CN107133979A - A kind of polarimetric radar building damage information extracting method - Google Patents
A kind of polarimetric radar building damage information extracting method Download PDFInfo
- Publication number
- CN107133979A CN107133979A CN201710283555.5A CN201710283555A CN107133979A CN 107133979 A CN107133979 A CN 107133979A CN 201710283555 A CN201710283555 A CN 201710283555A CN 107133979 A CN107133979 A CN 107133979A
- Authority
- CN
- China
- Prior art keywords
- building
- mrow
- msub
- area
- statistical model
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Abstract
The present invention provides a kind of polarimetric radar building damage information extracting method, including：Pretreatment is carried out to original PolSAR images comprising Selecting research area and coherence matrix is extracted；Characteristic value characteristic vector decomposition is carried out to coherence matrix, the pixel studied in area less than characteristic threshold value is identified as non-building area, non-building area is rejected；The coherence matrix of building area is modeled using statistical model, based on statistical model parametric texture texture feature extraction, the pixel that textural characteristics are more than default texture threshold is classified as collapsed building, the pixel less than or equal to default texture threshold is classified as intact building；Piecemeal is carried out to building area, information extraction result is damaged then in conjunction with the building of gained above, the precision that building damages information extraction result is evaluated.The present invention only extracts collapsed building with statistical model parametric texture, takes full advantage of the information of PolSAR images, while also improving precision and efficiency that building damages information extraction.
Description
Technical field
The present invention relates to polarimetric radar (Polarimetric Synthetic Aperture Radar, PolSAR) image
A kind of processing technology field, and in particular to polarimetric radar building damage information extracting method.
Background technology
The lives and properties that the natural calamities such as earthquake, typhoon give people bring extreme loss.Building is the master of people's life
Place is wanted, the loss that disaster is caused has building collapsing to cause mostly.Therefore the damage of building after calamity is accurately extracted
Information can be that disaster assistance and post-disaster reconstruction provide decision support.After disaster occurs, traffic and communication equipment are destroyed, day gas bar
Part is severe, while there is the danger for occurring secondary disaster so that obtain disaster area disaster-stricken situation in time extremely difficult.SAR is due to it
Ability to work turns into the main path for obtaining disaster information by force, all-time anf all-weather for wide coverage, penetrability.
The data difference that information extraction is used is damaged for building, existing extracting method has：
Building damage information extraction based on single channel or multi-Channel SAR images.Such method is mainly utilized before disaster
The change of SAR images such as correlation, coherence etc., or the texture information of SAR images extracts collapsed building after calamity afterwards.But single-pass
The terrestrial object information that road or multichannel SAR are obtained is not comprehensive enough, poor to collapsed building Detection results.
Building damage information extraction based on PolSAR images.PolSAR can obtain atural object under 4 POLARIZATION CHANNELs
Echo, it is more sensitive to atural object, for building damage information extraction provide enrich information.Based on multidate PolSAR shadows
The change of building scattering mechanism before and after disaster is mainly used as extracting collapsed building.But in some cases, matching
Data are difficult to obtain before and after disaster, and the registration of SAR images is more difficult, therefore utilize the building of collapsing of multidate PolSAR images
Thing is extracted and is subject to certain restrictions.Mainly have based on polarization using the method for single width PolSAR Extraction of Image collapsed buildings after calamity
Feature, based on textural characteristics, based on polarization characteristic and textural characteristics.It is currently based on single width PolSAR Extraction of Image after calamity and collapses and builds
The method for building thing is more using parameter, and process is more complicated.And for the texture information of PolSAR Extraction of Image collapsed buildings
General power Extraction of Image is typically based on, the diagonal entry in coherence matrix is only make use of, to the letter of PolSAR images
Breath utilizes not comprehensive.
The content of the invention
In view of this, object of the present invention is to provide a kind of polarimetric radar building damage information extracting method, to solve
It is certainly existing to extract the information not defect such as complete, many, process complexity of parameter.
