CN105261024B - Based on the remote sensing image Complex water body boundary extraction method for improving T Snake models - Google Patents
Based on the remote sensing image Complex water body boundary extraction method for improving T Snake models Download PDFInfo
- Publication number
- CN105261024B CN105261024B CN201510691283.3A CN201510691283A CN105261024B CN 105261024 B CN105261024 B CN 105261024B CN 201510691283 A CN201510691283 A CN 201510691283A CN 105261024 B CN105261024 B CN 105261024B
- Authority
- CN
- China
- Prior art keywords
- node
- snake
- water body
- contour curve
- remote sensing
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to water body remote sensing technology field, there is provided a kind of to be comprised the following steps based on the remote sensing image Complex water body boundary extraction method for improving T Snake models, this method：Initial profile and initial mesh size are set；Using orthogonal T Snake model extraction water boundaries, a contour curve is obtained；Judge whether square net width is 1 pixel, if it is flow terminates, and obtains contour curve now as final water boundary, if as new initial profile after otherwise carrying out node interpolating operations to the contour curve got, and halve sizing grid, it is then back to previous step.Technical scheme proposed by the present invention, the T Snake model calculation times can be not only reduced, while and can enough improves the precision of remote sensing image Complex water body Boundary Extraction.
Description
Technical field
It is more particularly to a kind of based on the remote sensing image for improving T-Snake models the present invention relates to water body remote sensing technology field
Complex water body boundary extraction method.
Background technology
The major technique that water boundary is extracted from remote sensing image is rim detection.Document 1 (Meng Lingkui, Lv Qifei, it is complicated
The orthogonal T-Snake models of improvement of Water recognition, survey and draw journal, 2015,44 (6)) provide it is a kind of adaptive using topology
The method for answering snake model (Topology adaptive Snake, T-Snake) extraction remote sensing image Complex water body border, the mould
Type is the improvement to classical Snake models, and its basic thought is that a series of square net is built in original image, constraint
Model evolution curve can only move along grid lines direction and curve node can be only positioned at grid vertex.Take T-Snake
Model extraction water boundary has main steps that：A manually initial point inside given water body, and according to square net first
One water body initial profile curve of big little structure；Then an energy letter is defined according to the image feature of water body and contour curve
Number, to control the deformation and motion of initial given closed contour curve；Energy function minimum value is finally asked for, obtains wheel now
Wide curve, as water boundary.
When asking for energy function minimum value, what document 1 was taken is greedy algorithm, first carry out node split then carry out by
The energy value of individual node is calculated and judged, is had main steps that：
(1) current curves S sequence node is traveled through, to each node, is split as four of four direction up and down
Point, this four point coordinates equidirectionals are different；Then remove those points for pointing to curvilinear inner, by remaining several points in order
It is inserted into sequence node；
(2) sequence node after traverse node is split, for every bit, calculates its target location that will be moved to；
Then the local energy functional value of the mobile front and rear point is calculated respectively, and is judged：If energy function value is more after mobile
Small, then the point is moved to new position, otherwise keeps constant；
(3) whether equal with before this curve deformation the total energy function value of whole contour curve is calculated, if so, then saying
Bright contour curve has arrived at coastal waters, then just exports the sequence node of contour curve, otherwise, then needs to carry out a new round
Iterative calculation.The contour curve finally given is exactly the closed contour in extracted waters.
In the T-Snake models of document 1, influence of the size to Water recognition precision for dividing the grid of image is special
It is not big.It is in particular in：Mesh width setting is excessive, the feature less than a sizing grid can be made to be ignored, so as to cause essence
The decline of degree；And mesh width is when setting too small, precision can increase, but can cause the increase of iterations, reduce
The efficiency of Water recognition.
The content of the invention
【Technical problems to be solved】
It is an object of the invention to provide a kind of improvement T-Snake based on variable grid towards Complex water body Boundary Extraction
Model, to reduce the T-Snake model calculation times, while and can enough improves the precision of remote sensing image Complex water body Boundary Extraction.
