CN114429453B - Method for extracting artificial targets from polarized synthetic aperture radar images driven by scattering mechanism - Google Patents
Method for extracting artificial targets from polarized synthetic aperture radar images driven by scattering mechanism Download PDFInfo
- Publication number
- CN114429453B CN114429453B CN202111673335.6A CN202111673335A CN114429453B CN 114429453 B CN114429453 B CN 114429453B CN 202111673335 A CN202111673335 A CN 202111673335A CN 114429453 B CN114429453 B CN 114429453B
- Authority
- CN
- China
- Prior art keywords
- matrix
- polarization
- scattering
- target
- synthetic aperture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000007246 mechanism Effects 0.000 title claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 79
- 230000010287 polarization Effects 0.000 claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 238000005388 cross polarization Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 5
- 230000021615 conjugation Effects 0.000 claims description 2
- 238000000605 extraction Methods 0.000 description 13
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000001427 coherent effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method for extracting an artificial target of a polarized synthetic aperture radar image driven by a scattering mechanism, which comprises the following steps: s1, utilizing polarization coherence matrix elements T corresponding to secondary scattering, cross polarization scattering and reflection asymmetry respectively according to the relative amplitude characteristics of element values of the polarization coherence matrix in a rotating building area, a non-rotating building area and a natural area 22 、T 33 、T 13 And T 23 Constructing a matrix element combination feature MCF; s2, calculating a polarization covariance matrix of the target, obtaining a co-polarization correlation coefficient according to the polarization covariance matrix of the target, and combining matrix element combination characteristics with the co-polarization correlation coefficient to form a characteristic decision detector; s3, determining a detection threshold value in the polarized synthetic aperture radar image by using a histogram threshold value method, and judging and determining a detection area by using the detection threshold value and a feature decision detector. The invention can analyze the scattering mechanism of the building more accurately and sufficiently.
Description
Technical Field
The invention relates to the technical field of building extraction, in particular to a method for extracting an artificial target of a polarized synthetic aperture radar image driven by a scattering mechanism.
Background
Building extraction is of great importance in both military and civilian applications. Through effective extraction of enemy building groups, the deployment condition of enemy soldiers can be known, and the geographic distribution of hit objects can be detected, so that guidance is provided for follow-up accurate guidance, and support is provided for combat damage effect evaluation. In civil aspect, building extraction is one of important research contents in the remote sensing field, so that the layout information of the whole city can be detected, and an important means is provided for planning management of the city; when a disaster occurs, the system can also provide accurate building damage information, and precious time is striven for rescue tasks.
At present, building extraction can be realized by means of statistical information, channel correlation, neural network, scattering mechanism analysis and the like. Building extraction methods based on statistical information are very widely used, but statistical models generally require fitting a mixture of a large number of simple models, and thus their mathematical expression is extremely complex. The building detection essence by using the channel correlation is to calculate matrix elements and coupling characteristics of different polarization bases/channels, and has the advantages of easy realization and higher efficiency, but the polarization SAR coherent imaging conceals fine information among channels, so that the method shows more various and complex randomness distribution rules and multimode properties. The neural network method is to construct a multi-layer network model to realize a specific signal processing or corresponding function, but so far, the neural network method is a black box method, and the implementation process is difficult to be expressed by analytic mathematics. Furthermore, training neural networks requires large amounts of data, which is difficult to achieve in military countermeasures.
Building extraction methods based on scattering mechanism analysis have been vigorously developed in the last twenty years, and many researchers have developed intensive researches on scattering mechanism characteristics of buildings and achieved certain effects, but the methods have more or less some disadvantages: 1) The natural target usually has strong cross polarization response, and when the building position deviates from the flight direction of the radar platform (a rotating building corresponds to a non-rotating building), obvious cross polarization response is generated, and the traditional method cannot distinguish the source of the cross polarization response, so that misjudgment of a scattering mechanism exists, and the effective classification of the building and the natural target is difficult; 2) Building scattering typically has a reflective asymmetry where the cross-polarized channels and homopolar channels are correlated and the polarization coherence matrix off-diagonal elements are non-zero. However, the conventional method does not mine and utilize the information contained in the off-diagonal elements, so that the problems of incomplete utilization of polarization information and inaccurate scattering modeling are caused.
