CN104899562A - Texture segmentation and fusion based radar remote-sensing image artificial building recognition algorithm - Google Patents
Texture segmentation and fusion based radar remote-sensing image artificial building recognition algorithm Download PDFInfo
- Publication number
- CN104899562A CN104899562A CN201510285547.5A CN201510285547A CN104899562A CN 104899562 A CN104899562 A CN 104899562A CN 201510285547 A CN201510285547 A CN 201510285547A CN 104899562 A CN104899562 A CN 104899562A
- Authority
- CN
- China
- Prior art keywords
- texture
- sensing image
- remote sensing
- space
- correlation
- 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.)
- Granted
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)
- Image Processing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The present invention discloses texture segmentation and fusion based radar remote-sensing image artificial building recognition algorithm. The algorithm comprises the following steps of: determining image segmentation scale factors and logic mask segmentation scales according to sensor types; searching, calculating and screening space autocorrelation structure index features and gray scale co-occurrence matrix texture features; performing logic masking on space feature indexes and texture information according to the mask scales; operating and filtering mask results according to mathematical morphology; performing primary logical clustering on filtration results, and searching obvious building regions; performing secondary logical clustering according to primary search results, and rebuilding the algorithm in combination with the mathematical morphology; updating and perfecting the obvious building regions; rebuilding the sections through the mathematical morphology; and finally accurately obtaining a building information recognition result. The recognition ability of the mathematical morphology and the logical clustering on an SAR (synthetic aperture radar) image building is maximally excavated; and the final recognition precision of building information can be improved.
Description
Technical field
What the present invention relates to is Remote Sensing Model recognition technology field, is specifically related to a kind of radar remote sensing image culture recognizer merged based on Texture Segmentation.
Background technology
Ecologic environment is a structure the most complicated, and be the basis of continuous creation of mankind social civilization, its topmost two feature is: growth property and dynamic.Which increase and utilize remotely-sensed data to carry out analyzing and cognitive complexity.Along with socio-economic development and scientific and technological progress, socialization process constantly accelerates, artificial earth's surface (especially buildings, road etc. are main aquiclude) replaces the natural landscape based on vegetation etc. gradually, causes the basic change of urban land use/covering.SAR satellite image has round-the-clock, round-the-clock feature compared with Optical satellite images, and within 1997, Henderson reviews the current situation and potential that SAR satellite data is applied to Monitoring Urban Environment first.Particularly the most significant advantage of SAR image is its complex texture information that can provide, signal phase load can provide more information than spatial domain strength signal, and therefore texture information extracts at radar image approval and the support that the effect played in urban architecture information obtains more and more scholar.
Owing to atural object classification being regarded as the extraction that be also more conducive to classified information more more scientific than independent building unit of block aggregation in urban area environment, therefore we adopt Mathematical Morphology to carry out segmentation cluster to spatial texture, but not the method for single pixel carries out artificial structure's identification.In high resolution SAR data, in the high resolution SAR data particularly as low latitude UAV system/spaceborne radar sensor acquisition, statistics segmentation is carried out highly significant to homogeney information.The process of segmentation can be regarded as, according to certain criterion, each object is finally confirmed as certain specific urban land cover type.Ideally, if one piece of region can fully be split, so these segmentation results perhaps can utilize some space characteristics, such as our space characteristics of selecting above, and reconfigure according to certain judgment criterion and become significant landscape pattern classification (as building body), namely achieve typical target identifying purpose.
A kind of UAV system/spaceborne radar remote sensing image culture recognizer merged based on Texture Segmentation that the present invention proposes, for the feature of high resolution SAR data, by the extraction of spatial texture segmentation and the method for mathematical morphology with carrying out culture class.The similarity measurement utilizing MORAN spatial autocorrelation indicators to assess the average of each desired value and its adjacent element weighs local homogeneity; Utilize the high variant area of GEARY space index identification pixel and its adjacent element to weigh the Local Phase opposite sex; The identification of GETIS space index is utilized to be gathered into the region that is very high or very low value of block.It is very useful for finding high relevant range, and particularly for SAR data, high relevant range represents the specific characteristic in region.Therefore the main thought based on the culture ground class identification of space correlation characteristic exponent is exactly, and identifies reliable highlighted target area, and utilize the complete building group of these highlighted target area reconstruction regions by finding SAR Image Segmentation.
