CN103413131B - Tower crane recognition method based on spectrum and geometric properties - Google Patents
Tower crane recognition method based on spectrum and geometric properties Download PDFInfo
- Publication number
- CN103413131B CN103413131B CN201310025473.2A CN201310025473A CN103413131B CN 103413131 B CN103413131 B CN 103413131B CN 201310025473 A CN201310025473 A CN 201310025473A CN 103413131 B CN103413131 B CN 103413131B
- Authority
- CN
- China
- Prior art keywords
- tower crane
- value
- image
- target
- color
- 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.)
- Expired - Fee Related
Links
Abstract
The present invention is identified it from aviation image using the intrinsic spectral characteristic of tower crane and special geometric properties, obtains its position coordinates and information of number.Extracted first with the spectral signature of tower crane by tower crane and with atural object as its spectral class from image, the geometrical properties such as its unique aspect ratio, area are recycled further to extract tower crane, the result of extraction reaches 100% precision and the good influence for having resisted noise.
Description
Technical field:The present invention relates to a kind of practical tower crane image-recognizing method, and in particular to target identification and numeral
Image processing techniques, it has a wide range of applications in terms of construction management monitoring.
Background technology:Images steganalysis be using the target signature that is extracted from image, realize detection to target,
Positioning and classification, are pattern-recognition and the integrated application of digital image processing techniques.(referring to document:Ma Yingjun are based on rough set
With the military aircraft recognizer Northwestern Polytechnical Universitys of support vector machines, 2007) images steganalysis be mainly used in aircraft,
The identification and classification of the feature atural object such as bridge, highway, river and car plate, there is presently no identification tower crane specific method, still
Symbol of the tower crane as construction site, there is quite varied application in terms of the monitoring of construction investment, therefore carries out tower crane figure
As target identification tool is of great significance.
Target identification method is broadly divided into two kinds:Identification and structural method based on decision-theoretic approach.(referring to text
Offer:Paul Gonzales Digital Image Processing Beijing:Electronic Industry Press, 2008) identification based on decision-theoretic approach is base
In the identification of decision-making (or differentiation) function.Make x=(x1, x2..., xn)TRepresent a n dimensional patterns vector.To W pattern class ω1,
ω2..., ωW, the basic problem of decision theory pattern-recognition is to find W discriminant function d according to attribute1(x), d2(x) ..., dW
(x), if pattern x belongs to class ωi, then
di(x) > dj(x) j=1,2 ..., W;j≠i (1)
(referring to document:Duda, R.O, Hart, P.E., and Stork, D.G.Pattern Classification,
John Wiley&Sons, New York, 2001)
Identification based on decision-theoretic approach can be divided into matching, optimal statistical sorter and neural net method again.(ginseng
See document:Paul Gonzales Digital Image Processing Beijing:Electronic Industry Press, 2008) passed through based on matched identification technology
A kind of each class of prototype pattern vector representation.One unknown pattern be endowed one by advance it is defined measurement it is most close with it
Class.Simplest method is minimum distance classifier, and this method as is suggested by the name, is calculated (in Euclid
In space) distance between unknown quantity and each prototype vector.Minimum range therein is selected to carry out decision-making.It is also a kind of according to phase
The matching process of pass, finds the subgraph that matched size is J*K in the image that size is M*N, determines the phase between two width figures
Relation number is matched.Formula is as follows:
Although correlation function can be normalized for changes in amplitude by using related coefficient, normalized ruler is obtained
It is very little change and it is rotationally-varying when it is relatively difficult.When occurring uncertain or free rotationally-varying, correlation is rarely employed
Method.(referring to document:Tou, J.T., and Gonzalez, R.C.Pattern Recognition Principles,
Addison-Wesley, Reading, Mass, 1974)
Optimal statistical sorter is a kind of probabilistic method.The occasion of physical event is measured and judged in most of processing, is led to
Random pattern classification can be often produced, including gaussian model class and Bayes classifier.(referring to document:Jain, A.K.,
Duin, R.P.W., and Mao, J.Statistical Pattern Recognition:A Review, IEEE
Trans.Pattern Anal.Machine Intell., 2000,22 (1):4-37)
Based on the statistical parameter of each pattern class is estimated using sample mode, training algorithm is divided into neutral net:
Linear separability from class, inseparable class.(referring to document:Principle, J.C., Euliano, N.R., and
Lefebre, W.C.Neural and Adaptive Systems:Fun-damentals through Simulations,
John Wiley&Sons, New York, 1999)
The above method all has been widely used for military and traffic etc., as China is to house, factory construction
Supervision it is increasing, people gradually strengthen the attention degree of living space and land use, the allusion quotation as construction site
Type heavy construction equipment --- tower crane also should be used as one of research object of target identification.Since remote sensing images have monitoring in real time
The characteristic observed on a large scale, can comprehensively utilize remote sensing images and the position of tower crane and number are carried out using target identification method
Detection, and by the analysis to tower crane number and distribution situation in statistical regions, space orientation is carried out to construction project, is sentenced at the same time
The construction speed of investment project in disconnected and monitoring demonstration area.Its research significance and importance can be typical with aircraft, highway etc.