Disclosure of Invention
The invention aims to provide a method for extracting an artificial target of a polarized synthetic aperture radar image driven by a scattering mechanism, which aims to overcome the defects in the prior art.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
the method for extracting the artificial target of the polarized synthetic aperture radar image driven by the scattering mechanism comprises the following steps:
s1, utilizing polarization coherence matrix elements T corresponding to secondary scattering, cross polarization scattering and reflection asymmetry respectively according to the relative amplitude characteristics of element values of the polarization coherence matrix in a rotating building area, a non-rotating building area and a natural area 22 、T 33 、T 13 And T 23 Constructing a matrix element combination feature MCF;
s2, calculating a polarization covariance matrix of the target, obtaining a co-polarization correlation coefficient according to the polarization covariance matrix of the target, and combining matrix element combination characteristics with the co-polarization correlation coefficient to form a characteristic decision detector;
s3, determining a detection threshold value in the polarized synthetic aperture radar image by using a histogram threshold value method, and judging and determining a detection area by using the detection threshold value and a feature decision detector.
Further, the method for calculating the polarization coherence matrix in the step S1 specifically includes:
setting a scattering matrix of a polarized synthetic aperture radar image target as follows:
vectorization processing is carried out on the scattering matrix under the basis of the orthogonal matrix by the following formula:
wherein Tr (& gt) represents the trace of the matrix, T represents the transpose of the matrix, and psi is a group of 2×2 complex base matrix sets which are orthogonal under the inner product of hermite conjugation;
using the orthogonal matrix basis of the Pauloy matrix basis to obtain a corresponding set of vectors, wherein the set of vectors are Pauloy scattering vectors:
in the case where the target satisfies single-station reciprocity, the brix scattering vector is expressed as:
the second moment of the brix scattering vector can be used to obtain a polarization coherence matrix:
further, the step S2 specifically includes the following steps:
according toThe orthometric matrix basis of the dictionary sequence matrix basis is adopted to obtain a corresponding group of vectors, and the group of vectors are dictionary sequence scattering vectors:
k 4L ＝[S hh S hv S vh S vv ] T
under the condition that the target meets single-station reciprocity, the dictionary sequence scattering vector is as follows:
obtaining a polarization covariance matrix of the target by using the second moment of the dictionary sequence scattering vector:
the co-polarization correlation coefficient is calculated according to the following formula:
combining the matrix element combination characteristic with the co-polarization correlation coefficient according to the following formula:
further, the specific step of determining the detection threshold in the polarized synthetic aperture radar image by using the histogram threshold method in the step S3 is as follows:
two peaks in the polarized synthetic aperture radar image are determined by using a histogram threshold method, and a trough between the two peaks is determined as a detection threshold.
Further, in the step S3, the specific steps of determining the detection area by using the detection threshold and the feature decision detector are as follows: if the feature decision detector is larger than the detection threshold, the detection area is a building, otherwise the detection area is a natural area.
Compared with the prior art, the invention has the advantages that: in the process of constructing matrix element combination characteristics by utilizing polarization coherent matrix elements, the method fully considers the heterogeneous characteristics of cross polarization energy, and introduces a parameter of reflection asymmetry to effectively describe a scattering mechanism of a building so as to be convenient for better separating the building from a natural target background in order to avoid interference of the scattering of the building by natural target scattering; according to the method, statistical modeling is not required to be carried out on background clutter, the selected polarization matrix elements have clear physical significance, and the algorithm is simple, stable and easy to realize, so that the real-time processing requirement of target extraction can be met; the method does not need priori knowledge, has ideal extraction effect and strong self-adaptability, and proves that the method is stable, high in calculation efficiency and good in performance through extracting the buildings in the polar compound pore-diameter radar image.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for extracting an artificial target from a polarized synthetic aperture radar image driven by a scattering mechanism of the present invention.