Summary of the invention
For the deficiency that prior art exists, the present invention seeks to be to provide a kind of radar remote sensing image culture recognizer merged based on Texture Segmentation, solve the problem effectively utilizing synthetic aperture radar (SAR) remotely-sensed data spatial texture feature extracted with high accuracy architecture information.
To achieve these goals, the present invention realizes by the following technical solutions: the radar remote sensing image culture recognizer merged based on Texture Segmentation, and its concrete steps are:
(1) SAR remote sensing image data is inputted;
(2) according to sensor type determination Image Segmentation scale factor and logic mask segmentation yardstick;
(3) find and calculate, screen spatial autocorrelation structure index characteristic and gray level co-occurrence matrixes textural characteristics;
(4) according to mask yardstick, logic mask is carried out to space characteristics exponential sum texture information, and utilize mathematical morphology to operate filtration mask result;
(5) result of filtration is carried out preliminary logic cluster, and find obvious construction area;
(6) according to the preliminary result found, logic cluster in conjunction with mathematics morphological reconstruction algorithm again, the obvious construction area of renolation;
(7) calculate the spatial texture feature of survey region, logic mask and mathematical morphology filter are carried out to spatial texture information, and the preliminary information that filter result and (5) step obtain is carried out logical and or fusion;
(8) density slice is carried out to logical and or result;
(9) mathematical morphology is carried out to density slice result and be communicated with operation, and carry out logical and or fusion, upgrade obvious construction area result;
(10) logic cluster and fusion are carried out to the architecture information of extracted twice, and by mathematical morphology profile Reconstruction, obtain final architecture information recognition result.
As preferably, in described step (1), algorithm support input SAR remote sensing image modality is various, the remote sensing image that satellite-borne SAR sensor obtains and the remote sensing image that unmanned aerial vehicle SAR sensor obtains.
As preferably, in described step (2), the spatial autocorrelation feature of input is the high resolution SAR remote sensing image inputted for step (1), through the local spatial feature factor that the statistical computation of local space auto-correlation obtains, tentatively construction area can be identified.
As preferably, in described step (3), the atural object texture information of input obtains based on gray level co-occurrence matrixes GLCM statistical computation, GLCM texture is effectively supplementing space correlation feature, can optimize further, improve accuracy of identification in algorithm to the preliminary construction area identified.
As preferably, in described step (4), extract the auto-correlation region positive with building type height and negative auto-correlation region method respectively.The mathematical model used in leaching process can be expressed as following formula:
（1）
（2）
（3）
In formula (1), x
ithe property value of space cell i, w
ijfor space right matrix, represent the influence degree between space cell i and j.I
ibe MORAN index, span is [-1,1], and similar to the property value of adjacent unit on the occasion of this space cell of expression, spatial auto-correlation is positive correlation; Negative value represents that the property value of this space cell and adjacent unit is dissimilar, and spatial auto-correlation is negative correlation; 0 represents do not have spatial correlation properties.
In formula (2), C
ibe GEARY index, span is generally [0,2], and GEARY=1 represents space and has nothing to do, and is less than 1 for space positive correlation, is space negative correlation, has very strong space negative correlation as GEARY=2 when being greater than 1.Therefore can be used for identifying pixel and contiguous Pixel domain similarity.
In formula (3), G
irepresenting GETIS space index, is the Local Indices of Spatial Autocorrelation based on distance weight matrix, can detect high level and assemble and low value gathering, w
ijbe the distance power between unit i and unit j, positive GETIS represents that the observed reading of unit neighbours is high, and negative GETIS represents that the observed reading of unit neighbours is low.
Remove isolated small size object, and use mathematical morphology filling to carry out growth calculating to significant object.In algorithm, Threshold segmentation and mathematical morphology are filled and are used mathematical model and be:
（4）
（5）
（6）
（7）
Formula (4), (5) represent the statement of B to the corrosion of A and expansive working set theory, it is the basis of mathematical morphology filter padding, for measuring the mathematical model of corrosion and expansion as shown in formula (6) and (7), in formula, S is marking image, and T is template image.As n=0, D (S)=S, E (S)=S, therefore can realize the mathematical morphology reconstruction of measuring corrosion and expanding by iteration.Because culture in radar image has aggregation and incoherence, the characteristic area utilizing image intersection operation to extract more is conducive to the identification of building area.