The identification of object compares favourably.
The content of the invention:
Tower crane recognition method based on spectrum and geometric properties, it is characterized in that first with spectral information to tower crane and and tower crane
Color is close
Atural object extracted, recycle the geometrical property of tower crane to distinguish tower crane and other atural objects, specific steps are such as
Under:
(1) according to spectral information coarse extraction target and target similar to spectrum atural object
By observe atural object find with tower crane color similar in atural object have and remained on curved dirt road and mound, and ground
Soil;Since tower crane with its background image color characteristic differs larger, Target scalar can be carried out according to spectral information thick
Extraction, obtains target and target similar to spectrum atural object;Since in the color table of R, G, B, yellow is complementary with blueness, so true yellow
R, G, B value of color are respectively 255,255,0;The histogram for being utilized respectively tri- wave bands of R, G and B of aviation image is carried out at analysis
Reason;
1. according to the histogram distribution situation of R wave bands, given threshold is less than 160, by less than the pixel of the value in three ripples
The gray value of section is both configured to zero;
2. according to the histogram distribution situation of G-band, given threshold is less than 100, by less than the pixel of the value in three ripples
The DN values of section are both configured to zero;
3. according to B wave band histogram distribution situations, given threshold is more than 170, will be greater than the pixel of the value in three wave bands
DN values be both configured to 0;
(2) according to Extraction of Geometrical Features Target scalar
1. cromogram is changed into gray-scale map, and automatic threshold processing is carried out to it, binaryzation then is carried out to image,
Wherein, the method that automatic thresholdization processing uses is maximum variance between clusters, makes target image and Background by given threshold
Variance as between reaches maximum, and threshold value at this time is as by threshold value used by gray-scale map progress binaryzation;
2. obtained binary map is carried out Labelling Regions, using neighbours' domain method, each point in image is scanned, such as
There is the point identical with its DN value in fruit, then this point is classified as same class with scanning element, is marked in the range of four neighborhoods of the point
It is denoted as same numerical value;
3. according to the special geometric properties of tower crane, itself and thing as its spectral class are accurately distinguished, set length and width ratio
More than 6, dirt road, hill and noise are removed;It can be incited somebody to action by the area more than 10 pixels and certain inclination angle
Crack between brick removes;It is defined using main axis length, thick head point is removed, but in most cases, tower
Hang and largely blocked by building, tower crane main shaft width and length are passed through according to the different characteristics of tower crane in image at this time
Maximum and minimum value is extracted, and is in summary analyzed, and respectively calculates obtained subregion its feature, including area, focus point are sat
Mark, tend to angle and main axis length and main shaft width;And qualifications are set, accurately extract tower crane boom portion;
4. calculate the center point coordinate and its quantity of tower crane in figure.
The present invention mainly using spectral information of the tower crane in remote sensing images and geometric properties by it from aviation shadow
Extracted as in and obtain its coordinate position and quantity.Make full use of the tower crane spectral characteristic different from other atural objects and spy
Different geometry, had not only eliminated the influence of noise, but also enhanced the information of tower crane, was convenient for the investment project letter of large scale
The sample investigation and verification of breath.
