CN104899562B - Radar remote sensing image culture's recognizer based on Texture Segmentation fusion - Google Patents
Radar remote sensing image culture's recognizer based on Texture Segmentation fusion Download PDFInfo
- Publication number
- CN104899562B CN104899562B CN201510285547.5A CN201510285547A CN104899562B CN 104899562 B CN104899562 B CN 104899562B CN 201510285547 A CN201510285547 A CN 201510285547A CN 104899562 B CN104899562 B CN 104899562B
- Authority
- CN
- China
- Prior art keywords
- texture
- remote sensing
- space
- sar
- mathematical morphology
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of radar remote sensing image culture's recognizers based on Texture Segmentation fusion.Its algorithm steps is：Determine that Image Segmentation scale factor and logic mask divide scale according to sensor type；It finds and calculates, screen spatial autocorrelation structure index characteristic and gray level co-occurrence matrixes textural characteristics；Logic mask is carried out to space characteristics index and texture information according to mask scale；Filtering mask result is operated using mathematical morphology；The result of filtering is subjected to preliminary logic cluster, and finds apparent construction area；According to tentatively finding as a result, logic clusters and combine mathematical morphology algorithm for reconstructing again, the apparent construction area of renolation, and pass through mathematical morphology profile Reconstruction is final accurate to obtain architecture information recognition result.The present invention, which maximizes, excavates mathematical morphology with logic cluster to the ability of SAR image Building recognitions, can improve the final accuracy of identification of architecture information.
Description
Technical field
The present invention relates to Remote Sensing Model identification technology fields, and in particular to a kind of radar based on Texture Segmentation fusion
Remote sensing image culture's recognizer.
Background technology
Ecological environment is a structure the most complicated, is the continuous basis for creating civilization of human society, it is main
Two features be：Growth property and dynamic.Which increase the complexities analyzed and recognized using remotely-sensed data.With society
The progress of meeting economic development and science and technology, socialization process constantly accelerates, and artificial earth's surface is (especially based on building, road etc.
Impermeable stratum) natural landscape based on vegetation etc. is gradually replaced, cause the basic change of urban land use/covering.SAR
Satellite image has the characteristics that round-the-clock, round-the-clock compared with Optical satellite images, and Henderson is summarized for the first time within 1997
SAR satellite datas are applied to the present situation and foreground of Monitoring Urban Environment.The especially most significant advantage of SAR images is
Its complex texture information that can be provided, signal phase load can provide more information, therefore texture than spatial domain strength signal
Information plays the role of obtaining the approval and support of more and more scholars in radar image extracts urban architecture information.
It is more more scientific than individual building unit since atural object classification is regarded as blocky aggregation in urban area environment
It is more favorable to the extraction of classification information, therefore we are split cluster, rather than single picture using Mathematical Morphology to spatial texture
The method of element carries out artificial structure's identification.In high resolution SAR data, especially as low latitude UAV system/spaceborne radar
In the high resolution SAR data that sensor obtains, it is meaningful that statistics segmentation is carried out to homogeney information.The process of segmentation can
Each object is finally confirmed as according to certain criterion by certain specific urban land cover type to regard as.Ideal situation
Under, if one piece of region can fully be divided, these segmentation results perhaps can utilize some space characteristics, such as
The space characteristics that our fronts select, and reconfigured as significant landscape pattern's classification according to certain judgment criterion
（Such as building body）, that is, realize typical target identifying purpose.
A kind of UAV system based on Texture Segmentation fusion/spaceborne radar remote sensing image culture proposed by the present invention knows
Other algorithm the characteristics of for high resolution SAR data, is manually built by spatial texture segmentation and the morphologic method of mathematics
Build the extraction of ground class.The similitude of each desired value and the mean value of its adjacent element is assessed using MORAN spatial autocorrelation indicators
It measures to weigh local homogeneity；It is weighed using the high variant area of GEARY space indexs identification pixel and its adjacent element
Local diversity；Assemble blocking very high or very low value region using the identification of GETIS space indexs.Finding high relevant range is
Highly useful, especially for SAR data, high relevant range indicates the specific characteristic in region.Therefore it is based on space correlation
The culture of characteristic index the main thought of class identification be exactly, it is reliable highlighted by finding identification to SAR Image Segmentations
Target area, and utilize these complete building groups of highlighted target area reconstruction regions.
