CN104794478B - A kind of building extracting method for being used in remote sensing image have uniform spectral characteristic - Google Patents
A kind of building extracting method for being used in remote sensing image have uniform spectral characteristic Download PDFInfo
- Publication number
- CN104794478B CN104794478B CN201510220949.7A CN201510220949A CN104794478B CN 104794478 B CN104794478 B CN 104794478B CN 201510220949 A CN201510220949 A CN 201510220949A CN 104794478 B CN104794478 B CN 104794478B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- building
- image
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Processing (AREA)
Abstract
The present invention relates to a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic.Comprise the following steps:Step 1, the value LS of each pixel in input remote sensing image is calculated using the likelihood function of neighborhood total variation;Step 2, binary conversion treatment is carried out;Step 3, it is labeled;Step 4, the barycenter of tab area is calculated;Step 5, Region growing segmentation is carried out;Step 6, building is carried out just to extract;Step 7, cutting object sequence S is obtained;Step 8, training sample is chosen;Step 9, texture feature extraction information;Step 10, classified.Solve the problems, such as in high spatial resolution remote sense image that building extraction accuracy rate is low, reach the effect of full automation, can be used for remote sensing image drawing, GIS-Geographic Information System data acquisition and automatically update.
Description
Technical field
It is specifically a kind of to be used for that to there is uniform spectrum in remote sensing image the present invention relates to a kind of remote sensing image process field
The building extracting method of characteristic.
Background technology
Building is one of main geographic element in city, is the important content of various city thematic maps, studies building
Extraction is significant to integrated survey urban geographic information environment.It is quick with high-resolution remote sensing image acquiring technology
Development, the processing of remote sensing image, analysis and application have more preferable data source, its digital product then have more extensively, deeper into
Application.Computer image processing technology, pattern-recognition, artificial intelligence etc. all obtain different degrees of progress, for height
Effective information in effect ground extraction huge image data provides possibility.But the extraction of building information than other information such as road,
The acquisition of water body is much more difficult, and main cause is as follows:
(1) data source is mainly the remote sensing image of two dimension, in most cases lacks direct three-dimensional data;
(2) different remote sensing image Chang Yinwei spectral regions, resolution ratio, the several picture of sensor and image-forming condition etc.
Factor difference and have larger difference;
(3) its outward appearance for being showed of different types of building and grain details etc. are ever-changing, show remote sensing
Widely different on image, unified building model storehouse is difficult to set up, and this causes automatically extracting for information to become extremely difficult;
(4) complexity of scene residing for building, as contrast it is relatively low when, house mutually block, the moon of building itself
Shadow and shade of other atural objects etc. is in, so thinking that the building that sharpness of border is automatically extracted from background is more tired
It is difficult.
The content of the invention
The invention provides a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic, can overcome
The problem of building extraction is difficult in high spatial resolution remote sense image at present, can detect in remote sensing image has more rule
The building target of shape is high without manual intervention, automaticity.
Technical scheme is used by realize the target of the present invention:Method comprises the following steps:
Step 1:The value of each pixel in input remote sensing image image1 is calculated using the likelihood function of neighborhood total variation
LS, and each value LS is normalized to section [0,255], obtain image image2;
Step 2:Selected threshold T obtains two-value image image3 to carrying out binary conversion treatment to image image2;
Step 3:Two-value image image3 is labeled, area is deleted and is less than MinsRegion, obtain image image4;
Step 4:The barycenter of each tab area in image image4 is calculated, obtains the image being made up of barycenter
image5;
Step 5:Region growing segmentation is carried out using each barycenter in image image5 as seed point, obtains respective numbers
Cutting object, obtain the image image6 being made up of cutting object;
Step 6:The minimum enclosed rectangle of each cutting object in image image6 is calculated, and with rectangular degree R and length-width ratio P
Building is carried out as constraints just to extract;
Step 7:Cutting object is pressed into corresponding building coefficient magnitude and carries out descending sort, obtains cutting object sequence S;
Step 8:Using before cutting object sequence S 30% as building training sample object B, by cutting object sequence S
It is rear 30% be used as non-building training sample object NB, using cutting object sequence S centre 40% as object C to be sorted;
Step 9:To building training sample object B, non-building training sample object NB and treated using Gabor filter
Object of classification C texture feature extraction information, respectively obtains characteristic information fB、fNBAnd fC;
Step 10:With fB、fNBAs training set, to fCClassified.
The likelihood function of described neighborhood total variation is:
LS(u(x0,y0)) bigger, show u (x0,y0) to belong to construction zone possibility bigger.
