave, and with certain frequency and resting period transmitting ultrasonic wave, receiving terminal is according to the signal received
Compare with transmission signal, with regard to that can judge in outlet pipe it is liquid or bubble.This method is easy and effective, but ultrasonic sensor into
This height, is realized complicated.
2. it can be reflected through different medium using light and the principle such as reflect and realize detection.I.e. in infusion pipeline two
Side, while setting transmitting LED, another side sets light sensor to receive.Light sensor receives light, produces faint small electricity
Stream, voltage signal is become by enhanced processing, and incoming analog-digital converter sampling, last CPU is calculated and handled.
The premise of the detection scheme is that infusion pipeline must be transparent material, and in order to light refraction effect more
Well, it is necessary to change woven hose pipeline shape, circular pipeline is typically changed over three-pointed hollow star or trapezoidal pipeline, selection folding
Penetrate light of the rate than larger wavelength.When light is (non-perpendicular) at a certain angle passes through different medium, there is a fixed refraction angle
Degree and light-path.Pipeline another side receives the light in light eye point.If being mixed into air in pipeline, light irradiation air, air
Refractive index is less than liquid refractivity, and light-path is changed, and the luminous intensity that pipeline another side is received dies down.Light sensor handle connects
The light received is converted into faint electric current, then is converted into voltage signal through oversampling circuit, eventually passes amplification filtering, ADC samplings, meter
After calculation machine is calculated, judge the size of voltage signal, to judge that the light intensity received is weak, and then judge whether infusion pipeline is mixed into
Air.This method principle is simple, but needs complicated structure of arranging in pairs or groups, and drive circuit is complicated.
In addition, air detection scheme goes back generally existing accuracy of detection not in actual application in existing woven hose
Height, a series of problems, such as stability is not high, this largely effects on its practicality.Thus there is provided a kind of high accuracy, high stable reliability
Woven hose in air detection scheme the problem of be this area urgent need to resolve.
The content of the invention
For the problems of air detection technology in existing woven hose, it is necessary to which a kind of precision is high, high defeated of reliability
Air detection scheme in liquid pipe.
Therefore, the technical problems to be solved by the invention are to provide air detection in a kind of woven hose based on machine vision
Method and device, its accuracy of detection is high, reliable and stable.
In order to solve the above-mentioned technical problem, air detection method in the woven hose based on machine vision that the present invention is provided,
Correspond to the shape in woven hose region in its woven hose image gathered in real time based on machine vision technique Direct Recognition, analysis image
State, the air form in woven hose is detected with this.
In this detection scheme, the detection method with the picture of the speed captured in real-time woven hose of at least 1 frame per second, and
Each frame picture is analyzed.
In this detection scheme, the detection method is carried by carrying out edge extracting to woven hose image, then by analysis
The edge image taken judges air conditions in woven hose.
In this detection scheme, under the conditions of corresponding light photograph, if in the edge image extracted, corresponding to the spy in woven hose
It is continuous in region to determine, and edge lines are single line bar, then judges that in woven hose be liquid entirely；
If in the edge image extracted, corresponding to being discontinuous in the specific region in woven hose, then judging woven hose
Inside there is liquid, there is bubble；
If in the edge image extracted, corresponding to being continuous in the specific region in woven hose, and edge lines are double
Lines, a line edge line is tube wall, and one is the reflective light of tube wall, then judges it is air entirely in woven hose.
In this detection scheme, the detection method analyzes correspondence by carrying out binary conversion treatment to woven hose image
In the distribution situation of black and white in the fixed position region of woven hose, air conditions in woven hose are judged with this.
In this detection scheme, if corresponding to being continuous all black in the fixed position region of woven hose, judging defeated
It is liquid entirely in liquid pipe；
If corresponding to there is white to have black in the fixed position region of woven hose, judging there is liquid in woven hose, there is gas
Bubble；
If corresponding to being continuous whole white in the fixed position region of woven hose, judging that in woven hose be air entirely.
In this detection scheme, during the binary conversion treatment, suitable threshold value is automatically selected by adaptively adjusting, will be adopted
The coloured image of collection carries out binary conversion treatment.
It is color to the woven hose collected first when carrying out binary conversion treatment in the detection method in this detection scheme
Color image is converted into greyish white image；
Then, binary conversion treatment is carried out to the greyish white image of woven hose according to default threshold value；
Then, whether non-woven hose region is all white pixel in analysis of binary image；If not white pixel, adjust
Whole threshold value, untill being all white pixel；
Then, whether transfusion wall section has continuous black picture element to wrap up in analysis of binary image, if it is not,
Threshold value is adjusted, until wrapping up the region by continuous black picture element；
Finally, binary conversion treatment is carried out to the image of collection with the threshold value.
In order to solve the above-mentioned technical problem, air detecting device in the woven hose based on machine vision that the present invention is provided,
The detection means includes：
Darkroom, the darkroom is fixedly installed relative to woven hose, builds woven hose image capture environment；
Image collecting device, described image harvester is arranged on darkroom, and collection in real time is located at the woven hose in darkroom
Image；
In graphics processing unit, the woven hose image that described image processing unit Direct Recognition is gathered in real time, analysis image
Corresponding to the form in woven hose region, the air form in woven hose is detected with this.
In the scheme of detection means, described image processing unit is with process chip and image recognition and analysis module
Constitute, described image identification and analysis module Direct Recognition collect woven hose image, and analyze in image corresponding to woven hose
The form in region, the form of transfusion inner air tube is detected with this；The process chip control image collecting device and image are known
Other and analysis module, which cooperates, completes IMAQ and discriminance analysis.