Invention content
In view of the shortcomings of the prior art, purpose of the present invention is to be to provide a kind of thunder merged based on Texture Segmentation
Up to remote sensing image culture's recognizer, solves and efficiently use synthetic aperture radar（SAR）Remotely-sensed data spatial texture is special
The problem of levying extracted with high accuracy architecture information.
To achieve the goals above, the present invention is to realize by the following technical solutions：Based on Texture Segmentation fusion
Radar remote sensing image culture's recognizer, the specific steps are：
(1) SAR remote sensing image datas are inputted；
(2) determine that Image Segmentation scale factor and logic mask divide scale according to sensor type；
(3) it finds and calculates, screens spatial autocorrelation structure index characteristic and gray level co-occurrence matrixes textural characteristics；
(4) logic mask is carried out to space characteristics index and texture information according to mask scale, and utilizes mathematical morphology
Operation filtering mask result；
(5) result of filtering is subjected to preliminary logic cluster, and finds apparent construction area；
(6) according to tentatively finding as a result, logic clusters and combines mathematical morphology algorithm for reconstructing, renolation bright again
Aobvious construction area；
(7) the spatial texture feature for calculating survey region carries out logic mask and mathematical morphology to spatial texture information
Filtering, and by filter result and the（5）The preliminary information that step obtains carries out logical AND or fusion；
(8) density slice is carried out to logical AND or result；
(9) mathematical morphology connection operation is carried out to density slice result, and carries out logical AND or fusion, update is obviously built
Build area results；
(10) logic cluster and fusion carried out to the architecture information that extracts twice, and by mathematical morphology profile Reconstruction,
Obtain final architecture information recognition result.
Preferably, in the step (1), algorithm supports input SAR remote sensing image modality various, spaceborne
The remote sensing image that the remote sensing image and unmanned aerial vehicle SAR sensor that SAR sensors obtain obtain.
Preferably, the spatial autocorrelation inputted in the step (2) is characterized in the high-resolution inputted for step (1)
Rate SAR remote sensing images count the local spatial feature factor for calculating and obtaining by local space auto-correlation, can tentatively identify and build
Build region.
Preferably, the step（3）The atural object texture information of middle input is based on gray level co-occurrence matrixes GLCM statistics meters
It obtains, GLCM textures are effective supplements to space correlation feature, can be to the construction area that tentatively identifies into one in algorithm
Step optimization, improves accuracy of identification.
Preferably, the step（4）It is middle extract the auto-correlation region positive with building type height respectively and bear from phase
Close region method.The mathematical model used in extraction process can be expressed as following formula：
（1）
（2）
（3）
Formula（1）In, xiIt is the attribute value of space cell i, wijFor space weight matrix, represent between space cell i and j
Influence degree.IiIt is MORAN indexes, value range is [- 1,1], and positive value indicates the attribute value of the space cell and adjacent unit
Similar, spatial auto-correlation is positive correlation；Negative value indicates that the attribute value of the space cell and adjacent unit is dissimilar, and space is from phase
Closing property is negatively correlated；0 indicates no spatial correlation properties.
Formula（2）In, CiIt is GEARY indexes, value range is generally [0,2], and it is unrelated that GEARY=1 represents space, is less than 1
For space positive correlation, it is that space is negatively correlated when being more than 1, has very strong space negatively correlated as GEARY=2.Therefore can be used for reflecting
Fixation member and neighbouring Pixel domain similarity.
Formula（3）In, GiIt indicates GETIS space indexs, is based on the Local Indices of Spatial Autocorrelation apart from weight matrix, energy
Detect high level aggregation and low value aggregation, wijIt is the distance between unit i and unit j power, positive GETIS indicates the sight of unit neighbours
Measured value is high, and negative GETIS indicates that the observation of unit neighbours is low.
It removes and isolates small area object, and growth calculating is carried out to significant object using mathematical morphology filling.It calculates
Threshold segmentation and mathematical morphology filling use mathematical model and are in method：
（4）
（5）
（6）
（7）
Formula（4）,（5）It indicates statements of the B to the corrosion and expansive working set theory of A, is that mathematical morphology filter is filled out
The basis for filling operation, for measuring the mathematical model such as formula for corroding and expanding（6）With（7）Shown, S is that label is schemed in formula
Picture, T are template image.As n=0, D (S)=S, E (S)=S, therefore the mathematics that may be implemented to measure corrosion and expand by iteration
Morphological reconstruction.Since culture has aggregation and incoherence in radar image, the extraction of image intersection operation is utilized
Characteristic area is more advantageous to the identification of building area.