To achieve the above object, the invention provides a kind of polarimetric radar building damage information extracting method, it is based on
PolSAR image processing techniques, comprise the following steps:
Step 101：Original PolSAR images are pre-processed, including Selecting research area and extraction coherence matrix；
Step 102：Characteristic value-characteristic vector is carried out to coherence matrix to decompose, the characteristic value setting feature threshold based on decomposition
Value, is identified as non-building area, the pixel more than characteristic threshold value is identified as building area by the pixel studied in area less than characteristic threshold value,
Reject non-building area；
Step 103：The coherence matrix of building area is modeled using statistical model, carried based on statistical model parametric texture
Textural characteristics are taken, the pixel that textural characteristics are more than default texture threshold collapsed building are classified as, less than or equal to default
The pixel of texture threshold is classified as intact building, obtains building damage information extraction result；
Step 104：Piecemeal is carried out to building area, information extraction result is damaged then in conjunction with the building obtained by step 103,
Evaluate the precision that building damages information extraction result.
Further, in step 102, characteristic value-characteristic vector decomposition is carried out to coherence matrix is specially：
Wherein, T is coherence matrix, λnAnd μnCharacteristic value and characteristic vector, λ are represented respectively1≥λ2≥λ3, H represent conjugation
Transposition, characteristic vector μnIt is expressed as：
Wherein, αnRepresent the corresponding target scattering mechanism of Scattering of Vector, βnFor azimuth of target, φn、δn、γnFor 3 phases
Parallactic angle, T represents transposition operation, by λ2+λ3Pixel less than characteristic threshold value is identified as non-building area, λ1＞ 0.
Further, the extraction process of textural characteristics includes the estimation to statistical model parametric texture and incited somebody to action in step 103
The statistical model parametric texture of estimation is taken the logarithm as textural characteristics.
Further, statistical model is G0Statistical model, its parametric texture is：
M=tr (Σ-1T)
Wherein, T is coherence matrix, and Σ=E [T], λ is the parametric texture of statistical model, and L, which is represented, regards number, and Var { } is represented
Variance, d represents the dimension of coherence matrix.
Further, the detailed process of step 104 is as follows：
Step 401：If the building damage index of the jth block in gained piecemeal is DLIj, then：
Wherein, CjRepresent the number of pixels of collapsed building in j-th of block, IjRepresent intact building in j-th of block
Number of pixels, building damage index D LIjRepresent the damage degree of building；
Step 402：According to DLIjRespective block is divided into different brackets with default classification thresholds, building damage journey is obtained
The classification results of degree；
Step 403：Using confusion matrix, the precision that building information is extracted is assessed with recall rate, false alarm rate or overall accuracy.
To achieve the above object, present invention also offers another polarimetric radar building damage information extracting method, it is based on
PolSAR image processing techniques, comprise the following steps：
Step 101：Original PolSAR images are pre-processed, including Selecting research area and extraction coherence matrix；
Step 102：Based on the building area in coherence matrix Study of recognition area and non-building area, non-building area is rejected；
Step 103：The coherence matrix of building area is modeled using statistical model, the texture ginseng of estimation statistical model
Number, then the parametric texture of estimation is taken the logarithm as textural characteristics, then textural characteristics are more than to the picture of default texture threshold
Element is classified as collapsed building, and the pixel less than or equal to default texture threshold is classified as intact building, obtains building damage
Information extraction result；
Step 104：Piecemeal is carried out to building area, information extraction result is damaged then in conjunction with step 103 gained building, comments
Valency building damages the precision of information extraction result.
Further, in step 103, statistical model is G0Statistical model, the estimation of its parametric texture is based on coherence matrix：
M=tr (Σ-1T)
Wherein, T is coherence matrix, and Σ=E [T], λ is the parametric texture of statistical model, and L, which is represented, regards number, and Var { } is represented
Variance, d represents the dimension of coherence matrix.