【Technical scheme】
The present invention is achieved by the following technical solutions.
The present invention relates to a kind of in the remote sensing image Complex water body boundary extraction method for improving T-Snake models, including step
Suddenly：
A, the square net width r of orthogonal T-Snake models is initialized, the initial profile for building remote sensing image water body is bent
Line, record each node of initial profile curve is Vi(i=1,2 ..., n), n is the sum of node in initial profile curve, node
Coordinate is (xi,yi), node direction of advance is Oi, calculate the energy of initial profile curve；
B, water boundary in remote sensing image is extracted using orthogonal T-Snake models, obtains the profile after deformation
Curve；
C, judge whether square net width is 1, if it is, using current contour curve as final water body side
Boundary simultaneously exits this method flow, otherwise performs step D；
D, node interpolating operations are carried out to the contour curve that step B is obtained, obtains a new contour curve；
E, current outline curve is updated to the contour curve that step D obtains, and square net width is arranged to work as
K times of preceding square net width, it is then back to and performs step B, wherein 0<k<1,
The step B specifically includes step：
B1, the width r and contour curve for obtaining current square net, gray average discrepancy threshold T, neighbor domain of node are set
△ x, initialization iterations t=1；
B2, initialization global energy ESnake (t)=0；
B3, first node V for obtaining contour curvei, make i=1；
B4, calculate node ViLocal energy E (i), obtain node ViTarget gridding summit Vi' coordinate；
B5, V is calculated respectivelyi、ViGray average μ (V in the ' neighborhood △ x in respective original imagei)、μ(Vi′)；
B6, judge whether to meet | μ (Vi)-μ(Vi′)|<T, step B7, on the contrary then execution step B8 are performed if meeting；
B7, calculate Vi' local energy functional value Ei', if Ei>Ei', then make Vi=Vi' and perform step B8, it is on the contrary then
Directly perform step B8；
B8, the global energy functional value E for updating contour curvesnake t=Esnake t+Ei；
B9, judge ViWhether be contour curve last node, if it is export ESnake (t)And perform step
B10, otherwise make i=i+1 and return to step B4；
B10：Judge whether to meet ESnake (t)≥ESnake (t-1), it is if meeting that the profile under current square net is bent
Line is on the contrary then iterations t is added into 1 and return to step B2 as water boundary.
As a preferred embodiment, the method that the initial profile curve of water body is built in the step A is：It is selected
Any point (x inside water body0,y0), with the point up and down on four direction at a distance of four pixel clock-wise orders for r
It is sequentially connected to build the initial profile of the water body.
As another preferred embodiment, the value of the k is 1/2.
As another preferred embodiment, the energy function is defined as：Wherein, η, γ, λ are coefficient, and C is current Snake curves
Geometric center, σ and δ are the gray standard deviation and extreme difference of neighbor domain of node respectively,It is node ViThe image gradient at place, ε
It is adjustment factor, Vi-1And Vi+1It is V respectivelyiPrevious node and latter node.
【Beneficial effect】
Technical scheme proposed by the present invention has the advantages that：
The present invention is improved based on T-Snake models and to it, and specifically, the present invention is realized using big grid first
The preliminary extraction of water boundary, then realize contour curve constantly forcing to water boundary by progressively reducing size of mesh opening
Closely, on the one hand, because the size of mesh opening of early stage is bigger so as to reduce the model calculation time, on the other hand, due to the net in later stage
Lattice size is less so as to capture minimum boundary characteristic (such as the less concave region of throat width), therefore the present invention is again
The precision of Boundary Extraction can be improved.In a word, relative to document 1, it is provided by the invention towards Complex water body Boundary Extraction based on
The improvement T-Snake models of variable grid, can not only reduce the T-Snake model calculation times, while and can enough improves remote sensing
The precision of image Complex water body Boundary Extraction.