The step（5）With（6）In obtained GETIS-ORD features as template, carry out mathematical morphology and rebuild opening and closing
Used mathematical model is：
,（8）
Mathematical morphology filling, mask extraction construction area are completed by iteration.
The step（7）With（8）In the middle image by SAR intersection fortune is carried out using the textural characteristics of gray level co-occurrence matrixes extraction
Calculate, and with the positive and negative relevant range intersection of space correlation feature extraction, make full use of gray level co-occurrence matrixes texture and space from phase
The respective advantage of feature texture is closed, ground class accuracy of identification is improved.
Preferably, the step（9）With（10）The construction area that different texture is extracted is merged, and is iterated
Screening, obtains final Building recognition result.
Present invention solution efficiently uses synthetic aperture radar（SAR）Remotely-sensed data spatial texture feature extracted with high accuracy is built
The problem of information.Spatial autocorrelation textural characteristics are split first and mathematics morphological reconstruction, predict preliminary classification knot
Then fruit optimizes and merges using gray level co-occurrence matrixes texture, and carry out prediction classification again, final to realize SAR remote sensing shadows
As accurate culture the purpose of class high-precision identification.
The present invention make full use of enriched in SAR remote sensing images spatial texture information and culture in radar image
Unique imaging features maximize and excavate mathematical morphology with logic cluster to the ability of SAR image Building recognitions, can improve
The final accuracy of identification of architecture information, while having the advantages that be easily achieved, computation complexity is low etc., it can be used for UAV system or star
Carry the city culture's information extraction of SAR remote sensing images, the monitoring of city dynamic expansion and the urban district correlations such as building investigation in violation of rules and regulations
A variety of applications in.
Description of the drawings
The following describes the present invention in detail with reference to the accompanying drawings and specific embodiments；
Fig. 1 is the step flow chart of the present invention.
Fig. 2 is that the spaceborne PALSAR data coal field culture of the present invention extracts result figure.
Fig. 3 is that the spaceborne PALSAR data city culture of the present invention extracts result figure.
Fig. 4 is that the UAV system MINI SAR datas city culture of the present invention extracts result figure.
Specific implementation mode
To make the technical means, the creative features, the aims and the efficiencies achieved by the present invention be easy to understand, with reference to
Specific implementation mode, the present invention is further explained.
Referring to Fig.1, present embodiment uses following technical scheme：Radar remote sensing image based on Texture Segmentation fusion
Culture's recognizer, the specific steps are：
Step 1：Input SAR remote sensing image datas
Input SAR remote sensing image types it is not specific, satellite-borne microwave radiometer sensor obtain SAR remote sensing images and nobody
The SAR remote sensing images that machine airborne microwave radiometer sensor obtains.
Step 2：Extract Space correlation degree texture
Rule-statistical, which is closed on, using Rook's case calculates research area MORAN, GEARY and GETIS-ORD Space correlation degrees
Index, and it is converted into the tonal gradations of G=256.
Step 3：Extract gray level co-occurrence matrixes texture
Extraction research area's gray level co-occurrence matrixes are calculated using moving window（GLCM）Texture information, and it is converted into the ashes of G=256
Spend grade.
Step 4：It extracts and optimizes space correlation region.
Space index is split and does spatial analysis using morphology, is calculating separately extraction and building type height just
Auto-correlation region and negative auto-correlation region.It removes and isolates small area object, and filled to significant using mathematical morphology
Object carry out growth calculating.Intersection operation is carried out to the object figure after optimization, identification extracts while having positive auto-correlation
With negative auto-correlation region.
Step 5：Rebuild apparent construction area
Using the auto-correlation provincial characteristics of extraction as label, the GETIS-ORD features that the 2nd step is calculated are as mould
Plate carries out mathematical morphology reconstruction, and carries out morphologic filtering to the result of reconstruction and delete too small erroneous judgement region.