In the scheme of detection means, described image harvester is constituted with camera lens and imaging sensor.
In the scheme of detection means, lighting unit is provided with the darkroom, the lighting unit coordinates closed dark
Chamber interior structure constitutes the constant woven hose image capture environment of illumination condition.
In the scheme of detection means, the detection means also includes a bin, and the bin, which has, can close door, in it
Fixed woven hose, and accommodate darkroom.
In the scheme of detection means, the cover plate at the top of the darkroom is arranged on the door of bin as background board.
The air form that air detection scheme can be in effective detection woven hose in the infusion pipeline constituted accordingly；Furthermore we
Case is realized simple in construction, it is easy to accomplish, reliability can effectively solve the problem that the problems of prior art.What is constituted accordingly is defeated
Air detection scheme in liquid pipe, it can effectively realize the accurate identification to inner air tube of infusing based on machine vision technique；Furthermore
This programme reliability is high, can effectively solve the problem that the problems of prior art.
In addition, the detection technique that this programme is provided, can be applied to medical field, this programme is integrated in infusion pump and fed
Support pump in, may be implemented in infusion to venous patient or enteral feed during, bubble and blank pipe in effective detection infusion tube, greatly
It is big to improve security.
Brief description of the drawings
The present invention is further illustrated below in conjunction with the drawings and specific embodiments.
Fig. 1 is the infusion pipeline structural representation that is related in present example；
Fig. 2 is the primary structure figure of air detecting device in woven hose in present example；
Fig. 3 is the primary structure figure in darkroom in present example；
Fig. 4 is the top view in darkroom in present example；
Fig. 5 obtains to be used in present example 1 for three kinds of different shape woven hose images after same threshold value, rim detection
The processing image arrived；
Fig. 6 is uses same threshold value in present example 2 for three kinds of different shape woven hose images, after the processing of two-value method
The processing image obtained respectively；
The schematic flow sheet that Fig. 7 automatically determines for two-value method threshold value in present example 2；
Fig. 8 is the schematic flow sheet of two-value method analysis in present example 2.
Embodiment
In order that the technical means, the inventive features, the objects and the advantages of the present invention are easy to understand, tie below
Conjunction is specifically illustrating, and the present invention is expanded on further.
First, the woven hose that this example is directed to is a class medical treatment consumptive materials, is not limited to be used for venous transfusion or enteral nutrition
The woven hose that liquid is fed, is also not limited to the use of the venoclysis of people and venoclysis and the enteral feed of enteral feed or animal.
Referring to Fig. 1, the woven hose 100 for automatic intravenous injection and automatic enteral feed generally comprises four parts：First
Transparent conduit 101, silica gel hose 102, the second transparent conduit 103, transparent conduit and silica gel hose joint 104.
Wherein, the first transparent conduit 101 is used to connect infusion bag or infusion bottle 105 arrives silica gel hose 102；And silica gel hose
102 can be transparent and opaque；Second transparent conduit 103 is used to connect silica gel hose to joint 106.
Here joint 106 is the joint of connection stomach tube in patient body, or syringe needle insertion patient's blood vessel.
Here silica gel hose 103 is plastic products, transparent, soft, flexible, coordinates peristaltic pump 105 to realize automatic defeated
Liquid and nursing.
So constituting woven hose 100, the flowing of liquid in pipe is controlled by peristaltic pump 107 (as shown in Figure 2) when in use
System.In actual application process, the meeting air inlet of woven hose 100, for the air in woven hose, there is two kinds of forms：It 1. is
It is mixed in the bubble of liquid, i.e. portion of air and a part of liquid；It is air entirely 2. being not have liquid in pipe.
Due to the difference containing air form in woven hose, its external morphology is also different.Therefore, this programme passes through based on machine
Device vision technique carrys out in the woven hose image that Direct Recognition is gathered in real time, analysis image to correspond to the form in woven hose region, with
This come detect transfusion inner air tube form.
This programme recognizes the figure of the infusion pipeline respective regions gathered in real time section especially by based on machine vision technique
Picture, the position of infusion pipeline in the picture immobilizes, and infusion pipeline is transparent material so that liquid or sky in pipeline
Gas is all presented in the picture.From there through the form for corresponding to woven hose region in analysis image, you can effective detection woven hose
Air inside whether is mixed into, or is full liquid, or is air detection scheme in the states such as air, the infusion pipeline constituted accordingly entirely
Air form that can be in effective detection woven hose.
On this basis, it is the real-time and high accuracy of guarantee testing result, this programme is specifically with the speed of at least 1 frame per second
The captured in real-time picture related to silica gel hose in woven hose is spent, then each frame picture of shooting is analyzed, with this determination
The change of woven hose internal state, then come detect transfusion inner air tube form.
Referring to Fig. 2, it show the totality of air detecting device in the woven hose based on machine vision of this programme offer
Structure chart.
As seen from the figure, this detection means 200 mainly includes pump bin 210, collection and identifying device 220, and this is several in darkroom 230
Individual part.
Wherein, bin 210 constitutes the space structure for detection means, fixed corresponding woven hose 100 to be detected；Together
When be used to dispose corresponding silica gel hose 102, peristaltic pump 107, motor 108, darkroom 240, collection and identifying device 220 etc..
Corresponding door lid 211 is provided with the bin 210, the detection space for constituting a closing, isolation is outside
Interference, prevents foreign matter from entering；Prevent extraneous light from entering in bin simultaneously, influence camera is taken pictures shooting, to ensure the present apparatus
Reliability.