Brief description of the drawings
Fig. 1 is being carried in the remote sensing image Complex water body border for improving T-Snake models for the offer of embodiments of the invention one
Take the flow chart of method；
Fig. 2 is the current grid bottom profiled curve update method flow chart that embodiments of the invention one provide.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below by the embodiment of the present invention
Carry out clear, complete description.
Embodiment one
Fig. 1 is being carried in the remote sensing image Complex water body border for improving T-Snake models for the offer of embodiments of the invention one
The flow chart of method is taken, as shown in figure 1, above-mentioned steps are carried out detailed by the method comprising the steps of S1 to step S5 separately below
Description.
Step S1：Initial profile and initial mesh size are set.
In step S1, the square net width r (r=2 of orthogonal T-Snake models are initializedn, n >=0), build and wait to carry
The initial profile curve of remote sensing image water body is taken, record each node of initial profile curve is Vi(i=1,2 ..., n), n is initial
The sum of node on contour curve, node coordinate are (xi, yi), node direction of advance is Oi, calculate the energy of initial profile curve
, it is necessary to illustrate, r value can be configured amount according to being actually needed.
Specifically, the method for the initial profile curve of step S1 structures water body is：Any point (x inside selected water body0, y0),
With being apart sequentially connected up and down on four direction for r four pixel clock-wise orders to build the water body for the point
The size of initial profile, i.e. initial profile is 2n×2nIndividual pixel.In addition, the present embodiment defines energy function is：
Wherein, η, γ, λ are coefficient, and C is the geometric center of current Snake curves, and σ and δ are the gray scale of neighbor domain of node respectively
Standard deviation and extreme difference,It is node ViThe image gradient at place, ε are adjustment factors, Vi-1And Vi+1It is V respectivelyiPrevious node
With latter node.The present embodiment calculates the energy of contour curve by the energy function.
Step S2：Using orthogonal T-Snake model extractions water boundary.
In step S2, water boundary in remote sensing image is extracted using orthogonal T-Snake models, obtained after deforming
Contour curve.Compared with document 1, the embodiment of the present invention still carries out Water recognition using greedy algorithm, i.e., every time repeatedly
During generation, first carry out node and split to carry out node motion again, but node moving process when the embodiment of the present invention is to the t times iteration
Improved, to ensure in the case where size of mesh opening is larger, contour curve will not cross over water boundary.The solution party taken
Formula is：In iterative process each time, for any one node V on contour curvei, determining whether this is moved to for it
Next grid vertex Vi' before, carry out a judgement：If V on the original imagei' and ViNeighborhood gray average difference not
Greatly, then V is illustratedi' it is still water body internal point, it is on the contrary then think Vi' have passed over water boundary.Only work as Vi' it is still water
During body internal point, V can be just calculatedi' local energy function, and and ViLocal energy function make comparisons, to determine ViWhether point
It should move.Specifically, step S2 includes step S201 to step S210：
Step S201：The width r and contour curve of current square net are obtained, initializes iteration control parameter.
In step S201, obtain the width r and contour curve of current square net, set gray average discrepancy threshold T,
Neighbor domain of node △ x, iterations t=1 is, it is necessary to illustrate for initialization, gray average discrepancy threshold T, neighbor domain of node △ x value can
It is configured according to being actually needed.
Step S202：Initialize global energy ESnake (t)=0.
Step S203：Obtain first node V of contour curvei, make i=1.
Step S204：Calculate node ViLocal energy E (i), obtain node ViTarget gridding summit Vi' coordinate；.
Step S205：V is calculated respectivelyi、ViGray average μ (V in the ' neighborhood △ x in respective original imagei)、μ
(Vi′)。
Step S206：Judge whether to meet | μ (Vi)-μ(Vi′)|<T, performs step S207 if meeting, on the contrary then hold
Row step S208,.
Step S207：Calculate Vi' local energy functional value Ei', if Ei>Ei', then make Vi=Vi' and perform step
S208, on the contrary then directly execution step S208.