Step 6：Assay tentatively obtains building area
Each cut zone picture dot number and area are calculated, carrying out analysis to the apparent construction area of the reconstruction of the 5th step tests
Card obtains the cutting unit BML that can be judged as construction area maximum probability
Step 7：Texture feature extraction and analysis
To VARIANCE the and CORRELATION texture informations of acquisition, carries out binaryzation and image intersection operation generates
The result of CVB, the result that intersection operation is generated and the 4th step carries out intersection operation and generates CVS, is to mark CVB as template using CVS
Mathematical morphology reconstruction is carried out, and morphologic filtering is carried out to the result of reconstruction and deletes too small erroneous judgement region acquisition MCV.
Step 8：Optimization of the textural characteristics to MORAN and GEARY
Each cut zone picture dot number and area are calculated again, analysis verification are carried out to the result of the 7th step, acquisition can
It is judged as the cutting unit BMT of construction area maximum probability.
Step 9：Optimization of the textural characteristics to GETIS-ORD
6th step and the 8th step are utilized to the building area of space characteristics and texture feature extraction（BML and BMT）It is merged, point
It is other morphology intersection to be done to BML and BMT and union operation obtains BALT and BULT
Step 10：Assay extracts final construction area
The BALT and BULT of acquisition are analyzed, mathematical morphology weight is carried out using BALT as label BULT as template
It builds, and combines all construction area patches extracted and the 6th step and the 8th step analysis setting TH5, the patch to meeting condition utilizes
Morphologic filtering, which optimizes, obtains final construction area recognition result.
Embodiment 1：UAV system/spaceborne radar remote sensing image culture's recognizer based on Texture Segmentation fusion is same
Specific implementation mode, Fig. 2 (a) and Fig. 3 (a) are the satellite-borne SAR remote sensing original images that the present invention uses, it is the earth observation of Japan
The phase array probe L-band synthetic aperture radar of satellite ALOS（PALSAR）Sensing data, not by cloud layer, weather and shadow round the clock
It rings, can be used for the round-the-clock land observation of round-the-clock, the acquisition time is 12 days, polarization mode HH November in 2008, spatial discrimination
Rate is 10m, and overlay area is the coal mine region and Xuzhou Urban District ' region to the east of the Jiawang District of Xuzhou City of Jiangsu Province to the west of Tongshan County.
In order to verify the validity of the method for the present invention, while being verified using unmanned aerial vehicle SAR data.UAV system MINI SAR are passed
Sensor is stripmap SAR data acquiring mode, is imaged bandwidth, 300~2000m, spatial resolution 0.3m.Imaging frequency is ku waves
Section, as shown in Fig. 4 (a).The method of the present invention does not need adjustment parameter, easy to use.It is logical that table 1 lists various different SAR datas
Cross the precision of this method culture identification.Fig. 2 is that spaceborne PALSAR data coal field culture extracts result figure, and Fig. 3 is
Spaceborne PALSAR data city culture extracts result figure, and Fig. 4 is that UAV system MINI SAR datas city culture carries
Take result figure.Table 2, table 3 and table 4 are listed to be identified with existing algorithm to not tying for different zones and sensor inventive algorithm
Fruit.
1 satellite-borne SAR data of table and unmanned aerial vehicle SAR data Building recognition precision：
2 invention algorithm of table is compared with existing algorithm recognition result（Mining area experimental result）：
3 invention algorithm of table is compared with existing algorithm recognition result（City experimental result）：
4 invention algorithm of table is compared with existing algorithm recognition result（UAV system data experiment result）：
Culture's recognition methods of the present embodiment can make full use of radar data characteristic information, according to spatial coherence
Theoretical and texture segmentation algorithm, the high-precision ground class recognition result that can be obtained.