Fig. 2 is a polarized SAR data building extraction experimental result.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making clear and defining the scope of the present invention.
Referring to fig. 1, the embodiment discloses a method for extracting an artificial target of a polarized synthetic aperture radar image driven by a scattering mechanism, which comprises the following steps:
step S1, utilizing corresponding secondary scattering, cross polarization scattering and reflection respectively according to the relative amplitude characteristics of the element values of the polarization coherence matrix in the rotating building area, the non-rotating building area and the natural areaAsymmetric polarization coherence matrix element T 22 、T 33 、T 13 And T 23 And constructing a matrix element combination characteristic MCF.
Specifically, the method for calculating the polarization coherence matrix in the step S1 specifically includes:
setting a scattering matrix of a polarized synthetic aperture radar image target as a formula (1):
vectorizing the scattering matrix under the basis of an orthogonal matrix by the following formula (2):
where Tr (·) represents the trace of the matrix, T represents the transpose of the matrix, and ψ is a set of orthogonal 2×2 complex basis matrices under hermite inner product.
The k is processed by using the Pauli matrix (Pauli matrix) to obtain a corresponding set of vectors (formula 3) based on the set of orthogonal matrix bases, namely the Pauli matrix, and the set of vectors are Pauli scattering vectors:
in the case where the target satisfies single-station reciprocity, the berkovich scattering vector is expressed as formula (4):
the second moment of the brix-ray vector can be used to obtain a polarization coherence matrix as shown in equation (5):
therefore, the present embodiment constructs a matrix element combination feature (MCF) as shown in formula (6), thereby effectively highlighting the building area.
MCF=(|T 13 |+|T 23 |)·T 33 1/2 +T 22 1/2
S2, calculating a polarization covariance matrix of the target, obtaining a co-polarization correlation coefficient according to the polarization covariance matrix of the target, and combining matrix element combination characteristics with the co-polarization correlation coefficient to form a characteristic decision detector.
Specifically, the step S2 specifically includes the following steps:
according to formula (7), the set of orthogonal matrix bases is used to obtain a corresponding set of vectors, which are dictionary order (Lexicographic) scatter vectors:
k 4L ＝[S hh S hv S vh S vv ] T (7)
in the case where the target satisfies single-station reciprocity, the dictionary order scatter vector is formula (8):
obtaining a polarization covariance matrix of the target by using the second moment of the dictionary sequence scattering vector, as shown in formula (9):
due to the co-polarized correlation coefficient |ρ of the natural region HHVV Larger and co-polarization correlation coefficient of building |ρ HHVV The I is smaller, and the co-polarization correlation coefficient I rho is introduced HHVV I, thereby further highlighting differences in building and natural areas:
the co-polarization correlation coefficient is calculated according to the following formula (10):
due to MCF and |ρ HHVV The trends in the building and natural areas are opposite, and combining these two features will be more effective in improving recognition. The method provides a feature decision detector driven by the combination of polarization matrix elements and polarization coherence, and specifically combines the combination features of the matrix elements with co-polarization correlation coefficients according to the following formula (11):
s3, determining a detection threshold T in the polarized synthetic aperture radar image by using a histogram threshold method U By using the detection threshold T U And judging and determining a detection area by a feature decision detector.
The specific steps of determining the detection threshold in the polarized synthetic aperture radar image by using the histogram threshold method are as follows: and determining two peaks in the polarized synthetic aperture radar image by using a histogram threshold method, determining a trough between the two peaks as a detection threshold, and determining detection thresholds of high-frequency three data and UAVSAR data as 1.0 and 1.3 respectively.