Here peristaltic pump 107, motor 108, the transparent pipe 101 of silica gel hose 102 and first and the second transparent pipe 103
For the plan of establishment of existing automatic infusion pipe, it is not repeated here herein.
Darkroom 230, it is arranged in bin 210, one closing of composition, the constant IMAQ space of illumination condition,
The silica gel hose 102 in woven hose 100 is shot for collection and identifying device 220, it is to avoid different illumination conditions, to successive image
The influence of identification, it is ensured that the precision of successive image detection identification.
As shown in Figures 2 and 3, the darkroom 230 holds the silica gel hose 102 being placed in bin 210 and passed through, and passes through joint
104 are connected to the first transparent conduit 101, the second transparent conduit 103.By coordinating with bin 210 so that silica gel hose 102 is consolidated
It is scheduled in bin 210, so that the silica gel hose 102 through darkroom 230 is fixed relative to darkroom 230, i.e., positioned at darkroom 230
Interior part is changeless, is used as IMAQ section.
The connecting portion 232 set simultaneously in the bottom in the darkroom 230, for connecting collection and identifying device 220；The darkroom
230 top is provided with corresponding cover plate 231, and the cover plate 231 corresponds to the top of darkroom 230, coordinates with it, can close completely,
Closed darkroom 230, reaches the purpose of shielding extraneous light, so as to form closed, the constant figure of illumination condition in darkroom 230
As collection space.
When implementing, the cover plate 231 in this programme can be further used as corresponding background board, for detecting door lid
Whether 211 close.Specifically, the cover plate 231 corresponds to the top of darkroom 230, it is arranged on door lid 211, and switched with door
Closure, after door closure, cover plate 231 and darkroom 230 are closed completely；After door opening, the cover plate 231 departs from darkroom 230；
By realizing whether detection door lid 211 closes by detecting whether the top in darkroom 230 has cover plate 231.It is preferred that, the background
It is provided with plate 231 for detecting pattern and/or color that whether door close.White background plate is such as used, is not limited to white
Color, and whole white or other colors, or with special icon.Material surface to light be not total reflection, using diffusing reflection as
It is main.
So can by collection and identifying device by shoot and identification background board on pattern and/or color to detect door be
It is no to close.Such as when camera is taken pictures to bin, in the picture of acquisition, judge whether FX has the icon in picture, to examine
Survey whether door closes.
In addition, the shooting, collecting of the collection and identifying device 220 for the ease of bottom, the bottom in darkroom 230 be it is transparent,
Constituted using fully transparent material, so in this darkroom 230, silica gel hose 102 is fixed on inside, is placed in fully transparent material
On, while being white background plate 231 on the top of silica gel hose 102.
Such fully transparent material, can be glass, it may also be said to be acrylic board, but do not limit to both.This is saturating
The effect of bright material is to facilitate machine vision to be clapped with camera through the transparent material the silica gel hose 102 in darkroom
According to while isolating extraneous unrestrained liquid, dust and exterior object, which enter, damages machine vision camera.
Referring to Fig. 3 and Fig. 4, collection and identifying device 220 in this programme are the processing center of whole detection means, and it leads to
The form for corresponding to woven hose region in the woven hose image that Direct Recognition is gathered in real time, analysis image is crossed, is detected with this defeated
The form of liquid inner air tube.
The collection and identifying device 220 (are not shown mainly by IMAQ part 221 and graphics processing unit part in figure
Go out) coordinate composition.
Wherein IMAQ part 221, specially collection of the camera for image, are placed in secretly by connecting portion 232
The bottom of room 230, i.e., under silica gel hose 102；The camera is under the control of processing unit part, LED illumination of arranging in pairs or groups
Lamp, takes pictures, and view data is passed to graphics processing unit part to the silica gel hose 102 in darkroom in real time.Taking the photograph here
As head includes black and white camera or colour imagery shot；And camera is made up of imaging sensor (CCD or CMOS) and camera lens；Camera lens
From the big depth of field, microspur.
Specifically, there is LED illumination lamp 222 inside coupling part 232, at the same in the middle of coupling part 232 and darkroom 230 across
Hyaline layer (as described above).The hyaline layer is to obstruct external contamination, and printing opacity completely, and picture is shot beneficial to camera.
Using 4 LED illumination lamps 222 in this programme, four angles of coupling part 232 are respectively arranged at, and positioned at shooting
Head side, and camera stretches out in the middle of coupling part 232.
In addition, being not limited to this for the installation position of LED illumination lamp 222, shooting head mirror is also can be placed in as needed
Under head, on, under transparent material, or in background board, as long as (exterior light can must be shielded when camera is taken pictures
Line) there is provided necessary illumination.
Graphics processing unit part in the collection and identifying device 220 is used for the processing and identification for completing woven hose image
Correspond to the form in woven hose region in the woven hose image of collection, analysis image, the shape of transfusion inner air tube is detected with this
State.
The graphics processing unit part is specific by corresponding circuit board and to be arranged on the circuit board process chip and constitutes.Image
Imaging sensor in collecting part 221 is set on the board, and the image collected is reached into process chip；Same phase
The LED illumination lamp answered is connected to circuit board, and is controlled by process chip；And process chip control imaging sensor is gathered in real time
Corresponding woven hose image, and coordinate corresponding image recognition and analysis module, it is identified and analysis chart to collecting image
Correspond to the form in woven hose region as in, the form of transfusion inner air tube is detected with this.