Brief description of the drawings:Fig. 1 is the flow chart that this method carries out tower crane position and number of extracted using remotely-sensed data;
Fig. 2 .1 are the unmanned plane images in Yunnan Airport on December 30th, 2009;
Fig. 2 .2 are the result figures carried out using the spectral characteristic of tower crane to image R wave bands after threshold value extraction;
Fig. 2 .3 are the result figures carried out to the G-band of Fig. 2 .2 after threshold value extraction;
Fig. 2 .4 are that tower crane and tower crane the carrying similar to spectrum atural object that threshold value extraction obtains afterwards are carried out to the B wave bands of Fig. 2 .3
Take result images;
Fig. 2 .5 are the result figures that binaryzation after automatic threshold extraction is carried out to Fig. 2 .4;
Fig. 2 .6 are the final result according to Extraction of Geometrical Features tower crane to Fig. 2 .5.
Embodiment:
First, according to spectral information coarse extraction target and target similar to spectrum atural object
Look first at the atural object in attached drawing 2.1, it is found that tower crane is in yellow, with tower crane color similar in atural object have curved soil
Remaining soil etc. on road and mound, and ground., can be according to light and tower crane differs larger with its background image color characteristic
Spectrum information carries out coarse extraction to Target scalar, obtains target and target similar to spectrum atural object.Spectral information by color model come
Expression, the color model in optics mainly have:HSV models, RGB models, HIS models, CHL models, LAB models and CMY moulds
Type etc..Wherein, RGB (red, green, blue) model is the most general model towards hardware in practice.(referring to document:Fortner,
B., and Meyer, T.E.Number by Colors, Springer-Verlag, New York, 1997).Due to RGB models
Generality and versatility, we are analyzed and are extracted to the spectral information of tower crane image using RGB models.In R, G, B
In color table, each spectral components are three reference axis based on cartesian coordinate system respectively, the value range of tonal gradation
It is 0 to 255, the rgb value of black is (0,0,0), and white is (255,255,255).In rgb space, for representing each
The bit number of pixel is known as pixel depth.Considering RGB image, each of which width red, green, blue image is all 8 bit images,
Under these conditions, each RGB color pixel is known as having 24 bit-depths.Full-color image is commonly used to define the colour of 24 bits
Image.In 24 bit R6B images, color sum is (256*256*256=16777216).(referring to document:Paul Gonzales
Digital Image Processing Beijing:Electronic Industry Press, 2008) in RGB models, yellow is complementary with blueness, so gilvous
R, G, B value are respectively 255,255,0.As can be seen that gilvous is all bigger than normal in red and green spectral value, in blue light
Spectral component value is less than normal.The present invention utilizes this characteristic, straight according to the statistical distribution of tri- wave bands of R, G and B of aviation image respectively
Square figure is analyzed and processed.
1st, the histogram distribution situation of 2.1 R wave bands, setting threshold value are 160 with reference to the accompanying drawings, will be existed less than the pixel of the value
The DN values of three wave bands are both configured to zero, filter out the pixel of the low gray level of R wave bands, obtain attached drawing 2.2.It can be seen that part blueness
And grey atural object has been filtered out.
2nd, the histogram distribution situation of 2.2 G-band with reference to the accompanying drawings, given threshold 100, will exist less than the pixel of the value
The DN values of three wave bands are both configured to zero, filter out the pixel of the low gray level of G-band, obtain attached drawing 2.3.Red atural object is also filtered
Remove.
3rd, 2.3 B wave band histogram distribution situations with reference to the accompanying drawings, given threshold 170, will be greater than the pixel of the value three
The DN values of a wave band are both configured to 0, filter out the pixel of B wave band high grade grey levels, obtain meeting yellow RGB particular pixel collection --- and it is attached
Fig. 2 .4.As can be seen that yellow atural object has nearly all been extracted out, the non-yellow atural object (blueness, grey etc.) of large area all by
Successfully filter out, black is presented.