Compared with prior art, its advantage is the present invention：Reflect the uniform of building area with statistical model parametric texture
Degree, it is high according to the more intact building area of the uniformity coefficient for the building area that collapses, utilize the line extracted based on statistical model parametric texture
Reason feature realizes the extraction of collapse building and intact building.All have for the non-building area such as building area and road, water body of collapsing
Higher uniformity coefficient, the characteristic value decomposed using characteristic value-characteristic vector rejects the non-building in research area, reduces non-building
Thing and collapsed building are obscured, so as to improve the precision that building damages information extraction.It is this to be based on PolSAR image statistics
The polarimetric radar building damage information extracting method of model parametric texture makes full use of the information of PolSAR images, and reduces pair
The dependence of data, efficiency and Evaluation accuracy all increase.
Brief description of the drawings
Fig. 1 is the step schematic diagram of polarimetric radar building damage information extracting method embodiment one of the present invention；
Fig. 2 is the principle schematic of polarimetric radar building damage information extracting method of the present invention.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to embodiment party of the present invention
Formula is further described.
Technical solution of the present invention can realize automatic running using computer technology, refer to shown in Fig. 1 and Fig. 2.The present invention
There is provided a kind of polarimetric radar building damage information extracting method, based on PolSAR image processing techniques, comprise the following steps：
Step 101：Original PolSAR images are pre-processed, including Selecting research area and extraction coherence matrix.
, it is necessary to be pre-processed to original PolSAR images before building damage information is extracted, including selection is ground
Study carefully region and extract coherence matrix.Because PolSAR images have substantial amounts of coherent spot, in order to reduce the influence of noise, typically need
Processing is filtered to original PolSAR images, such as fine Lee filtering, Sigma Lee filtering.When PolSAR resolution ratio compared with
When low, filtering process can not also be done in order to retain image information.
Step 102：Characteristic value-characteristic vector is carried out to coherence matrix to decompose, the characteristic value setting feature threshold based on decomposition
Value, is identified as non-building area, the pixel more than characteristic threshold value is identified as building area by the pixel studied in area less than characteristic threshold value,
Reject non-building area.
Coherence matrix carries out characteristic value-characteristic vector decomposition：
Wherein, T is coherence matrix, λnAnd μnCharacteristic value and characteristic vector, λ are represented respectively1≥λ2≥λ3, H represent conjugation
Transposition, characteristic vector μnIt is expressed as：
Wherein, αnRepresent the corresponding target scattering mechanism of Scattering of Vector, βnFor azimuth of target, φn、δn、γnFor 3 phases
Parallactic angle, T represents transposition operation, by λ2+λ3Pixel less than characteristic threshold value is identified as non-building area, and non-building area is rejected.
Because the present invention is that both are distinguished according to the uniformity coefficient of collapsed building and intact building, road, water
The uniformity coefficient of the non-building areas such as body and collapsed building is all higher, in order to reduce interference of the non-building to collapsed building,
The accuracy that collapsed building is extracted is improved, general non-building area such as road, water body etc. are typical single Scattering Targets, only
One characteristic value is larger, and meets λ1＞ 0, λ2With λ3It is smaller, close to 0.So by λ2+λ3Pixel less than characteristic threshold value is classified as
Non-building area, so the present invention utilizes λ2+λ3Reject the non-building area in survey region.Before subsequent extracted collapsed building,
Non-building area is rejected.
Step 103：The coherence matrix of building area is modeled using statistical model, the texture ginseng of estimation statistical model
Number, then the parametric texture of estimation is taken the logarithm as textural characteristics, then textural characteristics are more than to the picture of default texture threshold
Element is classified as collapsed building, and the pixel less than or equal to default texture threshold is classified as intact building, obtains building damage
Information extraction result.
The statistical model G set up with the coherence matrix based on building area0Exemplified by, statistical model G0For：
The statistical model G of estimation0Parametric texture be：
M=tr (Σ-1T)
Wherein, Σ=E [T], λ are G0The parametric texture of statistical model, L, which is represented, regards number, and Var { } represents variance, and d is represented
The dimension of coherence matrix, meets d=3 in the case of reciprocal theorem.
Coherence matrix T is inputted, parametric texture λ is estimated from the sliding window of k*k (k is odd number) size and is assigned in window
Center pixel, so as to obtain the parametric texture figure of whole survey region.But under normal circumstances, the parametric texture in whole research area
Value extreme difference is excessive, and display and statistics to parametric texture bring inconvenience.And the present invention takes the logarithm texture to the parametric texture of estimation
Feature can clearly reflect the uniformity coefficient of atural object.Based on G0The textural characteristics that statistical model parametric texture is extracted are as follows：
TF_G0=lg (λ)
Wherein, TF_G0Represent to be based on G0The textural characteristics that statistical model parametric texture is extracted.
Intact building area type of ground objects is complicated, comprising vegetation around building, road, building etc., therefore intact builds
The uniformity coefficient for building area is relatively low.Building covers the atural object of surrounding after collapsing completely, so that uniformity coefficient increases.Therefore
Collapse building area texture eigenvalue it is bigger than intact building area.
The pixel that the textural characteristics of extraction are more than texture threshold is identified as collapsed building, less than or equal to texture threshold
Pixel is classified as intact building.Texture threshold during specific implementation can determine that method determines texture threshold using existing texture threshold
Value center, then selects suitable texture threshold by manually finely tuning.
Step 104：Piecemeal is carried out to building area, information extraction result is damaged then in conjunction with the building obtained by step 103,
Evaluate the precision that building damages information extraction result.
General city of choosing is as survey region, and block is that based on road k-path partition, building has similar in same block
Structure.The damage degree of block is divided with reference to the building damage information extraction result extracted in step 103, is that building is damaged
The checking for ruining information extraction result provides foundation, i.e.,：(i.e. collapsed building is accounted for the building damage index of calculation block in block
The ratio of total building pixel) all blocks are divided into different grades：Serious damage, moderate damage, slight damage.According to step
The standard setting classification thresholds of the number of pixels of collapsed building and intact building in rapid 103.Confusion matrix is calculated, with detection
Rate, false alarm rate and overall accuracy evaluate the precision that building damages information extraction.Specially：
Step 401：If the building damage index of the jth block in gained piecemeal is DLIj, then：
Wherein, CjRepresent the number of pixels of collapsed building in j-th of block, IjRepresent intact building in j-th of block
Number of pixels, building damage index D LIjRepresent the damage degree of building；
Step 402：According to DLIjRespective block is divided into different brackets with default classification thresholds, building damage journey is obtained
The classification results of degree；
Step 403：Using confusion matrix, the essence that building information is extracted is assessed with recall rate or false alarm rate or overall accuracy
Degree.
The present invention compared with the prior art, this have the advantage that：Merely with single width PolSAR images after calamity, reduce to data
Dependence；Collapsed building only is extracted with statistical model parametric texture, the information of PolSAR images is taken full advantage of, while also carrying
High building damages the precision and efficiency of information extraction.
In summary, only the preferred embodiments of the invention, does not limit protection scope of the present invention with this, all according to the present invention
The equivalent changes and modifications that the scope of the claims and description are made, is all within the scope of patent of the present invention covers.
Claims (7)
1. a kind of polarimetric radar building damage information extracting method, based on polarization PolSAR image processing techniques, it is characterised in that
Comprise the following steps：
Step 101：Original PolSAR images are pre-processed, including Selecting research area and extraction coherence matrix；
Step 102：Characteristic value-characteristic vector is carried out to coherence matrix to decompose, the characteristic value setting characteristic threshold value based on decomposition will
The pixel for being less than characteristic threshold value in research area is identified as non-building area, and the pixel more than characteristic threshold value is identified as building area, rejects
Non-building area；
Step 103：The coherence matrix of building area is modeled using statistical model, line is extracted based on statistical model parametric texture
Feature is managed, the pixel that textural characteristics are more than default texture threshold collapsed building is classified as, less than or equal to default texture
The pixel of threshold value is classified as intact building, obtains building damage information extraction result；
Step 104：Piecemeal is carried out to building area, information extraction result is damaged then in conjunction with the building obtained by step 103, is evaluated
Building damages the precision of information extraction result.