Here process chip preferably corresponding CPU realizes that it controls imaging sensor with the speed of at least 1 frame per second
The captured in real-time picture related to silica gel hose in woven hose, then each frame picture of shooting is analyzed, it is defeated with this determination
The change of liquid pipe internal state, then come detect transfusion inner air tube form.
In this woven hose in air detecting device, due to relatively solid between silica gel hose, background board and camera three
It is fixed, so silica gel hose and background board appear in the fixed position of image, it will not change.In the case, gather and recognize dress
Lens focus is fixed in putting 220, the image of shooting will not zoom, image content is constant, and the image that then CPU is obtained, is fixed
Image, such CPU analyzes image, only need to analyze the region part of corresponding silica gel flexible pipe, you can carry out air detection.
Thus the detection means constituted operationally, when automatic infusion or nursing, close so that on door by door
Cover plate with and darkroom close completely, shield extraneous light, form closed in darkroom, the constant IMAQ of illumination condition
Space.
Motor drives the liquid in peristaltic pump rotate counterclockwise, extruding silica gel hose pipe, and silicon is flowed to from the first transparent conduit
Glue flexible pipe, then the second transparent conduit is flowed to, eventually flow in patient body.
During this, silica gel hose in the CPU control LED illuminations darkroom in collection and identifying device, to form constant light
According to condition.
At the same time, CPU shoots cover plate image by camera, to detect whether door lid closes.It is determined that door lid
After closing, the related image of silica gel hose in the speed captured in real-time darkroom that CPU passes through camera at least 1 frame per second；Camera
In imaging sensor the image of collection is reached into CPU in real time；CPU coordinates corresponding image recognition and parser, to collection
To each frame picture air form in analysis, discriminance analysis silica gel hose is identified.Due to light level, the irradiation of light
The environmental change such as angle factor has a great impact to the accuracy of post analysis result, and this programme is built by setting up darkroom
Closed dark indoor environment, is used as image capture environment.In the image capture environment intraoral illumination degree, the irradiating angle of light etc. because
Number is all constant in entirely analysis process, so as to be greatly improved post analysis accuracy.
In this example, in the woven hose image gathered in real time come Direct Recognition based on machine vision technique, analysis image
Corresponding to woven hose region form when, have a variety of implementations, illustrate below by way of specific application example.
Example 1：
This example judges transfusion by carrying out edge extracting to woven hose image, then by analyzing the edge image extracted
The form of inner air tube.
When implementing, this example builds corresponding closed structure (as shown in Figure 1) relative to woven hose, for infusing
During pipe image real-time acquisition, extraneous light is shielded, it is ensured that later stage edge extracting and the accuracy of analysis.
As shown in figure 1, the closed structure is dual closed structure, by bin, door, darkroom, cover plate and collection and knowledge
Other device, which coordinates, to be constituted, and as detailed above, is not repeated here herein.
In the closed structure, door is light tight, during work, and door must shut off.The effect of the door：
1st, during wriggling pump work, protect pump not by external interference, while peristaltic pump does not jeopardize the safety of user, and its yet
The safety for the human or animal that he contacts.
2nd, extraneous light is shielded, when Internal camera head works, is taken pictures in real time, it is to avoid extraneous light enters, influence imaging,
Interfere, make CPU processing increase difficulty in collection and identifying device, while preventing internal light from leaking out.
In the closed structure, cover plate is specific using the monochromatic background board, homochromy positive light of becoming clear as background board.
In the closed structure, using transparent woven hose, collection and camera and woven hose in identifying device are relatively solid
It is fixed, and woven hose is parallel to the face of shooting, several centimeters of the distance of camera lens and woven hose, and in closed darkroom, shielding is outside
Light.
In the closed structure, the realtime graphic of collection and identifying device for gathering transparent woven hose in closed darkroom,
And analysis is identified to the image collected, with the air form in woven hose in detection image.
The collection and identifying device are constituted with camera, CPU and image recognition and analysis module.Camera conduct
Image collecting device is made up of camera lens and imaging sensor, and wherein camera lens is placed on darkroom, and tubular with transfusion in darkroom
Structure is shot into spacing.
Image recognition and analysis module are for the form for the woven hose for recognizing, analyzing in the image that camera is collected.Should
Image recognition and analysis module judge by carrying out edge extracting to woven hose image, then by analyzing the edge image extracted
The form of transfusion inner air tube.
CPU controls camera and image recognition and analysis module to cooperate and completes IMAQ and discriminance analysis.Specifically
, CPU control cameras are taken pictures the image of woven hose in real time with the speed per second for being more than or equal to 1 frame, then control image recognition and
Analysis module is to each frame picture analyzing.
When analyzing picture, image recognition and analysis module carry out edge extracting first, to extract image inner flexible tube edge；
Furthermore, the edge image of extraction is analyzed to judge air conditions in woven hose.
Because the air form induction and conclusion inside woven hose has following three kinds of situations：
1st, it is liquid entirely, liquid may have a variety of colors；
2nd, there is liquid, there is bubble；
3rd, it is full air.
Accordingly, in this example image recognition and analysis module analyzes edge image in the following way, defeated to realize
The detection of liquid pipe inner air form：
If extract edge image in, corresponding to be in the specific region in flexible pipe it is continuous, and edge lines be single line
Bar, then judge that in woven hose be liquid entirely；
If in the edge image extracted, corresponding to being discontinuous in the specific region in flexible pipe, then judging in woven hose
There is liquid, there is bubble；
If extract edge image in, corresponding to be in the specific region in flexible pipe it is continuous, and edge lines be two-wire
Bar, then judge it is air entirely in woven hose.