The GETIS-ORD feature obtained in described step (5) and (6), as template, is carried out mathematical morphology and is rebuild switching station and use mathematical model and be:
，
（8）
Mathematical morphology filling, mask extraction construction area is completed by iteration.
In described step (7) and (8), the textural characteristics utilizing gray level co-occurrence matrixes to extract in SAR image is carried out intersection operation, and occur simultaneously with the positive and negative relevant range of space correlation feature extraction, make full use of gray level co-occurrence matrixes texture and spatial autocorrelation feature texture advantage separately, improve ground class accuracy of identification.
As preferably, the construction area that different texture is extracted merges by described step (9) and (10), and row iteration of going forward side by side is screened, and obtains final Building recognition result.
The present invention solves the problem effectively utilizing synthetic aperture radar (SAR) remotely-sensed data spatial texture feature extracted with high accuracy architecture information.First spatial autocorrelation textural characteristics is split and mathematical morphology reconstruction, dope preliminary classification result, then utilize gray level co-occurrence matrixes texture be optimized and merge, and carry out prediction classification again, finally realize the object of SAR remote sensing image accurate culture ground class high precision identification.
The present invention make full use of in SAR remote sensing image enrich spatial texture information and the imaging features unique in radar image of culture, maximization excavation mathematical morphology and logic cluster are to the ability of SAR image Building recognition, the final accuracy of identification of architecture information can be improved, have simultaneously and be easy to advantages such as realizing, computation complexity is low, can be used for UAV system or the culture's information extraction of satellite-borne SAR remote sensing image city, the monitoring of city dynamic expansion, and in the multiple application that building investigation etc. is relevant in violation of rules and regulations of urban district.
Accompanying drawing explanation
The present invention is described in detail below in conjunction with the drawings and specific embodiments;
Fig. 1 is flow chart of steps of the present invention.
Fig. 2 is that spaceborne PALSAR data coal field culture of the present invention extracts result figure.
Fig. 3 is that spaceborne PALSAR data city culture of the present invention extracts result figure.
Fig. 4 is that UAV system MINI SAR data city culture of the present invention extracts result figure.
Embodiment
The technological means realized for making the present invention, creation characteristic, reaching object and effect is easy to understand, below in conjunction with embodiment, setting forth the present invention further.
With reference to Fig. 1, this embodiment by the following technical solutions: the radar remote sensing image culture recognizer merged based on Texture Segmentation, its concrete steps are:
Step 1: input SAR remote sensing image data
Input SAR remote sensing image type is not specific, the SAR remote sensing image that satellite-borne microwave radiometer sensor obtains and the SAR remote sensing image that unmanned aerial vehicle onboard microwave flowmeter sensor obtains.
Step 2: extract Space correlation degree texture
Utilize Rook's case to close on rule-statistical and calculate study area MORAN, GEARY and GETIS-ORD Spatial correlation index, and be converted into G=256 gray shade scale.
Step 3: extract gray level co-occurrence matrixes texture
Utilize moving window to calculate and extract study area gray level co-occurrence matrixes (GLCM) texture information, and be converted into G=256 gray shade scale.
Step 4: extract and optimize space correlation region.
Space index split and utilizes morphology to do spatial analysis, calculating respectively and extract the auto-correlation region positive with building type height and negative auto-correlation region.Remove isolated small size object, and use mathematical morphology filling to carry out growth calculating to significant object.Intersection operation is carried out to the object figure after optimizing, identifies to extract that there is positive auto-correlation and negative auto-correlation region simultaneously.
Step 5: rebuild obvious construction area
Using the auto-correlation provincial characteristics extracted as mark, the GETIS-ORD feature the 2nd step calculated, as template, carries out mathematical morphology reconstruction, and the result of rebuilding is carried out to morphologic filtering and deleted too small erroneous judgement region.