Step S208：Update the global energy functional value E of contour curvesnake t=Esnake t+Ei。
Step S209：Judge ViWhether be contour curve last node, if it is export ESnake (t)And perform
Step S210, otherwise make i=i+1 and return to step S204.
Step S210：Judge whether to meet ESnake (t)≥ESnake (t-1), by under current square net if meeting
Contour curve is as water boundary and performs step S3, on the contrary then iterations t is added into 1 and return to step S202.
Step S3：Judge whether square net width is 1, if it is, using current outline curve as final water
This method flow is simultaneously exited in body border, otherwise performs step S4.
In step S3, first determine whether square net width is 1 pixel, if it is deformation terminates, will be current
Contour curve is as final water boundary and exits this method flow, otherwise performs step S4.
Step S4：Node interpolating operations are carried out to the contour curve got.
In step S4, node interpolating operations are carried out to the contour curve that step S2 is obtained, obtain a new contour curve.
Step S5：Update contour curve and sizing grid, return to step S2.
In step S5, using the contour curve that step S4 is obtained as current outline curve, and mesh width is arranged to work as
1/2 times of preceding mesh width, it is then back to and performs step S2.
L-G simulation test
For in a width image size is 1407 × 1835 pixels, spatial resolution is 16 meters GF1 near infrared images
Same water body target, test Intel Duos i5, CPU frequency 2.27GHz, internal memory 4GB computer on, eclipse+pydev
Python programming realizations are used under translation and compiling environment, are as a result found：Embodiment one extracts the correctness and integrity degree point of water boundary
Not Wei 99.8% and 99.6%, without improved T-Snake models extraction water boundary correctness and integrity degree be respectively
98.5% and 98.3%, and it is only 21.4 seconds that the former is time-consuming, the latter was taken as 116.7 seconds.It is of the invention in terms of the result of experiment
Embodiment one both can guarantee that the precision and can of Complex water body Boundary Extraction improved model calculation efficiency.
The embodiment of the present invention is can be seen that based on T-Snake models from above example and its l-G simulation test and it is entered
Improvement is gone, specifically, the embodiment of the present invention realizes the preliminary extraction of water boundary using big grid first, then by progressively
Reduce size of mesh opening to realize contour curve constantly approaching to water boundary, on the one hand, because the size of mesh opening of early stage compares
Greatly so as to reduce the model calculation time, on the other hand, because the size of mesh opening in later stage is less so as to capturing minimum side
Boundary's feature (such as the less concave region of throat width), therefore and can of the present invention improves the precision of Boundary Extraction.In a word, relative to
Document 1, the improvement T-Snake models based on variable grid provided in an embodiment of the present invention towards Complex water body Boundary Extraction,
The T-Snake model calculation times can be not only reduced, while and can enough improves the precision of remote sensing image Complex water body Boundary Extraction.
It is to be appreciated that the embodiment of foregoing description is the part of the embodiment of the present invention, rather than whole embodiments, also not
It is limitation of the present invention.Based on embodiments of the invention, those of ordinary skill in the art are not paying creative work premise
Lower obtained every other embodiment, belongs to protection scope of the present invention.
Claims (4)
- It is 1. a kind of based on the remote sensing image Complex water body boundary extraction method for improving T-Snake models, it is characterised in that including step Suddenly：A, the square net width r of orthogonal T-Snake models is initialized, builds the initial profile curve of remote sensing image water body, It is V to record each node of initial profile curvei(i=1,2 ..., n), n be initial profile curve on node sum, node coordinate For (xi,yi), node direction of advance is Oi, calculate the energy of initial profile curve；B, water boundary in remote sensing image is extracted using orthogonal T-Snake models, obtains the contour curve after deformation；C, judge whether square net width r is 1, if it is, using current contour curve as final water boundary And this method flow is exited, otherwise perform step D；D, node interpolating operations are carried out to the contour curve that step B is obtained, obtains a new contour curve；E, current outline curve is updated to the contour curve that step D obtains, and by square net width be arranged to it is current just K times of square net width, it is then back to and performs step B, wherein 0<k<1,The step B specifically includes step：B1, the width r and contour curve for obtaining current square net, gray average discrepancy threshold T, neighbor domain of node △ x are set, Initialize iterations t=1；B2, initialization global energy ESnake (t)=0；B3, first node V for obtaining contour curvei, make i=1；B4, calculate node ViLocal energy Ei, obtain node ViTarget gridding summit Vi' coordinate；B5, V is calculated respectivelyi、ViGray average μ (V in the ' neighborhood △ x in respective original imagei)、μ(Vi′)；B6, judge whether to meet | μ (Vi)-μ(Vi′)|<T, step B7, on the contrary then execution step B8 are performed if meeting；B7, calculate Vi' local energy functional value Ei', if Ei＞ Ei', then make Vi=Vi' and step B8 is performed, it is on the contrary then straight Connect and perform step B8；B8, the global energy functional value E for updating contour curvesnake t=Esnake t+Ei；B9, judge ViWhether be contour curve last node, if it is export ESnake (t)And step B10 is performed, it is no Then make i=i+1 and return to step B4；B10：Judge whether to meet ESnake (t)≥ESnake (t-1), the contour curve under current square net is made if meeting It is on the contrary then iterations t is added into 1 and return to step B2 for water boundary.
- 2. the remote sensing image Complex water body boundary extraction method according to claim 1 based on improvement T-Snake models, its The method of initial profile curve for being characterised by building water body in the step A is：Any point (x inside selected water body0,y0), with The point is sequentially connected on four direction at a distance of four pixel clock-wise orders for r to build the first of the water body up and down Beginning profile.
- 3. the remote sensing image Complex water body boundary extraction method according to claim 1 based on improvement T-Snake models, its The value for being characterised by the k is 1/2.
- 4. the remote sensing image Complex water body boundary extraction method according to claim 1 based on improvement T-Snake models, its It is characterised by that the local energy function is defined as：Wherein, η, γ, λ are coefficient, and C is the geometric center of current outline curve, and σ and δ are the gray standard deviation and extreme difference of neighbor domain of node respectively,It is node ViThe image gradient at place, ε are adjustment factors, Vi-1And Vi+1It is V respectivelyiPrevious node and latter node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510691283.3A CN105261024B (en) | 2015-10-22 | 2015-10-22 | Based on the remote sensing image Complex water body boundary extraction method for improving T Snake models |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510691283.3A CN105261024B (en) | 2015-10-22 | 2015-10-22 | Based on the remote sensing image Complex water body boundary extraction method for improving T Snake models |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105261024A CN105261024A (en) | 2016-01-20 |
| CN105261024B true CN105261024B (en) | 2018-02-16 |
Family
ID=55100696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510691283.3A Active CN105261024B (en) | 2015-10-22 | 2015-10-22 | Based on the remote sensing image Complex water body boundary extraction method for improving T Snake models |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105261024B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105938556B (en) * | 2016-04-22 | 2020-07-28 | 复旦大学 | Wide line detection method based on water flow method |
| CN110738133B (en) * | 2019-09-23 | 2023-10-27 | 中科禾信遥感科技（苏州）有限公司 | Method and device for identifying image contour boundaries of different agricultural facilities |