For above-mentioned analytical plan, this example is further by solvent of infusing for exemplified by transparency liquid and certain environment brightness
Under the conditions of carry out verification experimental verification.Other color liquids and other brightness conditions are handled with reference to this, and specific analytical method and threshold value are true
It is fixed possible different.
Referring to Fig. 5, it show use same threshold value, rim detection for three kinds of different shape woven hose images after obtain
Processing image.
Referring to Fig. 5 a, it is the image that camera is shot, using same threshold when being colourless transparent liquid entirely that it, which is shown in pipe,
The processing image obtained after value, rim detection.
Referring to Fig. 5 b, it is a part of colourless transparent liquid and portion of air, the figure that camera is shot that it, which is shown in pipe,
Picture, using same threshold value, the processing image obtained after rim detection.
Referring to Fig. 5 c, it show in pipe to be entirely the state of blank pipe, the image that camera is shot, using same threshold
The processing image obtained after value, rim detection.
Compare by analysis and understand：
It is liquid entirely in the case of the first, in flexible pipe.Liquid is cylindrical shape, the effect for having magnifying glass for light.Pipe
Sub- intermediate luminance is very high.Then in the edge image of its corresponding extraction, corresponding to be in the specific region in woven hose it is continuous,
And edge lines are single line bar, single line bar is flexible pipe outer wall.
In the case of second, there is liquid in flexible pipe, there is bubble.Then correspond to transfusion in the edge image of its corresponding extraction
It is discontinuous in specific region in pipe, and rambling distribution.
It is air entirely in the case of the third, in flexible pipe.Then correspond in the edge image of its corresponding extraction in woven hose
Specific region in be continuous, and edge lines are two-wire bar, and a line edge line is tube wall in two-wire bar, and one is that tube wall is anti-
The light of light.
As can be seen here, this example provides by analyzing the edge image extracted to judge the side of transfusion inner air tube form
Case, can be accurately detected the air form in woven hose.
Example 2：
This example especially by woven hose image carry out binary conversion treatment, and analyze corresponding to woven hose fixed position
The distribution situation of black and white in region, air conditions in woven hose are judged with this.
Here two-value method is the pixel (pixel for including different colours) image different colours, is first respectively converted into
0 to 255, totally 256 kinds of greyish white images of degree show, from complete black 0 to complete white 255.Then a threshold value, threshold value are chosen
Between 0 to 255, the pixel higher than threshold value is represented with 255 white pixels, and the pixel less than threshold value is represented with 0 black, most
Only have two kinds of pixels of black and white to represent eventually.
Accordingly method can Simplified analysis complexity, only analyze two kinds of pixel distribution situations, be known that woven hose pipe inside information
Condition.
When implementing, closed structure scheme in this example Case-based Reasoning 1 is carried out, closed structure scheme here with
It is identical in example 1, it is not repeated here herein.
Wherein, collection and the CPU control cameras in identifying device and image recognition and analysis module collaborative work completion
IMAQ and discriminance analysis；CPU control cameras are taken pictures the image of woven hose in real time with the speed per second for being more than or equal to 1 frame,
Image recognition and analysis module are controlled again to each frame picture analyzing.
When analyzing picture, image recognition and analysis module are directed to each two field picture collected and carry out two-value method processing,
So that there was only two kinds of colored pixels points (white and black) in image；Then analysis is corresponding in the fixed position region of woven hose
The distribution situation of black and white, air conditions in woven hose are judged with this.
For in the case of three kinds of woven hose inner air form (as described in example 1), the image recognition in this example
And analysis module carrys out analysis of binary image in the following way, to realize the detection of woven hose inner air form：
If corresponding to being continuous all black in the fixed position region of woven hose, judging that in woven hose be liquid entirely；
If corresponding to there is white to have black in the fixed position region of woven hose, judging there is liquid in woven hose, there is gas
Bubble；
If corresponding to being continuous whole white in the fixed position region of woven hose, judging that in woven hose be air entirely.
It is woven hose image space region in the picture for fixed position region here.Due to woven hose and shooting
Head position is relatively fixed, therefore fixed position is imaged woven hose in the picture.
In this example, when the image to collecting carries out binary conversion treatment, according to ambient light intensity size, one is selected
Suitable threshold value, shows coloured image with two-value method.
In order to ensure the accuracy of testing result in this example, adaptively adjusted and automatically selected suitably according to actual conditions
Binary-state threshold.
Specifically, this example is installed on pump in woven hose, and closes under conditions of pump door and be determined binaryzation
Threshold value.When being handled, due to not knowing whether there is liquid in deferent before this in advance, air, and a part of liquid and bubble mixing
These three situations, it is that liquid is not known yet for which kind of color, therefore automatically selects suitable binary-state threshold by adaptively adjusting,
Implementation process is following (referring to Fig. 7)：
First, infusion pump is started working, and the coloured image arrived for camera shooting, collecting is first converted into greyish white image,
The binary-state threshold of selection one predetermined (internal processes are fixed), starts binary conversion treatment.
Then nonspecific region, in analysis of binary image (is not the area in the region of woven hose, as white background plate
Domain), judge whether the region is all white pixel, if not white pixel, adjust threshold value, be until being all white pixel
Only.
Then specific region (woven hose region), in analysis of binary image, judges whether the region has continuous black
Color pixel is wrapped up, and the continuous black picture element is transfusion tube wall；If no, adjusting threshold value, until by continuous black picture element bag
Wrap up in the region.