With the continuous development of high resolution SAR technology, the approach for obtaining UAV system or Satellite imagery increases
Add, and can increasingly be easy, thing followed application also can be more and more, will be related to numerous fields.Therefore it studies
SAR remote sensing image culture's recognition methods has practical significance, and the present invention is the hair of SAR Remote Image Classifications
Exhibition provides a kind of new thinking.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (7)
1. based on Texture Segmentation fusion radar remote sensing image culture's recognizer, which is characterized in that its specific steps are：
(1) SAR remote sensing image datas are inputted：Algorithm supports input SAR remote sensing image modality various, satellite-borne SAR sensor
The remote sensing image that the remote sensing image and unmanned aerial vehicle SAR sensor of acquisition obtain；
(2) determine that Image Segmentation scale factor and logic mask divide scale according to sensor type；
(3) it finds and calculates, screens spatial autocorrelation structure index characteristic and gray level co-occurrence matrixes textural characteristics；
(4) logic mask is carried out to space characteristics index and texture information according to mask scale, and is operated using mathematical morphology
Filter mask result；
(5) result of filtering is subjected to preliminary logic cluster, and finds apparent construction area；
(6) according to tentatively finding as a result, logic clusters and mathematical morphology algorithm for reconstructing, renolation is combined obviously to build again
Build region；
(7) the spatial texture feature for calculating survey region carries out logic mask and mathematical morphology filter to spatial texture information,
And filter result is subjected to logical AND with the preliminary information that (5) step obtains or is merged；
(8) density slice is carried out to logical AND or result；
(9) mathematical morphology connection operation is carried out to density slice result, and carries out logical AND or fusion, update apparent building area
Field result；
(10) logic cluster and fusion are carried out to the architecture information extracted twice, and by mathematical morphology profile Reconstruction, obtained
Final architecture information recognition result；
The satellite-borne SAR remote sensing original image used, the phase array probe L-band synthetic aperture radar of earth observation satellite ALOS
(PALSAR) sensing data influences not by cloud layer, weather and round the clock, can be used for the round-the-clock land observation of round-the-clock, polarization side
Formula is HH, spatial resolution 10m, while being verified using unmanned aerial vehicle SAR data, UAV system MINI SAR sensors
For stripmap SAR data acquiring mode, it is imaged bandwidth, 300~2000m, spatial resolution 0.3m；Imaging frequency is ku waves
Section.
2. radar remote sensing image culture's recognizer according to claim 1 based on Texture Segmentation fusion, special
Sign is that the spatial autocorrelation inputted in the step (2) is characterized in the high resolution SAR remote sensing inputted for step (1)
Image counts the local spatial feature factor for calculating and obtaining by local space auto-correlation, can tentatively identify construction area.
3. radar remote sensing image culture's recognizer according to claim 1 based on Texture Segmentation fusion, special
Sign is that the atural object texture information inputted in the step (3) is calculated based on gray level co-occurrence matrixes GLCM, GLCM
Texture is effective supplement to space correlation feature, can be advanced optimized to the construction area tentatively identified in algorithm, is improved
Accuracy of identification.
4. radar remote sensing image culture's recognizer according to claim 1 based on Texture Segmentation fusion, special
Sign is, is extracted respectively and the positive auto-correlation region of building type height and negative auto-correlation region method in the step (4)；
The mathematical model used in extraction process can be expressed as following formula：
In formula (1), xiIt is the attribute value of space cell i, wijFor space weight matrix, the influence between space cell i and j is represented
Degree；IiIt is MORAN indexes, value range is [- 1,1], and positive value indicates that the space cell is similar to the attribute value of adjacent unit,
Spatial auto-correlation is positive correlation；Negative value indicates that the attribute value of the space cell and adjacent unit is dissimilar, spatial auto-correlation
It is negatively correlated；0 indicates no spatial correlation properties；
In formula (2), CiIt is GEARY indexes, value range is generally [0,2], and it is unrelated that GEARY=1 represents space, is less than 1 for sky
Between positive correlation, be more than negatively correlated for space when 1, have very strong space negatively correlated as GEARY=2；Therefore can be used for identifying
Pixel and neighbouring Pixel domain similarity；
In formula (3), GiIt indicates GETIS space indexs, can be detected based on the Local Indices of Spatial Autocorrelation apart from weight matrix
High level is assembled and low value aggregation, wijIt is the distance between unit i and unit j power, positive GETIS indicates the observation of unit neighbours
Height, negative GETIS indicate that the observation of unit neighbours is low；
It removes and isolates small area object, and growth calculating is carried out to significant object using mathematical morphology filling；In algorithm
Threshold segmentation and mathematical morphology filling use mathematical model and are：
Formula (4), (5) indicate statements of the B to the corrosion and expansive working set theory of A, are mathematical morphology filter filling behaviour
The basis of work, for measuring shown in mathematical model such as formula (6) and (7) of corrosion and expansion, S is tag image in formula, and T is
Template image；As n=0, D (S)=S, E (S)=S, therefore the mathematics shape that may be implemented to measure corrosion and expand by iteration
State is rebuild；Since culture has aggregation and incoherence in radar image, the spy extracted using image intersection operation
Sign region is more advantageous to the identification of building area.