2. polarimetric radar building damage information extracting method as claimed in claim 1, it is characterised in that in step 102, to phase
Dry matrix carries out characteristic value-characteristic vector decomposition：
<mrow>
<mi>T</mi>
<mo>=</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>n</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>3</mn>
</munderover>
<msub>
<mi>&lambda;</mi>
<mi>n</mi>
</msub>
<msub>
<mi>T</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<msub>
<mi>&lambda;</mi>
<mn>1</mn>
</msub>
<msub>
<mi>&mu;</mi>
<mn>1</mn>
</msub>
<msubsup>
<mi>&mu;</mi>
<mn>1</mn>
<mi>H</mi>
</msubsup>
<mo>+</mo>
<msub>
<mi>&lambda;</mi>
<mn>2</mn>
</msub>
<msub>
<mi>&mu;</mi>
<mn>2</mn>
</msub>
<msubsup>
<mi>&mu;</mi>
<mn>2</mn>
<mi>H</mi>
</msubsup>
<mo>+</mo>
<msub>
<mi>&lambda;</mi>
<mn>3</mn>
</msub>
<msub>
<mi>&mu;</mi>
<mn>3</mn>
</msub>
<msubsup>
<mi>&mu;</mi>
<mn>3</mn>
<mi>H</mi>
</msubsup>
</mrow>
Wherein, T is coherence matrix, λnAnd μnCharacteristic value and characteristic vector, λ are represented respectively1≥λ2≥λ3, H represent conjugation transposition,
λ1＞ 0, characteristic vector μnIt is expressed as：
<mrow>
<msub>
<mi>&mu;</mi>
<mi>n</mi>
</msub>
<mo>=</mo>
<msup>
<mi>e</mi>
<mrow>
<msub>
<mi>i&phi;</mi>
<mi>n</mi>
</msub>
</mrow>
</msup>
<msup>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>cos&alpha;</mi>
<mi>n</mi>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>sin&alpha;</mi>
<mi>n</mi>
</msub>
<msub>
<mi>cos&beta;</mi>
<mi>n</mi>
</msub>
<msup>
<mi>e</mi>
<mrow>
<msub>
<mi>i&delta;</mi>
<mi>n</mi>
</msub>
</mrow>
</msup>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>sin&alpha;</mi>
<mi>n</mi>
</msub>
<msub>
<mi>sin&beta;</mi>
<mi>n</mi>
</msub>
<msup>
<mi>e</mi>
<mrow>
<msub>
<mi>i&gamma;</mi>
<mi>n</mi>
</msub>
</mrow>
</msup>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mi>T</mi>
</msup>
</mrow>
Wherein, αnRepresent the corresponding target scattering mechanism of Scattering of Vector, βnFor azimuth of target, φn、δn、γnFor 3 phase angles,
T represents transposition operation, by λ2+λ3Pixel less than characteristic threshold value is identified as non-building area.
3. polarimetric radar building damage information extracting method according to claim 1, it is characterised in that line in step 103
The extraction process of reason feature includes taking the logarithm to the estimation of statistical model parametric texture and by the statistical model parametric texture of estimation
It is used as textural characteristics.
4. polarimetric radar building damage information extracting method according to claim 3, it is characterised in that：Statistical model is G0
Statistical model, its parametric texture is：
<mrow>
<mi>&lambda;</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mn>2</mn>
<mi>L</mi>
<mi>V</mi>
<mi>a</mi>
<mi>r</mi>
<mrow>
<mo>{</mo>
<mi>M</mi>
<mo>}</mo>
</mrow>
<mo>+</mo>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>L</mi>
<mi>d</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>L</mi>
<mi>V</mi>
<mi>a</mi>
<mi>r</mi>
<mrow>
<mo>{</mo>
<mi>M</mi>
<mo>}</mo>
</mrow>
<mo>-</mo>
<mi>d</mi>
</mrow>
</mfrac>
</mrow>
M=tr (Σ-1T)
Wherein, T is coherence matrix, and Σ=E [T], λ is the parametric texture of statistical model, and L, which is represented, regards number, Var { } expression side
Difference, d represents the dimension of coherence matrix.