The specific steps of judging and determining the detection area by using the detection threshold and the feature decision detector are as follows: if the feature decision detector is greater than the detection threshold, the detection area is a building, otherwise the detection area is a natural area, as shown in equation 12.
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method for extracting artificial targets of polarized synthetic aperture radar images, which comprises three steps of constructing matrix element combination features, introducing polarization coherence and extracting buildings.
Table 1 is a schematic diagram of the relative magnitudes of the polarization coherence matrix and co-polarization correlation coefficients in different regions.
TABLE 1
If T in the coherence matrix 22 The value of the term is high and the dominant scattering mechanism of the target is then secondary scattering. Thus T 22 The term may be used to extract non-rotating building areas. At the same time, for the rotating building area, the cross polarization energy will vary greatly due to the existence of the rotating dihedral structure, and thus its corresponding T 33 The value of the term is high. However, since the natural region also generates cross polarization energy, misclassification may occur. In view of this, the present method introduces a parameter of reflection asymmetry. Reflection asymmetry is usually present in artificial target areas such as buildings, for which T 13 Item and T 23 The value of the term is high. From the above analysis, a preliminary scattering eigenvalue was constructed as follows:
MCF＝(|T 13 |+|T 23 |)·T 33 +T 22
here, |T 13 |+|T 23 And/represents reflection asymmetry. It can be seen that for the natural region, although |T 13 |+|T 23 I and T 22 Is of small value but T 33 The value of (2) is much greater than |T 13 |+|T 23 The value of i. Thus, rotating the MCF values for the building area and the natural area will produce a partial overlap. In addition, consider T of non-rotating building areas 22 The value is much larger than the rotated building area (|t) 13 |+|T 23 |)·T 33 To better highlight the rotating building area and avoid overlapping with the natural area, MCF was modified to the following form:
MCF=(|T 13 |+|T 23 |)·T 33 1/2 +T 22 1/2
wherein T is given to 33 The term plus square root is for cuttingIn weak natural areas (|T) 13 |+|T 23 |)·T 33 Influence of the value. At the same time give T 22 The term plus square root is to balance (|T) 13 |+|T 23 |)·T 33 1/2 And T 22 1/2 Is of a size of (a) and (b). After such adjustment, the MCF values for the non-rotating building areas and the rotating building areas are relatively high. Furthermore, due to the co-polarized correlation coefficient |ρ of the natural region HHVV Larger and co-polarization correlation coefficient of building |ρ HHVV The I is smaller, and simultaneously the co-polarization correlation coefficient I rho is introduced HHVV I, thereby further highlighting differences in building and natural areas. Due to MCF and |ρ HHVV The trends in the building and natural areas are opposite, and combining these two features will be more effective in improving recognition.
Fig. 2 is a polarized SAR data building extraction experimental result. The method for detecting the characteristic decision driven by the scattering mechanism extracts the outline of the building clearly and retains many local detail information. Moreover, the result of verification by using the high-resolution third-order and UAVSAR data also shows that the method has higher robustness for different sensors and different wave bands.
In the process of constructing matrix element combination characteristics by utilizing polarization coherent matrix elements, the method fully considers the heterogeneous characteristics of cross polarization energy, and introduces a parameter of reflection asymmetry to effectively describe a scattering mechanism of a building so as to be convenient for better separating the building from a natural target background in order to avoid interference of the scattering of the building by natural target scattering; according to the method, statistical modeling is not required to be carried out on background clutter, the selected polarization matrix elements have clear physical significance, and the algorithm is simple, stable and easy to realize, so that the real-time processing requirement of target extraction can be met; the method does not need priori knowledge, has ideal extraction effect and strong self-adaptability, and proves that the method is stable, high in calculation efficiency and good in performance through extracting the buildings in the polar compound pore-diameter radar image.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, the patentees may make various modifications or alterations within the scope of the appended claims, and are intended to be within the scope of the invention as described in the claims.