5. radar remote sensing image culture's recognizer according to claim 1 based on Texture Segmentation fusion, special
Sign is that the GETIS-ORD features obtained in the step (5) and (6) carry out mathematical morphology and rebuild switching station as template
Using mathematical model is：
Mathematical morphology filling, mask extraction construction area are completed by iteration.
6. radar remote sensing image culture's recognizer according to claim 1 based on Texture Segmentation fusion, special
Sign is, intersection fortune will be carried out using the textural characteristics of gray level co-occurrence matrixes extraction in SAR images in the step (7) and (8)
Calculate, and with the positive and negative relevant range intersection of space correlation feature extraction, make full use of gray level co-occurrence matrixes texture and space from phase
The respective advantage of feature texture is closed, ground class accuracy of identification is improved.
7. radar remote sensing image culture's recognizer according to claim 1 based on Texture Segmentation fusion, special
Sign is that the construction area that different texture is extracted is merged in the step (9) and (10), and is iterated screening, obtains
Final Building recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510285547.5A CN104899562B (en) | 2015-05-29 | 2015-05-29 | Radar remote sensing image culture's recognizer based on Texture Segmentation fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510285547.5A CN104899562B (en) | 2015-05-29 | 2015-05-29 | Radar remote sensing image culture's recognizer based on Texture Segmentation fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104899562A CN104899562A (en) | 2015-09-09 |
| CN104899562B true CN104899562B (en) | 2018-10-30 |
Family
ID=54032218
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510285547.5A Expired - Fee Related CN104899562B (en) | 2015-05-29 | 2015-05-29 | Radar remote sensing image culture's recognizer based on Texture Segmentation fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104899562B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740825B (en) * | 2016-02-01 | 2018-11-23 | 福建师范大学 | It is a kind of for mixing the large format remote sensing image building extracting method of scene |
| CN106338775B (en) * | 2016-09-07 | 2018-07-10 | 民政部国家减灾中心（民政部卫星减灾应用中心） | Building based on interference of data of synthetic aperture radar falls to damage degree assessment method |
| CN107622269A (en) * | 2017-09-24 | 2018-01-23 | 国网江苏省电力公司常州供电公司 | Cartridge fuse body recognition methods based on geometrical constraint under complex background |
| CN108154158B (en) * | 2017-12-18 | 2021-03-16 | 西安交通大学 | Building image segmentation method for augmented reality application |
| CN108830203B (en) * | 2018-06-01 | 2022-03-08 | 中国科学院空天信息创新研究院 | Building area extraction method and system based on SAR image |
| CN109059849A (en) * | 2018-09-28 | 2018-12-21 | 中国科学院测量与地球物理研究所 | A kind of surface subsidence prediction technique based on InSAR technology in remote sensing |
| CN110309727B (en) * | 2019-06-11 | 2022-02-18 | 四川隧唐科技股份有限公司 | Building identification model establishing method, building identification method and building identification device |
| CN110189328B (en) * | 2019-06-11 | 2021-02-23 | 北华航天工业学院 | Satellite remote sensing image processing system and processing method thereof |
| CN112989940B (en) * | 2021-02-08 | 2023-08-01 | 国家海洋环境监测中心 | Raft culture area extraction method based on high-resolution third satellite SAR image |
| CN112907567B (en) * | 2021-03-19 | 2022-05-27 | 甘肃省地震局（中国地震局兰州地震研究所） | SAR image ordered artificial structure extraction method based on spatial reasoning method |
| CN115100536B (en) * | 2022-06-01 | 2023-03-28 | 中科星睿科技(北京)有限公司 | Building identification method and device, electronic equipment and computer readable medium |
| CN115631428B (en) * | 2022-11-01 | 2023-08-11 | 西南交通大学 | Unsupervised image fusion method and system based on structural texture decomposition |
| CN117237397B (en) * | 2023-07-13 | 2024-05-28 | 天翼爱音乐文化科技有限公司 | Portrait segmentation method, system, equipment and storage medium based on feature fusion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361589A (en) * | 2014-11-12 | 2015-02-18 | 河海大学 | High-resolution remote sensing image segmentation method based on inter-scale mapping |