Step 6: assay tentatively obtains building area
Calculate each cut zone picture dot number and area, analysis verification is carried out to the obvious construction area of the reconstruction of the 5th step, obtain the cutting unit BML that can be judged as construction area maximum probability
Step 7: texture feature extraction and analysis
To VARIANCE and the CORRELATION texture information obtained, carry out binaryzation and image intersection operation generation CVB, the result produce intersection operation and the result of the 4th step are carried out intersection operation and are produced CVS, be that mark CVB carries out mathematical morphology reconstruction for template with CVS, and morphologic filtering is carried out to the result of rebuilding delete too small erroneous judgement region and obtain MCV.
Step 8: textural characteristics is to the optimization of MORAN and GEARY
Again calculate each cut zone picture dot number and area, analysis verification is carried out to the result of the 7th step, obtain the cutting unit BMT that can be judged as construction area maximum probability.
Step 9: textural characteristics is to the optimization of GETIS-ORD
Utilize the building area of space characteristics and texture feature extraction (BML and BMT) to merge the 6th step and the 8th step, respectively to BML and BMT do morphology occur simultaneously and union operation obtain BALT and BULT
Step 10: assay extracts final construction area
BALT and BULT obtained is analyzed, mathematical morphology reconstruction is carried out as mark BULT as template using BALT, and combine all construction area patches and the 6th step and the 8th step analysis setting TH5 that extract, utilize morphologic filtering to be optimized to the patch satisfied condition and obtain final construction area recognition result.
Embodiment 1: the UAV system/same embodiment of spaceborne radar remote sensing image culture recognizer merged based on Texture Segmentation, Fig. 2 (a) and Fig. 3 (a) is the satellite-borne SAR remote sensing original image that the present invention uses, it is phase array probe L-band synthetic-aperture radar (PALSAR) sensing data of the earth observation satellite ALOS of Japan, not by cloud layer, weather and affecting round the clock, can be used for round-the-clock round-the-clock land observation, acquisition time is on November 12nd, 2008, polarization mode is HH, spatial resolution is 10m, overlay area is region, colliery to the east of Jiawang District, Xuzhou City of Jiangsu Province to the west of Tongshan County and region, Xuzhou Urban District '.In order to verify the validity of the inventive method, utilize unmanned aerial vehicle SAR data to verify simultaneously.UAV system MINI SAR sensor is stripmap SAR data acquiring mode, imaging bandwidth, 300 ~ 2000m, spatial resolution 0.3m.Imaging frequency is ku wave band, as shown in Fig. 4 (a).The inventive method does not need regulating parameter, easy to use.Table 1 lists the precision that various different SAR data is identified by this method culture.Fig. 2 is that spaceborne PALSAR data coal field culture extracts result figure, and Fig. 3 is that spaceborne PALSAR data city culture extracts result figure, and Fig. 4 is that UAV system MINI SAR data city culture extracts result figure.Table 2, table 3 and table 4 list for zones of different and sensor algorithm of the present invention and existing algorithm identification other result.
Table 1 satellite-borne SAR data and unmanned aerial vehicle SAR data Building recognition precision:
Table 2 invention algorithm and existing algorithm recognition result contrast (mining area experimental result):
Table 3 invention algorithm and existing algorithm recognition result contrast (city experimental result):
Table 4 invention algorithm and existing algorithm recognition result contrast (UAV system data experiment result):
Culture's recognition methods of the present embodiment can make full use of radar data characteristic information, the theoretical and texture segmentation algorithm according to spatial coherence, the high-precision ground class recognition result that can obtain.
Along with the development of high resolution SAR technology, the approach obtaining UAV system or Satellite imagery increases greatly, and can be more and more easier, and thing followed application also can get more and more, and will relate to numerous fields.Therefore study SAR remote sensing image culture recognition methods and have important realistic meaning, the present invention is that the development of SAR Remote Image Classification provides a kind of new thinking.
More than show and describe ultimate principle of the present invention and principal character and advantage of the present invention.The technician of the industry should understand; the present invention is not restricted to the described embodiments; what describe in above-described embodiment and instructions just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications, and these changes and improvements all fall in the claimed scope of the invention.Application claims protection domain is defined by appending claims and equivalent thereof.
Claims (8)
1. based on the radar remote sensing image culture recognizer that Texture Segmentation merges, it is characterized in that, its concrete steps are: (1) input SAR remote sensing image data;
(2) according to sensor type determination Image Segmentation scale factor and logic mask segmentation yardstick;
(3) find and calculate, screen spatial autocorrelation structure index characteristic and gray level co-occurrence matrixes textural characteristics;
(4) according to mask yardstick, logic mask is carried out to space characteristics exponential sum texture information, and utilize mathematical morphology to operate filtration mask result;
(5) result of filtration is carried out preliminary logic cluster, and find obvious construction area;
(6) according to the preliminary result found, logic cluster in conjunction with mathematics morphological reconstruction algorithm again, the obvious construction area of renolation;
(7) calculate the spatial texture feature of survey region, logic mask and mathematical morphology filter are carried out to spatial texture information, and the preliminary information that filter result and (5) step obtain is carried out logical and or fusion;
(8) density slice is carried out to logical and or result;
(9) mathematical morphology is carried out to density slice result and be communicated with operation, and carry out logical and or fusion, upgrade obvious construction area result;
(10) logic cluster and fusion are carried out to the architecture information of extracted twice, and by mathematical morphology profile Reconstruction, obtain final architecture information recognition result.
2. the radar remote sensing image culture recognizer merged based on Texture Segmentation according to claim 1, it is characterized in that, in described step (1), algorithm support input SAR remote sensing image modality is various, the remote sensing image that satellite-borne SAR sensor obtains and the remote sensing image that unmanned aerial vehicle SAR sensor obtains.
3. the radar remote sensing image culture recognizer merged based on Texture Segmentation according to claim 1, it is characterized in that, in described step (2), the spatial autocorrelation feature of input is the high resolution SAR remote sensing image inputted for step (1), through the local spatial feature factor that the statistical computation of local space auto-correlation obtains, tentatively construction area can be identified.
4. the radar remote sensing image culture recognizer merged based on Texture Segmentation according to claim 1, it is characterized in that, in described step (3), the atural object texture information of input obtains based on gray level co-occurrence matrixes GLCM statistical computation, GLCM texture is effectively supplementing space correlation feature, can optimize further the preliminary construction area identified in algorithm, improve accuracy of identification.
5. the radar remote sensing image culture recognizer merged based on Texture Segmentation according to claim 1, is characterized in that, extracts the auto-correlation region positive with building type height and negative auto-correlation region method respectively in described step (4); The mathematical model used in leaching process can be expressed as following formula:
（1）
（2）
（3）
In formula (1), x
ithe property value of space cell i, w
ijfor space right matrix, represent the influence degree between space cell i and j; I
ibe MORAN index, span is [-1,1], and similar to the property value of adjacent unit on the occasion of this space cell of expression, spatial auto-correlation is positive correlation; Negative value represents that the property value of this space cell and adjacent unit is dissimilar, and spatial auto-correlation is negative correlation; 0 represents do not have spatial correlation properties;
In formula (2), C
ibe GEARY index, span is generally [0,2], and GEARY=1 represents space and has nothing to do, and is less than 1 for space positive correlation, is space negative correlation, has very strong space negative correlation as GEARY=2 when being greater than 1; Therefore can be used for identifying pixel and contiguous Pixel domain similarity;
In formula (3), G
irepresenting GETIS space index, is the Local Indices of Spatial Autocorrelation based on distance weight matrix, can detect high level and assemble and low value gathering, w
ijbe the distance power between unit i and unit j, positive GETIS represents that the observed reading of unit neighbours is high, and negative GETIS represents that the observed reading of unit neighbours is low;
Remove isolated small size object, and use mathematical morphology filling to carry out growth calculating to significant object; In algorithm, Threshold segmentation and mathematical morphology are filled and are used mathematical model and be:
（4）
（5）
（6）
（7）
Formula (4), (5) represent the statement of B to the corrosion of A and expansive working set theory, it is the basis of mathematical morphology filter padding, for measuring the mathematical model of corrosion and expansion as shown in formula (6) and (7), in formula, S is marking image, and T is template image; As n=0, D (S)=S, E (S)=S, therefore can realize the mathematical morphology reconstruction of measuring corrosion and expanding by iteration; Because culture in radar image has aggregation and incoherence, the characteristic area utilizing image intersection operation to extract more is conducive to the identification of building area.
6. the radar remote sensing image culture recognizer merged based on Texture Segmentation according to claim 1, it is characterized in that, the GETIS-ORD feature obtained in described step (5) and (6), as template, is carried out mathematical morphology and is rebuild switching station and use mathematical model and be:
，
（8）
Mathematical morphology filling, mask extraction construction area is completed by iteration.
7. the radar remote sensing image culture recognizer merged based on Texture Segmentation according to claim 1, it is characterized in that, in described step (7) and (8), the textural characteristics utilizing gray level co-occurrence matrixes to extract in SAR image is carried out intersection operation, and occur simultaneously with the positive and negative relevant range of space correlation feature extraction, make full use of gray level co-occurrence matrixes texture and spatial autocorrelation feature texture advantage separately, improve ground class accuracy of identification.
8. the radar remote sensing image culture recognizer merged based on Texture Segmentation according to claim 1, it is characterized in that, the construction area that different texture is extracted merges by described step (9) and (10), and row iteration of going forward side by side is screened, and 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 true CN104899562A (en) | 2015-09-09 |
| CN104899562B 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) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740825A (en) * | 2016-02-01 | 2016-07-06 | 福建师范大学 | Large-breadth remote sensing image building extraction method used for hybrid scene |
| CN106338775A (en) * | 2016-09-07 | 2017-01-18 | 民政部国家减灾中心（民政部卫星减灾应用中心） | Building damage degree evaluation method based on interference synthetic aperture radar data |
| 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 |
| CN108154158A (en) * | 2017-12-18 | 2018-06-12 | 西安交通大学 | A kind of building image partition method applied towards augmented reality |
| CN108830203A (en) * | 2018-06-01 | 2018-11-16 | 中国科学院遥感与数字地球研究所 | A kind of building area extracting 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 |
| CN110189328A (en) * | 2019-06-11 | 2019-08-30 | 北华航天工业学院 | A kind of Remote sensing image processing system and its processing method |
| CN110309727A (en) * | 2019-06-11 | 2019-10-08 | 四川隧唐科技股份有限公司 | A kind of foundation of Building recognition model, Building recognition method and apparatus |
| CN112907567A (en) * | 2021-03-19 | 2021-06-04 | 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 |
| CN112989940A (en) * | 2021-02-08 | 2021-06-18 | 国家海洋环境监测中心 | Raft culture area extraction method based on high-resolution three-satellite SAR image |
| CN115100536A (en) * | 2022-06-01 | 2022-09-23 | 中科星睿科技(北京)有限公司 | Building identification method, building identification device, electronic equipment and computer readable medium |
| CN115631428A (en) * | 2022-11-01 | 2023-01-20 | 西南交通大学 | Unsupervised image fusion method and system based on structural texture decomposition |
| CN117237397A (en) * | 2023-07-13 | 2023-12-15 | 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 |
|---|
| JAVIER MARCELLO .ETC: ""Evaluation of Spatial and Spectral Effectiveness of Pixel-Level Fusion Techniques"", 《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,》 * |
| 刘培: ""基于主被动遥感数据协同处理的地表环境监测与分析"", 《中国博士学位论文全文数据库（基础科学辑）》 * |
| 王润生 ，等: ""遥感地质勘查技术与应用研究"", 《地质学报》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740825A (en) * | 2016-02-01 | 2016-07-06 | 福建师范大学 | Large-breadth remote sensing image building extraction method used for hybrid scene |
| 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 |
| CN106338775A (en) * | 2016-09-07 | 2017-01-18 | 民政部国家减灾中心（民政部卫星减灾应用中心） | Building damage degree evaluation method based on interference synthetic aperture radar data |
| 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 |
| CN108154158A (en) * | 2017-12-18 | 2018-06-12 | 西安交通大学 | A kind of building image partition method applied towards augmented reality |
| 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 |
| CN108830203A (en) * | 2018-06-01 | 2018-11-16 | 中国科学院遥感与数字地球研究所 | A kind of building area extracting 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 |
| CN110189328A (en) * | 2019-06-11 | 2019-08-30 | 北华航天工业学院 | A kind of Remote sensing image processing system and its processing method |
| CN110309727A (en) * | 2019-06-11 | 2019-10-08 | 四川隧唐科技股份有限公司 | A kind of foundation of Building recognition model, Building recognition method and apparatus |
| CN112989940A (en) * | 2021-02-08 | 2021-06-18 | 国家海洋环境监测中心 | Raft culture area extraction method based on high-resolution three-satellite SAR image |
| 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 |
| CN112907567A (en) * | 2021-03-19 | 2021-06-04 | 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 |
| 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 |
| CN115100536A (en) * | 2022-06-01 | 2022-09-23 | 中科星睿科技(北京)有限公司 | Building identification method, building identification device, electronic equipment and computer readable medium |
| CN115631428A (en) * | 2022-11-01 | 2023-01-20 | 西南交通大学 | Unsupervised image fusion method and system based on structural texture decomposition |
| 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 |
| CN117237397A (en) * | 2023-07-13 | 2023-12-15 | 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104899562B (en) | 2018-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104899562A (en) | Texture segmentation and fusion based radar remote-sensing image artificial building recognition algorithm | |
| Xu et al. | Urban morphology detection and computation for urban climate research | |
| Wang et al. | Analyzing parcel-level relationships between Luojia 1-01 nighttime light intensity and artificial surface features across Shanghai, China: A comparison with NPP-VIIRS data | |
| Zhao et al. | Slope unit-based landslide susceptibility mapping using certainty factor, support vector machine, random forest, CF-SVM and CF-RF models | |
| Zhang et al. | Land cover classification of the North China Plain using MODIS_EVI time series | |
| CN103632363B (en) | Object level high-resolution remote sensing image change detecting method based on Multiscale Fusion | |
| Tehrany et al. | Remote sensing data reveals eco-environmental changes in urban areas of Klang Valley, Malaysia: contribution from object based analysis | |
| CN104408463B (en) | High-resolution construction land pattern spot identification method | |
| Jun et al. | The extraction of urban built-up areas by integrating night-time light and POI data—A case study of Kunming, China | |
| Zheng et al. | The desaturation method of DMSP/OLS nighttime light data based on vector data: Taking the rapidly urbanized China as an example | |
| Halder et al. | An assessment of urban expansion impacts on land transformation of Rajpur-Sonarpur Municipality | |
| CN103440490A (en) | Urban impervious surface extraction method under SAR (Synthetic Aperture Radar) image space-time similarity analysis | |
| Piyoosh et al. | Semi-automatic mapping of anthropogenic impervious surfaces in an urban/suburban area using Landsat 8 satellite data | |
| Tormos et al. | Object-based image analysis for operational fine-scale regional mapping of land cover within river corridors from multispectral imagery and thematic data | |
| Zhao et al. | Combining ICESat-2 photons and Google Earth Satellite images for building height extraction | |
| Zhang et al. | Prior-knowledge-based spectral mixture analysis for impervious surface mapping | |
| Vieira et al. | Estimating water erosion from the brightness index of orbital images: A framework for the prognosis of degraded pastures | |
| Liu et al. | Spatial-temporal hidden Markov model for land cover classification using multitemporal satellite images | |
| Tran et al. | Improving hydrologic modeling using cloud-free modis flood maps | |
| CN101561882A (en) | Sub-pixel spatial mapping method based on spatial correlation | |
| Yang et al. | Urban roads network detection from high resolution remote sensing | |
| Chen et al. | Remote sensing for detecting changes of land use in Taipei City, Taiwan | |
| Shukla et al. | Monitoring land use/land cover changes in a river basin due to urbanization using remote sensing and GIS approach | |
| CN105825222A (en) | Land automatic classification method based on multisource and multi-temporal satellite image data | |
| Li et al. | High spatiotemporal resolution river networks mapping on catchment scale using satellite remote sensing imagery and DEM data |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181030 Termination date: 20210529 |