2nd, according to Extraction of Geometrical Features Target scalar
As can be seen that the target extracted also has many tiny spots similar to spectrum atural object in addition to dirt road from attached drawing 2.4,
Their shapes with tower crane, size characteristic are differed, therefore accurately extracted using the special geometric shape of tower crane.
1st, since Fig. 2 .4 are still cromogram, extract for convenience, convert it into gray-scale map, and automatic threshold is carried out to it
Value is handled, and is then carried out binaryzation to image, is obtained attached drawing 2.5.Wherein, the method that automatic thresholdization processing uses is maximum
Ostu method.This method is the variance between target image and background image is reached maximum by given threshold, then this
When threshold value be by gray-scale map carry out binaryzation used by threshold value.Following (the source document of its algorithm steps:Otsu, N.,
AThreshold Selection Method from Gray-Level Histograms, IEEE Transactions on
Systems, Man, and Cybernetics, 1979,9 (1):62-66):
(1) set image and include L gray level (0,1 ..., L-1), the pixel number that gray level is i is Ni, the total picture of image
Vegetarian refreshments number is
N=N0+N1+…N(L-1) (3)
(2) the point probability that gray level is i is Pi=Ni/N (4)
(3) entire image is divided into dark space c by threshold value t1With clear zone c2Two classes, then inter-class variance σ is the function of t:
σ=a1*a2*(u1-u2)2 (5)
In formula, ajFor class cjArea and the ratio between total image area, a1=sum (Pi) i → t, a2=1-a1
Selection optimal threshold makes variances sigma reach maximum.
2nd, obtained binary map is subjected to Labelling Regions.Using neighbours' domain method, each point in image is scanned, such as
There is the point identical with its DN value in fruit, then this point is classified as same class with scanning element, is marked in the range of four neighborhoods of the point
It is denoted as same numerical value.Wherein, four neighborhoods refer to for each pixel in image, its upper and lower, left and right four direction
Pixel set.In order to avoid four neighborhood of image boundarg pixel is not complete, it is necessary to the problem of Taxonomic discussion, in the process that algorithm is realized
In, the expansion that first four borders of image are carried out with a Pixel-level is scanned again, so can both improve the efficiency of scanning
The complexity of code can be reduced again.
3rd, according to the special geometric properties of tower crane, itself and thing as its spectral class can accurately be distinguished.Using compared with
Big length and width ratio (being more than 6) can remove dirt road, hill and noise;Larger area (being more than 10 pixels) and
Certain inclination angle can remove the crack between brick;Due to tower crane at thicker head some be black, with
Tower crane color differs greatly, therefore breakpoint is had during spectral detection, in order not to be impacted to the quantity that tower crane detects,
It is defined using main axis length, thick head point is removed.But in most cases, tower crane is largely hidden by building
Gear, will be extracted according to the different characteristics of tower crane in image by the maximum and minimum value of tower crane main shaft width and length at this time.
In summary analyze, calculate obtained subregion its feature, including area, center of gravity point coordinates, trend angle and main shaft length respectively
Degree and main shaft width.And qualifications are set, accurately extract tower crane boom portion.
4th, the center point coordinate and its quantity of tower crane in figure are calculated, tower crane quantity is 3, its position in figure is respectively:
(149.6250357.3594), (184.6061107.9242), (214.3350230.3299), compare and analyze with artwork 2
It was found that tower crane position, shape and the number of extraction fit like a glove, 100% precision is reached.
The present invention is identified tower crane image based on spectrum and geometric properties, using spectral information to tower crane and and tower
Hang atural object similar in color to be extracted, recycle geometric properties to distinguish tower crane and other atural objects, the accuracy rate of identification is high, resists
Performance of making an uproar is good, can efficiently extract the tower crane target in remote sensing images, with good stability and versatility, monitors in building
Field is with a wide range of applications.