| CN104463193A (en) * | 2014-11-04 | 2015-03-25 | 西安电子科技大学 | Polarization SAR image classifying method based on depth sparsity ICA |
-
2015
- 2015-05-29 CN CN201510285547.5A patent/CN104899562B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463193A (en) * | 2014-11-04 | 2015-03-25 | 西安电子科技大学 | Polarization SAR image classifying method based on depth sparsity ICA |
| CN104361589A (en) * | 2014-11-12 | 2015-02-18 | 河海大学 | High-resolution remote sensing image segmentation method based on inter-scale mapping |
Non-Patent Citations (3)
| Title |
|---|
| "Evaluation of Spatial and Spectral Effectiveness of Pixel-Level Fusion Techniques";Javier Marcello .etc;《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,》;20130531;第10卷(第3期);全文 * |
| "基于主被动遥感数据协同处理的地表环境监测与分析";刘培;《中国博士学位论文全文数据库（基础科学辑）》;20150415(第4期);第1.1.1节、第3.2节、第4章 * |
| "遥感地质勘查技术与应用研究";*** ，等;《地质学报》;20111130;第85卷(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104899562A (en) | 2015-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104899562B (en) | Radar remote sensing image culture's recognizer based on Texture Segmentation fusion | |
| Esch et al. | Breaking new ground in mapping human settlements from space–The Global Urban Footprint | |
| Li et al. | A 30-year (1984–2013) record of annual urban dynamics of Beijing City derived from Landsat data | |
| CN109919875B (en) | High-time-frequency remote sensing image feature-assisted residential area extraction and classification method | |
| Zhou et al. | Individual tree parameters estimation for plantation forests based on UAV oblique photography | |
| CN102521273B (en) | High-resolution remote-sensing multifunctional urban land spatial information generation method | |
| CN103632363A (en) | Object-level high-resolution remote sensing image change detection method based on multi-scale fusion | |
| Piyoosh et al. | Semi-automatic mapping of anthropogenic impervious surfaces in an urban/suburban area using Landsat 8 satellite data | |
| CN106340005A (en) | High-resolution remote sensing image unsupervised segmentation method based on scale parameter automatic optimization | |
| CN103035006A (en) | High-resolution aerial image partition method based on LEGION and under assisting of LiDAR | |
| Fan et al. | Land cover classification of resources survey remote sensing images based on segmentation model | |
| Ming et al. | Cropland extraction based on OBIA and adaptive scale pre-estimation | |
| Yang et al. | The spatial distribution and expansion of subsided wetlands induced by underground coal mining in eastern China | |
| Zhao et al. | Automatic extraction of yardangs using Landsat 8 and UAV images: A case study in the Qaidam Basin, China | |
| CN114943902A (en) | Urban vegetation unmanned aerial vehicle remote sensing classification method based on multi-scale feature perception network | |
| Chi et al. | Remote sensing data processing and analysis for the identification of geological entities | |
| CN112166688B (en) | Method for monitoring desert and desertification land based on minisatellite | |
| Wang et al. | Rapid identification of post-earthquake collapsed buildings via multi-scale morphological profiles with multi-structuring elements | |
| Lyu et al. | A deep information based transfer learning method to detect annual urban dynamics of Beijing and Newyork from 1984–2016 | |
| Sun et al. | Geo-parcel based Crops Classification with Sentinel-1 Time Series Data via Recurrent Reural Network | |
| Shukla et al. | Monitoring land use/land cover changes in a river basin due to urbanization using remote sensing and GIS approach | |
| CN112907567B (en) | SAR image ordered artificial structure extraction method based on spatial reasoning method | |
| Lyu et al. | Four seasonal composite Sentinel-2 images for the large-scale estimation of the number of stories in each individual building | |
| Bai et al. | Estimating the Aboveground Biomass of Urban Trees by Combining Optical and Lidar Data: A Case Study of Hengqin, Zhuhai, China | |
| Elshorbagy et al. | Rice area inter annual variation through a remote sensing based mapping algorithm |
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: 20181030 Termination date: 20210529 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |