CN103352283A - Identification method for judging fine motion sate of image with yarn-state sensor - Google Patents
Identification method for judging fine motion sate of image with yarn-state sensor Download PDFInfo
- Publication number
- CN103352283A CN103352283A CN2013103046341A CN201310304634A CN103352283A CN 103352283 A CN103352283 A CN 103352283A CN 2013103046341 A CN2013103046341 A CN 2013103046341A CN 201310304634 A CN201310304634 A CN 201310304634A CN 103352283 A CN103352283 A CN 103352283A
- Authority
- CN
- China
- Prior art keywords
- yarn
- image
- state
- center line
- motion state
- 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
Images
Landscapes
- Treatment Of Fiber Materials (AREA)
- Filamentary Materials, Packages, And Safety Devices Therefor (AREA)
Abstract
The invention discloses an identification method for judging the fine motion state of an image with a yarn-state sensor. The yarn-state sensor is provided with a case and an electronic control unit which is arranged inside the case. The electronic control unit comprises a power circuit, a processor, a communication interface circuit, a state indicator light, an image cache device, an infrared emission unit and an imaging sensor, wherein the communication interface circuit, the state indicator light, the image cache device and the infrared emission unit are connected with the processor, the imaging sensor is connected with the image cache device, an infrared filter is arranged on the infrared emission unit, and the yarn-state sensor which can judges the fine motion state of the image is arranged inside the processor. The identification method for judging the fine motion state of the image with the yarn-state sensor includes the following step of 1, periodically collecting images of yarn, 2, conducting binarization processing on the images of the yarn, 3, computing the center line of the projection area of the yarn in the y axis direction, 4, computing the similar value of the current center line and the former center line with the similarity algorithm, confirming that the yarn is in a motion state if L is larger than or equal to the preset threshold value K, and confirming that the yarn is in a stationary state if L is smaller than the preset threshold value K.
Description
Technical field
The present invention relates to a kind of yarn conditions sensor and judge the image-recognizing method of fine motion state, belong to the technical field of the electronics of weaving.
Background technology
For textile machinery, the inspection of yarn conditions is extremely important.Such as, seamless underwear machine and socks machine, one group of yarn broken yarn or scarce yarn, if untimely discovery, then whole ready-made clothes just scrapped.Therefore yarn conditions detects effectively reduction in the numbers of seconds, enhances productivity, and reduces production costs.
The yarn conditions sensor that uses at present adopts the infrared photodiode of differential type to detect.It is simple that this mode has principle, the advantage that cost is low, but the gain of amplifying circuit is very large, easily be interfered, and surveyed area is very narrow and small, very high to installation requirement, and the yarn detectability for slow motion is poor, such as the few multicolored yarn of some use amounts.Therefore under slow motion state, the amplitude of moving about yarn is very little, detection difficult.
Although yarn has many burr slowly mobile status lower swing amplitude is little all around because of yarn, under slow motion state, the position of burr can change, and this variation that detects burr just can be differentiated the fine motion state of yarn.
Summary of the invention
The objective of the invention is in order to overcome weak point of the prior art, adopt the detection mode of imageing sensor, utilize the change in location of yarn burr under the fine motion state, extract the y coordinate center line of figure warp thread picture, adopt the similitude comparative approach, can judge the fine motion state of yarn, this scheme principle is simple, reliable operation, and be touchless detection scheme, insensitive to the variation of ambient lighting.
The technical solution adopted for the present invention to solve the technical problems is:
The yarn conditions sensor is judged the image-recognizing method of fine motion state, the shell of described yarn conditions sensor setting U-shaped, and the electronic-controlled installation that is arranged on described enclosure, described electronic-controlled installation comprises the power circuit that power supply is provided, carry out the processor of calculation process, the communication interface circuit that is connected with described processor, carry out the status indicator lamp of state indication, image buffer storage, infrared emission unit, and the imageing sensor that is connected with described image buffer storage, on the described imageing sensor infrared filter is set, described infrared emission unit be arranged on described imageing sensor directly over, described yarn passes from the below of described infrared emission unit, and project on the described imageing sensor, the inside of described processor arranges the image-recognizing method of yarn fine motion state, described image-recognizing method can detect static or motion state under described yarn light exercise state, the steps include:
(1), every fixed cycle T, described processor gathers the view data of described imageing sensor output by described image buffer storage
f t(x, y), x=1 ~ M, y=1 ~ N, the view data that last time gathered is
f T-1(x, y), wherein, M is the maximum pixel number on the x direction of principal axis, N is the maximum pixel number on the y direction of principal axis;
(2), adopt Binarization methods, with described view data
f t(x, y) carries out binary conversion treatment, obtains two-valued function
y t(x, y), and the view field of described yarn
y t(x, y)=1, the non-view field of described yarn
y t(x, y)=0;
(3), along the y direction of principal axis, adopt the central line pick-up algorithm, calculate the center line of described yarn view field
z t(x), the center line that and last time gathered the described yarn view field of image is
z T-1(x);
(4), adopt similitude algorithm, computer center's line
z t(x) and center line last time be
z T-1(x) similar value L when L is greater than or equal to predetermined threshold value K, judges that described yarn is kept in motion; As L during less than predetermined threshold value K, judge that described yarn remains static.
In the step 3, described central line pick-up algorithm, the mean value of the ordinate of the described yarn of employing calculating view field,
In the step 4, described similitude algorithm adopts center line
z t(x) with last time center line
z T-1(x) poor quadratic sum, i.e. L=
(
z t(x)-
z T-1(x))
2
Implementing good effect of the present invention is: 1, with the detection mode of imageing sensor, utilize the change in location of yarn burr under the fine motion state, extract the y coordinate center line of figure warp thread picture, adopt the similitude comparative approach, can judge the fine motion state of yarn; 2, principle is simple, reliable operation; 3, insensitive to the variation of ambient lighting, and non-contact type detects, on yarn without impact.
Description of drawings
Fig. 1 is the installation diagram of the electronic-controlled installation of yarn conditions sensor;
Fig. 2 is the theory diagram of the electronic-controlled installation of yarn conditions sensor;
Fig. 3 is the image discriminating schematic diagram.
The specific embodiment
Now the invention will be further described by reference to the accompanying drawings:
With reference to Fig. 1-3, the yarn conditions sensor is judged the image-recognizing method of fine motion state, the shell of described yarn conditions sensor setting U-shaped, and the electronic-controlled installation that is arranged on described enclosure.Described shell plays protection and holds the effect of described electronic-controlled installation.
Described electronic-controlled installation comprises the power circuit 2 that power supply is provided, the processor 1 that carries out calculation process, the communication interface circuit 4 that is connected with described processor 1, the status indicator lamp 3, image buffer storage 6, the infrared emission unit 5 that carry out the state indication.Described electronic-controlled installation is installed on the circuit board 8.
Described power circuit 2 is that input power is carried out level conversion, and voltage stabilizing, for other circuit provide power supply.
Described status indicator lamp 3 is used to indicate the duty of described yarn, can represent with different colors different states, such as, infrared expression halted state, green expression motion state.
Described communication interface circuit 4 is responsible for the central controller of the state superior of described yarn is transmitted, like this, and just can be with the co-ordination of a plurality of described yarn conditions sensor.
The imageing sensor 7 of being responsible for gathering the figure warp thread picture also is set, is connected with described image buffer storage 6.Described imageing sensor 7 is set to the CCD linear imaging sensor of infrared ray responsive or CMOS linear imaging sensor.Described image buffer storage 6 is that described processor 1 can read as required for view data high speed, a large amount of of described imageing sensor 7 outputs of interim storage.
On the described imageing sensor 7 infrared filter 9 is set, but the light beyond the filtering infrared light can improve environmental suitability so greatly, avoids the interference of external light source.For definition and the contrast of reinforcement yarn imaging, described infrared emission unit 5 be arranged on described imageing sensor 7 directly over, described yarn passes from the below of described infrared emission unit 5, and projects on the described imageing sensor 7.
The inside of described processor 1 arranges the image-recognizing method of yarn fine motion state, and described image-recognizing method can detect static or motion state under described yarn light exercise state, the steps include:
(1), every fixed cycle T, described processor 1 gathers the view data of described imageing sensor 7 outputs by described image buffer storage 6
f t(x, y), x=1 ~ M, y=1 ~ N, the view data that last time gathered is
f T-1(x, y), wherein, M is the maximum pixel number on the x direction of principal axis, N is the maximum pixel number on the y direction of principal axis;
(2), adopt Binarization methods, with described view data
f t(x, y) carries out binary conversion treatment, obtains two-valued function
y t(x, y), and the view field of described yarn
y t(x, y)=1, the non-view field of described yarn
y t(x, y)=0;
(3), along the y direction of principal axis, adopt the central line pick-up algorithm, calculate the center line of described yarn view field
z t(x), the center line that and last time gathered the described yarn view field of image is
z T-1(x);
(4), adopt similitude algorithm, computer center's line
z t(x) and center line last time be
z T-1(x) similar value L when L is greater than or equal to predetermined threshold value K, judges that described yarn is kept in motion; As L during less than predetermined threshold value K, judge that described yarn remains static.
In step 1, described processor 1 is sampled every fixed cycle T, obtains the image sequence of two-dimensional matrix
f t(x, y),
f T-1(x, y),
f T-2(x, y) ...
In step 2, described Binarization methods can adopt the method for experiment to determine segmentation threshold, also can adopt histogram method to obtain segmentation threshold, if
f t(x, y) is greater than or equal to segmentation threshold, then
y t(x, y)=0 is the non-view field of described yarn herein; If
f t(x, y) is less than segmentation threshold, then
y t(x, y)=1 is the view field of described yarn herein.
In step 3, described central line pick-up algorithm, the mean value of the ordinate of the described yarn of employing calculating view field,
Namely
z t(x)=
(
y t(x, y) * y)/
y t(x, y).This algorithm is averaged the view field of described yarn along the y direction of principal axis, obtain the center line function.Along with the movement of described yarn, top burr also can change by occurrence positions, finally cause the marked change of center line function.
In step 4, described similitude algorithm adopts center line
z t(x) with last time center line
z T-1(x) poor quadratic sum, i.e. L=
(
z t(x)-
z T-1(x))
2Because the slow movement of described yarn, the amplitude of oscillation of yarn is very little, but the marked change of top burr meeting occurrence positions, and its center line function also can marked change.Therefore, with center line
z t(x) with last time center line
z T-1(x) subtract each other, then carry out a square summation, just can detect the motion change of described yarn, and differentiate: when L is greater than or equal to predetermined threshold value K, judge that described yarn is kept in motion; As L during less than predetermined threshold value K, judge that described yarn remains static.
Claims (3)
1. the yarn conditions sensor is judged the image-recognizing method of fine motion state, the shell of described yarn conditions sensor setting U-shaped, and the electronic-controlled installation that is arranged on described enclosure, described electronic-controlled installation comprises the power circuit that power supply is provided, carry out the processor of calculation process, the communication interface circuit that is connected with described processor, carry out the status indicator lamp of state indication, image buffer storage, infrared emission unit, and the imageing sensor that is connected with described image buffer storage, on the described imageing sensor infrared filter is set, described infrared emission unit be arranged on described imageing sensor directly over, described yarn passes from the below of described infrared emission unit, and project on the described imageing sensor, it is characterized in that: the inside of described processor arranges the image-recognizing method of yarn fine motion state, described image-recognizing method can detect static or motion state under described yarn light exercise state, the steps include:
(1), every fixed cycle T, described processor gathers the view data of described imageing sensor output by described image buffer storage
f t(x, y), x=1 ~ M, y=1 ~ N, the view data that last time gathered is
f T-1(x, y), wherein, M is the maximum pixel number on the x direction of principal axis, N is the maximum pixel number on the y direction of principal axis;
(2), adopt Binarization methods, with described view data
f t(x, y) carries out binary conversion treatment, obtains two-valued function
y t(x, y), and the view field of described yarn
y t(x, y)=1, the non-view field of described yarn
y t(x, y)=0;
(3), along the y direction of principal axis, adopt the central line pick-up algorithm, calculate the center line of described yarn view field
z t(x), the center line that and last time gathered the described yarn view field of image is
z T-1(x);
(4), adopt similitude algorithm, computer center's line
z t(x) and center line last time be
z T-1(x) similar value L when L is greater than or equal to predetermined threshold value K, judges that described yarn is kept in motion; As L during less than predetermined threshold value K, judge that described yarn remains static.
2. yarn conditions sensor according to claim 1 is judged the image-recognizing method of fine motion state, it is characterized in that: in the step 3, and described central line pick-up algorithm, the mean value of the ordinate of the described yarn of employing calculating view field,
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103046341A CN103352283A (en) | 2013-07-19 | 2013-07-19 | Identification method for judging fine motion sate of image with yarn-state sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013103046341A CN103352283A (en) | 2013-07-19 | 2013-07-19 | Identification method for judging fine motion sate of image with yarn-state sensor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103352283A true CN103352283A (en) | 2013-10-16 |
Family
ID=49308691
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013103046341A Pending CN103352283A (en) | 2013-07-19 | 2013-07-19 | Identification method for judging fine motion sate of image with yarn-state sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103352283A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111005152A (en) * | 2019-12-20 | 2020-04-14 | 杭州晶一智能科技有限公司 | Yarn detection method based on graph similarity comparison |
CN111058131A (en) * | 2019-12-31 | 2020-04-24 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on moving distance analysis |
CN111058182A (en) * | 2019-12-25 | 2020-04-24 | 杭州晶一智能科技有限公司 | Yarn state detection method based on projection area statistics |
CN111058183A (en) * | 2019-12-19 | 2020-04-24 | 杭州晶一智能科技有限公司 | Yarn detection method based on image form recognition |
CN111058270A (en) * | 2019-12-24 | 2020-04-24 | 杭州晶一智能科技有限公司 | Yarn state detection method based on gravity center analysis |
CN111088597A (en) * | 2019-12-23 | 2020-05-01 | 杭州晶一智能科技有限公司 | Contour line analysis-based yarn state detection method |
CN111139562A (en) * | 2019-12-31 | 2020-05-12 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on gradient analysis |
CN111139579A (en) * | 2019-12-27 | 2020-05-12 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on longitudinal width distribution |
CN111139580A (en) * | 2019-12-28 | 2020-05-12 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on longitudinal histogram analysis |
CN111139582A (en) * | 2019-12-28 | 2020-05-12 | 杭州晶一智能科技有限公司 | Textile machine yarn monitoring method based on edge projection analysis |
CN111285185A (en) * | 2018-12-07 | 2020-06-16 | 卓郎纺织解决方案两合股份有限公司 | Winding machine and device for identifying residual yarn |
CN111519296A (en) * | 2020-04-14 | 2020-08-11 | 江南大学 | On-line detection device and method for distribution of speed change points in drafting zone |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07288689A (en) * | 1994-04-15 | 1995-10-31 | Fuji Photo Film Co Ltd | Device and method for binarization processing of image signal |
EP1282076A2 (en) * | 2001-07-31 | 2003-02-05 | Canon Kabushiki Kaisha | Self-adaptive binarization of digital images |
CN1924734A (en) * | 2006-03-23 | 2007-03-07 | 浙江工业大学 | Control method for online quality detection |
CN201406511Y (en) * | 2009-05-15 | 2010-02-17 | 慈溪市太阳纺织器材有限公司 | Device for detecting motion state of yarn |
CN102031605A (en) * | 2010-11-12 | 2011-04-27 | 刘瑜 | Detection device for spinning machine yarn state and detection method thereof |
CN201896216U (en) * | 2010-11-12 | 2011-07-13 | 刘瑜 | Yarn-state detecting device for spinning machine |
CN102409458A (en) * | 2011-07-14 | 2012-04-11 | 刘瑜 | Yarn state detecting device based on small-size image sensor and detecting method |
CN202247113U (en) * | 2011-07-14 | 2012-05-30 | 刘瑜 | Yarn state detector based on small-sized image sensor |
CN102495026A (en) * | 2011-11-23 | 2012-06-13 | 天津大学 | Acquiring method of optical zone central line used in linear laser scanning vision measurement system |
-
2013
- 2013-07-19 CN CN2013103046341A patent/CN103352283A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07288689A (en) * | 1994-04-15 | 1995-10-31 | Fuji Photo Film Co Ltd | Device and method for binarization processing of image signal |
EP1282076A2 (en) * | 2001-07-31 | 2003-02-05 | Canon Kabushiki Kaisha | Self-adaptive binarization of digital images |
CN1924734A (en) * | 2006-03-23 | 2007-03-07 | 浙江工业大学 | Control method for online quality detection |
CN201406511Y (en) * | 2009-05-15 | 2010-02-17 | 慈溪市太阳纺织器材有限公司 | Device for detecting motion state of yarn |
CN102031605A (en) * | 2010-11-12 | 2011-04-27 | 刘瑜 | Detection device for spinning machine yarn state and detection method thereof |
CN201896216U (en) * | 2010-11-12 | 2011-07-13 | 刘瑜 | Yarn-state detecting device for spinning machine |
CN102409458A (en) * | 2011-07-14 | 2012-04-11 | 刘瑜 | Yarn state detecting device based on small-size image sensor and detecting method |
CN202247113U (en) * | 2011-07-14 | 2012-05-30 | 刘瑜 | Yarn state detector based on small-sized image sensor |
CN102495026A (en) * | 2011-11-23 | 2012-06-13 | 天津大学 | Acquiring method of optical zone central line used in linear laser scanning vision measurement system |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111285185A (en) * | 2018-12-07 | 2020-06-16 | 卓郎纺织解决方案两合股份有限公司 | Winding machine and device for identifying residual yarn |
CN111285185B (en) * | 2018-12-07 | 2022-02-25 | 卓郎纺织解决方案两合股份有限公司 | Winding machine and device for identifying residual yarn |
CN111058183A (en) * | 2019-12-19 | 2020-04-24 | 杭州晶一智能科技有限公司 | Yarn detection method based on image form recognition |
CN111058183B (en) * | 2019-12-19 | 2021-08-10 | 佛山市君丽织造有限公司 | Yarn detection method based on image form recognition |
CN111005152A (en) * | 2019-12-20 | 2020-04-14 | 杭州晶一智能科技有限公司 | Yarn detection method based on graph similarity comparison |
CN111088597A (en) * | 2019-12-23 | 2020-05-01 | 杭州晶一智能科技有限公司 | Contour line analysis-based yarn state detection method |
CN111088597B (en) * | 2019-12-23 | 2021-08-13 | 安徽尧舜智能袜业有限公司 | Contour line analysis-based yarn state detection method |
CN111058270A (en) * | 2019-12-24 | 2020-04-24 | 杭州晶一智能科技有限公司 | Yarn state detection method based on gravity center analysis |
CN111058182A (en) * | 2019-12-25 | 2020-04-24 | 杭州晶一智能科技有限公司 | Yarn state detection method based on projection area statistics |
CN111139579A (en) * | 2019-12-27 | 2020-05-12 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on longitudinal width distribution |
CN111139582A (en) * | 2019-12-28 | 2020-05-12 | 杭州晶一智能科技有限公司 | Textile machine yarn monitoring method based on edge projection analysis |
CN111139580A (en) * | 2019-12-28 | 2020-05-12 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on longitudinal histogram analysis |
CN111139562A (en) * | 2019-12-31 | 2020-05-12 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on gradient analysis |
CN111058131A (en) * | 2019-12-31 | 2020-04-24 | 杭州晶一智能科技有限公司 | Method for monitoring yarns of spinning machine based on moving distance analysis |
CN111519296A (en) * | 2020-04-14 | 2020-08-11 | 江南大学 | On-line detection device and method for distribution of speed change points in drafting zone |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103352283A (en) | Identification method for judging fine motion sate of image with yarn-state sensor | |
CN103336962A (en) | Image judgment method of yarn status sensor | |
St-Charles et al. | Flexible background subtraction with self-balanced local sensitivity | |
CN102409458A (en) | Yarn state detecting device based on small-size image sensor and detecting method | |
CN103226712B (en) | A kind of remnant object detection method based on finite state machine | |
CN103389841A (en) | Detecting method and device for suppressing interference of low-frequency noise | |
KR102676085B1 (en) | Sensor control device, sensor control method and program | |
JPH07336694A (en) | Mobile object detection method using background difference method | |
CN102830247A (en) | Method and device for detecting rotation state of rotation part | |
CN103999127A (en) | Object detection device and object detection method | |
CN106023249A (en) | Moving object detection method based on local binary similarity pattern | |
CN103810718A (en) | Method and device for detection of violently moving target | |
CN102402306B (en) | Lifting detection method for optical mouse and optical mouse with lifting detection | |
CN101621629B (en) | Method of automatic exposure | |
CN109881356B (en) | Hosiery machine knitting needle online detection device and method based on SVM image classification | |
CN106609428B (en) | Cloth detecting system and sewing machine | |
CN103793921A (en) | Moving object extraction method and moving object extraction device | |
CN106844394B (en) | Video retrieval method based on pedestrian clothes and shirt color discrimination | |
CN110688969A (en) | Video frame human behavior identification method | |
CN111005152B (en) | Yarn detection method based on graph similarity comparison | |
Caliskan et al. | Design and realization of an automatic optical inspection system for PCB solder joints | |
CN111058182A (en) | Yarn state detection method based on projection area statistics | |
CN111088597B (en) | Contour line analysis-based yarn state detection method | |
CN111058183B (en) | Yarn detection method based on image form recognition | |
CN112760802A (en) | Yarn state discrimination method based on feature two-dimensional description |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131016 |