| CN110738686B (en) * | 2019-10-12 | 2022-12-02 | 四川航天神坤科技有限公司 | Static and dynamic combined video man-vehicle detection method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6256039B1 (en) * | 1998-08-14 | 2001-07-03 | The Board Of The Leland Stanford Junior University | Methods for manipulating curves constrained to unparameterized surfaces |
| CN101599174A (en) * | 2009-08-13 | 2009-12-09 | 哈尔滨工业大学 | Method for outline extraction of level set medical ultrasonic image area based on edge and statistical nature |
| CN102968798A (en) * | 2012-12-12 | 2013-03-13 | 北京航空航天大学 | SAR (Synthetic Aperture Radar) image sea-land segmentation method based on wavelet transform and OTSU threshold |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6947040B2 (en) * | 2001-10-23 | 2005-09-20 | Siemens Corporate Research, Inc. | Vessel detection by mean shift based ray propagation |
-
2015
- 2015-10-22 CN CN201510691283.3A patent/CN105261024B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6256039B1 (en) * | 1998-08-14 | 2001-07-03 | The Board Of The Leland Stanford Junior University | Methods for manipulating curves constrained to unparameterized surfaces |
| CN101599174A (en) * | 2009-08-13 | 2009-12-09 | 哈尔滨工业大学 | Method for outline extraction of level set medical ultrasonic image area based on edge and statistical nature |
| CN102968798A (en) * | 2012-12-12 | 2013-03-13 | 北京航空航天大学 | SAR (Synthetic Aperture Radar) image sea-land segmentation method based on wavelet transform and OTSU threshold |
Non-Patent Citations (4)
| Title |
|---|
| An intensive restraint topology adaptive snake model and its application in tracking dynamic image sequence;Sun Zheng;《Information Sciences》;20100815;第180卷(第16期);第2940-2959页 * |
| T-snakes：Topology adaptive snakes;Tim Mclnerney et al;《Medical Image Analysis》;20000630;第4卷(第2期);第73-91页 * |
| 基于T-snake模型的超声左心室心肌分割方法的研究;袁艳红 等;《生物医学工程研究》;20131231;第32卷(第1期);第7-11页 * |
| 复杂水体边界提取的改进正交T-Snake模型;孟令奎 等;《测绘学报》;20150630;第44卷(第6期);第670-677页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105261024A (en) | 2016-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636905B (en) | Environment semantic mapping method based on deep convolutional neural network | |
| CN107392097B (en) | Three-dimensional human body joint point positioning method of monocular color video | |
| CN110135354B (en) | Change detection method based on live-action three-dimensional model | |
| CN110262250B (en) | B spline curve fitting method and system based on particle swarm optimization | |
| CN108761461B (en) | Rainfall forecasting method based on weather radar echo time sequence image | |
| CN109523013B (en) | Air particulate matter pollution degree estimation method based on shallow convolutional neural network | |
| CN105261024B (en) | Based on the remote sensing image Complex water body boundary extraction method for improving T Snake models | |
| CN105427308A (en) | Sparse and dense characteristic matching combined image registration method | |
| CN110543906B (en) | Automatic skin recognition method based on Mask R-CNN model | |
| Wei et al. | BuildMapper: A fully learnable framework for vectorized building contour extraction | |
| CN114037802A (en) | Three-dimensional face model reconstruction method and device, storage medium and computer equipment | |
| CN104835168B (en) | Quick multiphase image dividing method based on global convex optimization Variation Model | |
| CN112017178A (en) | Remote sensing image region change detection method based on double-temporal difference image method | |
| CN104851133A (en) | Image self-adaptive grid generation variational method | |
| CN106097277B (en) | A kind of rope substance point-tracking method that view-based access control model measures | |
| CN109741258B (en) | Image super-resolution method based on reconstruction | |
| CN108898611B (en) | Fuzzy region active contour segmentation model based on significant perception prior | |
| CN111091560A (en) | Nasopharyngeal carcinoma primary tumor image identification method and system | |
| CN110991230B (en) | Method and system for detecting ship by using remote sensing images in any direction based on rotation candidate frame | |
| CN111310772A (en) | Point line feature selection method and system for binocular vision SLAM | |
| CN108615240B (en) | Non-parametric Bayesian over-segmentation method combining neighborhood information and distance weight | |
| CN110135224A (en) | A kind of the foreground target extracting method and system, storage medium and terminal of monitor video | |
| CN109377538B (en) | Automatic image construction method | |
| CN102915524A (en) | Method for eliminating shadow based on match of inside and outside check lines of shadow area | |
| JP6962662B2 (en) | Detection device and program |
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 |