Claims (3)
1. the tower crane recognition method based on spectrum and geometric properties, it is characterized in that first with spectral information to tower crane and with tower crane face
Atural object is extracted similar in color, is recycled the geometric properties of tower crane to distinguish tower crane and other atural objects, is comprised the following steps that:
(1) according to spectral information coarse extraction target and target similar to spectrum atural object
There is remaining mud on curved dirt road and mound, and ground by observing atural object searching and atural object similar in tower crane color
Soil;Since tower crane with its background image color characteristic differs larger, coarse extraction can be carried out to Target scalar according to spectral information,
Target and target are obtained similar to spectrum atural object;Since in the color table of R, G, B, yellow is complementary with blueness, so gilvous
R, G, B value are respectively 255,255,0;The histogram for being utilized respectively tri- wave bands of R, G and B of aviation image is analyzed and processed;
1. according to the histogram distribution situation of R wave bands, given threshold is less than 160, by less than the pixel of the value in three wave bands
Gray value is both configured to zero;
2. according to the histogram distribution situation of G-band, given threshold is less than 100, by less than the pixel of the value in three wave bands
DN values are both configured to zero;
3. according to B wave band histogram distribution situations, given threshold is more than 170, will be greater than DN of the pixel in three wave bands of the value
Value is both configured to 0;
(2) according to Extraction of Geometrical Features Target scalar
1. cromogram is changed into gray-scale map, and automatic threshold processing is carried out to it, binaryzation then is carried out to image, its
In, the method that automatic thresholdization processing uses is maximum variance between clusters, makes target image and background image by given threshold
Between variance reach maximum, threshold value at this time is that gray-scale map is carried out threshold value used by binaryzation;
2. obtained binary map is carried out Labelling Regions, using neighbours' domain method, each point in image is scanned, if
There is the point identical with its DN value in the range of four neighborhoods of the point, then this point is classified as same class with scanning element, is labeled as
Same numerical value;
3. according to the special geometric properties of tower crane, itself and thing as its spectral class are accurately distinguished, setting length and width ratio is more than
6, dirt road, hill and noise are removed;Can be by brick by the area more than 10 pixels and certain inclination angle
Between crack remove;It is defined using main axis length, thick head point is removed, but in most cases, tower crane quilt
Building largely blocks, and to pass through tower crane main shaft width and the maximum of length according to the different characteristics of tower crane in image at this time
Extract with minimum value, in summary analyze, calculate obtained subregion its feature respectively, including area, center of gravity point coordinates, become
To angle and main axis length and main shaft width;And qualifications are set, accurately extract tower crane boom portion;
4. calculate the center point coordinate and its quantity of tower crane in figure.
2. method according to claim 1, it is characterised in that yellow is presented in tower crane in true color image, and background is equal
The concrete floor to differ greatly for color, can clearly differentiate.
3. method according to claim 1 or claim 2, it is characterised in that the aspect ratio of tower crane is 6, and the length of main shaft is 20 pictures
Plain level, threshold value are set greater than 10 and filter out other trifling atural objects.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310025473.2A CN103413131B (en) | 2013-01-24 | 2013-01-24 | Tower crane recognition method based on spectrum and geometric properties |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310025473.2A CN103413131B (en) | 2013-01-24 | 2013-01-24 | Tower crane recognition method based on spectrum and geometric properties |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103413131A CN103413131A (en) | 2013-11-27 |
CN103413131B true CN103413131B (en) | 2018-05-11 |
Family
ID=49606138
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310025473.2A Expired - Fee Related CN103413131B (en) | 2013-01-24 | 2013-01-24 | Tower crane recognition method based on spectrum and geometric properties |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103413131B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104240196A (en) * | 2014-08-21 | 2014-12-24 | 陕西理工学院 | Four-neighborhood classification method based on FCM |