Thus, obtained threshold value is adjusted, then is the binary-state threshold of this suitable infusion process air detection.Whole defeated
During note, threshold value need to only be determined at the beginning, untill when this infusion is completed, all with all collections of the threshold process
Image.
The binary-state threshold automatically selected is adaptively adjusted based on such scheme, this example carries out two-value to woven hose image
Change is handled, and analyzes distribution situation black, white in the fixed position region corresponding to woven hose, and inner air tube of infusing is judged with this
The whole process of situation is following (referring to Fig. 8)：
1st, continuously taken pictures by the camera speed per second for being more than or equal to 1 frame the image of woven hose.
2nd, the binary-state threshold automatically selected based on above-mentioned adaptive adjustment, two-value is carried out to each two field picture collected
Method processing, obtains corresponding binary image (i.e. black white image).
3rd, in analysis of binary image (i.e. black white image) in specific region (i.e. in woven hose), black and white pixel
Distribution situation.
4th, analysis judges whether there is a white pixel region in specific region, along woven hose directional spreding：If so, then
The width in white pixel region is judged, if very wide represent to be all liquid in pipe, without drum and air；If it is not, being then transferred to
Step 5.
Whether it is continuous white pixel point along woven hose directional spreding that the 5th, analysis judges in specific region：If so, then sentencing
The width in disconnected defeated white pixel region, if it is very narrow, and surrounding has discontinuous black picture element, then manages interior all air,
It is empty pipe condition now；If it is not, then judging to be mixed into bubble in woven hose.
For above-mentioned binary image analysis scheme, this example further by solvent of infusing for exemplified by colourless transparent liquid and
Verification experimental verification is carried out under certain environment brightness conditions.Other color liquids and other brightness conditions are handled with reference to this, and other are specific
Analysis method and threshold value are determined may be different.
Referring to Fig. 6, it is shown in this example uses same threshold value for three kinds of different shape woven hose images, carries out two
The processing image obtained respectively after the processing of value method.)
Referring to Fig. 6 a, it is the image that camera is shot, using same threshold when being colourless transparent liquid entirely that it, which is shown in pipe,
Value, the processing image obtained respectively after the processing of two-value method.
Referring to Fig. 6 b, when it is shown in pipe as part colourless transparent liquid and portion of air, the figure that camera is shot
Picture, using same threshold value, the processing image obtained respectively after the processing of two-value method.
Referring to Fig. 6 c, it is shown in pipe when being entirely the state of blank pipe, the image that camera is shot, using same threshold
Value, the processing image obtained respectively after the processing of two-value method.
It is (defeated by fixed position region in analysis of binary image in this example because camera and woven hose are relatively fixed
Liquid pipe region) distribution situation of interior monochrome pixels point judges air conditions in woven hose with this：
After the processing of two-value method, if the region both sides are continuous completely black color pixel zonal distribution, that is, tube wall of infusing.In
Between be continuous white pixel, because liquid is shaped as column in pipe, (principle of magnifying glass) has convergence effect to light,
So white pixel region is wide, without black picture element doping；It is then liquid entirely in woven hose.
After the processing of two-value method, if the region has white and pixel to have black, as a sheet of white pixel region, liquid
Body region.Positioned at the black picture element band of edge distribution, tube wall of as infusing；There is black picture element in intermediate region and white pixel is mixed
Close, as bubble；Then air is mixed into woven hose.
After the processing of two-value method, if infusion pipeline region black picture element is more than white；But, because tube wall is reflective, have
One white light belt, the white pixel band, elongated linear branch；Then represent that in woven hose be air entirely.
As can be seen here, this example provide binary image analysis method, can analyze completely in woven hose be full liquid,
It is air or a part of liquid and three kinds of situations of a part of bubble entirely.
General principle, principal character and the advantages of the present invention of the present invention has been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the simply explanation described in above-described embodiment and specification is originally
The principle of invention, without departing from the spirit and scope of the present invention, various changes and modifications of the present invention are possible, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (14)
1. air detection method in the woven hose based on machine vision, it is characterised in that based on machine vision technique Direct Recognition
Correspond to the form in woven hose region in the woven hose image gathered in real time, analysis image, the sky in woven hose is detected with this
Gas form.
2. air detection method in woven hose according to claim 1, it is characterised in that the detection method with it is per second extremely
The picture of the speed captured in real-time woven hose of few 1 frame, and each frame picture is analyzed.
3. air detection method in woven hose according to claim 1, it is characterised in that the detection method passes through to defeated
Liquid pipe image carries out edge extracting, then judges air conditions in woven hose by analyzing the edge image extracted.
4. air detection method in woven hose according to claim 3, it is characterised in that under the conditions of corresponding light photograph, if
In the edge image of extraction, corresponding to be in the specific region in woven hose it is continuous, and edge lines be single line bar, then judge
It is liquid entirely in woven hose；
If in the edge image extracted, corresponding to being discontinuous in the specific region in woven hose, then judging have in woven hose
Liquid, there is bubble；
If extract edge image in, corresponding to be in the specific region in woven hose it is continuous, and edge lines be two-wire bar,
A line edge line is tube wall, and one is the reflective light of tube wall, then judges it is air entirely in woven hose.
5. air detection method in woven hose according to claim 1, it is characterised in that the detection method passes through to defeated
Liquid pipe image carries out binary conversion treatment, and analyzes the distribution situation of black and white in the fixed position region corresponding to woven hose, with this
Judge air conditions in woven hose.