Claims (2)
1. The method for extracting the artificial target of the polarized synthetic aperture radar image driven by the scattering mechanism is characterized by comprising the following steps of:
s1, utilizing polarization coherence matrix elements T corresponding to secondary scattering, cross polarization scattering and reflection asymmetry respectively according to the relative amplitude characteristics of element values of the polarization coherence matrix in a rotating building area, a non-rotating building area and a natural area 22 、T 33 、T 13 And T 23 Constructing matrix element combination characteristics MCF, and MCF= (|T) 13 |+|T 23 |)·T 33 1/2 +T 22 1/2 ；
S2, calculating a polarization covariance matrix of the target, obtaining a co-polarization correlation coefficient according to the polarization covariance matrix of the target, and combining matrix element combination characteristics with the co-polarization correlation coefficient to form a characteristic decision detector;
s3, determining a detection threshold value in the polarized synthetic aperture radar image by using a histogram threshold value method, and judging and determining a detection area by using the detection threshold value and a feature decision detector;
the method for calculating the polarization coherence matrix in the step S1 specifically includes:
the scattering matrix s of the polarized synthetic aperture radar image target is set as follows:
vectorization processing is carried out on the scattering matrix under the basis of the orthogonal matrix by the following formula:
wherein Tr (& gt) represents the trace of the matrix, T represents the transpose of the matrix, and psi is a group of 2×2 complex base matrix sets which are orthogonal under the inner product of hermite conjugation;
using the orthogonal matrix basis of the Pauloy matrix basis to obtain a corresponding set of vectors, wherein the set of vectors is the Pauloy scattering vector k 4P ：
In case the target satisfies single-station reciprocity, the Brix scattering vector k 3P Expressed as:
using the brix scattering vector k 3P The second moment of (2) may result in a polar coherence matrix T:
the step S2 specifically includes the following steps:
according toUsing the orthogonal matrix basis of the dictionary sequence matrix basis to obtain a corresponding set of vectors, wherein the set of vectors is dictionary sequence scattering vector k 4L ：
k 4L ＝[S hh S hv S vh S vv ] T
Dictionary order scatter vector k in case the target satisfies single-site reciprocity 3L The method comprises the following steps:
using the dictionary order scatter vector k 3L To obtain a polarization covariance matrix C of the target:
the co-polarization correlation coefficient is calculated according to the following formula:
combining the matrix element combination characteristic with the co-polarization correlation coefficient according to the following formula:
the specific step of determining the detection threshold in the polarized synthetic aperture radar image by using the histogram threshold method in the step S3 is as follows:
two peaks in the polarized synthetic aperture radar image are determined by using a histogram threshold method, and a trough between the two peaks is determined as a detection threshold.
2. The method for extracting an artificial target from a polarized synthetic aperture radar image driven by a scattering mechanism according to claim 1, wherein the specific steps of determining the detection area by using the detection threshold and the feature decision detector in the step S3 are as follows: if the feature decision detector is larger than the detection threshold, the detection area is a building, otherwise the detection area is a natural area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111673335.6A CN114429453B (en) | 2021-12-31 | 2021-12-31 | Method for extracting artificial targets from polarized synthetic aperture radar images driven by scattering mechanism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111673335.6A CN114429453B (en) | 2021-12-31 | 2021-12-31 | Method for extracting artificial targets from polarized synthetic aperture radar images driven by scattering mechanism |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114429453A CN114429453A (en) | 2022-05-03 |
| CN114429453B true CN114429453B (en) | 2023-11-14 |
Family