CN104299002B (en) * | 2014-10-11 | 2017-06-23 | 嘉兴学院 | A kind of tower crane image detecting method based on monitoring system |
CN106629394B (en) * | 2015-10-28 | 2018-01-16 | 上海振华重工电气有限公司 | Camera extrinsic number calibration system and method applied to the detection of track sling pose |
CN106529430A (en) * | 2016-10-31 | 2017-03-22 | 武汉大学 | High spatial resolution image residential area extraction method based on characteristics of spatial correlation and heterogeneity |
CN111061265A (en) * | 2019-12-06 | 2020-04-24 | 常州节卡智能装备有限公司 | Object carrying method, device and system |
CN112561487B (en) * | 2020-12-21 | 2024-01-23 | 广联达科技股份有限公司 | Method, device and equipment for calculating construction progress and readable storage medium |
CN113255626B (en) * | 2021-07-14 | 2021-12-03 | 杭州大杰智能传动科技有限公司 | Intelligent tower crane structure state detection method and device based on scanned image analysis |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599120A (en) * | 2009-07-07 | 2009-12-09 | 华中科技大学 | A kind of identification method of remote sensing image building |
CN102385694A (en) * | 2010-09-06 | 2012-03-21 | 邬明权 | Hyperspectral identification method for land parcel-based crop variety |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8180146B2 (en) * | 2009-12-22 | 2012-05-15 | The Chinese University Of Hong Kong | Method and apparatus for recognizing and localizing landmarks from an image onto a map |
-
2013
- 2013-01-24 CN CN201310025473.2A patent/CN103413131B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101599120A (en) * | 2009-07-07 | 2009-12-09 | 华中科技大学 | A kind of identification method of remote sensing image building |
CN102385694A (en) * | 2010-09-06 | 2012-03-21 | 邬明权 | Hyperspectral identification method for land parcel-based crop variety |
Non-Patent Citations (2)
Title |
---|
An automatic and effective approach in identifying tower cranes;Bo Yu et al;《Proc. SPIE 8334, Fourth International Conference on Digital Image Processing》;20121231;第1-7页 * |
结合对象关系特征的高分辨率卫星影像建筑物识别方法;周小成 等;《国土资源遥感》;20081231(第4期);第27-31页 * |
Also Published As
Publication number | Publication date |
---|---|
CN103413131A (en) | 2013-11-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103413131B (en) | Tower crane recognition method based on spectrum and geometric properties | |
CN107103323B (en) | Target identification method based on image contour features | |
Cord et al. | Automatic road defect detection by textural pattern recognition based on AdaBoost | |
Sirmacek et al. | Urban-area and building detection using SIFT keypoints and graph theory | |
Sirmacek et al. | Urban area detection using local feature points and spatial voting | |
CN103020605B (en) | Bridge identification method based on decision-making layer fusion | |
CN104182763B (en) | A kind of floristics identifying system based on flower feature | |
CN105809121A (en) | Multi-characteristic synergic traffic sign detection and identification method | |
CN101847163A (en) | Design patent image retrieval method with multi-characteristics fusion | |
CN105139011B (en) | A kind of vehicle identification method and device based on mark object image | |
Zakir et al. | Road sign detection and recognition by using local energy based shape histogram (LESH) | |
CN108491498A (en) | A kind of bayonet image object searching method based on multiple features detection | |
CN111242046B (en) | Ground traffic sign recognition method based on image retrieval | |
Obaidullah et al. | A system for handwritten script identification from Indian document | |
CN105005565A (en) | Onsite sole trace pattern image retrieval method | |
CN109255279A (en) | A kind of method and system of road traffic sign detection identification | |
Baluyan et al. | Novel approach for rooftop detection using support vector machine | |
CN108564130A (en) | It is a kind of based on the Infrared Target Recognition Method for singly drilling feature and Multiple Kernel Learning | |
Sallah et al. | Road sign detection and recognition system for real-time embedded applications | |
WO2018042208A1 (en) | Street asset mapping | |
Mokhtari et al. | Statistical selection and interpretation of imagery features for computer vision-based pavement crack–detection systems | |
KR101294347B1 (en) | Mehtod for brick path recognition using image shape pattern and texture feature | |
CN108197540A (en) | A kind of fire image Feature extraction and recognition method based on SURF | |
CN109829511B (en) | Texture classification-based method for detecting cloud layer area in downward-looking infrared image | |
Deb et al. | Automatic vehicle identification by plate recognition for intelligent transportation system applications |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180511 Termination date: 20200124 |
|
CF01 | Termination of patent right due to non-payment of annual fee |