The threshold value T of described selection is automatically determined by OSTU algorithms.
Described MinsTake 1/10 of building average area in image.
Described rectangular degree R and length-width ratio P is calculated by below equation respectively:
Wherein, S0For the area of cutting object;SRFor the area of the minimum enclosed rectangle of cutting object;l1And l2Table respectively
Show the length and width of the minimum enclosed rectangle of cutting object, and rectangular degree R lower limit is arranged to 0.75, the length-width ratio P upper limit is set
It is set to 4.
The building coefficient cof of described cutting objectkCalculated according to rectangular degree R and length-width ratio P, and rectangular degree R and length
The wide weight than P respectively accounts for 50%, and specific formula for calculation is:
Wherein, MAXRFor the maximum occurrences of rectangular degree, MINRFor the minimum value of rectangular degree, MAXPFor the maximum of length-width ratio
Value, MINPFor the minimum value of length-width ratio, KRFor the rectangular degree of cutting object, KPFor the length-width ratio of cutting object.
Described Gabor filter carries out 3 yardsticks, the Gabor transformation in 8 directions, and to same chi to cutting object
The feature of degree different directions is averaged to obtain 3 textural characteristics subbands, and this 3 subband features are further extracted, and is calculated
The average and variance in each cutting object region, the characteristic vector of one 6 dimension is formed, as their texture feature information.
Described sorting technique uses naive Bayes classifier.
The beneficial effects of the invention are as follows:Solve in high spatial resolution remote sense image building extraction accuracy rate is low and ask
Topic, reach the effect of full automation.Can be used for remote sensing image drawing, GIS-Geographic Information System data acquisition and it is automatic more
Newly.
Brief description of the drawings
Fig. 1 is the overall process flow figure of the present invention.
Embodiment
The embodiment of the present invention is described in detail below in conjunction with the accompanying drawings.
In step 101, it is high spatial resolution remote sense image to input pending remote sensing image image1, Ke Yishi
The satellite images such as Quick bird, World view or all kinds of aerial images, spatial resolution require defeated below 1 meter
The remote sensing image entered needs to carry out the pretreatment such as radiant correction and geometric correction.
In step 102, with the likelihood function of neighborhood total variation:
The value LS of each pixel is calculated, and each value LS is normalized to section [0,255], obtains image
image2.Likelihood function LS characterizes a bit (x in image0,y0) local homogeneous degree.
Below with pixel (x0,y0) exemplified by, analyze above-mentioned formula:
DrIt is with (x0,y0) it is the center of circle, radius is r circular support region, and λ (x, y) is support region DrMiddle corresponding pixel points
Weights, weights are calculated by following Gaussian template:
▽ u (x, y) are pixel (x, y) gradient magnitude, and β is adjustable parameter, and it is 0 to avoid the denominator when gradient is 0.
LS(u(x0,y0)) bigger, show u (x0,y0) to belong to construction zone possibility bigger.
In step 103, threshold value T is automatically determined by OSTU algorithms, two are carried out according to function f (x, y) to image image2
Value is handled:
Obtain two-value image image3.
In step 104, two-value image image3 is carried out using four neighborhood methods, in order to prevent the interference of noise, deleted
Tab area area is less than MinsPart, MinsValue be image in building average area 1/10, obtain image
image4。
In step 105, the barycenter of each tab areas of image image4 is calculated, obtains the image being made up of barycenter
image5。
In step 106, Region growing segmentation is carried out using each barycenter in image image5 as seed point, is obtained corresponding
The cutting object of quantity, obtain the image image6 being made up of cutting object.
The minimum enclosed rectangle of each cutting object in step 107, calculating image image6, and with rectangular degree R and length
Wide to carry out building just extraction as constraints than P, wherein rectangular degree R and length-width ratio P are calculated by below equation respectively:
Wherein, S0For the area of cutting object;SRFor the area of the minimum enclosed rectangle of cutting object;l1And l2Table respectively
Show the length and width of the minimum enclosed rectangle of cutting object, and rectangular degree R lower limit is arranged to 0.75, the length-width ratio P upper limit is set
It is set to 4.In this step, the interference of the objects such as road can be excluded.
In step 108, the building coefficient of each cutting object is calculated, specific method is as follows:
Remember MAXRFor the maximum occurrences of rectangular degree, MINRFor the minimum value of rectangular degree, MAXPTaken for the maximum of length-width ratio
Value, MINPFor the minimum value of length-width ratio, cutting object K rectangular degree is KR, length-width ratio KP, then its building coefficient cofk
For:
Finally, cutting object is pressed into corresponding building coefficient magnitude and carries out descending sort, obtain cutting object sequence S.