6. air detection method in woven hose according to claim 5, it is characterised in that if corresponding to the fixation of woven hose
It is continuous all black in the band of position, then judges that in woven hose be liquid entirely；
If corresponding to there is white to have black in the fixed position region of woven hose, judging there is liquid in woven hose, there is bubble；
If corresponding to being continuous whole white in the fixed position region of woven hose, judging that in woven hose be air entirely.
7. air detection method in woven hose according to claim 5, it is characterised in that during the binary conversion treatment, leads to
Cross adaptive adjustment and automatically select suitable threshold value, the coloured image of collection is subjected to binary conversion treatment.
8. air detection method in woven hose according to claim 7, it is characterised in that two are carried out in the detection method
When value is handled, greyish white image is converted into the woven hose coloured image collected first；
Then, binary conversion treatment is carried out to the greyish white image of woven hose according to default threshold value；
Then, whether non-woven hose region is all white pixel in analysis of binary image；If not white pixel, threshold is adjusted
Value, untill being all white pixel；
Then, whether transfusion wall section has continuous black picture element to wrap up in analysis of binary image, if it is not, adjustment
Threshold value, until wrapping up the region by continuous black picture element；
Finally, binary conversion treatment is carried out to the image of collection with the threshold value.
9. air detecting device in the woven hose based on machine vision, it is characterised in that the detection means includes：
Darkroom, the darkroom is fixedly installed relative to woven hose, builds woven hose image capture environment；
Image collecting device, described image harvester is arranged on darkroom, and collection in real time is located at the woven hose image in darkroom；
Graphics processing unit, the woven hose image of described image processing unit Direct Recognition image acquisition device, analysis chart
Correspond to the form in woven hose region as in, the air form in woven hose is detected with this.
10. air detecting device in woven hose according to claim 9, it is characterised in that described image processing unit by
Process chip and image recognition and analysis module, which coordinate, to be constituted, and described image identification and analysis module Direct Recognition collect transfusion
Pipe image, and the form for corresponding to woven hose region in image is analyzed, the form of transfusion inner air tube is detected with this；The place
Manage chip controls image collecting device and image recognition and analysis module cooperates and completes IMAQ and discriminance analysis.
11. air detecting device in woven hose according to claim 9, it is characterised in that described image harvester by
Camera lens and imaging sensor, which coordinate, to be constituted.
12. air detecting device in woven hose according to claim 9, it is characterised in that be provided with photograph in the darkroom
Bright unit, the lighting unit coordinates closed darkroom internal structure to constitute the constant woven hose IMAQ ring of illumination condition
Border.
13. air detecting device in woven hose according to claim 9, it is characterised in that the detection means also includes
One bin, the bin, which has, can close door, fixed woven hose in it, and accommodate darkroom.
14. air detecting device in woven hose according to claim 13, it is characterised in that the cover plate at the top of the darkroom
It is arranged on as background board on the door of bin.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710380377.8A CN107261257A (en) | 2017-05-25 | 2017-05-25 | Air detection method and device in a kind of woven hose based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710380377.8A CN107261257A (en) | 2017-05-25 | 2017-05-25 | Air detection method and device in a kind of woven hose based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107261257A true CN107261257A (en) | 2017-10-20 |
Family
ID=60064673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710380377.8A Pending CN107261257A (en) | 2017-05-25 | 2017-05-25 | Air detection method and device in a kind of woven hose based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107261257A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108069575A (en) * | 2017-12-15 | 2018-05-25 | 江苏和合环保集团有限公司 | A kind of Treatment of Sludge exhaust system |
| CN113144327A (en) * | 2021-03-18 | 2021-07-23 | 华南理工大学 | Medical intelligent auxiliary infusion device and infusion method based on machine vision |
| CN113252702A (en) * | 2021-07-02 | 2021-08-13 | 北京力耘柯创医学研究院 | Automatic detection method for defects of infusion catheter by machine vision system |
| CN114897871A (en) * | 2022-05-23 | 2022-08-12 | 凯联医疗科技(上海)有限公司 | Bubble detection device and bubble detection method based on light refraction and reflection |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101357726A (en) * | 2007-08-01 | 2009-02-04 | 株式会社日立建筑系统 | Abnormality monitoring device in elevator car |
| CN101663577A (en) * | 2007-04-23 | 2010-03-03 | 巴尔龙匈牙利公司楚格分公司 | Investigation system and technique |
| JP2011240866A (en) * | 2010-05-20 | 2011-12-01 | Kobe Steel Ltd | Method for detection of vehicle side lamp mounted to traveling body, and movable fence control device for opening and closing door mounted to movable fence using the detection method |
| JP2013059567A (en) * | 2011-09-14 | 2013-04-04 | Tosho Inc | Narcotic drug storage apparatus |
| CN103179995A (en) * | 2010-07-15 | 2013-06-26 | 陶锴 | Iv monitoring by video and image processing |
| US20130201471A1 (en) * | 2010-10-19 | 2013-08-08 | Baxter International Inc. | Optical imaging system for air bubble and empty bag detection in an infusion tube |