ID=81310906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111673335.6A Active CN114429453B (en) | 2021-12-31 | 2021-12-31 | Method for extracting artificial targets from polarized synthetic aperture radar images driven by scattering mechanism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114429453B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375189A (en) * | 2018-12-25 | 2019-02-22 | 杭州世平信息科技有限公司 | Polarimetric radar remote sensing images city goal decomposition method based on cross scatter model |
| CN110223311A (en) * | 2019-05-24 | 2019-09-10 | 杭州世平信息科技有限公司 | Polarimetric radar edge Detection Method of Remote Sensing Images based on power drive adaptive windows |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102195458B1 (en) * | 2019-01-04 | 2020-12-28 | 한국과학기술원 | High-resolution fully polarimetric frequency modulation continuous wave synthetic aperture radar and signal processing method |
-
2021
- 2021-12-31 CN CN202111673335.6A patent/CN114429453B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375189A (en) * | 2018-12-25 | 2019-02-22 | 杭州世平信息科技有限公司 | Polarimetric radar remote sensing images city goal decomposition method based on cross scatter model |
| CN110223311A (en) * | 2019-05-24 | 2019-09-10 | 杭州世平信息科技有限公司 | Polarimetric radar edge Detection Method of Remote Sensing Images based on power drive adaptive windows |
Non-Patent Citations (4)
| Title |
|---|
| PolSAR图像极化目标分解方法研究及其应用;曹宁;中国优秀硕士学位论文全文数据库 信息科技辑;1136-561 * |
| SAR/PolSAR图像建筑物信息提取技术研究;项德良;中国博士学位论文全文数据库 信息科技辑;1136-315 * |
| 基于散射特征的极化SAR影像建筑物提取研究;闫丽丽;中国博士学位论文全文数据库 基础科学辑;A0008-13 * |
| 基于非平稳性和极化相干系数比的PolSAR图像建筑物检测;范庆辉; 慕建君; 项德良; 宋文青;电子与信息学报;第38卷(第12期);3238-3244 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114429453A (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | Hyperspectral anomaly detection via a sparsity score estimation framework | |
| Gu et al. | A selective KPCA algorithm based on high-order statistics for anomaly detection in hyperspectral imagery | |
| CN107992891B (en) | Multispectral remote sensing image change detection method based on spectral vector analysis | |
| CN103839073B (en) | Polarization SAR image classification method based on polarization features and affinity propagation clustering | |
| CN107563355A (en) | Hyperspectral abnormity detection method based on generation confrontation network | |
| CN109901130B (en) | Rotor unmanned aerial vehicle detection and identification method based on Radon transformation and improved 2DPCA | |
| CN108256436A (en) | A kind of radar HRRP target identification methods based on joint classification | |
| Camilo et al. | A large comparison of feature-based approaches for buried target classification in forward-looking ground-penetrating radar | |
| CN107194936A (en) | The high spectrum image object detection method represented based on super-pixel joint sparse | |
| Keshava | Best bands selection for detection in hyperspectral processing | |
| Cheng et al. | Regional-based object detection using polarization and Fisher vectors in passive millimeter-wave imaging | |
| Imani | Hyperspectral anomaly detection using differential image | |
| Shi et al. | Riemannian nearest-regularized subspace classification for polarimetric SAR images | |
| Li et al. | Spectral–spatial depth-based framework for hyperspectral underwater target detection | |
| Zhang et al. | Feature-band-based unsupervised hyperspectral underwater target detection near the coastline | |
| CN108229426B (en) | Remote sensing image change vector change detection method based on difference descriptor | |
| CN114429453B (en) | Method for extracting artificial targets from polarized synthetic aperture radar images driven by scattering mechanism | |
| CN105825512B (en) | The abnormal target in hyperspectral remotely sensed image object detection method returned based on steady background | |
| CN111460943A (en) | Remote sensing image ground object classification method and system | |
| Masarik et al. | End-to-end ATR leveraging deep learning | |
| Ovarlez et al. | Robust detection using the sirv background modelling for hyperspectral imaging | |
| Yang et al. | Compressive Hyperspectral Target Detection with Restricted Distribution Property | |
| CN108106500A (en) | A kind of missile target kind identification method based on multisensor | |
| CN108710816A (en) | A kind of polarimetric SAR image building analyte detection method based on probability fusion | |
| Song et al. | Hyperspectral anomaly detection via graphical connected point estimation and multiple support vector machines |
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 |