In step 109, using before cutting object sequence S 30% as building training sample object B, by cutting object sequence
Arrange S rear 30% is used as non-building training sample object NB, using cutting object sequence S centre 40% as object to be sorted
C
In step 110, using Gabor filter to building training sample object B, non-building training sample object NB
It is as follows with object C texture feature extraction information to be sorted, method:
Gabor filter carries out 3 yardsticks to cutting object, the Gabor transformation in 8 directions, and different to same yardstick
The feature in direction is averaged to obtain 3 textural characteristics subbands, and this 3 subband features are further extracted, and calculates each point
The average and variance of subject area are cut, the characteristic vector of one 6 dimension is formed, as their texture feature information.
Finally respectively obtain C pairs of building training sample object B, non-building training sample object NB and object to be sorted
The texture feature information f answeredB、fNBAnd fC。
In step 111, using naive Bayes classifier, with fB、fNBAs training set, to fCClassified.
In step 112, the building object that border is rectangle is obtained.
Claims (8)
1. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic, it is characterised in that including following step
Suddenly:
Step 1:The value LS of each pixel in input remote sensing image image1 is calculated using the likelihood function of neighborhood total variation, and
Each value LS is normalized to section [0,255], obtains image image2;
Step 2:Selected threshold T carries out binary conversion treatment to image image2, obtains two-value image image3;
Step 3:Two-value image image3 is labeled, area is deleted and is less than MinsRegion, obtain image image4;
Step 4:The barycenter of each tab area in image image4 is calculated, obtains the image image5 being made up of barycenter;
Step 5:Region growing segmentation is carried out using each barycenter in image image5 as seed point, obtains point of respective numbers
Object is cut, obtains the image image6 being made up of cutting object;
Step 6:Calculate the minimum enclosed rectangle of each cutting object in image image6, and using rectangular degree R and length-width ratio P as
Constraints carries out building and just extracted;
Step 7:Cutting object is pressed into corresponding building coefficient magnitude and carries out descending sort, obtains cutting object sequence S;
Step 8:Using before cutting object sequence S 30% as building training sample object B, after cutting object sequence S
30% is used as non-building training sample object NB, using cutting object sequence S centre 40% as object C to be sorted;
Step 9:Using Gabor filter to building training sample object B, non-building training sample object NB and to be sorted
Object C texture feature extraction information, respectively obtains characteristic information fB、fNBAnd fC;
Step 10:With fB、fNBAs training set, to fCClassified.
2. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic according to claim 1,
It is characterized in that the likelihood function of neighborhood total variation is:
<mrow>
<mi>L</mi>
<mi>S</mi>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>(</mo>
<mrow>
<msub>
<mi>x</mi>
<mn>0</mn>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<munder>
<mo>&Integral;</mo>
<mrow>
<msup>
<mi>D</mi>
<mi>r</mi>
</msup>
<mi>u</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>0</mn>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</munder>
<mi>&lambda;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mi>d</mi>
<mi>x</mi>
<mi>d</mi>
<mi>y</mi>
</mrow>
<mrow>
<munder>
<mo>&Integral;</mo>
<mrow>
<msup>
<mi>D</mi>
<mi>r</mi>
</msup>
<mi>u</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>0</mn>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</munder>
<mi>&lambda;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<msqrt>
<mrow>
<mo>&dtri;</mo>
<mi>u</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>&beta;</mi>
</mrow>
</msqrt>
<mi>d</mi>
<mi>x</mi>
<mi>d</mi>
<mi>y</mi>
</mrow>
</mfrac>
</mrow>
LS(u(x0,y0)) bigger, show u (x0,y0) to belong to construction zone possibility bigger;
Described DrIt is with (x0,y0) it is the center of circle, radius is r circular support region;
Described λ (x, y) is support region DrThe weights of middle corresponding pixel points;
Described ▽ u (x, y) are pixel (x, y) gradient magnitude;
Described β is adjustable parameter, and it is 0 to avoid the denominator when gradient is 0.
3. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic according to claim 1,
It is characterized in that the threshold value T chosen is automatically determined by OSTU algorithms.
4. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic according to claim 1,
It is characterized in that MinsTake 1/10 of building average area in image.
5. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic according to claim 1,
It is characterized in that rectangular degree R and length-width ratio P are calculated by below equation respectively:
<mrow>
<mi>R</mi>
<mo>=</mo>
<mfrac>
<msub>
<mi>S</mi>
<mn>0</mn>
</msub>
<msub>
<mi>S</mi>
<mi>R</mi>
</msub>
</mfrac>
</mrow>
<mrow>
<mi>P</mi>
<mo>=</mo>
<mfrac>
<msub>
<mi>l</mi>
<mn>1</mn>
</msub>
<msub>
<mi>l</mi>
<mn>2</mn>
</msub>
</mfrac>
</mrow>
Wherein, S0For the area of cutting object;SRFor the area of the minimum enclosed rectangle of cutting object;l1And l2Segmentation is represented respectively
The length and width of the minimum enclosed rectangle of object, and rectangular degree R lower limit is arranged to 0.75, the length-width ratio P upper limit is arranged to 4.
6. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic according to claim 1,
It is characterized in that the building coefficient cof of cutting objectkCalculated according to rectangular degree R and length-width ratio P, and rectangular degree R and length-width ratio P
Weight respectively account for 50%, specific formula for calculation is:
<mrow>
<msub>
<mi>cof</mi>
<mi>k</mi>
</msub>
<mo>=</mo>
<mn>0.5</mn>
<mo>&times;</mo>
<mfrac>
<mrow>
<msub>
<mi>K</mi>
<mi>R</mi>
</msub>
<mo>-</mo>
<msub>
<mi>MIN</mi>
<mi>R</mi>
</msub>
</mrow>
<mrow>
<msub>
<mi>MAX</mi>
<mi>R</mi>
</msub>
<mo>-</mo>
<msub>
<mi>MIN</mi>
<mi>R</mi>
</msub>
</mrow>
</mfrac>
<mo>+</mo>
<mn>0.5</mn>
<mo>&times;</mo>
<mfrac>
<mrow>
<msub>
<mi>K</mi>
<mi>P</mi>
</msub>
<mo>-</mo>
<msub>
<mi>MIN</mi>
<mi>P</mi>
</msub>
</mrow>
<mrow>
<msub>
<mi>MAX</mi>
<mi>P</mi>
</msub>
<mo>-</mo>
<msub>
<mi>MIN</mi>
<mi>P</mi>
</msub>
</mrow>
</mfrac>
</mrow>
Wherein, MAXRFor the maximum occurrences of rectangular degree, MINRFor the minimum value of rectangular degree, MAXPFor the maximum occurrences of length-width ratio,
MINPFor the minimum value of length-width ratio, KRFor the rectangular degree of cutting object, KPFor the length-width ratio of cutting object.
7. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic according to claim 1,
It is characterized in that Gabor filter carries out 3 yardsticks, the Gabor transformation in 8 directions, and to same yardstick not to cutting object
Equidirectional feature is averaged to obtain 3 textural characteristics subbands, and this 3 subband features are further extracted, and is calculated each
The average and variance in cutting object region, the characteristic vector of one 6 dimension is formed, as their texture feature information.
8. a kind of building extracting method for being used in remote sensing image have uniform spectral characteristic according to claim 1,
It is characterized in that sorting technique uses naive Bayes classifier.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510220949.7A CN104794478B (en) | 2015-05-04 | 2015-05-04 | A kind of building extracting method for being used in remote sensing image have uniform spectral characteristic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510220949.7A CN104794478B (en) | 2015-05-04 | 2015-05-04 | A kind of building extracting method for being used in remote sensing image have uniform spectral characteristic |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104794478A CN104794478A (en) | 2015-07-22 |
CN104794478B true CN104794478B (en) | 2017-12-19 |
Family
ID=53559265
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510220949.7A Expired - Fee Related CN104794478B (en) | 2015-05-04 | 2015-05-04 | A kind of building extracting method for being used in remote sensing image have uniform spectral characteristic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104794478B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491826B (en) * | 2018-04-08 | 2021-04-30 | 福建师范大学 | Automatic extraction method of remote sensing image building |
CN109635715B (en) * | 2018-12-07 | 2022-09-30 | 福建师范大学 | Remote sensing image building extraction method |
CN113313273B (en) * | 2021-07-28 | 2021-10-29 | 佛山市东信科技有限公司 | Public facility detection method, system and storage medium based on big data environment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101950361A (en) * | 2010-09-06 | 2011-01-19 | 中国科学院遥感应用研究所 | Adaptive extraction method of remote sensing image thematic information based on spectrum matching degree |
CN102663394A (en) * | 2012-03-02 | 2012-09-12 | 北京航空航天大学 | Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion |
CN103745453A (en) * | 2013-12-11 | 2014-04-23 | 河海大学 | Town information extraction method based on Google Earth remote sensing image |