5. polarimetric radar building damage information extracting method according to claim 1, it is characterised in that the tool of step 104
Body process is as follows：
Step 401：If the building damage index of the jth block in gained piecemeal is DLIj, then：
<mrow>
<msub>
<mi>DLI</mi>
<mi>j</mi>
</msub>
<mo>=</mo>
<mfrac>
<msub>
<mi>C</mi>
<mi>j</mi>
</msub>
<mrow>
<msub>
<mi>I</mi>
<mi>j</mi>
</msub>
<mo>+</mo>
<msub>
<mi>C</mi>
<mi>j</mi>
</msub>
</mrow>
</mfrac>
</mrow>
Wherein, CjRepresent the number of pixels of collapsed building in j-th of block, IjRepresent the picture of intact building in j-th of block
Plain number, building damage index D LIjRepresent the damage degree of building；
Step 402：According to DLIjRespective block is divided into different brackets with default classification thresholds, building damage degree is obtained
Classification results；
Step 403：Using confusion matrix, the precision that building information is extracted is assessed with recall rate, false alarm rate or overall accuracy.
6. a kind of polarimetric radar building damage information extracting method, based on PolSAR image processing techniques, it is characterised in that including
Following steps：
Step 101：Original PolSAR images are pre-processed, including Selecting research area and extraction coherence matrix；
Step 102：Based on the building area in coherence matrix Study of recognition area and non-building area, non-building area is rejected；
Step 103：The coherence matrix of building area is modeled using statistical model, the parametric texture of statistical model is estimated, then
The parametric texture of estimation is taken the logarithm as textural characteristics, be then classified as the pixel that textural characteristics are more than default texture threshold
Collapsed building, the pixel less than or equal to default texture threshold is classified as intact building, obtains building damage information and carries
Take result；
Step 104：Piecemeal is carried out to building area, information extraction result is damaged then in conjunction with the building obtained by step 103, is evaluated
Building damages the precision of information extraction result.
7. polarimetric radar building damage information extracting method according to claim 6, it is characterised in that：In step 103, system
Meter model is G0Statistical model, the estimation of its parametric texture is based on coherence matrix：
<mrow>
<mi>&lambda;</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mn>2</mn>
<mi>L</mi>
<mi>V</mi>
<mi>a</mi>
<mi>r</mi>
<mrow>
<mo>{</mo>
<mi>M</mi>
<mo>}</mo>
</mrow>
<mo>+</mo>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>L</mi>
<mi>d</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>L</mi>
<mi>V</mi>
<mi>a</mi>
<mi>r</mi>
<mrow>
<mo>{</mo>
<mi>M</mi>
<mo>}</mo>
</mrow>
<mo>-</mo>
<mi>d</mi>
</mrow>
</mfrac>
</mrow>
M=tr (Σ-1T)
Wherein, T is coherence matrix, and Σ=E [T], λ is the parametric texture of statistical model, and L, which is represented, regards number, Var { } expression side
Difference, d represents the dimension of coherence matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710283555.5A CN107133979B (en) | 2017-04-26 | 2017-04-26 | Polarized radar building damage information extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710283555.5A CN107133979B (en) | 2017-04-26 | 2017-04-26 | Polarized radar building damage information extraction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107133979A true CN107133979A (en) | 2017-09-05 |
| CN107133979B CN107133979B (en) | 2019-12-17 |
Family
ID=59716065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710283555.5A Expired - Fee Related CN107133979B (en) | 2017-04-26 | 2017-04-26 | Polarized radar building damage information extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107133979B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761740A (en) * | 2014-01-23 | 2014-04-30 | 武汉大学 | Construction damage assessment method based on single post-earthquake POLSAR image |