| CN105372252A (en) * | 2014-08-25 | 2016-03-02 | 研祥智能科技股份有限公司 | Detecting system and method based on machine vision |
| CN105682310A (en) * | 2014-11-19 | 2016-06-15 | 刘皓强 | Combined lighting device and method based on image quality control |
| CN106250823A (en) * | 2016-07-21 | 2016-12-21 | 同济大学 | A kind of palm print and palm vein recognition methods and palm print and palm vein image capture instrument |
| CN106526917A (en) * | 2016-12-07 | 2017-03-22 | 北京工业大学 | Liquid crystal screen dot matrix detection device achieving scanning by means of line-scan digital camera |
| CN208114878U (en) * | 2017-05-25 | 2018-11-20 | 江苏优鼎医疗科技有限公司 | Air detecting device in a kind of high-precision perfusion tube |
-
2017
- 2017-05-25 CN CN201710380377.8A patent/CN107261257A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101663577A (en) * | 2007-04-23 | 2010-03-03 | 巴尔龙匈牙利公司楚格分公司 | Investigation system and technique |
| CN101357726A (en) * | 2007-08-01 | 2009-02-04 | 株式会社日立建筑系统 | Abnormality monitoring device in elevator car |
| JP2011240866A (en) * | 2010-05-20 | 2011-12-01 | Kobe Steel Ltd | Method for detection of vehicle side lamp mounted to traveling body, and movable fence control device for opening and closing door mounted to movable fence using the detection method |
| CN103179995A (en) * | 2010-07-15 | 2013-06-26 | 陶锴 | Iv monitoring by video and image processing |
| US20130201471A1 (en) * | 2010-10-19 | 2013-08-08 | Baxter International Inc. | Optical imaging system for air bubble and empty bag detection in an infusion tube |
| JP2013059567A (en) * | 2011-09-14 | 2013-04-04 | Tosho Inc | Narcotic drug storage apparatus |
| CN105372252A (en) * | 2014-08-25 | 2016-03-02 | 研祥智能科技股份有限公司 | Detecting system and method based on machine vision |
| CN105682310A (en) * | 2014-11-19 | 2016-06-15 | 刘皓强 | Combined lighting device and method based on image quality control |
| CN106250823A (en) * | 2016-07-21 | 2016-12-21 | 同济大学 | A kind of palm print and palm vein recognition methods and palm print and palm vein image capture instrument |
| CN106526917A (en) * | 2016-12-07 | 2017-03-22 | 北京工业大学 | Liquid crystal screen dot matrix detection device achieving scanning by means of line-scan digital camera |
| CN208114878U (en) * | 2017-05-25 | 2018-11-20 | 江苏优鼎医疗科技有限公司 | Air detecting device in a kind of high-precision perfusion tube |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108069575A (en) * | 2017-12-15 | 2018-05-25 | 江苏和合环保集团有限公司 | A kind of Treatment of Sludge exhaust system |
| CN113144327A (en) * | 2021-03-18 | 2021-07-23 | 华南理工大学 | Medical intelligent auxiliary infusion device and infusion method based on machine vision |
| CN113252702A (en) * | 2021-07-02 | 2021-08-13 | 北京力耘柯创医学研究院 | Automatic detection method for defects of infusion catheter by machine vision system |
| CN113252702B (en) * | 2021-07-02 | 2021-09-28 | 北京力耘柯创医学研究院 | Automatic detection method for defects of infusion catheter by machine vision system |
| CN114897871A (en) * | 2022-05-23 | 2022-08-12 | 凯联医疗科技(上海)有限公司 | Bubble detection device and bubble detection method based on light refraction and reflection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107261257A (en) | Air detection method and device in a kind of woven hose based on machine vision | |
| CN105181714B (en) | A kind of bottling liquid Impurity Detection System and its detection method based on image procossing | |
| CN107110879B (en) | Liquid level inspection device, automatic analysis device and processing device | |
| EP2540214A1 (en) | Apparatus for detection of catheter location for intravenous access | |
| CN203490180U (en) | Impurity detection device of automatic light inspection machine | |
| US20160206204A1 (en) | Organ Imaging Device | |
| CN104458760B (en) | Automatic lamp-checking machine detection device for foreign matter | |
| KR100664644B1 (en) | Ringer's Fluid Flow Measurement System Using Image Signal Processing | |
| CN105784722B (en) | On a kind of assembly line in medicinal liquid bottle visible foreign matters detection method and system | |
| CN101209207A (en) | Eyelid detecting apparatus, eyelid detecting method and program thereof | |
| CN102788801A (en) | Online detection system and detection method thereof | |
| AU2003290334A1 (en) | A pupilometer | |
| CN103385539A (en) | Single cigarette empty end detection method and special equipment based on machine vision | |
| CN217385116U (en) | Automatic change device of measurement mud settlement ratio | |
| CN208114878U (en) | Air detecting device in a kind of high-precision perfusion tube | |
| CN111242011A (en) | Display and input device | |
| CN110960194A (en) | Ear phase acquisition device and acquisition method | |
| CN115170493A (en) | Identification method and system for micro-defect of sterile package and storage medium | |
| CN106053484A (en) | Testing apparatus and method for foreign matters on surface of liquid crystal glass | |
| CN205844212U (en) | A kind of detection equipment of liquid-crystalline glasses Superficial Foreign Body | |
| CN108745444A (en) | A kind of test tube and rack for test tube identifying system | |
| CN114897871B (en) | A bubble detection device and bubble detection method based on light refraction and reflection | |
| CN112752003A (en) | Light supplementing method and device, light supplementing equipment and monitoring equipment | |
| CN209387542U (en) | A kind of detection device for eliminating material shade | |
| CN113588650B (en) | Medical sewage purification monitoring system |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180330 Address after: 215600, Suzhou, Jiangsu province Zhangjiagang Le Yu town (Zhangjiagang Linjiang green science and Technology Innovation Park) Applicant after: Jiangsu Youding Medical Technology Co.,Ltd. Address before: 201612 nine new road, Jiuting Town, Songjiang District, Shanghai, room 76, room 1208 Applicant before: Shanghai Yukang Medical Equipment Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171020 |