CN104331698A (en) * | 2014-11-19 | 2015-02-04 | 中国农业科学院农业资源与农业区划研究所 | Remote sensing type urban image extracting method |
-
2015
- 2015-05-04 CN CN201510220949.7A patent/CN104794478B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101950361A (en) * | 2010-09-06 | 2011-01-19 | 中国科学院遥感应用研究所 | Adaptive extraction method of remote sensing image thematic information based on spectrum matching degree |
CN102663394A (en) * | 2012-03-02 | 2012-09-12 | 北京航空航天大学 | Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion |
CN103745453A (en) * | 2013-12-11 | 2014-04-23 | 河海大学 | Town information extraction method based on Google Earth remote sensing image |
CN104331698A (en) * | 2014-11-19 | 2015-02-04 | 中国农业科学院农业资源与农业区划研究所 | Remote sensing type urban image extracting method |
Non-Patent Citations (2)
Title |
---|
光谱和形状特征相结合的高分辨率遥感图像的建筑物提取方法;吴炜等;《武汉大学学报.信息科学版》;20120731;第37卷(第7期);全文 * |
基于分类器集成的高光谱遥感图像分类方法;樊利恒等;《光学学报》;20140930;第34卷(第9期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN104794478A (en) | 2015-07-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | A multiresolution hierarchical classification algorithm for filtering airborne LiDAR data | |
CN103400151B (en) | The optical remote sensing image of integration and GIS autoregistration and Clean water withdraw method | |
CN106683091A (en) | Target classification and attitude detection method based on depth convolution neural network | |
CN104766343B (en) | A kind of visual target tracking method based on rarefaction representation | |
CN112766184B (en) | Remote sensing target detection method based on multi-level feature selection convolutional neural network | |
CN106971156A (en) | Rare earth mining area remote sensing information extraction method based on object-oriented classification | |
CN101901343A (en) | Remote sensing image road extracting method based on stereo constraint | |
CN107341837B (en) | Grid-vector data conversion and continuous scale expression method based on image pyramid | |
CN104794478B (en) | A kind of building extracting method for being used in remote sensing image have uniform spectral characteristic | |
CN103778436B (en) | A kind of pedestrian's attitude detecting method based on image procossing | |
CN108051371A (en) | A kind of shadow extraction method of ecology-oriented environment parameter remote-sensing inversion | |
Li et al. | Water extraction in high resolution remote sensing image based on hierarchical spectrum and shape features | |
Kang et al. | Identifying tree crown areas in undulating eucalyptus plantations using JSEG multi-scale segmentation and unmanned aerial vehicle near-infrared imagery | |
CN111882573B (en) | Cultivated land block extraction method and system based on high-resolution image data | |
CN117197686A (en) | Satellite image-based high-standard farmland plot boundary automatic identification method | |
Sjahputera et al. | Clustering of detected changes in high-resolution satellite imagery using a stabilized competitive agglomeration algorithm | |
He et al. | A calculation method of phenotypic traits of soybean pods based on image processing technology | |
Kim et al. | Generation of a DTM and building detection based on an MPF through integrating airborne lidar data and aerial images | |
Mohammadi et al. | Estimation of leaf area in bell pepper plant using image processing techniques and artificial neural networks | |
CN117197661A (en) | Method for identifying loess water falling hole by utilizing laser radar point cloud data | |
Vukadinov et al. | An algorithm for coastline extraction from satellite imagery | |
CN116704373A (en) | Remote sensing target detection method based on centrality and mutual exclusion constraint | |
Liang et al. | Mapping Pu’er tea plantations from GF-1 images using Object-Oriented Image Analysis (OOIA) and Support Vector Machine (SVM) | |
Ukhnaa et al. | Modification of urban built-up area extraction method based on the thematic index-derived bands | |
CN109859145A (en) | It is a kind of that texture method is gone with respect to the image of total variance based on multistage weight |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 350300 R & D center, Fu Xin Normal University, No.1 campus village, Longjiang street, Fuqing, Fujian Applicant after: Fujian Normal University Address before: Minhou County of Fuzhou City, Fujian province 350108 University City streets Qishan Campus University Department of science and technology Applicant before: Fujian Normal University |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171219 |
|
CF01 | Termination of patent right due to non-payment of annual fee |