| CN105321163A (en) * | 2014-07-31 | 2016-02-10 | 中国科学院遥感与数字地球研究所 | Method and apparatus for detecting variation region of fully polarimetric SAR (Synthetic Aperture Radar) image |
| CN105975986A (en) * | 2016-05-03 | 2016-09-28 | 河海大学 | Fully-polarimetric SAR image supervised classification method based on improved genetic algorithm |
-
2017
- 2017-04-26 CN CN201710283555.5A patent/CN107133979B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761740A (en) * | 2014-01-23 | 2014-04-30 | 武汉大学 | Construction damage assessment method based on single post-earthquake POLSAR image |
| CN105321163A (en) * | 2014-07-31 | 2016-02-10 | 中国科学院遥感与数字地球研究所 | Method and apparatus for detecting variation region of fully polarimetric SAR (Synthetic Aperture Radar) image |
| CN105975986A (en) * | 2016-05-03 | 2016-09-28 | 河海大学 | Fully-polarimetric SAR image supervised classification method based on improved genetic algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107133979B (en) | 2019-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sato et al. | Polarimetric SAR analysis of tsunami damage following the March 11, 2011 East Japan earthquake | |
| Li et al. | A new approach to collapsed building extraction using RADARSAT-2 polarimetric SAR imagery | |
| Taskin Kaya et al. | Damage assessment of 2010 Haiti earthquake with post-earthquake satellite image by support vector selection and adaptation | |
| CN105335975B (en) | Polarization SAR image segmentation method based on low-rank decomposition and statistics with histogram | |
| CN105701481B (en) | A kind of collapsed building extracting method | |
| Zhai et al. | Fast building damage mapping using a single post-earthquake PolSAR image: a case study of the 2010 Yushu earthquake | |
| CN103761752A (en) | Method and device for processing PolSAR image | |
| CN105891832A (en) | Sea surface wind speed inversion method based on cross polarization model and CMOD5N | |
| Rathje et al. | Damage patterns from satellite images of the 2003 Bam, Iran, earthquake | |
| CN115236655B (en) | Landslide identification method, system, equipment and medium based on fully-polarized SAR | |
| CN105321163A (en) | Method and apparatus for detecting variation region of fully polarimetric SAR (Synthetic Aperture Radar) image | |
| Brunner et al. | Change detection for earthquake damage assessment in built-up areas using very high resolution optical and SAR imagery | |
| Kwak et al. | A new approach for rapid urban flood mapping using ALOS-2/PALSAR-2 in 2015 Kinu River Flood, Japan | |
| Gokon et al. | Verification of a method for estimating building damage in extensive tsunami affected areas using L-band SAR data | |
| Guo et al. | Study of detecting method with advanced airborne and spaceborne synthetic aperture radar data for collapsed urban buildings from the Wenchuan earthquake | |
| CN107133979A (en) | A kind of polarimetric radar building damage information extracting method | |
| Chen et al. | Building collapse extraction using modified freeman decomposition from post-disaster polarimetric SAR image | |
| CN105551021B (en) | The building method of estimation of falling loss rate based on multidate full-polarization SAR | |
| Dell'Acqua et al. | Experiences in optical and SAR imagery analysis for damage assessment in the Wuhan, May 2008 earthquake | |
| Liu et al. | An automatic high confidence sets selection strategy for SAR images change detection | |
| Matsuoka et al. | Estimation of building damage ratio due to earthquakes and tsunamis using satellite SAR imagery | |
| Zhai et al. | Building damage assessment using a single post-earthquake PolSAR image: a case of the 2010 Yushu earthquake | |
| CN111929680B (en) | Rapid flood inundation degree evaluation method based on SAR image | |
| CN107748875A (en) | A kind of earthquake building recognition method based on multidate radar image texture feature | |
| Ohki et al. | Flood-area detection using Palsar-2 data for heavy rainfall disasters in Japan |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for 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: 20191217 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |